| Title: | Taxometric Analysis |
|---|---|
| Description: | We provide functions to perform taxometric analyses. This package contains 46 functions, but only 5 should be called directly by users. CheckData() should be run prior to any taxometric analysis to ensure that the data are appropriate for taxometric analysis. RunTaxometrics() performs taxometric analyses for a sample of data. RunCCFIProfile() performs a series of taxometric analyses to generate a CCFI profile. CreateData() generates a sample of categorical or dimensional data. ClassifyCases() assigns cases to groups using the base-rate classification method. |
| Authors: | John Ruscio <[email protected]> and Shirley Wang <[email protected]> |
| Maintainer: | John Ruscio <[email protected]> |
| License: | MIT + file LICENSE |
| Version: | 3.2.1 |
| Built: | 2024-12-08 06:57:56 UTC |
| Source: | CRAN |
This function adds variance if necessary
AddVariance(x, k, parameters)AddVariance(x, k, parameters)
x |
The supplied data matrix. |
k |
The number of variables. |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
Data with necessary variance added
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function assigns variables to input/output configurations for MAMBAC analysis.
AssignMAMBAC(parameters)AssignMAMBAC(parameters)
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
Input/output variables per curve
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function assigns variables to input/output configurations for MAXEIG analysis.
AssignMAXEIG(parameters)AssignMAXEIG(parameters)
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
Input/output variables per curve
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates and reports base rate estimates for taxometric analysis.
CalculateBaseRates(x.results, parameters)CalculateBaseRates(x.results, parameters)
x.results |
Empirical data results |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
This program returns nothing, and provides text output only.
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates CCFIs for a MAMBAC, MAXEIG, or MAXSLOPE curve
CalculateCCFI(curve, curve.dim, curve.cat)CalculateCCFI(curve, curve.dim, curve.cat)
curve |
Empirical data curve |
curve.dim |
Average curve for dimensional comparison data |
curve.cat |
Average curve for categorical comparison data |
Called by higher-order functions; users do not need to call this function directly.
CCFI value
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates CCFI results for CCFI profiles
CalculateCCFIs(x.results, x.dim.results, x.cat.results, parameters)CalculateCCFIs(x.results, x.dim.results, x.cat.results, parameters)
x.results |
Empirical data results |
x.dim.results |
Dimensional comparison data results |
x.cat.results |
Categorical comparison data results |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
CCFI values
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates CCFI results for CCFI profiles
CalculateCCFIsProfile(x.results, x.dim.results, x.cat.results, parameters)CalculateCCFIsProfile(x.results, x.dim.results, x.cat.results, parameters)
x.results |
Empirical data results |
x.dim.results |
Dimensional comparison data results |
x.cat.results |
Categorical comparison data results |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
CCFI values
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates fit for L-Mode curves
CalculateFitDensities(shift, data)CalculateFitDensities(shift, data)
shift |
Horizontal shift |
data |
Curves for empirical and comparison data |
Called by higher-order functions; users do not need to call this function directly.
Fit value
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates the sample kurtosis of a distribution
CalculateKurtosis(x)CalculateKurtosis(x)
x |
The data vector |
Called by higher-order functions; users do not need to call this function directly.
The sample kurtosis of x
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates CCFI for an L-Mode curve
CalculateLModeCCFI(curve.x, curve.y, curve.dim.x, curve.dim.y, curve.cat.x, curve.cat.y)CalculateLModeCCFI(curve.x, curve.y, curve.dim.x, curve.dim.y, curve.cat.x, curve.cat.y)
curve.x |
Empirical data curve, x |
curve.y |
Empirical data curve, y |
curve.dim.x |
Average curve for dimensional comparison data, x |
curve.dim.y |
Average curve for dimensional comparison data, y |
curve.cat.x |
Average curve for categorical comparison data, x |
curve.cat.y |
Average curve for categorical comparison data, y |
Called by higher-order functions; users do not need to call this function directly.
CCFI value
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates one MAMBAC curve
CalculateMAMBAC(input, output, parameters)CalculateMAMBAC(input, output, parameters)
input |
Input indicator |
output |
Output indicator |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
One MAMBAC curve
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates one MAXEIG curve
CalculateMAXEIG(input, outputs, parameters)CalculateMAXEIG(input, outputs, parameters)
input |
Input indicator |
outputs |
Output indicators |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
List object with one MAXEIG curve:
curve.x |
x values |
curve.y |
y values |
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates one MAXSLOPE curve
CalculateMAXSLOPE(x, curve)CalculateMAXSLOPE(x, curve)
x |
The data matrix |
curve |
Curve number |
Called by higher-order functions; users do not need to call this function directly.
List object with one MAXSLOPE curve:
curve.x |
x values |
curve.y |
y values |
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function provides aggregated CCFIs and base rate estimates for CCFI profile
CalculateProfileOutput(CCFIs, parameters)CalculateProfileOutput(CCFIs, parameters)
CCFIs |
CCFI values across base rates and procedures |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
This function returns aggregated CCFI values.
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates the sample skewness of a distribution
CalculateSkew(x)CalculateSkew(x)
x |
The data vector |
Called by higher-order functions; users do not need to call this function directly.
The sample skewness of x
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates the standardized mean difference between two groups (Cohen's D)
CalculateValidity(x.1, x.2)CalculateValidity(x.1, x.2)
x.1 |
Data for the first group |
x.2 |
Data for the second group |
Called by higher-order functions; users do not need to call this function directly.
The standardized mean difference between groups
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function checks classification for problems, and terminates the program if necessary
CheckClassification(group, n)CheckClassification(group, n)
group |
Classification of cases |
n |
Sample size |
Called by higher-order functions; users do not need to call this function directly.
Nothing; text output if problem occurs
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function checks whether the supplied empirical data set is appropriate for taxometric analysis, and provides descriptive statistics about the data set. If data do not meet certain requirements, the program prints warnings in the output, with details about which specific criteria are not met.
CheckData(x)CheckData(x)
x |
The supplied data matrix. Cases missing any data will be removed prior to analysis. |
This function should be called directly by users before performing any taxometric procedures.
This program returns nothing, and provides text output only.
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
# create or import data set # creates a categorical data set test.cat <- CreateData("cat") # Checks data CheckData(test.cat) # creates a dimensional data set test.dim <- CreateData("dim") # Checks data CheckData(test.dim)# create or import data set # creates a categorical data set test.cat <- CreateData("cat") # Checks data CheckData(test.cat) # creates a dimensional data set test.dim <- CreateData("dim") # Checks data CheckData(test.dim)
This function checks the parameter specifications for problems, and adjusts these parameters as needed.
CheckParameters(x, parameters)CheckParameters(x, parameters)
x |
The data matrix |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
Data parameters, adjusted as needed
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function assigns cases to groups using the base-rate classification technique. Cases are sorted according to their total scores on all indicators, and the highest-scoring cases are assigned to the taxon such that the proportion of taxon members equals the specified base rate estimate.
ClassifyCases(x, p, cols = 0)ClassifyCases(x, p, cols = 0)
x |
The supplied data matrix. |
p |
The base rate estimate that will be used to classify cases. |
cols |
The column numbers that contain variables |
Users should call this function directly if they wish to assign cases to groups.
Data matrix with a new classification variable.
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
Ruscio, J. (2009). Assigning cases to groups using taxometric results: an empirical comparison of classification techniques. Assessment, 16(1), 55-70.
This function creates an artificial data set based on either dimensional or categorical latent structure, which can vary according to a number of basic parameters. Such data can be useful for getting to know the taxometric programs and becoming familiar with their output by conducting analyses using data sets whose parameters are known.
CreateData(str, n = 600, k = 4, p = 0.5, d = 2, r = 0, r.tax = 0, r.comp = 0, g = 0, h = 0, cuts = 0, uniform = F, seed = 1)CreateData(str, n = 600, k = 4, p = 0.5, d = 2, r = 0, r.tax = 0, r.comp = 0, g = 0, h = 0, cuts = 0, uniform = F, seed = 1)
str |
The type of data to be generated. Specify either "dim" for dimensional data or "cat" (or anything else) for categorical data. |
n |
Sample size. The default value is 600. |
k |
Number of variables. The default value is 4. |
p |
Taxon base rate. The default value is .5. |
d |
Standardized mean difference between groups. The default value is 2. |
r |
Correlation among variables. The default value is 0. |
r.tax |
Correlation among variables within the taxon. The default value is 0. |
r.comp |
Correlation among variables within the complement. The default value is 0. |
g |
Parameter used to control asymmetry (scalar); sign indicates direction and absolute value indicates magnitude of skew (e.g., +/- .30 yields substantial asymmetry). |
h |
Parameter used to control tail weight (scalar); positive values yield tails that are longer/thinner than a standard normal curve, negative values do the reverse (e.g., +/- .15 is a substantial departure from normality). |
cuts |
Parameter used to create ordered categorieas, if nonzero (scalar); number of categories will be cuts + 1. |
uniform |
Whether to generate random values (the program default) or use uniformly distributed quantiles (T/F). |
seed |
Random number seed; specifying the same seed enables users to generate and analyze identical data sets. The default value is 1. |
Users should call this function directly if they wish to create an artificial data set.
Data matrix; k columns contain data, final column contains classification.
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
# creates a categorical data set test.cat <- CreateData("cat") # creates a dimensional data set test.dim <- CreateData("dim")# creates a categorical data set test.cat <- CreateData("cat") # creates a dimensional data set test.dim <- CreateData("dim")
Generates sample of correlated data with univariate g-and-h distributions.
CreateSample(n, k, r, g, h, uniform)CreateSample(n, k, r, g, h, uniform)
n |
Sample size |
k |
Number of variables |
r |
Correlation among variables |
g |
Parameter used to control asymmetry (scalar); sign indicates direction and absolute value indicates magnitude of skew (e.g., +/- .30 yields substantial asymmetry). |
h |
Parameter used to control tail weight (scalar); positive values yield tails that are longer/thinner than a standard normal curve, negative values do the reverse (e.g., +/- .15 is a substantial departure from normality). |
uniform |
Whether to generate random values (the program default) or use uniformly distributed quantiles (T/F). |
Called by higher-order functions; users do not need to call this function directly.
Sample of data
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
Generates variable with g-and-h distribution.
CreateVariable(n, g, h, uniform)CreateVariable(n, g, h, uniform)
n |
Size of sample to create |
g |
Parameter used to control asymmetry (scalar); sign indicates direction and absolute value indicates magnitude of skew (e.g., +/- .30 yields substantial asymmetry). |
h |
Parameter used to control tail weight (scalar); positive values yield tails that are longer/thinner than a standard normal curve, negative values do the reverse (e.g., +/- .15 is a substantial departure from normality). |
uniform |
Whether to generate random values (the program default) or use uniformly distributed quantiles (T/F). |
Called by higher-order functions; users do not need to call this function directly.
Single variable
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function provides panels of graphs for taxometric analysis
DisplayPanels(x.results, x.dim.results, x.cat.results, parameters)DisplayPanels(x.results, x.dim.results, x.cat.results, parameters)
x.results |
Empirical data results |
x.dim.results |
Dimensional comparison data results |
x.cat.results |
Categorical comparison data results |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
This function returns nothing, and provides graphical output only
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function plots CCFI profiles
DisplayProfiles(CCFIs, parameters)DisplayProfiles(CCFIs, parameters)
CCFIs |
CCFI values across base rates and procedures |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
This function returns nothing, and provides graphical output only
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function estimates the taxon base rate for an L-Mode curve
EstimateLMode(curve.x, curve.y, parameters)EstimateLMode(curve.x, curve.y, parameters)
curve.x |
X values of density |
curve.y |
Y values of density |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
List of base rate estimates:
p.r |
Based on location of left mode |
p.l |
Based on location of right mode |
p.estimate |
mean |
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function estimates the taxon base rate for a MAMBAC curve
EstimateMAMBAC(curve)EstimateMAMBAC(curve)
curve |
MAMBAC curve |
Called by higher-order functions; users do not need to call this function directly.
Base rate estimate
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function estimates the taxon base rate for a MAXEIG curve
EstimateMAXEIG(curve)EstimateMAXEIG(curve)
curve |
MAXEIG curve |
Called by higher-order functions; users do not need to call this function directly.
Base rate estiamte
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function estimates the taxon base rate for a MAXSLOPE curve
EstimateMAXSLOPE(curve.x, curve.y)EstimateMAXSLOPE(curve.x, curve.y)
curve.x |
X values of curve |
curve.y |
Y values of curve |
Called by higher-order functions; users do not need to call this function directly.
Base rate estimate
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function generates a population of comparison data
GenerateData(x, n, n.factors = 0, max.trials = 5, initial.multiplier = 1)GenerateData(x, n, n.factors = 0, max.trials = 5, initial.multiplier = 1)
x |
The data matrix |
n |
Size of population to create |
n.factors |
The number of factors used to reproduce correlations. The default value is 0. |
max.trials |
Maximum number of trials. The default value is 5. |
initial.multiplier |
Size of multiplier to adjust target correlations. The default value is 1. |
Called by higher-order functions; users do not need to call this function directly.
Population of comparison data
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function provides analytic specifications
GetSpecifications(parameters)GetSpecifications(parameters)
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
This function returns nothing, and provides text output only
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function plots a two-panel graph with results for empirical and comparison data
PlotPanel(x.results, x.dim.results, x.cat.results, parameters, procedure)PlotPanel(x.results, x.dim.results, x.cat.results, parameters, procedure)
x.results |
Empirical data results |
x.dim.results |
Dimensional comparison data results |
x.cat.results |
Categorical comparison data results |
parameters |
The data and program parameters |
procedure |
Name of taxometric procedure |
Called by higher-order functions; users do not need to call this function directly.
This function returns nothing, and provides graphical output only
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates the aggregated CCFI and base rate estimate for one CCFI profile
ProcessProfile(CCFIs, parameters)ProcessProfile(CCFIs, parameters)
CCFIs |
CCFI values across base rates for a single procedure |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
List of aggregated CCFI and base rate estimate
CCFI |
Aggregated CCFI |
p.est |
Base rate estimate |
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function performs listwise deletion of missing data
RemoveMissingData(x)RemoveMissingData(x)
x |
The data matrix |
Called by higher-order functions; users do not need to call this function directly.
Data after listwise deletion of missing data
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function performs a series of taxometric analysis using categorical comparison data sets that vary in taxon base rates, and plots a profile of CCFI values across this range of base rates. Results can be assigned to an object to store results; otherwise results will be displayed on-screen.
RunCCFIProfile(x, seed = 0, min.p = 0.025, max.p = 0.975, num.p = 39, n.pop = 1e+05, n.samples = 100, reps = 1, MAMBAC = TRUE, assign.MAMBAC = 1, n.cuts = 50, n.end = 25, MAXEIG = TRUE, assign.MAXEIG = 1, windows = 50, overlap = 0.9, LMode = TRUE, mode.l = -0.001, mode.r = 0.001, MAXSLOPE = FALSE, graph = 1, text.file = FALSE, profile = TRUE)RunCCFIProfile(x, seed = 0, min.p = 0.025, max.p = 0.975, num.p = 39, n.pop = 1e+05, n.samples = 100, reps = 1, MAMBAC = TRUE, assign.MAMBAC = 1, n.cuts = 50, n.end = 25, MAXEIG = TRUE, assign.MAXEIG = 1, windows = 50, overlap = 0.9, LMode = TRUE, mode.l = -0.001, mode.r = 0.001, MAXSLOPE = FALSE, graph = 1, text.file = FALSE, profile = TRUE)
x |
Supplied data matrix. Cases missing any data will be removed prior to analysis. |
seed |
Random number seed provided prior to analysis of empirical data as well as prior to generating each population of comparison data. The default value is 0. |
min.p |
Minimum base rate for CCFI profile. The default value is .025. |
max.p |
Maximum base rate for CCFI profile. The default value is .975. |
num.p |
Number of base rates for CCFI profile. The default value is 39. |
n.pop |
Size of the finite populations of categorical and dimensional comparison data. The default value is 100,000. |
n.samples |
Number of comparison data sets of each structure to generate and analyze. The default value is 100. |
reps |
Number of times to resort cases along the input indicator at random and redo the calculations (if tied scores are found), averaging to obtain final results.The default value is 1 if no tied scores are found, and 10 if tied scores are found. |
MAMBAC |
Whether the MAMBAC procedure is performed. The default value is TRUE. |
assign.MAMBAC |
How variables are assigned as input and output variables in the MAMBAC procedure. Variables may be used in all possible input-output pairings (assing.MAMBAC = 1), or variables may be summed to form the input variable (assign.MAMBAC = 2). The default value is 1. |
n.cuts |
The total number of cuts to make along the input variable when performing the MAMBAC procedure. The default value is 25. |
n.end |
The number of cases to set aside at each extreme along the input variable before making the first and last cuts when performing the MAMBAC procedure. The default value is 25. |
MAXEIG |
Whether the MAXEIG procedure is performed. The default value is TRUE if k is >= 3, and FALSE if k < 3. |
assign.MAXEIG |
How variables are assigned as input and output variables in the MAXEIG procedure. Variables may be used in all input-output triplets (assign.MAXEIG = 1), each variable may serve as input once (assign.MAXEIG = 2), or variables may be summed to form the input (assign.MAXEIG = 3). The default value is 1. |
windows |
The nubmer of overlapping windows to use when performing the MAXEIG procedure. The default value is 50. |
overlap |
The amount of overlap between windows when performing the MAXEIG procedure. The default value is .90. |
LMode |
Whether the L-Mode procedure is performed. The default value is TRUE if k is >= 3, and FALSE if k < 3. |
mode.l |
Position beyond which to serach for the left mode when performing the L-Mode procedure. The default value is -.001. |
mode.r |
Position beyond which to serach for the right mode when performing the L-Mode procedure. The default value is .001. |
MAXSLOPE |
Whether the MAXSLOPE procedure is performed. The default value is FALSE if k >= 3, and TRUE if k < 3. |
graph |
Whether to display graphs on screen (1), save as a compressed .jpeg file (2), or save as a high-resolution .tiff file (3). The default value is 1. |
text.file |
Whether to divert text output to a .txt file (T/F). The default value is FALSE. |
profile |
Whether a CCFI profile is generated. The default value is TRUE. |
This function should be called directly by users who wish to perform taxometric analyses to generate a CCFI profile.
This program returns CCFI values, and provides text and graphical output. Note that any CCFI values of 0 represent missing values, as analyses will never yield a CCFI of 0.
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function performs factor analysis
RunFactorAnalysis(x, cor.matrix = FALSE, n.factors = 0, max.iter = 50, criterion = 0.01)RunFactorAnalysis(x, cor.matrix = FALSE, n.factors = 0, max.iter = 50, criterion = 0.01)
x |
The data or correlation matrix |
cor.matrix |
Whether x is a correlation matrix. The default is FALSE. |
n.factors |
The number of factors to use. The default value is 0. |
max.iter |
The maximum number of iterations. The default value is 50. |
criterion |
Acceptably small change in h2 between interations. The default value is .01. |
Called by higher-order functions; users do not need to call this function directly.
List of factor loadings and number of factors
loadings |
The factor loadings |
factors |
The number of factors |
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function performs the L-Mode analysis
RunLMode(x)RunLMode(x)
x |
The data matrix |
Called by higher-order functions; users do not need to call this function directly.
L-Mode curve:
curve.x |
X values of curve |
curve.y |
Y values of curve |
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
Waller, N.G., & Meehl, P.E. (1998). Multivariate taxometric procedures: Distinguishing types from continua. Thousand Oaks, CA, US: Sage Publications, Inc.
This function performs the MAMBAC analysis
RunMAMBAC(x, parameters)RunMAMBAC(x, parameters)
x |
The data matrix |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
Panel of MAMBAC curves
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
Meehl, P.E., & Yonce, L.J. (1994). Taxometric analysis: I. Detecting taxonomy with two quantitative indicators using means above and below a sliding cut (MAMBAC procedure). Psychological Reports, 74(3, Pt 2), 1059-1274.
This function performs the MAXEIG analysis
RunMAXEIG(x, parameters)RunMAXEIG(x, parameters)
x |
The data matrix |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
Panel of MAXEIG curves:
curve.x |
X values of curve |
curve.y |
Y values of curve |
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
Waller, N.G., & Meehl, P.E. (1998). Multivariate taxometric procedures: Distinguishing types from continua. Thousand Oaks, CA, US: Sage Publications, Inc.
This function performs the MAXSLOPE analysis
RunMAXSLOPE(x)RunMAXSLOPE(x)
x |
The data matrix |
Called by higher-order functions; users do not need to call this function directly.
Panel of MAXSLOPE curves
curve.x |
X values of curve |
curve.y |
Y values of curve |
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
Grove, W.M., & Meehl, P.E. (1993). Simple regression-based procedures for taxometric investigations. Psychological Reports, 73, 707-737.
This function runs the MAMBAC, MAXEIG, L-Mode, and MAXSLOPE analyses for empirical data
RunProcedures(x, parameters)RunProcedures(x, parameters)
x |
The data matrix |
parameters |
The data and program parameters |
Called by higher-order functions; users do not need to call this function directly.
A list of curve-level data for each procedure performed:
MAMBAC |
MAMBAC curve |
MAXEIG.x |
X values of MAXEIG curve |
MAXEIG.y |
Y values of MAXEIG curve |
LMode.x |
X values of LMode curve |
LMode.y |
Y values of LMode curve |
MAXSLOPE.x |
X values of MAXSLOPE curve |
MAXSLOPE.y |
Y values of MAXSLOPE curve |
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function runs the MAMBAC, MAXEIG, L-Mode, and MAXSLOPE analyses for comparison data
RunProceduresComp(x, parameters)RunProceduresComp(x, parameters)
x |
The data matrix |
parameters |
The data and program parameters. |
Called by higher-order functions; users do not need to call this function directly.
A list of averaged curves for each procedure performed:
MAMBAC |
MAMBAC curve |
MAXEIG.x |
X values of MAXEIG curve |
MAXEIG.y |
Y values of MAXEIG curve |
LMode.x |
X values of LMode curve |
LMode.y |
Y values of LMode curve |
MAXSLOPE.x |
X values of MAXSLOPE curve |
MAXSLOPE.y |
Y values of MAXSLOPE curve |
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
Performs taxometric analysis for a sample of data and provides text (analytic specifications, CCFI values, base rate estimates) and graphical (panels of empirical data curves superimposed above comparison data curves) output. By default, the function will run MAMBAC, MAXEIG, and L-Mode, unless only 2 variables are provided, in which case the program will run MAMBAC and MAXSLOPE. Results can be assigned to an object to store results; otherwise results will be displayed on-screen.
RunTaxometrics(x, seed = 0, n.pop = 1e+05, n.samples = 100, reps = 1, MAMBAC = TRUE, assign.MAMBAC = 1, n.cuts = 50, n.end = 25, MAXEIG = TRUE, assign.MAXEIG = 1, windows = 50, overlap = 0.9, LMode = TRUE, mode.l = -0.001, mode.r = 0.001, MAXSLOPE = FALSE, graph = 1)RunTaxometrics(x, seed = 0, n.pop = 1e+05, n.samples = 100, reps = 1, MAMBAC = TRUE, assign.MAMBAC = 1, n.cuts = 50, n.end = 25, MAXEIG = TRUE, assign.MAXEIG = 1, windows = 50, overlap = 0.9, LMode = TRUE, mode.l = -0.001, mode.r = 0.001, MAXSLOPE = FALSE, graph = 1)
x |
The supplied data matrix. Cases missing any data will be removed prior to analysis. |
seed |
Random number seed provided prior to analysis of empirical data as well as prior to generating each population of comparison data. The default value is 0. |
n.pop |
Size of the finite populations of categorical and dimensional comparison data. The default value is 100,000. |
n.samples |
Number of comparison data sets of each structure to generate and analyze. The default value is 100. |
reps |
Number of times to resort cases along the input indicator at random and redo the calculations (if tied scores are found), averaging to obtain final results.The default value is 1 if no tied scores are found, and 10 if tied scores are found. |
MAMBAC |
Whether the MAMBAC procedure is performed. The default value is TRUE. |
assign.MAMBAC |
How variables are assigned as input and output variables in the MAMBAC procedure. Variables may be used in all possible input-output pairings (assing.MAMBAC = 1), or variables may be summed to form the input variable (assign.MAMBAC = 2). The default value is 1. |
n.cuts |
The total number of cuts to make along the input variable when performing the MAMBAC procedure. The default value is 25. |
n.end |
The number of cases to set aside at each extreme along the input variable before making the first and last cuts when performing the MAMBAC procedure. The default value is 25. |
MAXEIG |
Whether the MAXEIG procedure is performed. The default value is TRUE if k is >= 3, and FALSE if k < 3. |
assign.MAXEIG |
How variables are assigned as input and output variables in the MAXEIG procedure. Variables may be used in all input-output triplets (assign.MAXEIG = 1), each variable may serve as input once (assign.MAXEIG = 2), or variables may be summed to form the input (assign.MAXEIG = 3). The default value is 1. |
windows |
The nubmer of overlapping windows to use when performing the MAXEIG procedure. The default value is 50. |
overlap |
The amount of overlap between windows when performing the MAXEIG procedure. The default value is .90. |
LMode |
Whether the L-Mode procedure is performed. The default value is TRUE if k is >= 3, and FALSE if k < 3. |
mode.l |
Position beyond which to serach for the left mode when performing the L-Mode procedure. The default value is -.001. |
mode.r |
Position beyond which to serach for the right mode when performing the L-Mode procedure. The default value is .001. |
MAXSLOPE |
Whether the MAXSLOPE procedure is performed. The default value is FALSE if k >= 3, and TRUE if k < 3. |
graph |
Whether to display graphs on screen (1), save as a compressed .jpeg file (2), or save as a high-resolution .tiff file (3). The default value is 1. |
This function should be called directly by users who wish to perform taxometric analyses for a sample of data.
This program returns CCFI values, and provides text and graphical output. Note that any CCFI values of 0 represent missing values, as analyses will never yield a CCFI of 0.
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>
This function calculates the sample mean, standard deviation, skewness, and kurtosis
SummarizeDist(x)SummarizeDist(x)
x |
The data vector |
Called by higher-order functions; users do not need to call this function directly.
The sample mean, standard deviation, skewness, and kurtosis of x.
John Ruscio <[email protected]> and Shirley Wang <[email protected]> Maintainer: John Ruscio <[email protected]>