Type: Package
Title: Fits Psychometric Functions for Multiple Groups
Version: 0.1.5.1
URL: http://dlinares.org/quickpsy.html
Description: Quickly fits and plots psychometric functions (normal, logistic, Weibull or any or any function defined by the user) for multiple groups.
Depends: R (≥ 3.1.2), DEoptim, dplyr, ggplot2
Imports: MPDiR
Encoding: UTF-8
License: MIT + file LICENSE
LazyData: true
RoxygenNote: 6.0.1
NeedsCompilation: no
Packaged: 2019-10-02 15:47:49 UTC; hornik
Author: Linares Daniel [aut, cre], L<U+00F3>pez-Moliner Joan [aut]
Maintainer: Linares Daniel <danilinares@gmail.com>
Repository: CRAN
Date/Publication: 2019-10-02 15:54:02 UTC

Calculates the AICs

Description

aic calculates the AICs.

Usage

aic(qp)

Arguments

qp

output from quickpsy

Creates bootstrap samples

Description

avbootstrap creates bootstrap samples

Usage

avbootstrap(qp, bootstrap = "parametric", B = 100)

Arguments

qp

output from quickpsy

bootstrap

'parametric' performs parametric bootstrap; 'nonparametric' performs non-parametric bootstrap; 'none' does not perform bootstrap (default is 'parametric').

B

number of bootstrap samples (default is 100 ONLY).

Creates the full negative log-likelihood function create_full_nll Creates the full negative log-likelihood function

Description

Creates the full negative log-likelihood function create_full_nll Creates the full negative log-likelihood function

Usage

create_full_nll(d, x, k, n, psyfunguesslapses)

Creates the negative log-likelihood function create_nll Creates the negative log-likelihood function

Description

Creates the negative log-likelihood function create_nll Creates the negative log-likelihood function

Usage

create_nll(d, x, k, n, psyfunguesslapses)

Creates the full saturated negative log-likelihood function create_nll Creates the full saturated negative log-likelihood function

Description

Creates the full saturated negative log-likelihood function create_nll Creates the full saturated negative log-likelihood function

Usage

create_nllsaturated(d, x, k, n, psyfunguesslapses)

Creates the psychometric function create_psy_fun creates the psychometric function

Description

Creates the psychometric function create_psy_fun creates the psychometric function

Usage

create_psy_fun(psy_fun, guess, lapses)

Cumulative normal function

Description

Cumulative normal function.

Usage

cum_normal_fun(x, p)

Arguments

x

Vector of values of the explanatory variable.

p

Vector of parameters p = c(mean, standard_deviation).

Value

Probability at each x.

See Also

inv_cum_normal_fun

Examples

xseq <- seq(0,4,.01)
yseq <- cum_normal_fun(xseq, c(2, .5))
curve <- data.frame(x = xseq, y = yseq)
ggplot(curve, aes(x = x, y = y)) + geom_line()

Creates the bootstrap curves curvesbootstrap creates the bootstrap curves

Description

Creates the bootstrap curves curvesbootstrap creates the bootstrap curves

Usage

curvesbootstrap(qp, xmin = NULL, xmax = NULL, log = F)

Calculates the deviances

Description

deviance calculates the deviances.

Usage

deviance(qp)

Arguments

qp

output from quickpsy

Examples

library(MPDiR) # contains the Vernier data
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), B = 20)
deviance(fit)

Calculates the bootsrap deviances

Description

deviance calculates the bootstrap deviances.

Usage

devianceboot(qp)

Arguments

qp

output from quickpsy

Examples

library(MPDiR) # contains the Vernier data
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), B = 20)
devianceboot(fit)

Calculates the probability of obtaining the deviance value or larger if the parametric model holds deviancep calculates the probability of obtaining the deviance value or larger if the parametric model holds.

Description

Calculates the probability of obtaining the deviance value or larger if the parametric model holds deviancep calculates the probability of obtaining the deviance value or larger if the parametric model holds.

Usage

deviancep(qp)

Fits the curve fitpsy fits de curve

Description

Fits the curve fitpsy fits de curve

Usage

fitpsy(d, x, k, n, random, within, between, grouping, xmin, xmax, log, funname,
  parini, pariniset, guess, lapses, optimization)

Predefined functions

Description

getfunctions lists the predefined functions in quickpsy.

Usage

get_functions()

See Also

cum_normal_fun, logistic_fun, weibull_fun

Inverse cumulative normal function

Description

Inverse cumulative normal function

Usage

inv_cum_normal_fun(prob, p)

Arguments

prob

Vector of probabilities.

p

Vector of parameters p = c(mean, standard_deviation).

Value

x at each probability. #' @seealso cum_normal_fun

Examples

yseq <- seq(0, 1, .01)
xseq <- inv_cum_normal_fun(yseq, c(2, .5))
curve <- data.frame(x = xseq, y = yseq)
ggplot(curve, aes(x = x, y = y)) + geom_line()

Inverse logistic function

Description

Inverse logistic function

Usage

inv_logistic_fun(q, p)

Arguments

q

Vector of probabilities.

p

Vector of parameters p = c(\alpha, \beta).

Value

x at each probability.

See Also

logistic_fun

Examples

yseq <- seq(0, 1, .01)
xseq <- inv_logistic_fun(yseq, c(2, 4))
curve <- data.frame(x = xseq, y = yseq)
ggplot(curve, aes(x = x, y = y)) + geom_line()

Inverse Weibull function

Description

Inverse Weibull function

Usage

inv_weibull_fun(q, p)

Arguments

q

Vector of probabilities.

p

Vector of parameters p = c(alpha, beta).

Value

x at each probability.

See Also

weibull_fun

Examples

yseq <- seq(0, 1, .01)
xseq <- inv_weibull_fun(yseq, c(2, 4))
curve <- data.frame(x = xseq, y = yseq)
ggplot(curve, aes(x = x, y = y)) + geom_line()

Creates the limits limits creates the limits

Description

Creates the limits limits creates the limits

Usage

limits(d, x, xmin, xmax, log)

Logistic function

Description

Logistic function of the form (1 + exp(-\beta * (x - \alpha)))^(-1)

Usage

logistic_fun(x, p)

Arguments

x

Vector of values of the explanatory variable.

p

Vector of parameters p = c(\alpha, \beta).

Value

Probability at each x.

See Also

inv_logistic_fun

Examples

xseq <- seq(0, 4, .01)
yseq <- logistic_fun(xseq, c(2, 4))
curve <- data.frame(x = xseq, y = yseq)
ggplot(curve, aes(x = x, y = y)) + geom_line()

Calculates the loglikelihoods logliks calculates the loglikelihoods.

Description

Calculates the loglikelihoods logliks calculates the loglikelihoods.

Usage

logliks(qp)

Arguments

qp

output from quickpsy

Calculates the bootstrap loglikelihoods

Description

logliksboot calculates the bootstraploglikelihoods.

Usage

logliksboot(qp)

Arguments

qp

output from quickpsy

Examples

library(MPDiR) # contains the Vernier data
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), B = 20)
logliksboot(fit)

Calculates the bootstrap loglikelihoods for the saturated model

Description

logliks calculates the bootstrap loglikelihoods for the saturated model.

Usage

logliksbootsaturated(qp)

Arguments

qp

output from quickpsy

Examples

library(MPDiR) # contains the Vernier data
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), B = 20)
logliksbootsaturated(fit)

Calculates the loglikelihoods of the saturated model

Description

loglikssaturated calculates the loglikelihoods of the saturated model.

Usage

loglikssaturated(qp)

Arguments

qp

output from quickpsy

Examples

library(MPDiR) # contains the Vernier data
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), B = 20)
loglikssaturated(fit)

Calculates the AIC for one condition one_aic creates the deviance for one condition one_deviance

Description

Calculates the AIC for one condition one_aic creates the deviance for one condition one_deviance

Usage

one_aic(d, groups, par)

Creates the curve for one condition one_curve Creates the curve for one condition

Description

Creates the curve for one condition one_curve Creates the curve for one condition

Usage

one_curve(d, xmin, xmax, log, groups, limits, psyfunguesslapses)

Creates the deviance for one condition one_deviance creates the deviance for one condition one_deviance

Description

Creates the deviance for one condition one_deviance creates the deviance for one condition one_deviance

Usage

one_deviance(d, groups, loglikssaturated)

Calculates the probability of obtaining the deviance value or larger if the parametric model holds for one condition one_deviancep calculates the probability of obtaining the deviance value or larger if the parametric model holds for one condition

Description

Calculates the probability of obtaining the deviance value or larger if the parametric model holds for one condition one_deviancep calculates the probability of obtaining the deviance value or larger if the parametric model holds for one condition

Usage

one_deviancep(d, groups, deviance)

Creates the limits for one condition one_limit creates the limits for one condition

Description

Creates the limits for one condition one_limit creates the limits for one condition

Usage

one_limit(d, x, xmin, xmax, log)

Creates the loglik for one condition one_loglik creates the loglik for one condition one_loglik

Description

Creates the loglik for one condition one_loglik creates the loglik for one condition one_loglik

Usage

one_loglik(d, x, k, n, psyfunguesslapses, groups, par)

Creates the loglik for the saturated model for one condition one_logliksaturated creates the loglik for the saturated model for one condition one_loglik

Description

Creates the loglik for the saturated model for one condition one_logliksaturated creates the loglik for the saturated model for one condition one_loglik

Usage

one_logliksaturated(d, x, k, n, psyfunguesslapses, groups, par)

Obtains the parameters for one condition one_parameters obtains the parameters for one condition

Description

Obtains the parameters for one condition one_parameters obtains the parameters for one condition

Usage

one_parameters(d, x, k, n, psyfunguesslapses, funname, parini, pariniset, guess,
  lapses, optimization, groups)

Calculates the confidence intervals for one condition one_parci calculates the confidence intervals for one condition

Description

Calculates the confidence intervals for one condition one_parci calculates the confidence intervals for one condition

Usage

one_parci(d, ci)

Pair comparisons of the parameters using bootstrap (for each parameter) one_parcomparisons Calculates the bootstrap confidence intervals for the difference in the parameters for two groups for all possible pairs of groups (for each parameter)

Description

Pair comparisons of the parameters using bootstrap (for each parameter) one_parcomparisons Calculates the bootstrap confidence intervals for the difference in the parameters for two groups for all possible pairs of groups (for each parameter)

Usage

one_parcomparisons(d, para, groups, ci)

Calculates the sum of squared errors of prediction one_sse calculates the sum of squared errors of prediction for one condition

Description

Calculates the sum of squared errors of prediction one_sse calculates the sum of squared errors of prediction for one condition

Usage

one_sse(d, groups, averages)

Calculates the threshold for one condition one_threshold calculates the threshold for one condition one_threshold

Description

Calculates the threshold for one condition one_threshold calculates the threshold for one condition one_threshold

Usage

one_threshold(d, prob, log, groups, funname, guess, lapses, curves)

Pair comparisons of the thresholds using bootstrap one_thresholdcomparisons Calculates the bootstrap confidence intervals for the difference in the thresholds for two groups for all possible pairs of groups

Description

Pair comparisons of the thresholds using bootstrap one_thresholdcomparisons Calculates the bootstrap confidence intervals for the difference in the thresholds for two groups for all possible pairs of groups

Usage

one_thresholdcomparisons(d, thresholds, groups, ci)

Calculates the confidence intervals for the threshold of one condition one_thresholdsci calculates the confidence intervals for the threshold of one condition

Description

Calculates the confidence intervals for the threshold of one condition one_thresholdsci calculates the confidence intervals for the threshold of one condition

Usage

one_thresholdsci(d, ci, method)

Calculate the predictions of the response variable for one condition one_ypred calculate the predictions of the response variable for one condition

Description

Calculate the predictions of the response variable for one condition one_ypred calculate the predictions of the response variable for one condition

Usage

one_ypred(d, log, groups, averages, x, psyfunguesslapses)

Calculates the parameters parameters calculates the parameters

Description

Calculates the parameters parameters calculates the parameters

Usage

parameters(d, x, k, n, psyfunguesslapses, funname, parini, pariniset, guess,
  lapses, optimization, groups)

Creates bootstrap samples of the parameters

Description

parbootstrap creates bootstrap samples of the parameters.

Usage

parbootstrap(qp)

Arguments

qp

output from quickpsy

Calculates the confidence intervals for the parameters parci calculates the confidence intervals for the parameters

Description

Calculates the confidence intervals for the parameters parci calculates the confidence intervals for the parameters

Usage

parci(qp, ci = 0.95)

Pair comparisons of the parameters using bootstrap parcomparisons Calculates the bootstrap confidence intervals for the difference in the parameters for two groups for all possible pairs of groups

Description

Pair comparisons of the parameters using bootstrap parcomparisons Calculates the bootstrap confidence intervals for the difference in the parameters for two groups for all possible pairs of groups

Usage

parcomparisons(qp, ci = 0.95)

Calculates some initial parameters parini calculates some initial parameters

Description

Calculates some initial parameters parini calculates some initial parameters

Usage

parini(d, x, k, n, guess, lapses, psyfun)

Creates one bootstrap sample one_bootstrapav creates one bootstrap sample

Description

Creates one bootstrap sample one_bootstrapav creates one bootstrap sample

Usage

parn

Format

An object of class character of length 1.

Plot the curves

Description

plotcurves plot the curves.

Usage

plotcurves(qp, panel = NULL, xpanel = NULL, ypanel = NULL, color = NULL,
  averages = T, curves = T, thresholds = T, ci = T)

Arguments

qp

output from quickpsy

panel

Name of the variable to be split in panels.

xpanel

Name of the variable to be split in horizontal panels.

ypanel

Name of the variable to be split in vertical panels.

color

Name of the variable codded by color.

averages

If FALSE averaged probabilities are not plotted (default is TRUE).

curves

If FALSE curves are not plotted (default is TRUE)

thresholds

If FALSE thresholds are not plotted (default is TRUE)

ci

If FALSE confidence intervals are not plotted (default is TRUE)

See Also

plotcurves_

Examples

library(MPDiR) # contains the Vernier data
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), B = 5)
plotcurves(fit)
plotcurves(fit, xpanel = Direction)
plotcurves(fit, xpanel = Direction, color = WaveForm, ci = FALSE)

Plot the curves

Description

plotcurves_ is the standard evaluation SE function associated to the non-standard evaluation NSE function plotcurves. SE functions can be more easily called from other functions. In SE functions, you need to quote the names of the variables.

Usage

plotcurves_(qp, panel = NULL, xpanel = NULL, ypanel = NULL,
  color = NULL, averages = TRUE, curves = TRUE, thresholds = TRUE,
  ci = TRUE)

Arguments

qp

output from quickpsy

panel

Name of the variable to be split in panels.

xpanel

Name of the variable to be split in horizontal panels.

ypanel

Name of the variable to be split in vertical panels.

color

Name of the variable codded by color.

averages

If FALSE averaged probabilities are not plotted (default is TRUE).

curves

If FALSE curves are not plotted (default is TRUE)

thresholds

If FALSE thresholds are not plotted (default is TRUE)

ci

If FALSE confidence intervals are not plotted (default is TRUE)

See Also

plotcurves

Examples

library(MPDiR) # contains the Vernier data
data(Vernier) # ?Venier for the reference
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), B = 5)

plotcurves_(fit, xpanel = 'Direction')
plotcurves_(fit, color = 'Direction')
plotcurves_(fit, xpanel = 'Direction', color = 'WaveForm', ci = FALSE)

Plot the values of the parameters

Description

plotpar plot the values of the parameters.

Usage

plotpar(qp, x = NULL, panel = NULL, xpanel = NULL, ypanel = NULL,
  color = NULL, geom = "bar", ci = T)

Arguments

qp

output from quickpsy.

x

Name of the variable to displayed in the x-axis.

panel

Name of the variable to be split in panels.

xpanel

Name of the variable to be split in horizontal panels.

ypanel

Name of the variable to be split in vertical panels.

color

Name of the variable codded by color.

geom

If 'bar' displays bars. If 'point' displays points (default is 'bar').

ci

If FALSE confidence intervals are not plotted (default is TRUE).

See Also

plotpar_

Examples

library(MPDiR) # contains the Vernier data
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), B = 10)
plotpar(fit)
plotpar(fit, x = WaveForm)
plotpar(fit, xpanel = Direction)
plotpar(fit, color = Direction)
plotpar(fit, color = Direction, ypanel = WaveForm, geom = 'point')

Plot the values of the parameters

Description

plotpar_ is the standard evaluation SE function associated to the non-standard evaluation NSE function plotpar. SE functions can be more easily called from other functions. In SE functions, you need to quote the names of the variables.

Usage

plotpar_(qp, x = NULL, panel = NULL, xpanel = NULL, ypanel = NULL,
  color = NULL, geom = "bar", ci = T)

Arguments

qp

output from quickpsy.

x

Name of the variable to displayed in the x-axis.

panel

Name of the variable to be split in panels.

xpanel

Name of the variable to be split in horizontal panels.

ypanel

Name of the variable to be split in vertical panels.

color

Name of the variable codded by color.

geom

If 'bar' displays bars. If 'point' displays points (default is 'bar').

ci

If FALSE confidence intervals are not plotted (default is TRUE).

See Also

plotpar

Examples

library(MPDiR) # contains the Vernier data
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), bootstrap = 'none')

plotpar_(fit, x = 'WaveForm')
plotpar_(fit, xpanel = 'Direction')
plotpar_(fit, color = 'Direction')
plotpar_(fit, color = 'Direction', ypanel = 'WaveForm', geom = 'point')

Plot the thresholds

Description

plotthresholds plot the thresholds.

Usage

plotthresholds(qp, x = NULL, panel = NULL, xpanel = NULL, ypanel = NULL,
  color = NULL, geom = "bar", ci = T, sizeerrorbar = 0.5)

Arguments

qp

output from quickpsy.

x

Name of the variable to displayed in the x-axis.

panel

Name of the variable to be split in panels.

xpanel

Name of the variable to be split in horizontal panels.

ypanel

Name of the variable to be split in vertical panels.

color

Name of the variable codded by color.

geom

If 'bar' displays bars.

ci

If FALSE confidence intervals are not plotted (default is TRUE).

sizeerrorbar

Line width of the error bars. If 'point' displays points (default is 'bar').

See Also

plotthresholds_

Examples

library(MPDiR) # contains the Vernier data
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), B = 10)
plotthresholds(fit)
plotthresholds(fit, x = WaveForm)
plotthresholds(fit, xpanel = Direction)
plotthresholds(fit, color = Direction, ypanel = WaveForm, geom = 'point')

Plot the thresholds

Description

plotthresholds_ is the standard evaluation SE function associated to the non-standard evaluation NSE function plotthresholds. SE functions can be more easily called from other functions. In SE functions, you need to quote the names of the variables.

Usage

plotthresholds_(qp, x = NULL, panel = NULL, xpanel = NULL,
  ypanel = NULL, color = NULL, geom = "bar", ci = T,
  sizeerrorbar = 0.5)

Arguments

qp

output from quickpsy.

x

Name of the variable to displayed in the x-axis.

panel

Name of the variable to be split in panels.

xpanel

Name of the variable to be split in horizontal panels.

ypanel

Name of the variable to be split in vertical panels.

color

Name of the variable codded by color.

geom

If 'bar' displays bars.

ci

If FALSE confidence intervals are not plotted (default is TRUE).

sizeerrorbar

Line width of the error bars. If 'point' displays points (default is 'bar').

See Also

plotthresholds

Examples

library(MPDiR) # contains the Vernier data
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), B = 10)

plotthresholds_(fit, x = 'WaveForm')
plotthresholds_(fit, xpanel = 'Direction')
plotthresholds_(fit, color = 'Direction')
plotthresholds_(fit, color = 'Direction', ypanel = 'WaveForm', geom = 'point')

Data set for demonstration

Description

It is part of the data associated with the paper 'Motion signal and the perceived positions of moving objects'.

Usage

qpdat

Format

An object of class grouped_df (inherits from tbl_df, tbl, data.frame) with 6240 rows and 8 columns.

References

Linares, D., López-Moliner, J., & Johnston, A. (2007). Motion signal and the perceived positions of moving objects. Journal of Vision, 7(7), 1.

Fits psychometric functions

Description

quickpsy fits, by direct maximization of the likelihood (Prins and Kingdom, 2010; Knoblauch and Maloney, 2012), psychometric functions of the form

\psi(x) = \gamma + (1 - \gamma - \lambda) * fun(x)

where \gamma is the guess rate, \lambda is the lapse rate and fun is a sigmoidal-shape function with asymptotes at 0 and 1.

Usage

quickpsy(d, x = x, k = k, n = n, grouping, random, within, between,
  xmin = NULL, xmax = NULL, log = FALSE, fun = cum_normal_fun,
  parini = NULL, guess = 0, lapses = 0, prob = NULL, thresholds = T,
  bootstrap = "parametric", B = 100, ci = 0.95, optimization = "optim")

Arguments

d

Data frame with the results of a Yes-No experiment to fit. It should have a tidy form in which each column corresponds to a variable and each row is an observation.

x

Name of the explanatory variable.

k

Name of the response variable. The response variable could be the number of trials in which a yes-type response was given or a vector of 0s (or -1s; no-type response) and 1s (yes-type response) indicating the response on each trial.

n

Only necessary if k refers to the number of trials in which a yes-type response was given. It corresponds to the name of the variable indicating the total number of trials.

grouping

Name of the grouping variables. It should be specified as grouping = .(variable_name1, variable_name2).

random

Name of the random variable. It should be specified as random = .(variable_name1, variable_name2). In the current version of quickpsy, the random variable has not special treatment. It does the same as grouping.

within

Name of the within variable. It should be specified as within = .(variable_name1, variable_name2). In the current version of quickpsy, the within variable has not special treatment. It does the same as grouping.

between

Name of the between variable. It should be specified as between = .(variable_name1, variable_name2). In the current version of quickpsy, the between variable has not special treatment. It does the same as grouping.

xmin

Minimum value of the explanatory variable for which the curves should be calculated (the default is the minimum value of the explanatory variable).

xmax

Maximum value of the explanatory variable for which the curves should be calculated (the default is the maximum value of the explanatory variable).

log

If TRUE, the logarithm of the explanatory variable is used to fit the curves (default is FALSE).

fun

Name of the shape of the curve to fit. It could be a predefined shape (cum_normal_fun, logistic_fun, weibull_fun) or the name of a function introduced by the user (default is cum_normal_fun).

parini

Initial parameters. quickpsy calculates default initial parameters using probit analysis, but it is also possible to specify a vector of initial parameters or a list of the form list(c(par1min, par1max), c(par2min, par2max)) to constraint the lower and upper bounds of the parameters (when optimization = 'DE', parini should be also a list).

guess

Value indicating the guess rate \gamma (default is 0). If TRUE, the guess rate is estimated as the i + 1 paramEter where i corresponds to the number of parameters of fun. If, for example, fun is a predefined shape with parameters p1 and p2, then the guess rate corresponds to parameter p3.

lapses

Value indicating the lapse rate \lambda (default is 0). If TRUE, the lapse rate is estimated as the i + 1 parameter where i corresponds to the number of parameters of fun plus one if the guess rate is estimated. If, for example, fun is a predefined shape with parameters p1 and p2, then the lapse rate corresponds to parameter p3. If the guess rate is also estimated, p3 will be the guess rate and p4 the lapse rate.

prob

Probability to calculate the threshold (default is guess + .5 * (1 - guess)).

thresholds

If FALSE, thresholds are not calculated (default is TRUE).

bootstrap

'parametric' performs parametric bootstrap; 'nonparametric' performs non-parametric bootstrap; 'none' does not perform bootstrap (default is 'parametric').

B

number of bootstrap samples (default is 100 ONLY).

ci

Confidence intervals level based on percentiles (default is .95).

optimization

Method used for optimization. The default is 'optim' which uses the optim function. It can also be 'DE' which uses de function DEoptim from the package DEoptim, which performs differential evolution optimization. By using DEoptim, it is less likely that the optimization finishes in a local minimum, but the optimization is slow. When 'DE' is used, parini should be specified as a list with lower and upper bounds.

Value

A list containing the following components:

References

Burnham, K. P., & Anderson, D. R. (2003). Model selection and multimodel inference: a practical information-theoretic approach. Springer Science & Business Media.

Knoblauch, K., & Maloney, L. T. (2012). Modeling Psychophysical Data in R. New York: Springer.

Prins, N., & Kingdom, F. A. A. (2016). Psychophysics: a practical introduction. London: Academic Press.

See Also

quickpsy_

Examples

# make sure that all the requires packages are installed
# and loaded; instructions at https://github.com/danilinares/quickpsy
library(MPDiR) # contains the Vernier data; use ?Vernier for the reference
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), B = 10)
plotcurves(fit)
plotpar(fit)
plotthresholds(fit, geom = 'point')

Fits psychometric functions

Description

quickpsy_ is the standard evaluation SE function associated to the non-standard evaluation NSE function quickpsy. SE functions can be more easily called from other functions. In SE functions, you need to quote the names of the variables.

Usage

quickpsy_(d, x = "x", k = "k", n = "n", grouping, random, within, between,
  xmin = NULL, xmax = NULL, log = FALSE, fun = "cum_normal_fun",
  parini = NULL, guess = 0, lapses = 0, prob = NULL, thresholds = T,
  bootstrap = "parametric", B = 100, ci = 0.95, optimization = "optim")

Arguments

d

Data frame with the results of a Yes-No experiment to fit. It should have a tidy form in which each column corresponds to a variable and each row is an observation.

x

Name of the explanatory variable.

k

Name of the response variable. The response variable could be the number of trials in which a yes-type response was given or a vector of 0s (or -1s; no-type response) and 1s (yes-type response) indicating the response on each trial.

n

Only necessary if k refers to the number of trials in which a yes-type response was given. It corresponds to the name of the variable indicating the total number of trials.

grouping

Name of the grouping variables. It should be specified as grouping = .(variable_name1, variable_name2).

random

Name of the random variable. It should be specified as random = .(variable_name1, variable_name2). In the current version of quickpsy, the random variable has not special treatment. It does the same as grouping.

within

Name of the within variable. It should be specified as within = .(variable_name1, variable_name2). In the current version of quickpsy, the within variable has not special treatment. It does the same as grouping.

between

Name of the between variable. It should be specified as between = .(variable_name1, variable_name2). In the current version of quickpsy, the between variable has not special treatment. It does the same as grouping.

xmin

Minimum value of the explanatory variable for which the curves should be calculated (the default is the minimum value of the explanatory variable).

xmax

Maximum value of the explanatory variable for which the curves should be calculated (the default is the maximum value of the explanatory variable).

log

If TRUE, the logarithm of the explanatory variable is used to fit the curves (default is FALSE).

fun

Name of the shape of the curve to fit. It could be a predefined shape (cum_normal_fun, logistic_fun, weibull_fun) or the name of a function introduced by the user (default is cum_normal_fun).

parini

Initial parameters. quickpsy calculates default initial parameters using probit analysis, but it is also possible to specify a vector of initial parameters or a list of the form list(c(par1min, par1max), c(par2min, par2max)) to constraint the lower and upper bounds of the parameters (when optimization = 'DE', parini should be also a list).

guess

Value indicating the guess rate \gamma (default is 0). If TRUE, the guess rate is estimated as the i + 1 parameter where i corresponds to the number of parameters of fun. If, for example, fun is a predefined shape with parameters p1 and p2, then the guess rate corresponds to parameter p3.

lapses

Value indicating the lapse rate \lambda (default is 0). If TRUE, the lapse rate is estimated as the i + 1 parameter where i corresponds to the number of parameters of fun plus one if the guess rate is estimated. If, for example, fun is a predefined shape with parameters p1 and p2, then the lapse rate corresponds to parameter p3. If the guess rate is also estimated, p3 will be the guess rate and p4 the lapse rate.

prob

Probability to calculate the threshold (default is guess + .5 * (1 - guess)).

thresholds

If FALSE, thresholds are not calculated (default is TRUE).

bootstrap

'parametric' performs parametric bootstrap; 'nonparametric' performs non-parametric bootstrap; 'none' does not perform bootstrap (default is 'parametric').

B

number of bootstrap samples (default is 100 ONLY).

ci

Confidence intervals level based on percentiles (default is .95).

optimization

Method used for optimizization. The default is 'optim' which uses the optim function. It can also be 'DE' which uses de function DEoptim from the package DEoptim, which performs differential evolution optimization. By using DEoptim, it is less likely that the optimization finishes in a local minimum, but the optimization is slow. When 'DE' is used, parini should be specified as a list with lower and upper bounds.

See Also

quickpsy

Reads several files

Description

quickreadfiles builts a data frame from several txt files. It assumes that in each file, the first row has the names of the variables.

Usage

quickreadfiles(path = getwd(), extension = "txt", ...)

Arguments

path

Path of the file (default is the working directory).

extension

Specify whether the file extension is 'txt' or 'csv'.

...

arguments of the form name_var = c('value1', 'value2',..). A new column with variable name name_var is addes to the data frame.

Examples

# download the 3 files in
# https://github.com/danilinares/quickpsy/tree/master/inst/extdata/example1
# and add them to your working directory
# dat <- quickreadfiles(subject = c('aa', 'bb', 'cc'), session = c('1', '2'))
# fit <- quickpsy(dat, phase, resp, grouping=.(subject), lapses = T, guess = T)
# plotcurves(fit)

Sum of squared errors of prediction

Description

ypred calculates the sum of squared errors of prediction

Usage

sse(qp)

Arguments

qp

output from quickpsy

Plot the parameters and its confidence intervals summary Plot the parameters and its confidence intervals

Description

Plot the parameters and its confidence intervals summary Plot the parameters and its confidence intervals

Usage

## S3 method for class 'quickpsy'
summary(object, ...)

Arguments

object

An object for which a summary is desired.

...

Additional arguments affecting the summary produced.

Pair comparisons of the parameters using bootstrap thresholdcomparisons Calculates the bootstrap confidence intervals for the difference in the parameters for two groups for all possible pairs of groups

Description

Pair comparisons of the parameters using bootstrap thresholdcomparisons Calculates the bootstrap confidence intervals for the difference in the parameters for two groups for all possible pairs of groups

Usage

thresholdcomparisons(qp, ci = 0.95)

Calculates the thresholds

Description

Calculates the thresholds

Usage

thresholds(qp, prob = NULL, log = FALSE)

Arguments

qp

output from quickpsy

prob

Probability to calculate the threshold.

log

Use TRUE, if the logarithm of the independent variable has been used to fit the curves (default is FALSE).

Calculates bootstrap thresholds thresholdsbootstrap calculates bootstrap thresholds

Description

Calculates bootstrap thresholds thresholdsbootstrap calculates bootstrap thresholds

Usage

thresholdsbootstrap(qp, prob = NULL, log = F)

Calculates the confidence intervals for the thresholds thresholdsci calculates the confidence intervals for the thresholds

Description

Calculates the confidence intervals for the thresholds thresholdsci calculates the confidence intervals for the thresholds

Usage

thresholdsci(qp, ci = 0.95, method = "percent")

Weibull function

Description

Weibull function of the form (1 - exp(-(x/\alpha)^\beta)

Usage

weibull_fun(x, p)

Arguments

x

Vector of values of the explanatory variable.

p

Vector of parameters p = c(\alpha, \beta).

Value

Probability at each x.

Examples

xseq <- seq(0, 4, .01)
yseq <- weibull_fun(xseq, c(2, 4))
curve <- data.frame(x = xseq, y = yseq)
ggplot(curve, aes(x = x, y = y)) + geom_line()

Predicted probabilities

Description

ypred calculates the predicted probabilities at the values of the explanatory variable.

Usage

ypred(qp)

Arguments

qp

output from quickpsy

Examples

library(MPDiR) # contains the Vernier data
data(Vernier) # ?Venier for the reference
fit <- quickpsy(Vernier, Phaseshift, NumUpward, N,
                grouping = .(Direction, WaveForm, TempFreq), B = 20)
ypred(fit)