Package 'OpenRepGrid'

Description

Methods for "[", i.e., subsetting of repgrid objects.

Usage

## S4 method for signature 'repgrid'
x[i, j, ..., drop = TRUE]

Arguments

Examples

x <- randomGrid()
x[1:4, ]
x[, 1:3]
x[1:4, 1:3]
x[1, 1]

Description

It should be possible to use it for ratings on all layers.

Usage

## S4 replacement method for signature 'repgrid'
x[i, j, ...] <- value

Arguments

Examples

## Not run: 
x <- randomGrid()
x[1, 1] <- 2
x[1, ] <- 4
x[, 2] <- 3

# settings values outside defined rating scale
# range throws an error
x[1, 1] <- 999

# removing scale range allows arbitary values to be set
x <- setScale(x, min = NA, max = NA)
x[1, 1] <- 999

## End(Not run)

Description

Simple concatenation of repgrid objects or list containing repgrid objects using the '+' operator.

Usage

## S4 method for signature 'repgrid,repgrid'
e1 + e2

## S4 method for signature 'list,repgrid'
e1 + e2

## S4 method for signature 'repgrid,list'
e1 + e2

Arguments

Details

Methods for "+" function.

Examples

x <- bell2010
x + x
x + list(x, x)
list(x, x) + x

Description

The direction of the constructs in a grid is arbitrary and a reflection of a scale does not affect the information contained in the grid. Nonetheless, the direction of a scale has an effect on inter-element correlations (Mackay, 1992) and on the spatial representation and clustering of the grid (Bell, 2010). Hence, it is desirable to follow a protocol to align constructs that will render unique results. A common approach is to align constructs by pole preference, i. e. aligning all positive and negative poles. This can e. g. be achieved using swapPoles(). If an ideal element is present, this element can be used to identify the positive and negative pole. The function alignByIdeal will align the constructs accordingly. Note that this approach does not always yield definite results as sometimes ratings do not show a clear preference for one pole (Winter, Bell & Watson, 2010). If a preference cannot be determined definitely, the construct direction remains unchanged (a warning is issued in that case).

Usage

alignByIdeal(x, ideal, high = TRUE)

Arguments

Value

repgrid object with aligned constructs.

References

Bell, R. C. (2010). A note on aligning constructs. Personal Construct Theory & Practice, 7, 42-48.

Mackay, N. (1992). Identification, Reflection, and Correlation: Problems in the bases of repertory grid measures. International Journal of Personal Construct Psychology, 5(1), 57-75.

Winter, D. A., Bell, R. C., & Watson, S. (2010). Midpoint ratings on personal constructs: Constriction or the middle way? Journal of Constructivist Psychology, 23(4), 337-356.

See Also

alignByLoadings()

Examples

feixas2004 # original grid
alignByIdeal(feixas2004, 13) # aligned with preference pole on the right

raeithel # original grid
alignByIdeal(raeithel, 3, high = FALSE) # aligned with preference pole on the left

Description

In case a construct loads negatively on the first principal component, the function alignByLoadings() will reverse it so that all constructs have positive loadings on the first principal component (see detail section for more).

Usage

alignByLoadings(x, trim = 20, index = TRUE)

Arguments

Details

The direction of the constructs in a grid is arbitrary and a reflection of a scale does not affect the information contained in the grid. Nonetheless, the direction of a scale has an effect on inter-element correlations (Mackay, 1992) and on the spatial representation and clustering of the grid (Bell, 2010). Hence, it is desirable to follow a protocol to align constructs that will render unique results. A common approach is to align constructs by pole preference, but this information is not always accessible. Bell (2010) proposed another solution for the problem of construct alignment. As a unique protocol he suggests to align constructs in a way so they all have positive loadings on the first component of a grid PCA.

Value

An object of class alignByLoadings containing a list of calculations with the following entries:

• cor.before: Construct correlation matrix before reversal

• loadings.before: Loadings on PCs before reversal

• reversed: Constructs that have been reversed

• cor.after: Construct correlation matrix after reversal

• loadings.after: Loadings on PCs after reversal

Note

Bell (2010) proposed a solution for the problem of construct alignment. As construct reversal has an effect on element correlation and thus on any measure that based on element correlation (Mackay, 1992), it is desirable to have a standard method for construct alignment independently from its semantics (preferred pole etc.). Bell (2010) proposes to align constructs in a way so they all have positive loadings on the first component of a grid PCA.

References

Bell, R. C. (2010). A note on aligning constructs. Personal Construct Theory & Practice, 7, 42-48.

Mackay, N. (1992). Identification, Reflection, and Correlation: Problems in the bases of repertory grid measures. International Journal of Personal Construct Psychology, 5(1), 57-75.

See Also

alignByIdeal()

Examples

# reproduction of the example in the Bell (2010)
# constructs aligned by loadings on PC 1
bell2010
alignByLoadings(bell2010)

# save results
a <- alignByLoadings(bell2010)

# modify printing of resukts
print(a, digits = 5)

# access results for further processing
names(a)
a$cor.before
a$loadings.before
a$reversed
a$cor.after
a$loadings.after

Description

One of the most popular ways of displaying grid data has been adopted from Bertin's (1974) graphical proposals, which have had an immense influence onto data visualization. One of the most appealing ideas presented by Bertin is the concept of the reorderable matrix. It is comprised of graphical displays for each cell, allowing to identify structures by eye-balling reordered versions of the data matrix (see Bertin, 1974). In the context of repertory grids, the display is made up of a simple colored rectangle where the color denotes the corresponding score. Bright values correspond to low, dark to high scores. For an example of how to analyze a Bertin display see e.g. Dick (2000) and Raeithel (1998).

Usage

bertin(
  x,
  colors = c("white", "black"),
  showvalues = TRUE,
  xlim = c(0.2, 0.8),
  ylim = c(0, 0.6),
  margins = c(0, 1, 1),
  cex.elements = 0.7,
  cex.constructs = 0.7,
  cex.text = 0.6,
  col.text = NA,
  border = "white",
  lheight = 0.75,
  id = c(T, T),
  cc = 0,
  cr = 0,
  cc.old = 0,
  cr.old = 0,
  col.mark.fill = "#FCF5A4",
  print = TRUE,
  ...
)

Arguments

Value

NULL just for the side effects, i.e. printing.

References

Bertin, J. (1974). Graphische Semiologie: Diagramme, Netze, Karten. Berlin, New York: de Gruyter.

Dick, M. (2000). The Use of Narrative Grid Interviews in Psychological Mobility Research. Forum Qualitative Sozialforschung / Forum: Qualitative Social Research, 1(2).

Raeithel, A. (1998). Kooperative Modellproduktion von Professionellen und Klienten - erlauetert am Beispiel des Repertory Grid. Selbstorganisation, Kooperation, Zeichenprozess: Arbeiten zu einer kulturwissenschaftlichen, anwendungsbezogenen Psychologie (pp. 209-254). Opladen: Westdeutscher Verlag.

Examples

bertin(feixas2004)
bertin(feixas2004, c("white", "darkblue"))
bertin(feixas2004, showvalues = FALSE)
bertin(feixas2004, border = "grey")
bertin(feixas2004, cex.text = .9)
bertin(feixas2004, id = c(FALSE, FALSE))

bertin(feixas2004, cc = 3, cr = 4)
bertin(feixas2004, cc = 3, cr = 4, col.mark.fill = "#e6e6e6")

Description

Element columns and constructs rows are ordered according to cluster criterion. Various distance measures as well as cluster methods are supported.

Usage

bertinCluster(
  x,
  dmethod = c("euclidean", "euclidean"),
  cmethod = c("ward.D", "ward.D"),
  p = c(2, 2),
  align = TRUE,
  trim = NA,
  type = c("triangle"),
  xsegs = c(0, 0.2, 0.7, 0.9, 1),
  ysegs = c(0, 0.1, 0.7, 1),
  x.off = 0.01,
  y.off = 0.01,
  cex.axis = 0.6,
  col.axis = grey(0.4),
  draw.axis = TRUE,
  ...
)

Arguments

Value

A list of two hclust() object, for elements and constructs respectively.

See Also

cluster()

Examples

# default is euclidean distance and ward clustering
bertinCluster(bell2010)

### applying different distance measures and cluster methods

# euclidean distance and single linkage clustering
bertinCluster(bell2010, cmethod = "single")
# manhattan distance and single linkage clustering
bertinCluster(bell2010, dmethod = "manhattan", cm = "single")
# minkowksi distance with power of 2 = euclidean distance
bertinCluster(bell2010, dm = "mink", p = 2)

### using different methods for constructs and elements

# ward clustering for constructs, single linkage for elements
bertinCluster(bell2010, cmethod = c("ward.D", "single"))
# euclidean distance measure for constructs, manhatten
# distance for elements
bertinCluster(bell2010, dmethod = c("euclidean", "man"))
# minkowski metric with different powers for constructs and elements
bertinCluster(bell2010, dmethod = "mink", p = c(2, 1))

### clustering either constructs or elements only
# euclidean distance and ward clustering for constructs no
# clustering for elements
bertinCluster(bell2010, cmethod = c("ward.D", NA))
# euclidean distance and single linkage clustering for elements
# no clustering for constructs
bertinCluster(bell2010, cm = c(NA, "single"), align = FALSE)

### changing the appearance
# different dendrogram type
bertinCluster(bell2010, type = "rectangle")
# no axis drawn for dendrogram
bertinCluster(bell2010, draw.axis = FALSE)

### passing on arguments to bertin function via ...
# grey cell borders in bertin display
bertinCluster(bell2010, border = "grey")
# omit printing of grid scores, i.e. colors only
bertinCluster(bell2010, showvalues = FALSE)

### changing the layout
# making the vertical dendrogram bigger
bertinCluster(bell2010, xsegs = c(0, .2, .5, .7, 1))
# making the horizontal dendrogram bigger
bertinCluster(bell2010, ysegs = c(0, .3, .8, 1))

Description

The biplot is the central way to create a joint plot of elements and constructs. Depending on the parameters chosen it contains information on the distances between elements and constructs. Also the relative values the elements have on a construct can be read off by projection the element onto the construct vector. A lot of parameters can be changed rendering different types of biplots (ESA, Slater's) and different looks (colors, text size). See the example section below to get started.

Usage

biplot2d(
  x,
  dim = c(1, 2),
  map.dim = 3,
  center = 1,
  normalize = 0,
  g = 0,
  h = 1 - g,
  col.active = NA,
  col.passive = NA,
  e.point.col = "black",
  e.point.cex = 0.9,
  e.label.col = "black",
  e.label.cex = 0.7,
  e.color.map = c(0.4, 1),
  c.point.col = "black",
  c.point.cex = 0,
  c.label.col = "black",
  c.label.cex = 0.7,
  c.color.map = c(0.4, 1),
  c.points.devangle = 91,
  c.labels.devangle = 91,
  c.points.show = TRUE,
  c.labels.show = TRUE,
  e.points.show = TRUE,
  e.labels.show = TRUE,
  inner.positioning = TRUE,
  outer.positioning = TRUE,
  c.labels.inside = FALSE,
  c.lines = TRUE,
  col.c.lines = grey(0.9),
  flipaxes = c(FALSE, FALSE),
  strokes.x = 0.1,
  strokes.y = 0.1,
  offsetting = TRUE,
  offset.labels = 0,
  offset.e = 1,
  axis.ext = 0.1,
  mai = c(0.2, 1.5, 0.2, 1.5),
  rect.margins = c(0.01, 0.01),
  srt = 45,
  cex.pos = 0.7,
  xpd = TRUE,
  unity = FALSE,
  unity3d = FALSE,
  scale.e = 0.9,
  zoom = 1,
  var.show = TRUE,
  var.cex = 0.7,
  var.col = grey(0.1),
  ...
)

Arguments

Details

For the construction of a biplot the grid matrix is first centered and normalized according to the prompted options.

Next, the matrix is decomposed by singular value decomposition (SVD) into

$X = UDV^T$

The biplot is made up of two matrices

$X = GH^T$

These matrices are construed on the basis of the SVD results.

$\hat{X} = UD^gD^hV^T$

Note that the grid matrix values are only recovered and the projection property is only given if $g + h = 1$

See Also

• Unsophisticated biplot: biplotSimple();

• 2D biplots:biplot2d(), biplotEsa2d(), biplotSlater2d();

• Pseudo 3D biplots: biplotPseudo3d(), biplotEsaPseudo3d(), biplotSlaterPseudo3d();

• Interactive 3D biplots: biplot3d(), biplotEsa3d(), biplotSlater3d();

• Function to set view in 3D: home()

Examples

## Not run: 

biplot2d(boeker) # biplot of boeker data
biplot2d(boeker, c.lines = T) # add construct lines
biplot2d(boeker, center = 2) # with column centering
biplot2d(boeker, center = 4) # midpoint centering
biplot2d(boeker, normalize = 1) # normalization of constructs

biplot2d(boeker, dim = 2:3) # plot 2nd and 3rd dimension
biplot2d(boeker, dim = c(1, 4)) # plot 1st and 4th dimension

biplot2d(boeker, g = 1, h = 1) # assign singular values to con. & elem.
biplot2d(boeker, g = 1, h = 1, center = 1) # row centering (Slater)
biplot2d(boeker, g = 1, h = 1, center = 4) # midpoint centering (ESA)

biplot2d(boeker, e.color = "red", c.color = "blue") # change colors
biplot2d(boeker, c.color = c("white", "darkred")) # mapped onto color range

biplot2d(boeker, unity = T) # scale con. & elem. to equal length
biplot2d(boeker, unity = T, scale.e = .5) # scaling factor for element vectors

biplot2d(boeker, e.labels.show = F) # do not show element labels
biplot2d(boeker, e.labels.show = c(1, 2, 4)) # show labels for elements 1, 2 and 4
biplot2d(boeker, e.points.show = c(1, 2, 4)) # only show elements 1, 2 and 4
biplot2d(boeker, c.labels.show = c(1:4)) # show constructs labels 1 to 4
biplot2d(boeker, c.labels.show = c(1:4)) # show constructs labels except 1 to 4

biplot2d(boeker, e.cex.map = 1) # change size of texts for elements
biplot2d(boeker, c.cex.map = 1) # change size of texts for constructs

biplot2d(boeker, g = 1, h = 1, c.labels.inside = T) # constructs inside the plot
biplot2d(boeker,
  g = 1, h = 1, c.labels.inside = T, # different margins and elem. color
  mai = c(0, 0, 0, 0), e.color = "red"
)

biplot2d(boeker, strokes.x = .3, strokes.y = .05) # change length of strokes

biplot2d(boeker, flipaxes = c(T, F)) # flip x axis
biplot2d(boeker, flipaxes = c(T, T)) # flip x and y axis

biplot2d(boeker, outer.positioning = F) # no positioning of con.-labels

biplot2d(boeker, c.labels.devangle = 20) # only con. within 20 degree angle

## End(Not run)

Description

The 3D biplot opens an interactive 3D device that can be rotated and zoomed using the mouse. A 3D device facilitates the exploration of grid data as significant proportions of the sum-of-squares are often represented beyond the first two dimensions. Also, in a lot of cases it may be of interest to explore the grid space from a certain angle, e.g. to gain an optimal view onto the set of elements under investigation (e.g. Raeithel, 1998).

Usage

biplot3d(
  x,
  dim = 1:3,
  labels.e = TRUE,
  labels.c = TRUE,
  lines.c = TRUE,
  lef = 1.3,
  center = 1,
  normalize = 0,
  g = 0,
  h = 1,
  col.active = NA,
  col.passive = NA,
  c.sphere.col = grey(0.4),
  c.cex = 0.6,
  c.text.col = grey(0.4),
  e.sphere.col = grey(0),
  e.cex = 0.6,
  e.text.col = grey(0),
  alpha.sphere = 0.05,
  col.sphere = "black",
  unity = FALSE,
  unity3d = FALSE,
  scale.e = 0.9,
  zoom = 1,
  ...
)

Arguments

References

Raeithel, A. (1998). Kooperative Modellproduktion von Professionellen und Klienten - erlauetert am Beispiel des Repertory Grid. Selbstorganisation, Kooperation, Zeichenprozess: Arbeiten zu einer kulturwissenschaftlichen, anwendungsbezogenen Psychologie (pp. 209-254). Opladen: Westdeutscher Verlag.

See Also

Unsophisticated biplot: biplotSimple();
2D biplots: biplot2d(), biplotEsa2d(), biplotSlater2d();
Pseudo 3D biplots: biplotPseudo3d(), biplotEsaPseudo3d(), biplotSlaterPseudo3d();
Interactive 3D biplots: biplot3d(), biplotEsa3d(), biplotSlater3d();
Function to set view in 3D: home().

Examples

## Not run: 

biplot3d(boeker)
biplot3d(boeker, unity3d = T)

biplot3d(boeker,
  e.sphere.col = "red",
  c.text.col = "blue"
)
biplot3d(boeker, e.cex = 1)
biplot3d(boeker, col.sphere = "red")

biplot3d(boeker, g = 1, h = 1) # INGRID biplot
biplot3d(boeker,
  g = 1, h = 1, # ESA biplot
  center = 4
)

## End(Not run)

Description

The ESA is a special type of biplot suggested by Raeithel (e.g. 1998). It uses midpoint centering as a default. Note that the eigenstructure analysis is just a special case of a biplot that can also be produced using the biplot2d() function with the arguments ⁠center=4, g=1, h=1⁠. Here, only the arguments that are modified for the ESA biplot are described. To see all the parameters that can be changed see biplot2d().

Usage

biplotEsa2d(x, center = 4, g = 1, h = 1, ...)

Arguments

References

Raeithel, A. (1998). Kooperative Modellproduktion von Professionellen und Klienten. Erlaeutert am Beispiel des Repertory Grid. In A. Raeithel (1998). Selbstorganisation, Kooperation, Zeichenprozess. Arbeiten zu einer kulturwissenschaftlichen, anwendungsbezogenen Psychologie (p. 209-254). Opladen: Westdeutscher Verlag.

See Also

• Unsophisticated biplot: biplotSimple();

• 2D biplots:biplot2d(), biplotEsa2d(), biplotSlater2d();

• Pseudo 3D biplots: biplotPseudo3d(), biplotEsaPseudo3d(), biplotSlaterPseudo3d();

• Interactive 3D biplots: biplot3d(), biplotEsa3d(), biplotSlater3d();

• Function to set view in 3D: home()

Examples

## Not run: 
# See examples in [biplot2d()] as the same arguments
# can used for this function.

## End(Not run)

Description

The 3D biplot opens an interactive 3D device that can be rotated and zoomed using the mouse. A 3D device facilitates the exploration of grid data as significant proportions of the sum-of-squares are often represented beyond the first two dimensions. Also, in a lot of cases it may be of interest to explore the grid space from a certain angle, e.g. to gain an optimal view onto the set of elements under investigation (e.g. Raeithel, 1998). Note that the eigenstructure analysis just a special case of a biplot that can also be produced using the biplot3d() function with the arguments ⁠center=4, g=1, h=1⁠.

Usage

biplotEsa3d(x, center = 1, g = 1, h = 1, ...)

Arguments

See Also

Unsophisticated biplot: biplotSimple();
2D biplots: biplot2d(), biplotEsa2d(), biplotSlater2d();
Pseudo 3D biplots: biplotPseudo3d(), biplotEsaPseudo3d(), biplotSlaterPseudo3d();
Interactive 3D biplots: biplot3d(), biplotEsa3d(), biplotSlater3d();
Function to set view in 3D: home().

Examples

## Not run: 

biplotEsa3d(boeker)
biplotEsa3d(boeker, unity3d = T)

biplotEsa3d(boeker,
  e.sphere.col = "red",
  c.text.col = "blue"
)
biplotEsa3d(boeker, e.cex = 1)
biplotEsa3d(boeker, col.sphere = "red")

## End(Not run)

Description

The ESA is a special type of biplot suggested by Raeithel (e.g. 1998). It uses midpoint centering as a default. Note that the eigenstructure analysis is just a special case of a biplot that can also be produced using the biplot2d() function with the arguments ⁠center=4, g=1, h=1⁠. Here, only the arguments that are modified for the ESA biplot are described. To see all the parameters that can be changed see biplot2d() and biplotPseudo3d().

Usage

biplotEsaPseudo3d(x, center = 4, g = 1, h = 1, ...)

Arguments

See Also

• Unsophisticated biplot: biplotSimple();

• 2D biplots:biplot2d(), biplotEsa2d(), biplotSlater2d();

• Pseudo 3D biplots: biplotPseudo3d(), biplotEsaPseudo3d(), biplotSlaterPseudo3d();

• Interactive 3D biplots: biplot3d(), biplotEsa3d(), biplotSlater3d();

• Function to set view in 3D: home()

Examples

## Not run: 
# See examples in [biplotPseudo3d()] as the same arguments
# can used for this function.

## End(Not run)

Description

This version is basically a 2D biplot. It only modifies color and size of the symbols in order to create a 3D impression of the data points. This function will call the standard biplot2d() function with some modified arguments. For the whole set of arguments that can be used see biplot2d(). Here only the arguments special to biplotPseudo3d are outlined.

Usage

biplotPseudo3d(
  x,
  dim = 1:2,
  map.dim = 3,
  e.point.col = c("white", "black"),
  e.point.cex = c(0.6, 1.2),
  e.label.col = c("white", "black"),
  e.label.cex = c(0.6, 0.8),
  e.color.map = c(0.4, 1),
  c.point.col = c("white", "darkred"),
  c.point.cex = c(0.6, 1.2),
  c.label.col = c("white", "darkred"),
  c.label.cex = c(0.6, 0.8),
  c.color.map = c(0.4, 1),
  ...
)

Arguments

See Also

• Unsophisticated biplot: biplotSimple();

• 2D biplots:biplot2d(), biplotEsa2d(), biplotSlater2d();

• Pseudo 3D biplots: biplotPseudo3d(), biplotEsaPseudo3d(), biplotSlaterPseudo3d();

• Interactive 3D biplots: biplot3d(), biplotEsa3d(), biplotSlater3d();

• Function to set view in 3D: home()

Examples

## Not run: 
# biplot with 3D impression
biplotPseudo3d(boeker)
# Slater's biplot with 3D impression
biplotPseudo3d(boeker, g = 1, h = 1, center = 1)

# show 2nd and 3rd dim. and map 4th
biplotPseudo3d(boeker, dim = 2:3, map.dim = 4)

# change elem. colors
biplotPseudo3d(boeker, e.color = c("white", "darkgreen"))
# change con. colors
biplotPseudo3d(boeker, c.color = c("white", "darkgreen"))
# change color mapping range
biplotPseudo3d(boeker, c.colors.map = c(0, 1))

# set uniform con. text size
biplotPseudo3d(boeker, c.cex = 1)
# change text size mapping range
biplotPseudo3d(boeker, c.cex = c(.4, 1.2))

## End(Not run)

Description

It will draw elements and constructs vectors using similar arguments as biplot2d(). It is a version for quick exploration used during development.

Usage

biplotSimple(
  x,
  dim = 1:2,
  center = 1,
  normalize = 0,
  g = 0,
  h = 1 - g,
  unity = T,
  col.active = NA,
  col.passive = NA,
  scale.e = 0.9,
  zoom = 1,
  e.point.col = "black",
  e.point.cex = 1,
  e.label.col = "black",
  e.label.cex = 0.7,
  c.point.col = grey(0.6),
  c.label.col = grey(0.6),
  c.label.cex = 0.6,
  ...
)

Arguments

Value

repgrid object.

See Also

Unsophisticated biplot: biplotSimple();
2D biplots: biplot2d(), biplotEsa2d(), biplotSlater2d();
Pseudo 3D biplots: biplotPseudo3d(), biplotEsaPseudo3d(), biplotSlaterPseudo3d();
Interactive 3D biplots: biplot3d(), biplotEsa3d(), biplotSlater3d();
Function to set view in 3D: home().

Examples

## Not run: 

biplotSimple(boeker)
biplotSimple(boeker, unity = F)

biplotSimple(boeker, g = 1, h = 1) # INGRID biplot
biplotSimple(boeker, g = 1, h = 1, center = 4) # ESA biplot

biplotSimple(boeker, zoom = .9) # zooming out
biplotSimple(boeker, scale.e = .6) # scale element vectors

biplotSimple(boeker, e.point.col = "brown") # change colors
biplotSimple(boeker,
  e.point.col = "brown",
  c.label.col = "darkblue"
)

## End(Not run)

Description

The default is to use row centering and no normalization. Note that Slater's biplot is just a special case of a biplot that can be produced using the biplot2d() function with the arguments ⁠center=1, g=1, h=1⁠. The arguments that can be used in this function are the same as in biplot2d(). Here, only the arguments that are set for Slater's biplot are described. To see all the parameters that can be changed see biplot2d().

Usage

biplotSlater2d(x, center = 1, g = 1, h = 1, ...)

Arguments

See Also

• Unsophisticated biplot: biplotSimple();

• 2D biplots:biplot2d(), biplotEsa2d(), biplotSlater2d();

• Pseudo 3D biplots: biplotPseudo3d(), biplotEsaPseudo3d(), biplotSlaterPseudo3d();

• Interactive 3D biplots: biplot3d(), biplotEsa3d(), biplotSlater3d();

• Function to set view in 3D: home()

Examples

## Not run: 
# See examples in [biplot2d()] as the same arguments
# can used for this function.

## End(Not run)

Description

The 3D biplot opens an interactive 3D device that can be rotated and zoomed using the mouse. A 3D device facilitates the exploration of grid data as significant proportions of the sum-of-squares are often represented beyond the first two dimensions. Also, in a lot of cases it may be of interest to explore the grid space from a certain angle, e.g. to gain an optimal view onto the set of elements under investigation (e.g. Raeithel, 1998). Note that Slater's biplot is just a special case of a biplot that can be produced using the biplot3d() function with the arguments ⁠center=1, g=1, h=1⁠.

Usage

biplotSlater3d(x, center = 1, g = 1, h = 1, ...)

Arguments

See Also

Unsophisticated biplot: biplotSimple();
2D biplots: biplot2d(), biplotEsa2d(), biplotSlater2d();
Pseudo 3D biplots: biplotPseudo3d(), biplotEsaPseudo3d(), biplotSlaterPseudo3d();
Interactive 3D biplots: biplot3d(), biplotEsa3d(), biplotSlater3d();
Function to set view in 3D: home().

Examples

## Not run: 

biplotSlater3d(boeker)
biplotSlater3d(boeker, unity3d = T)

biplotSlater3d(boeker,
  e.sphere.col = "red",
  c.text.col = "blue"
)
biplotSlater3d(boeker, e.cex = 1)
biplotSlater3d(boeker, col.sphere = "red")

## End(Not run)

Description

The default is to use row centering and no normalization. Note that Slater's biplot is just a special case of a biplot that can be produced using the biplotPseudo3d() function with the arguments ⁠center=1, g=1, h=1⁠. Here, only the arguments that are modified for Slater's biplot are described. To see all the parameters that can be changed see biplot2d() and biplotPseudo3d().

Usage

biplotSlaterPseudo3d(x, center = 1, g = 1, h = 1, ...)

Arguments

See Also

• Unsophisticated biplot: biplotSimple();

• 2D biplots:biplot2d(), biplotEsa2d(), biplotSlater2d();

• Pseudo 3D biplots: biplotPseudo3d(), biplotEsaPseudo3d(), biplotSlaterPseudo3d();

• Interactive 3D biplots: biplot3d(), biplotEsa3d(), biplotSlater3d();

• Function to set view in 3D: home()

Examples

## Not run: 
# See examples in [biplotPseudo3d()] as the same arguments
# can used for this function.

## End(Not run)

Description

Centering of rows (constructs) and/or columns (elements).

Usage

center(x, center = 1, ...)

Arguments

Value

matrix containing the transformed values.

Note

If scale midpoint centering is applied no row or column centering can be applied simultaneously. TODO: After centering the standard representation mode does not work any more as it remains unclear what color values to attach to the centered values.

Examples

center(bell2010) # no centering
center(bell2010, rows = T) # row centering of grid
center(bell2010, cols = T) # column centering of grid
center(bell2010, rows = T, cols = T) # row and column centering

Description

cluster is a preliminary implementation of a cluster function. It supports various distance measures as well as cluster methods. More is to come.

Usage

cluster(
  x,
  along = 0,
  dmethod = "euclidean",
  cmethod = "ward.D",
  p = 2,
  align = TRUE,
  trim = NA,
  main = NULL,
  mar = c(4, 2, 3, 15),
  cex = 0,
  lab.cex = 0.8,
  cex.main = 0.9,
  print = TRUE,
  ...
)

Arguments

Details

align: Aligning will reverse constructs if necessary to yield a maximal similarity between constructs. In a first step the constructs are clustered including both directions. In a second step the direction of a construct that yields smaller distances to the adjacent constructs is preserved and used for the final clustering. As a result, every construct is included once but with an orientation that guarantees optimal clustering. This approach is akin to the procedure used in FOCUS (Jankowicz & Thomas, 1982).

Value

Reordered repgrid object.

References

Jankowicz, D., & Thomas, L. (1982). An Algorithm for the Cluster Analysis of Repertory Grids in Human Resource Development. Personnel Review, 11(4), 15-22. doi:10.1108/eb055464.

See Also

bertinCluster()

Examples

cluster(bell2010)
cluster(bell2010, main = "My cluster analysis") # new title
cluster(bell2010, type = "t") # different drawing style
cluster(bell2010, dmethod = "manhattan") # using manhattan metric
cluster(bell2010, cmethod = "single") # do single linkage clustering
cluster(bell2010, cex = 1, lab.cex = 1) # change appearance
cluster(bell2010, lab.cex = .7, edgePar = list(lty = 1:2, col = 2:1)) # advanced appearance changes

Description

p-values are calculated for each branch of the cluster dendrogram to indicate the stability of a specific partition. clusterBoot will yield the same clusters as the cluster() function (i.e. standard hierarchical clustering) with additional p-values. Two kinds of p-values are reported: bootstrap probabilities (BP) and approximately unbiased (AU) probabilities (see Details section for more information).

Usage

clusterBoot(
  x,
  along = 1,
  align = TRUE,
  dmethod = "euclidean",
  cmethod = "ward.D",
  p = 2,
  nboot = 1000,
  r = seq(0.8, 1.4, by = 0.1),
  seed = NULL,
  ...
)

Arguments

Details

In standard (hierarchical) cluster analysis the question arises which of the identified structures are significant or just emerged by chance. Over the last decade several methods have been developed to test structures for robustness. One line of research in this area is based on resampling. The idea is to resample the rows or columns of the data matrix and to build the dendrogram for each bootstrap sample (Felsenstein, 1985). The p-values indicates the percentage of times a specific structure is identified across the bootstrap samples. It was shown that the p-value is biased (Hillis & Bull, 1993; Zharkikh & Li, 1995). In the literature several methods for bias correction have been proposed. In clusterBoot a method based on the multiscale bootstrap is used to derive corrected (approximately unbiased) p-values (Shimodaira, 2002, 2004). In conventional bootstrap analysis the size of the bootstrap sample is identical to the original sample size. Multiscale bootstrap varies the bootstrap sample size in order to infer a correction formula for the biased p-value on the basis of the variation of the results for the different sample sizes (Suzuki & Shimodaira, 2006).

align: Aligning will reverse constructs if necessary to yield a maximal similarity between constructs. In a first step the constructs are clustered including both directions. In a second step the direction of a construct that yields smaller distances to the adjacent constructs is preserved and used for the final clustering. As a result, every construct is included once but with an orientation that guarantees optimal clustering. This approach is akin to the procedure used in FOCUS (Jankowicz & Thomas, 1982).

Value

A pvclust object as returned by the function pvclust::pvclust()

References

Felsenstein, J. (1985). Confidence Limits on Phylogenies: An Approach Using the Bootstrap. Evolution, 39(4), 783. doi:10.2307/2408678

Hillis, D. M., & Bull, J. J. (1993). An Empirical Test of Bootstrapping as a Method for Assessing Confidence in Phylogenetic Analysis. Systematic Biology, 42(2), 182-192.

Jankowicz, D., & Thomas, L. (1982). An Algorithm for the Cluster Analysis of Repertory Grids in Human Resource Development. Personnel Review, 11(4), 15-22. doi:10.1108/eb055464.

Shimodaira, H. (2002) An approximately unbiased test of phylogenetic tree selection. Syst, Biol., 51, 492-508.

Shimodaira,H. (2004) Approximately unbiased tests of regions using multistep- multiscale bootstrap resampling. Ann. Stat., 32, 2616-2614.

Suzuki, R., & Shimodaira, H. (2006). Pvclust: an R package for assessing the uncertainty in hierarchical clustering. Bioinformatics, 22(12), 1540-1542. doi:10.1093/bioinformatics/btl117

Zharkikh, A., & Li, W.-H. (1995). Estimation of confidence in phylogeny: the complete-and-partial bootstrap technique. Molecular Phylogenetic Evolution, 4(1), 44-63.

Examples

## Not run: 

# pvclust must be loaded
library(pvclust)

# p-values for construct dendrogram
s <- clusterBoot(boeker)
plot(s)
pvrect(s, max.only = FALSE)

# p-values for element dendrogram
s <- clusterBoot(boeker, along = 2)
plot(s)
pvrect(s, max.only = FALSE)

## End(Not run)

Description

Different types of correlations can be requested: PMC, Kendall tau rank correlation, Spearman rank correlation.

Usage

constructCor(
  x,
  method = c("pearson", "kendall", "spearman"),
  trim = 20,
  index = FALSE
)

Arguments

Value

Returns a matrix of construct correlations.

See Also

elementCor()

Examples

# three different types of correlations
constructCor(mackay1992)
constructCor(mackay1992, method = "kendall")
constructCor(mackay1992, method = "spearman")

# format output
constructCor(mackay1992, trim = 6)
constructCor(mackay1992, index = TRUE, trim = 6)

# save correlation matrix for further processing
r <- constructCor(mackay1992)
r
print(r, digits = 5)

# accessing the correlation matrix
r[1, 3]

Description

Somer's d is an asymmetric association measure as it depends on which variable is set as dependent and independent. The direction of dependency needs to be specified.

Usage

constructD(x, dependent = "columns", trim = 30, index = TRUE)

Arguments

Value

matrix of construct correlations.

Note

         Thanks to Marc Schwartz for supplying the code to calculate
               Somers' d.

References

Somers, R. H. (1962). A New Asymmetric Measure of Association for Ordinal Variables. American Sociological Review, 27(6), 799-811.

Examples

## Not run: 

constructD(fbb2003) # columns as dependent (default)
constructD(fbb2003, "c") # row as dependent
constructD(fbb2003, "s") # symmetrical index

# suppress printing
d <- constructD(fbb2003, out = 0, trim = 5)
d

# more digits
constructD(fbb2003, dig = 3)

# add index column, no trimming
constructD(fbb2003, col.index = TRUE, index = F, trim = NA)

## End(Not run)

Description

Various methods for rotation and methods for the calculation of the correlations are available. Note that the number of factors has to be specified. For more information on the PCA function itself type ?principal.

Usage

constructPca(
  x,
  nfactors = 3,
  rotate = "varimax",
  method = "pearson",
  trim = NA
)

Arguments

Value

Returns an object of class constructPca.

References

Fransella, F., Bell, R. & Bannister, D. (2003). A Manual for Repertory Grid Technique (2. Ed.). Chichester: John Wiley & Sons.

See Also

To extract the PCA loadings for further processing see constructPcaLoadings().

Examples

constructPca(bell2010)

# data from grid manual by Fransella et al. (2003, p. 87)
# note that the construct order is different
constructPca(fbb2003, nfactors = 2)

# no rotation
constructPca(fbb2003, rotate = "none")

# use a different type of correlation (Spearman)
constructPca(fbb2003, method = "spearman")

# save output to object
m <- constructPca(fbb2003, nfactors = 2)
m

# different printing options
print(m, digits = 5)
print(m, cutoff = .3)

Description

Extract loadings from PCA of constructs.

Usage

constructPcaLoadings(x)

Arguments

Value

A matrix containing the factor loadings.

Examples

p <- constructPca(bell2010)
l <- constructPcaLoadings(p)
l[1, ]
l[, 1]
l[1, 1]

Description

The RMS is also known as 'quadratic mean' of the inter-construct correlations. The RMS serves as a simplification of the correlation table. It reflects the average relation of one construct to all other constructs. Note that as the correlations are squared during its calculation, the RMS is not affected by the sign of the correlation (cf. Fransella, Bell & Bannister, 2003, p. 86).

Usage

constructRmsCor(x, method = "pearson", trim = NA)

Arguments

Value

dataframe of the RMS of inter-construct correlations

References

Fransella, F., Bell, R. C., & Bannister, D. (2003). A Manual for Repertory Grid Technique (2. Ed.). Chichester: John Wiley & Sons.

See Also

elementRmsCor(), constructCor()

Examples

# data from grid manual by Fransella, Bell and Bannister
constructRmsCor(fbb2003)
constructRmsCor(fbb2003, trim = 20)

# modify output
r <- constructRmsCor(fbb2003)
print(r, digits = 5)
   # access calculation results
   r[2, 1]

Description

Allows to get and set construct poles. Replaces the older functions getConstructNames, getConstructNames2, and eNames which are deprecated.

Usage

constructs(x, collapse = FALSE, sep = " - ")

constructs(x, i, j) <- value

leftpoles(x)

leftpoles(x, position) <- value

rightpoles(x)

rightpoles(x, position) <- value

Arguments

Examples

# shorten object name
x <- boeker

## get construct poles
constructs(x) # both left and right poles
leftpoles(x) # left poles only
rightpoles(x)
constructs(x, collapse = TRUE)

## replace construct poles
constructs(x)[1, 1] <- "left pole 1"
constructs(x)[1, "leftpole"] <- "left pole 1" # alternative
constructs(x)[1:3, 2] <- paste("right pole", 1:3)
constructs(x)[1:3, "rightpole"] <- paste("right pole", 1:3) # alternative
constructs(x)[4, 1:2] <- c("left pole 4", "right pole 4")

l <- leftpoles(x)
leftpoles(x) <- sample(l) # brind poles into random order
leftpoles(x)[1] <- "new left pole 1" # replace name of first left pole

# replace left poles of constructs 1 and 3
leftpoles(x)[c(1, 3)] <- c("new left pole 1", "new left pole 3")

Description

Grid data originated (but is not shown in the paper) from a study by Haritos, Gindinis, Doan and Bell (2004) on element role titles. It was used to demonstrate the effects of construct alignment in Bell (2010, p. 46).

References

Bell, R. C. (2010). A note on aligning constructs. Personal Construct Theory and Practice, 7, 43-48.

Haritos, A., Gindidis, A., Doan, C., & Bell, R. C. (2004). The effect of element role titles on construct structure and content. Journal of constructivist psychology, 17(3), 221-236.

Examples

bell2010

Description

The grid data set is used in Bell's technical report "Using SPSS to Analyse Repertory Grid Data" (1997, p. 6). Originally, the data comes from a study by Bell and McGorry (1992).

References

Bell, R. C. (1977). Using SPSS to Analyse Repertory Grid Data. Technical Report, University of Melbourne.

Bell, R. C., & McGorry, P. (1992). The analysis of repertory grids used to monitor the perceptions of recovering psychotic patients. In A. Thomson & P. Cummins (Eds.), European Perspectives in Personal Construct Psychology (p. 137-150). Lincoln, UK: European Personal Construct Association.

Examples

bellmcgorry1992

Description

Grid data from a schizophrenic patient undergoing psychoanalytically oriented psychotherapy. The data was taken during the last stage of therapy (Boeker, 1996, p. 163).

References

Boeker, H. (1996). The reconstruction of the self in the psychotherapy of chronic schizophrenia: a case study with the Repertory Grid Technique. In: Scheer, J. W., Catina, A. (Eds.): Empirical Constructivism in Europe - The Personal Construct Approach (p. 160-167). Giessen: Psychosozial-Verlag.

Examples

boeker

# data is also available as Excel file
path <- system.file("extdata", "boeker.xlsx", package = "OpenRepGrid")
x <- importExcel(path)

Description

A dataset used throughout the book "A Manual for Repertory Grid Technique" (Fransella, Bell and Bannister, 2003, p. 60).

References

Fransella, F., Bell, R. & Bannister, D. (2003). A Manual for Repertory Grid Technique (2. Ed.). Chichester: John Wiley & Sons.

Examples

fbb2003

Description

A description by the authors: "When Teresa, 22 years old, was seen by the second author (LAS) at the psychological services of the University of Salamanca, she was in the final year of her studies in chemical sciences. Although Teresa proves to be an excellent student, she reveals serious doubts about her self worth. She cries frequently, and has great difficulty in meeting others, even though she has a boyfriend who is extremely supportive. Teresa is anxiously hesitant about accepting a new job which would involve moving to another city 600 Km away from home." (Feixas & Saul, 2004, p. 77).

References

Feixas, G., & Saul, L. A. (2004). The Multi-Center Dilemma Project: an investigation on the role of cognitive conflicts in health. The Spanish Journal of Psychology, 7(1), 69-78.

Examples

feixas2004

Description

Case as described by the authors: "Sarah, aged 32, was referred with problems of depression and sexual difficulties relating to childhood sexual abuse. She had three children and was living with her male partner. From the age of 9, her brother, an adult, had sexually abused Sarah. She attended a group for survivors of child sexual abuse and completed repertory grids prior to the group, immediately after the group and at 3- and 6-month follow-up." (Leach et al. 2001, p. 230).

Details

leach2001a is the pre-therapy, leach2001b is the post-therapy therapy dataset. The construct and elements are identical.

References

Leach, C., Freshwater, K., Aldridge, J., & Sunderland, J. (2001). Analysis of repertory grids in clinical practice. The British Journalof Clinical Psychology, 40, 225-248.

Examples

leach2001a
leach2001b

Description

Data set 'Grid C' used in Mackay's paper on inter-element correlation (1992, p. 65).

References

Mackay, N. (1992). Identification, reflection, and correlation: Problems in the bases of repertory grid measures. International Journal of Personal Construct Psychology, 5(1), 57-75.

Examples

mackay1992

Description

Grid data to demonstrate the use of Bertin diagrams (Raeithel, 1998, p. 223). The context of its administration is unknown.

References

Raeithel, A. (1998). Kooperative Modellproduktion von Professionellen und Klienten. Erlaeutert am Beispiel des Repertory Grid. In A. Raeithel (1998). Selbstorganisation, Kooperation, Zeichenprozess. Arbeiten zu einer kulturwissenschaftlichen, anwendungsbezogenen Psychologie (p. 209-254). Opladen: Westdeutscher Verlag.

Examples

raeithel

Description

Drug addict's grid data set from Slater (1977, p. 32).

References

Slater, P. (1977). The measurement of intrapersonal space by grid technique. London: Wiley.

Examples

slater1977a

Description

Grid data (ranked) from a seventeen year old female psychiatric patient (Slater, 1977, p. 110). She was depressed, anxious and took to cutting herself. The data was originally reported by Watson (1970).

References

Slater, P. (1977). The measurement of intrapersonal space by grid technique. London: Wiley.

Watson, J. P. (1970). The relationship between a self-mutilating patient and her doctor. Psychotherapy and Psychosomatics, 18(1), 67-73.

Examples

slater1977b

Description

Various distance measures between elements or constructs are calculated.

Usage

distance(
  x,
  along = 1,
  dmethod = "euclidean",
  p = 2,
  normalize = FALSE,
  trim = 20,
  index = TRUE,
  ...
)

Arguments

Value

matrix object.

Examples

# between constructs
distance(bell2010, along = 1)
distance(bell2010, along = 1, normalize = TRUE)

# between elements
distance(bell2010, along = 2)

# several distance methods
distance(bell2010, dm = "man") # manhattan distance
distance(bell2010, dm = "mink", p = 3) # minkowski metric to the power of 3

# to save the results without printing to the console
d <- distance(bell2010, trim = 7)
d

# some more options when printing the distance matrix
print(d, digits = 5)
print(d, col.index = FALSE)
print(d, upper = FALSE)

# accessing entries from the matrix
d[1, 3]

Description

Calculate Hartmann distance

Usage

distanceHartmann(
  x,
  method = "paper",
  reps = 10000,
  prob = NULL,
  progress = TRUE,
  distributions = FALSE
)

Arguments

Details

Hartmann (1992) showed in a simulation study that Slater distances (see distanceSlater()) based on random grids, for which Slater coined the expression quasis, have a skewed distribution, a mean and a standard deviation depending on the number of constructs elicited. He suggested a linear transformation (z-transformation) which takes into account the estimated (or expected) mean and the standard deviation of the derived distribution to standardize Slater distance scores across different grid sizes. 'Hartmann distances' represent a more accurate version of 'Slater distances'. Note that Hartmann distances are multiplied by -1. Hence, negative Hartmann values represent dissimilarity, i.e. a big Slater distance.

There are two ways to use this function. Hartmann distances can either be calculated based on the reference values (i.e. means and standard deviations of Slater distance distributions) as given by Hartmann in his paper. The second option is to conduct an instant simulation for the supplied grid size for each calculation. The second option will be more accurate when a big number of quasis is used in the simulation.

It is also possible to return the quantiles of the sample distribution and only the element distances considered 'significant' according to the quantiles defined.

Value

A matrix containing Hartmann distances. In the attributes several additional parameters can be found:

• arguments: A list of several parameters including mean and sd of Slater distribution.

• quantiles: Quantiles for Slater and Hartmann distance distribution.

• distributions: List with values of the simulated distributions.

Calculation

The 'Hartmann distance' is calculated as follows (Hartmann 1992, p. 49).

$D = -1 (\frac{D_{slater} - M_c}{sd_c})$

Where $D_{slater}$ denotes the Slater distances of the grid, $M_c$ the sample distribution's mean value and $sd_c$ the sample distribution's standard deviation.

References

Hartmann, A. (1992). Element comparisons in repertory grid technique: Results and consequences of a Monte Carlo study. International Journal of Personal Construct Psychology, 5(1), 41-56.

See Also

distanceSlater()

Examples

## Not run: 

### basics  ###

distanceHartmann(bell2010)
distanceHartmann(bell2010, method = "simulate")
h <- distanceHartmann(bell2010, method = "simulate")
h

# printing options
print(h)
print(h, digits = 6)
# 'significant' distances only
print(h, p = c(.05, .95))

# access cells of distance matrix
h[1, 2]

### advanced  ###

# histogram of Slater distances and indifference region
h <- distanceHartmann(bell2010, distributions = TRUE)
l <- attr(h, "distributions")
hist(l$slater, breaks = 100)
hist(l$hartmann, breaks = 100)

## End(Not run)

Description

Hartmann (1992) suggested a transformation of Slater (1977) distances to make them independent from the size of a grid. Hartmann distances are supposed to yield stable cutoff values used to determine 'significance' of inter-element distances. It can be shown that Hartmann distances are still affected by grid parameters like size and the range of the rating scale used (Heckmann, 2012). The function distanceNormalize applies a Box-Cox (1964) transformation to the Hartmann distances in order to remove the skew of the Hartmann distance distribution. The normalized values show to have more stable cutoffs (quantiles) and better properties for comparison across grids of different size and scale range.

Usage

distanceNormalized(
  x,
  reps = 1000,
  prob = NULL,
  progress = TRUE,
  distributions = TRUE
)

Arguments

Details

The function distanceNormalize can also return the quantiles of the sample distribution and only the element distances considered 'significant' according to the quantiles defined.

Value

A matrix containing the standardized distances.
Further data is contained in the object's attributes:

Calculations

The 'power transformed Hartmann distance' are calculated as follows: The simulated Hartmann distribution is added a constant as the Box-Cox transformation can only be applied to positive values. Then a range of values for lambda in the Box-Cox transformation (Box & Cox, 1964) are tried out. The best lambda is the one maximizing the correlation of the quantiles with the standard normal distribution. The lambda value maximizing normality is used to transform Hartmann distances. As the resulting scale of the power transformation depends on lambda, the resulting values are z-transformed to derive a common scaling.

The code for the calculation of the optimal lambda was written by Ioannis Kosmidis.

References

Box, G. E. P., & Cox, D. R. (1964). An Analysis of Transformations. Journal of the Royal Statistical Society. Series B (Methodological), 26(2), 211-252.

Hartmann, A. (1992). Element comparisons in repertory grid technique: Results and consequences of a Monte Carlo study. International Journal of Personal Construct Psychology, 5(1), 41-56.

Heckmann, M. (2012). Standardizing inter-element distances in grids - A revision of Hartmann's distances, 11th Biennal Conference of the European Personal Construct Association (EPCA), Dublin, Ireland, Paper presentation, July 2012.

Slater, P. (1977). The measurement of intrapersonal space by Grid technique. London: Wiley.

See Also

distanceHartmann() and distanceSlater().

Examples

## Not run: 

### basics  ###

distanceNormalized(bell2010)
n <- distanceNormalized(bell2010)
n

# printing options
print(n)
print(n, digits = 4)
# 'significant' distances only
print(n, p = c(.05, .95))

# access cells of distance matrix
n[1, 2]

### advanced  ###

# histogram of Slater distances and indifference region
n <- distanceNormalized(bell2010, distributions = TRUE)
l <- attr(n, "distributions")
hist(l$bc, breaks = 100)

## End(Not run)

Description

The euclidean distance is often used as a measure of similarity between elements (see distance(). A drawback of this measure is that it depends on the range of the rating scale and the number of constructs used, i. e. on the size of a grid.
An approach to standardize the euclidean distance to make it independent from size and range of ratings and was proposed by Slater (1977, pp. 94). The 'Slater distance' is the Euclidean distance divided by the expected distance. Slater distances bigger than 1 are greater than expected, lesser than 1 are smaller than expected. The minimum value is 0 and values bigger than 2 are rarely found. Slater distances have been be used to compare inter-element distances between different grids, where the grids do not need to have the same constructs or elements. Hartmann (1992) showed that Slater distance is not independent of grid size. Also the distribution of the Slater distances is asymmetric. Hence, the upper and lower limit to infer 'significance' of distance is not symmetric. The practical relevance of Hartmann's findings have been demonstrated by Schoeneich and Klapp (1998). To calculate Hartmann's version of the standardized distances see distanceHartmann()

Usage

distanceSlater(x, trim = 20, index = TRUE)

Arguments

Value

A matrix with Slater distances.

Calculation

The Slater distance is calculated as follows. For a derivation see Slater (1977, p.94).
Let matrix $D$ contain the row centered ratings. Then

$P = D^TD$

and

$S = tr(P)$

The expected 'unit of expected distance' results as

$U = (2S/(m-1))^{1/2}$

where $m$ denotes the number of elements of the grid. The standardized Slater distances is the matrix of Euclidean distances $E$ divided by the expected distance $U$.

$E/U$

References

Hartmann, A. (1992). Element comparisons in repertory grid technique: Results and consequences of a Monte Carlo study. International Journal of Personal Construct Psychology, 5(1), 41-56.

Schoeneich, F., & Klapp, B. F. (1998). Standardization of interelement distances in repertory grid technique and its consequences for psychological interpretation of self-identity plots: An empirical study. Journal of Constructivist Psychology, 11(1), 49-58.

Slater, P. (1977). The measurement of intrapersonal space by Grid technique. Vol. II. London: Wiley.

See Also

distanceHartmann()

Examples

distanceSlater(bell2010)
distanceSlater(bell2010, trim = 40)

d <- distanceSlater(bell2010)
print(d)
print(d, digits = 4)

# using Norris and Makhlouf-Norris (problematic) cutoffs
print(d, cutoffs = c(.8, 1.2))

Description

Note that simple element correlations as a measure of similarity are flawed as they are not invariant to construct reflection (Mackay, 1992; Bell, 2010). A correlation index invariant to construct reflection is Cohen's rc measure (1969), which can be calculated using the argument rc=TRUE which is the default option.

Usage

elementCor(x, rc = TRUE, method = "pearson", trim = 20, index = TRUE)

Arguments

Value

matrix of element correlations

References

Bell, R. C. (2010). A note on aligning constructs. Personal Construct Theory & Practice, (7), 42-48.

Cohen, J. (1969). rc: A profile similarity coefficient invariant over variable reflection. Psychological Bulletin, 71(4), 281-284.

Mackay, N. (1992). Identification, Reflection, and Correlation: Problems In The Bases Of Repertory Grid Measures. International Journal of Personal Construct Psychology, 5(1), 57-75.

See Also

constructCor()

Examples

elementCor(mackay1992) # Cohen's rc
elementCor(mackay1992, rc = FALSE) # PM correlation
elementCor(mackay1992, rc = FALSE, method = "spearman") # Spearman correlation

# format output
elementCor(mackay1992, trim = 6)
elementCor(mackay1992, index = FALSE, trim = 6)

# save as object for further processing
r <- elementCor(mackay1992)
r

# change output of object
print(r, digits = 5)
print(r, col.index = FALSE)
print(r, upper = FALSE)

# accessing elements of the correlation matrix
r[1, 3]

Description

The RMS is also known as 'quadratic mean' of the inter-element correlations. The RMS serves as a simplification of the correlation table. It reflects the average relation of one element with all other elements. Note that as the correlations are squared during its calculation, the RMS is not affected by the sign of the correlation (cf. Fransella, Bell & Bannister, 2003, p. 86).

Usage

elementRmsCor(x, rc = TRUE, method = "pearson", trim = NA)

Arguments

Details

Note that simple element correlations as a measure of similarity are flawed as they are not invariant to construct reflection (Mackay, 1992; Bell, 2010). A correlation index invariant to construct reflection is Cohen's rc measure (1969), which can be calculated using the argument rc=TRUE which is the default option in this function.

Value

dataframe of the RMS of inter-element correlations.

References

Fransella, F., Bell, R. C., & Bannister, D. (2003). A Manual for Repertory Grid Technique (2. Ed.). Chichester: John Wiley & Sons.

See Also

constructRmsCor(), elementCor()

Examples

# data from grid manual by Fransella, Bell and Bannister
elementRmsCor(fbb2003)
elementRmsCor(fbb2003, trim = 10)

# modify output
r <- elementRmsCor(fbb2003)
print(r, digits = 5)

# access second row of calculation results
r[2, "RMS"]

Description

Allows to get and set element names. Replaces the older functions getElementNames, getElementNames2, and eNames which are deprecated.

Usage

elements(x)

elements(x, position) <- value

Arguments

Examples

# copy Boeker grid to x
x <- boeker

## get element names
e <- elements(x)
e

## replace element names
elements(x) <- rev(e) # reverse all element names
elements(x)[1] <- "Hannes" # replace name of first element

# replace names of elements 1 and 3
elements(x)[c(1, 3)] <- c("element 1", "element 3")

Description

Add repgrids into a gridlist

Test or create object of class gridlist

Usage

gridlist(...)

is.gridlist(x)

as.gridlist(x)

Arguments

Description

The goal of resampling is to build variations of a single grid. Two variants are implemented: The first is the leave-n-out approach which builds all possible grids when dropping n constructs. The second is a bootstrap approach, randomly drawing n constructs from the grid.

Usage

grids_leave_n_out(x, n = 0)

grids_bootstrap(x, n = nrow(x), reps = 100, replace = TRUE)

Arguments

Value

List of grids.

Examples

## All results for PVAFF index when one construct is left out 
p <- indexPvaff(boeker)
l <- grids_leave_n_out(boeker, n = 1)
pp <- sapply(l, indexPvaff)  # apply indexPvaff function to all grids
range(pp)   # min and max PVAFF
hist(pp, xlab = "PVAFF values")    # visualize
abline(v = p, col = "blue", lty = 2)

Description

Rotate the interactive 3D device to a default viewpoint or to a position defined by theta and phi in Euler angles. Three default viewpoints are implemented rendering a view so that two axes span a plane and the third axis is pointing out of the screen.

Usage

home(view = 1, theta = NULL, phi = NULL)

Arguments

See Also

Interactive 3D biplots: biplot3d(), biplotSlater3d(), biplotEsa3d().

Examples

## Not run: 

biplot3d(boeker)
home(2)
home(3)
home(1)
home(theta = 45, phi = 45)

## End(Not run)

Description

You can define a grid using Microsoft Excel and by saving it as a .xlsx file. The .xlsx file has to be in a specified fixed format (see section Details).

Usage

importExcel(file, dir = NULL, sheetIndex = 1, min = NULL, max = NULL)

Arguments

Details

Excel file structure: The first row contains the minimum of the rating scale, the names of the elements and the maximum of the rating scale. Below every row contains the left construct pole, the ratings and the right construct pole.

Note that the maximum and minimum value has to be defined using the min and max arguments if no values are supplied at the beginning and end of the first row. Otherwise the scaling range is inferred from the available data and a warning is issued as the range may be erroneous. This may effect other functions that depend on knowing the correct range and it is thus strongly recommended to set the scale range correctly.

Value

A single repgrid object in case one file and a list of repgrid objects in case multiple files are imported.

See Also

importGridcor(), importGridstat(), importScivesco(), importGridsuite(), importTxt()

Examples

## Not run: 

# Open Excel file delivered along with the package
file <- system.file("extdata", "grid_01.xlsx", package = "OpenRepGrid")
rg <- importExcel(file)

# To see the structure of the Excel file try to open it as follows.
# Requires Excel to be installed.
system2("open", file)

# Import more than one Excel file
files <- system.file("extdata", c("grid_01.xlsx", "grid_02.xlsx"), package = "OpenRepGrid")
rg <- importExcel(files)

## End(Not run)

Description

Reads the file format that is used by the grid program GRIDCOR (Feixas & Cornejo, 2002).

Usage

importGridcor(file, dir = NULL)

Arguments

Value

a single repgrid object in case one file and a list of repgrid objects in case multiple files are imported.

Note

Note that the GRIDCOR data sets the minimum ratings scale range to 1. The maximum value can differ and is defined in the data file.

Also note that both Gridcor and Gridstat data files do have the same suffix .dat. Make sure not to mix them up.

References

Feixas, G., & Cornejo, J. M. (2002). GRIDCOR: Correspondence Analysis for Grid Data (version 4.0). Barcelona: Centro de Terapia Cognitiva. Retrieved from https://repertorygrid.net/en/.

See Also

importGridcor(), importGridstat(), importScivesco(), importGridsuite(), importTxt(), importExcel()

Examples

## Not run: 

# supposing that the data file gridcor.dat is in the current directory
file <- "gridcor.dat"
rg <- importGridcor(file)

# specifying a directory (arbitrary example directory)
dir <- "/Users/markheckmann/data"
rg <- importGridcor(file, dir)

# using a full path
rg <- importGridcor("/Users/markheckmann/data/gridcor.dat")

## End(Not run)

Description

Reads the file format that is used by the latest version of the grid program gridstat (Bell, 1998).

Usage

importGridstat(file, dir = NULL, min = NULL, max = NULL)

Arguments

Value

A single repgrid object in case one file and a list of repgrid objects in case multiple files are imported.

Note

Note that the gridstat data format does not contain explicit information about the range of the rating scale used (minimum and maximum). By default the range is inferred by scanning the ratings and picking the minimal and maximal values as rating range. You can set the minimal and maximal value by hand using the min and max arguments or by using the setScale() function. Note that if the rating range is not set, it may cause several functions to not work properly. A warning will be issued if the range is not set explicitly when using the importing function.

The function only reads data from the latest GridStat version. The latest version allows the separation of the left and right pole by using on of the following symbols ⁠/:-⁠ (hyphen, colon and dash). Older versions may not separate the left and right pole. This will cause all labels to be assigned to the left pole only when importing. You may fix this by simply entering one of the construct separator symbols into the GridStat file between each left and right construct pole.

The third line of a GridStat file may contain a no labels statement (i.e. a line containing any string of 'NOLA', 'NO L', 'NoLa', 'No L', 'Nola', 'No l', 'nola' or 'no l'). In this case only ratings are supplied, hence, default names are assigned to elements and constructs.

References

Bell, R. C. (1998) GRIDSTAT: A program for analyzing the data of a repertory grid. Melbourne: Author.

See Also

importGridcor(), importGridstat(), importScivesco(), importGridsuite(), importTxt(), importExcel()

Examples

## Not run: 

# supposing that the data file gridstat.dat is in the current working directory
file <- "gridstat.dat"
rg <- importGridstat(file)

# specifying a directory (example)
dir <- "/Users/markheckmann/data"
rg <- importGridstat(file, dir)

# using a full path (example)
rg <- importGridstat("/Users/markheckmann/data/gridstat.dat")

# setting rating scale range
rg <- importGridstat(file, dir, min = 1, max = 6)

## End(Not run)

Description

Import Gridsuite data files.

Usage

importGridsuite(file, dir = NULL)

Arguments

Value

A single repgrid object in case one file and a list of repgrid objects in case multiple files are imported.

Note

The developers of Gridsuite have proposed to use an XML scheme as a standard exchange format for repertory grid data (Walter, Bacher & Fromm, 2004).

TODO: The element and construct IDs are not used yet. Thus, if the output should be in different order the current mechanism will cause false assignments.

References

http://www.gridsuite.de/

Walter, O. B., Bacher, A., & Fromm, M. (2004). A proposal for a common data exchange format for repertory grid data.Journal of Constructivist Psychology, 17(3), 247. doi:10.1080/10720530490447167

See Also

importGridcor(), importGridstat(), importScivesco(), importGridsuite(), importTxt(), importExcel()

Examples

## Not run: 

# supposing that the data file gridsuite.xml is in the current directory
file <- "gridsuite.xml"
rg <- importGridsuite(file)

# specifying a directory (arbitrary example directory)
dir <- "/Users/markheckmann/data"
rg <- importGridsuite(file, dir)

# using a full path
rg <- importGridsuite("/Users/markheckmann/data/gridsuite.xml")

## End(Not run)

Description

Import sci:vesco data files.

Usage

importScivesco(file, dir = NULL)

Arguments

Value

A single repgrid object in case one file and a list of repgrid objects in case multiple files are imported.

Note

Sci:Vesco offers the options to rate the construct poles separately or using a bipolar scale. The separated rating is done using the "tetralemma" field. The field is a bivariate plane on which each of the four (tetra) corners has a different meaning in terms of rating. Using this approach also allows ratings like: "both poles apply", "none of the poles apply" and all intermediate ratings can be chosen. This relaxes the bipolarity assumption often assumed in grid theory and allows for deviation from a strict bipolar rating if the constructs are not applied in a bipolar way. Using the tetralemma field for rating requires to analyze each construct separately though. This means we get a double entry grid where the emergent and contrast pole ratings might not simply be a reflection of on another. The tetralemma field is not yet supported and importing will fail. Currently only bipolar ratings are supported.

If a tetralemma field has been used for rating, OpenRepGrid will offer the option to transform the scores into "normal" grid ratings (i.e. restricted to bipolarity) by projecting the ratings from the bivariate tetralemma field onto the diagonal of the tetralemma field and thus forcing a bipolar rating type. This option is not recommended due to the fact that the conversion is susceptible to error when both ratings are near to zero.

TODO: For developers: The element IDs are not used yet. This might cause wrong assignments.

References

Menzel, F., Rosenberger, M., Buve, J. (2007). Emotionale, intuitive und rationale Konstrukte verstehen. Personalfuehrung, 4(7), 91-99.

See Also

importGridcor(), importGridstat(), importScivesco(), importGridsuite(), importTxt(), importExcel()

Examples

## Not run: 

# supposing that the data file scivesco.scires is in the current directory
file <- "scivesco.scires"
rg <- importScivesco(file)

# specifying a directory (arbitrary example directory)
dir <- "/Users/markheckmann/data"
rg <- importScivesco(file, dir)

# using a full path
rg <- importScivesco("/Users/markheckmann/data/scivesco.scires")

## End(Not run)

Description

You can define a grid using a standard text editor and saving it as a .txt file. The Details section describes the required format of the .txt file. However, you may also consider using the Excel format instead, as it has a more intuitive format (see importExcel()).

Usage

importTxt(file, dir = NULL, min = NULL, max = NULL)

Arguments

Details

The .txt file has to be in a fixed format. There are three mandatory blocks each starting and ending with a predefined tag in uppercase letters. The first block starts with ELEMENTS and ends with ⁠END ELEMENTS⁠ and contains one element in each line. The other mandatory blocks contain the constructs and ratings (see below). In the block containing the constructs the left and right pole are separated by a colon (:). To define missing values use NA like in the example below. One optional block contains the range of the rating scale used defined by two numbers. The order of the blocks is arbitrary. All text not contained within the blocks is discarded and can thus be used for comments.

The content of a sample .txt file is shown below. The package also contains a sample file (see Examples).

---------------- sample .txt file -------------------

    Note: anything outside the tag pairs is discarded

ELEMENTS
element 1
element 2
element 3
END ELEMENTS

CONSTRUCTS
left pole 1 : right pole 1
left pole 2 : right pole 2
left pole 3 : right pole 3
left pole 4 : right pole 4
END CONSTRUCTS

RATINGS
1 3 2
4 1 1
1 4 4
3 1 1
END RATINGS

RANGE
1 4
END RANGE

------------------ end of file ------------------

Note that the maximum and minimum value has to be defined using the min and max arguments if no RANGE block is contained in the data file. Otherwise the scaling range is inferred from the available data and a warning is issued as the range may be erroneous. This may effect other functions that depend on knowing the correct range and it is thus strongly recommended to set the scale range correctly.

Value

A single repgrid object in case one file and a list of repgrid objects in case multiple files are imported.

See Also

importGridcor(), importGridstat(), importScivesco(), importGridsuite(), importTxt(), importExcel()

Examples

# Import a .txt file delivered along with the package
file <- system.file("extdata", "grid_01.txt", package = "OpenRepGrid")
rg <- importTxt(file)

## Not run: 
# To see the structure of the Excel file try to open it as follows.
# May not work on all systems.
file.show(file)

## End(Not run)

# Import more than one .txt file
files <- system.file("extdata", c("grid_01.txt", "grid_02.txt"), package = "OpenRepGrid")
rgs <- importTxt(files)

Description

"Bias records a tendency for responses to accumulate at one end of the grading scale" (Slater, 1977, p.88).

Usage

indexBias(x, min = NULL, max = NULL, digits = 2)

Arguments

Value

Numeric.

Note

STATUS: Working and checked against example in Slater, 1977, p. 87.

References

Slater, P. (1977). The measurement of intrapersonal space by Grid technique. London: Wiley.

See Also

indexVariability()

Examples

indexBias(boeker)

Description

The index builds on the number of rating matches between pairs of constructs. It is the relation between the total number of matches and the possible number of matches.

Usage

indexBieri(x, deviation = 0)

Arguments

Details

CAVEAT: The Bieri index will change when constructs are reversed.

Value

List of class indexBieri:

• grid: The grid used to calculate the index

• deviation The deviation parameter.

• matches_max Maximum possible number of matches across constructs.

• matches Total number of matches across constructs.

• constructs: Matrix with no. of matches for constructs.

• bieri: Bieri index (= matches / matches_max)

Examples

m <- indexBieri(boeker)

# several output options
print(m)
print(m, output = "IC")  # construct matches

# extract the matrix of matches
m$constructs

# CAVEAT: Bieri's index changes when constructs are reversed
nr <- nrow(boeker)
l <- replicate(1000, swapPoles(boeker, sample(nr, sample(nr, 1))))
bieri <- sapply(l, function(x) indexBieri(x)$bieri)
hist(bieri, breaks = 50)
abline(v = mean(bieri), col = "red", lty = 2)

Description

Conflict measure as proposed by Slade and Sheehan (1979)

Usage

indexConflict1(x)

Arguments

Details

The first approach to mathematically derive a conflict measure based on grid data was presented by Slade and Sheehan (1979). Their operationalization is based on an approach by Lauterbach (1975) who applied the balance theory (Heider, 1958) for a quantitative assessment of psychological conflict. It is based on a count of balanced and imbalanced triads of construct correlations. A triad is imbalanced if one or all three of the correlations are negative, i. e. leading to contrary implications. This approach was shown by Winter (1982) to be flawed. An improved version was proposed by Bassler et al. (1992) and has been implemented in the function indexConflict2.

The table below shows when a triad made up of the constructs A, B, and C is balanced and imbalanced:

Value

A list with the following elements:

• total: Total number of triads

• imbalanced: Number of imbalanced triads

• prop.balanced: Proportion of balanced triads

• prop.imbalanced: Proportion of imbalanced triads

References

Bassler, M., Krauthauser, H., & Hoffmann, S. O. (1992). A new approach to the identification of cognitive conflicts in the repertory grid: An illustrative case study. Journal of Constructivist Psychology, 5(1), 95-111.

Heider, F. (1958). The Psychology of Interpersonal Relation. John Wiley & Sons.

Lauterbach, W. (1975). Assessing psychological conflict. The British Journal of Social and Clinical Psychology, 14(1), 43-47.

Slade, P. D., & Sheehan, M. J. (1979). The measurement of 'conflict' in repertory grids. British Journal of Psychology, 70(4), 519-524.

Winter, D. A. (1982). Construct relationships, psychological disorder and therapeutic change. The British Journal of Medical Psychology, 55 (Pt 3), 257-269.

See Also

indexConflict2() for an improved version of this measure; see indexConflict3() for a measure based on distances.

Examples

indexConflict1(feixas2004)
indexConflict1(boeker)

Description

The function calculates the conflict measure as devised by Bassler et al. (1992). It is an improved version of the ideas by Slade and Sheehan (1979) that have been implemented in the function indexConflict1(). The new approach also takes into account the magnitude of the correlations in a trait to assess whether it is balanced or imbalanced. As a result, small correlations that are psychologically meaningless are considered accordingly. Also, correlations with a small magnitude, i. e. near zero, which may be positive or negative due to chance alone will no longer distort the measure (Bassler et al., 1992).

Usage

indexConflict2(x, crit = 0.03)

Arguments

Details

Description of the balance / imbalance assessment:

1. Order correlations of the triad by absolute magnitude, so that $r_{max} > r_{mdn} > r_{min}$, $r_{max} > r_{mdn} > r_{min}$.

2. Apply Fisher's Z-transformation and division by 3 to yield values between 1 and -1 ($Z_{max} > Z_{mdn} > Z_{min}, Z_{max} > Z_{mdn} > Z_{min}$).

3. Check whether the triad is balanced by assessing if the following relation holds:

   • If $Z_{max} Z_{mdn} > 0, Z_{max} x Z_{mdn} > 0$, the triad is balanced if $Z_{max} Z_{mdn} - Z_{min} <= crit$, $Z_{max} x Z_{mdn} - Z_{min} <= crit$.

   • If $Z_{max} Z_{mdn} < 0, Z_{max} x Z_{mdn} < 0$, the triad is balanced if $Z_{min} - Z_{max} Z_{mdn} <= crit$, $Z_{min} - Z_{max} x Z_{mdn} <= crit$.

Personal remarks (MH)

I am a bit suspicious about step 2 from above. To devide by 3 appears pretty arbitrary. The r for a z-values of 3 is 0.9950548 and not 1. The r for 4 is 0.9993293. Hence, why not a value of 4, 5, or 6? Denoting the value to devide by with a, the relation for the first case translates into $a Z_{max} Z_{mdn} <= \frac{crit}{a} + Z_{min}$, $a x Z_{max} x Z_{mdn} =< crit/a + Z_{min}$. This shows that a bigger value of a will make it more improbable that the relation will hold.

References

Bassler, M., Krauthauser, H., & Hoffmann, S. O. (1992). A new approach to the identification of cognitive conflicts in the repertory grid: An illustrative case study. Journal of Constructivist Psychology, 5(1), 95-111.

Slade, P. D., & Sheehan, M. J. (1979). The measurement of 'conflict' in repertory grids. British Journal of Psychology, 70(4), 519-524.

See Also

See indexConflict1() for the older version of this measure; see indexConflict3() for a measure based on distances instead of correlations.

Examples

indexConflict2(bell2010)

x <- indexConflict2(bell2010)
print(x)

# show conflictive triads
print(x, output = 2)

# accessing the calculations for further use
x$total
x$imbalanced
x$prop.balanced
x$prop.imbalanced
x$triads.imbalanced

Description

Measure of conflict or inconsistency as proposed by Bell (2004). The identification of conflict is based on distances rather than correlations as in other measures of conflict indexConflict1() and indexConflict2(). It assesses if the distances between all components of a triad, made up of one element and two constructs, satisfies the "triangle inequality" (cf. Bell, 2004). If not, a triad is regarded as conflictive. An advantage of the measure is that it can be interpreted not only as a global measure for a grid but also on an element, construct, and element by construct level making it valuable for detailed feedback. Also, differences in conflict can be submitted to statistical testing procedures.

Usage

indexConflict3(
  x,
  p = 2,
  e.out = NA,
  e.threshold = NA,
  c.out = NA,
  c.threshold = NA,
  trim = 20
)

Arguments

Details

Status: working; output for euclidean and manhattan distance checked against Gridstat output.
TODO: standardization and z-test for discrepancies; Index of Conflict Variation.

Value

A list (invisibly) containing:

• potential: number of potential conflicts

• actual: count of actual conflicts

• overall: percentage of conflictive relations

• e.count: number of involvements of each element in conflictive relations

• e.perc: percentage of involvement of each element in total of conflictive relations

• c.count: number of involvements of each construct in conflictive relation

• c.perc: percentage of involvement of each construct in total of conflictive relations

• e.stats: detailed statistics for prompted elements

• c.stats: detailed statistics for prompted constructs

• e.threshold: threshold percentage. Used by print method

• c.threshold: threshold percentage. Used by print method

• enames: trimmed element names. Used by print method

• cnames: trimmed construct names. Used by print method

output

For further control over the output see print.indexConflict3().

References

Bell, R. C. (2004). A new approach to measuring inconsistency or conflict in grids. Personal Construct Theory & Practice, (1), 53-59.

See Also

See indexConflict1() and indexConflict2() for conflict measures based on triads of correlations.

Examples

# calculate conflicts
indexConflict3(bell2010)

# show additional stats for elements 1 to 3
indexConflict3(bell2010, e.out = 1:3)

# show additional stats for constructs 1 and 5
indexConflict3(bell2010, c.out = c(1, 5))

# finetune output
## change number of digits
x <- indexConflict3(bell2010)
print(x, digits = 4)

## omit discrepancy matrices for constructs
x <- indexConflict3(bell2010, c.out = 5:6)
print(x, discrepancies = FALSE)

Description

Measures the degree of dispersion of dependency in a situation-resource grid (dependency grid), i.e. the degree to which a person dispersed critical situations over resource persons (Walker et al., 1988, p. 66). The index is a renamed adoption of the ⁠diversity index⁠ from the field of ecology where it is used to measure the diversity of species in a sample. Both are computationally identical. The index is applicable to dependency grids (e.g., situation-resource) only, i.e., all grid ratings must be 0 or 1.

Usage

indexDDI(x, ds)

Arguments

Details

Caveat: The DDI depends on the chosen sample size ds. Also, its measurement range is not normalized between 0 and 1, allowing only comparison between similarly sized grids (see Bell, 2001).

Theoretical Background: Dispersion of Dependency: Kelly (1969) proposed that it is problematic to view people as either independent or dependent because everyone is, to greater or lesser degrees, dependent upon others in life. What Kelly felt was important was how well people disperse their dependencies across different people. Whereas young children tend to have their dependencies concentrated on a small number of people (typically parents), adults are more likely to spread their dependencies across a variety of others. Dispersing one's dependencies is generally considered more psychologically adjusted for adults (Walker et al., 1988).

References

Bell, R. C. (2001). Some new Measures of the Dispersion of Dependency in a Situation-Resource Grid. Journal of Constructivist Psychology, 14(3), 227-234, doi:10.1080/713840106.

Kelly, G. A. (1962). In whom confide: On whom depend for what. In Maher, B. (Ed.). Clinical psychology and personality: The selected papers of George Kelly, 189-206. New York Krieger.

Walker, B. M., Ramsey, F. L., & Bell, R. (1988). Dispersed and Undispersed Dependency. International Journal of Personal Construct Psychology, 1(1), 63-80, doi:10.1080/10720538808412765.

See Also

indexUncertainty

Examples

# sample grid from Walker et al. (1988), p. 67
file <- system.file("extdata", "dep_grid_walker_1988_2.xlsx" , package = "OpenRepGrid")
x <- importExcel(file)

indexDDI(x, ds = 2:5) 

# using named vector
ds = c("2"=2, "3"=3, "4"=4, "5"=5)  
indexDDI(x, ds)