QCA: XYplot – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

XYplot

Create an XY plot

Description

This function creates an XY plot from the first two columns of a dataframe/matrix, or from two separate vectors of numeric values.

Usage

XYplot(x, y, data, relation = "sufficiency", mguides = TRUE,
       jitter = FALSE, clabels, enhance = FALSE, model = FALSE, ...)

Arguments

`x`	Character, the name of the column from the `data` for the X axis, or the coordinates of points in the plot (either a matrix/dataframe with at least two columns, or a vector of numerical values for the X axis), or a valid SOP expression.
`y`	Character, the name of the column from the `data` for the Y axis, or the Y coordinates of points in the plot, optional if `x` is a matrix/dataframe.
`data`	A calibrated dataset, only if `x` and `y` are names.
`relation`	The set relation to Y, either `"sufficiency"` (default) or `"necessity"`.
`mguides`	Logical, print the middle guides.
`jitter`	Logical, jitter the points.
`clabels`	A vector of case labels with the same length as `x` and `y`, or a logical vector of the same length as the number of rows in the `data` (if provided).
`enhance`	Logical, if `TRUE` print the points using different characters for each of the five significant regions for process tracing.
`model`	Logical, for an enhanced plot specify if the SOP expression in argument `x` is a solution model.
`...`	Other graphical parameters from `?par`

Details

If x is a dataframe or a matrix, the axes labels will be taken from the column names of x, otherwise they will be inferred from the names of the x and y objects that are passed to this function.

x can also be a string containing either the name of the column for the X axis, or two column names separated by a comma, referring to the X and Y axis respectively. When x contains both X and Y column names, the next argument will be considered as the data.

If data is provided, and the names of the X and Y columns are valid R statements, quoting them is not even necessary and they can be negated using either a tilde "~" or "1 - ".

The numeric values should be restricted between 0 and 1, otherwise an error is generated.

The XY plot will also provide inclusion and coverage scores for a sufficiency (along with PRI) or a necessity relation (along with RoN).

The argument x can also be a SOP - sum of products expression, in which case the relation is determined by the usual forward arrow "=>" for sufficiency and backward arrow "<=" for necessity.

The argument ... is used to pass arguments to the various graphical parameters from ?par, and also to the settings from ?jitter.

The points have a default cex (character expansion) value of 0.8, and a default pch value of 21 (filled points), which can be modified accordingly (for example with value 1 of empty points). When pch = 21, the color for the margins of the points can be specified via the argument col, while the argument bg will determine the fill color of the points.

The axes' labels have a default cex.axis value of 0.8, which affects both the tickmarks labels and the axis labels.

When jittering the points, default values of 0.01 are used for the parameters factor and amount, on both horizontal and vertical axes.

The argument enhance does all the work for the shape of the points and their colors, acording to the five regions specified by Schneider & Rohlfing (2016), who augmented the classical XY plot with process tracing.

The default enhanced XY plot has even more settings when the input SOP expression is a minimization model (different colors, different regions where to place the labels etc.), available by activating the argument model. The model is automatically detected if the input for x is a minimization object.

Value

A list of x and y values, especially useful when the points are jittered.

Author(s)

Adrian Dusa

References

Schneider, C.; Wagemann, C. (2012) Set-Theoretic Metods for the Social Sciences. A Guide to Qualitative Comparative Analysis. Cambridge: Cambridge University Press.

Cebotari, V.; Vink, M.P. (2013) “A Configurational Analysis of Ethnic Protest in Europe”. International Journal of Comparative Sociology vol.54, no.4, pp.298-324.

Schneider, C.; Rohlfing, I. (2016) “Case Studies Nested in Fuzzy-set QCA on Sufficiency. Formalizing Case Selection and Causal Inference”. Sociological Methods and Research vol.45, no.3, pp.536-568, doi: 10.1177/0049124114532446

Examples

# Cebotari & Vink (2013)
# necessity relation between NATPRIDE and PROTEST
XYplot(CVF[, 5:6])

# same using two numeric vectors
XYplot(CVF$NATPRIDE, CVF$PROTEST)

# same using two column names
XYplot(NATPRIDE, PROTEST, data = CVF)

# since they are valid R statements, it works even without quotes
# (this only works in normal R console, not in the GUI version)
XYplot(NATPRIDE, PROTEST, data = CVF)

# negating the X axis, using numeric vectors
XYplot(1 - CVF$NATPRIDE, CVF$PROTEST)

# same thing using quotes
XYplot(1 - NATPRIDE, PROTEST, data = CVF)

# using tilde for negation
XYplot(~NATPRIDE, PROTEST, data = CVF)

# different color for the points
XYplot(~NATPRIDE, PROTEST, data = CVF, col = "blue")

# using a different character expansion for the axes
XYplot(~NATPRIDE, PROTEST , data = CVF, cex.axis = 0.9)

# custom axis labels
XYplot(~NATPRIDE, PROTEST, data = CVF, xlab = "Negation of NATPRIDE",
       ylab = "Outcome: PROTEST")

# necessity relation
XYplot(~NATPRIDE, PROTEST, data = CVF, relation = "necessity")

# jitter the points
XYplot(~NATPRIDE, PROTEST, data = CVF, jitter = TRUE)

# jitter with more amount
XYplot(~NATPRIDE, PROTEST, data = CVF, jitter = TRUE, amount = 0.02)

# adding labels to points
XYplot(~NATPRIDE, PROTEST, data = CVF, jitter = TRUE, cex = 0.8,
       clabels = rownames(CVF))

# or just the row numbers, since the row names are too long
XYplot(~NATPRIDE, PROTEST, data = CVF, jitter = TRUE, cex = 0.8,
       clabels = seq(nrow(CVF)))


# using a SOP expression (necessity relation)
XYplot(NATPRIDE <- ~PROTEST, data = CVF, jitter = TRUE, cex = 0.8,
       clabels = seq(nrow(CVF)))


#-----
# enhanced XY plot for process tracing
XYplot(~NATPRIDE, PROTEST, data = CVF, enhance = TRUE, jitter = TRUE)


# enhanced XY plot for a solution model
ttCVF <- truthTable(CVF, outcome = PROTEST, incl.cut = 0.85)
pCVF <- minimize(ttCVF, include = "?")
XYplot(pCVF$solution[[1]], PROTEST, data = CVF, enhance = TRUE)


# same plot, using the solution as a SOP expression
XYplot(~NATPRIDE + DEMOC*GEOCON*POLDIS + DEMOC*ETHFRACT*GEOCON,
      PROTEST, data = CVF, enhance = TRUE, model = TRUE)

QCA

Qualitative Comparative Analysis

v3.11

GPL (>= 3)

Authors

Adrian Dusa [aut, cre, cph] (<https://orcid.org/0000-0002-3525-9253>), Ciprian Paduraru [ctb] (<https://orcid.org/0000-0002-4518-374X>), jQuery Foundation [cph] (jQuery library and jQuery UI library), jQuery contributors [ctb, cph] (jQuery library; authors listed in inst/gui/www/lib/jquery-AUTHORS.txt), lp_solve [cph] (http://lpsolve.sourceforge.net), Vasil Dinkov [ctb, cph] (jquery.smartmenus.js library), Dmitry Baranovskiy [ctb, cph] (raphael.js library), Emmanuel Quentin [ctb, cph] (raphael.inline_text_editing.js library), Jimmy Breck-McKye [ctb, cph] (raphael-paragraph.js library), Alrik Thiem [aut] (from version 1.0-0 up to version 1.1-3)

Initial release

2021-01-21