| Title: | Permutation Distancing Test |
|---|---|
| Description: | Permutation (randomisation) test for single-case phase design data with two phases (e.g., pre- and post-treatment). Correction for dependency of observations is done through stepwise resampling the time series while varying the distance between observations. The required distance 0,1,2,3.. is determined based on repeated dependency testing while stepwise increasing the distance. In preparation: Vroegindeweij et al. "A Permutation distancing test for single-case observational AB phase design data: A Monte Carlo simulation study". |
| Authors: | Jan Houtveen [aut, cre], Anouk Vroegindeweij [ctb] |
| Maintainer: | Jan Houtveen <[email protected]> |
| License: | GPL-3 |
| Version: | 0.0.2 |
| Built: | 2025-01-29 03:36:59 UTC |
| Source: | https://github.com/cran/pdt |
Performs a randomisation test for two phases (A and B) that corrects for dependency. The correcting is done through stepwise resampling the time series while varying the distance between observations. The required distance 0,1,2,3.. is determined based on repeated dependency testing while stepwise increasing the distance. The input x and y values should be equidistant (with NA's included) using insert_NA_and_try_to_shift. The distance per cycles = k-1. k_max should be max 25 If de_A_trend=TRUE, phase A will be first de_A_trended. If de_B_trend=TRUE, phase B will be first de_B_trended. If detrend_x_position = "first" : take predicted value for first valid observation. If detrend_x_position = "center": take predicted value for center observation. If detrend_x_position = "last" : take predicted value for last valid observation. The p-value returned corresponds with the lowest Ljung-Box test (minimal) p-value found. The statistic returned correspond with median chi-square k with p_box larger than alpha_p_box_test or statistic_box smaller than max_statistic_p_box_test (i.e., not dependent).
AB_permutation_distancing_test( x, y, test_statistic = "*", test_statistic_function = "mean", reps_max = 2000, k_max = NULL, alpha_p_box_test = 0.1, max_statistic_p_box_test = 2.7, no_duplicates = FALSE, remove_NA_series_above_k = TRUE, de_A_trend = FALSE, detrend_A_position = "center", de_B_trend = FALSE, detrend_B_position = "center", show_plot = FALSE, show_plot_header = "" )AB_permutation_distancing_test( x, y, test_statistic = "*", test_statistic_function = "mean", reps_max = 2000, k_max = NULL, alpha_p_box_test = 0.1, max_statistic_p_box_test = 2.7, no_duplicates = FALSE, remove_NA_series_above_k = TRUE, de_A_trend = FALSE, detrend_A_position = "center", de_B_trend = FALSE, detrend_B_position = "center", show_plot = FALSE, show_plot_header = "" )
x |
factor vector to indicate conditions or phases (e.g., "A" and "B") |
y |
numerical vector with the observed y-values |
test_statistic |
character how to compute the test statistic c("A-B", "B-A", "*") *=two-sided |
test_statistic_function |
character compute and compare "mean" or "median" for A and B |
reps_max |
numerical maximum number of permutation replications (the theoretical number= n!) |
k_max |
numerical maximum k value |
alpha_p_box_test |
numerical see above |
max_statistic_p_box_test |
numerical see above |
no_duplicates |
boolean do a permutation test without duplicates (makes it much slower) |
remove_NA_series_above_k |
boolean first clean the data by skipping repeated NA's |
de_A_trend |
boolean de-trend A first (optional) |
detrend_A_position |
character c("first", "center", "last"), see detrend_A |
de_B_trend |
boolean de-trend B first (optional) |
detrend_B_position |
character c("first", "center", "last"), see detrend_B |
show_plot |
boolean show test plot of statistical test |
show_plot_header |
character header of test plot |
List with the permutation distancing test results: de_A_trend setting in call, detrend_A_position in call, de_B_trend setting in call, detrend_B_position in call, ar1 = vector of computed ar1 values per distancing step (0,1,2, etc), p_box = vector of computed box-test p-values per distancing step, statistic_box = vector of box-test statistics per distancing step, observed_test_statistic = computed overall AB test statistic (before distancing), effect_size_overall = computed overall effect size (before distancing), p = vector of computed permutation test p-values per distancing step, effect_size vector of computed permutation test effect-sizes per distancing step, p_fitted = vector of lm-fitted line p-values through p_box, k_max = k_max setting in call or computed based on the number of observations, k_selected_based_on_Box_test = selected k values, p_selected_based_on_Box_test = selected p-value, effect_size_selected_based_on_Box_test = selected effect-size values.
pdt::AB_permutation_distancing_test( as.factor(c(rep("A",20), rep("B",20))), c(rnorm(20), rnorm(20)+2), test_statistic="B-A", test_statistic_function="mean", reps_max=1000, k_max=NULL, alpha_p_box_test=0.1, max_statistic_p_box_test=2.7, no_duplicates=FALSE, remove_NA_series_above_k=TRUE, de_A_trend=FALSE, detrend_A_position="center", de_B_trend=FALSE, detrend_B_position="center", show_plot=FALSE, show_plot_header="")pdt::AB_permutation_distancing_test( as.factor(c(rep("A",20), rep("B",20))), c(rnorm(20), rnorm(20)+2), test_statistic="B-A", test_statistic_function="mean", reps_max=1000, k_max=NULL, alpha_p_box_test=0.1, max_statistic_p_box_test=2.7, no_duplicates=FALSE, remove_NA_series_above_k=TRUE, de_A_trend=FALSE, detrend_A_position="center", de_B_trend=FALSE, detrend_B_position="center", show_plot=FALSE, show_plot_header="")
Performs a regular permutations test for two conditions or phases (A and B).
AB_permutation_test( x, y, test_statistic = "*", test_statistic_function = "mean", reps_max = 2000, no_duplicates = FALSE, show_plot = FALSE, show_plot_header = "" )AB_permutation_test( x, y, test_statistic = "*", test_statistic_function = "mean", reps_max = 2000, no_duplicates = FALSE, show_plot = FALSE, show_plot_header = "" )
x |
factor vector to indicate conditions or phases (e.g., "A" and "B") |
y |
numerical vector with the observed y-values |
test_statistic |
character how to compute the test statistic c("A-B", "B-A", "*") *=two-sided |
test_statistic_function |
character compute and compare "mean" or "median" for A and B |
reps_max |
numerical maximum number of permutation replications (the theoretical number= n!) |
no_duplicates |
boolean do a permutation test without duplicates (makes it much slower) |
show_plot |
boolean show test plot of statistical test |
show_plot_header |
character header of test plot |
List with the permutation test results: observed_test_statistic = computed test statistic, effect_size = computed effect size (similar to Cohen's d), random_assignments, p_randomization_AB = p value randomization AB test, one_sided_p = one-sided p-value in case of B-A or A-B.
pdt::AB_permutation_test( as.factor(c(rep("A",20), rep("B",20))), c(rnorm(20), rnorm(20)+2), test_statistic="B-A", test_statistic_function="mean", reps_max=1000, no_duplicates=FALSE, show_plot=FALSE, show_plot_header="")pdt::AB_permutation_test( as.factor(c(rep("A",20), rep("B",20))), c(rnorm(20), rnorm(20)+2), test_statistic="B-A", test_statistic_function="mean", reps_max=1000, no_duplicates=FALSE, show_plot=FALSE, show_plot_header="")
Creates a permutation distancing test plot. Several plot options are available, e.g., to show both the observed and detrended lines.
AB_permutation_test_plot( x, x_values, y, test_statistic_function = "mean", de_A_trend = FALSE, detrend_A_position = "center", show_de_A_trended = FALSE, de_B_trend = FALSE, detrend_B_position = "center", show_de_B_trended = FALSE, show_plot_header = "", xlab = "", ylab = "", ylim = NULL, labels = NULL, line_colors = c("blue", "red", "blue", "red", "blue", "cyan"), show_legend = TRUE )AB_permutation_test_plot( x, x_values, y, test_statistic_function = "mean", de_A_trend = FALSE, detrend_A_position = "center", show_de_A_trended = FALSE, de_B_trend = FALSE, detrend_B_position = "center", show_de_B_trended = FALSE, show_plot_header = "", xlab = "", ylab = "", ylim = NULL, labels = NULL, line_colors = c("blue", "red", "blue", "red", "blue", "cyan"), show_legend = TRUE )
x |
factor vector to indicate conditions or phases (e.g., "A" and "B") |
x_values |
numerical vector with distance (time markers) between observations |
y |
numerical vector with the observed y-values |
test_statistic_function |
character compute and compare "mean" or "median" for phase A and B |
de_A_trend |
boolean de-trend A (optional) |
detrend_A_position |
character c("first", "center", "last"), see detrend_A |
show_de_A_trended |
boolean show de-trend A line (optional) |
de_B_trend |
boolean de-trend B (optional) |
detrend_B_position |
character c("first", "center", "last"), see detrend_B |
show_de_B_trended |
boolean show de-trend B line (optional) |
show_plot_header |
character header |
xlab |
character x-axis label |
ylab |
character y-axis label |
ylim |
numerical vector of y-axis limits |
labels |
character vector of labels |
line_colors |
character vector with colors of the succeeding lines c("blue", "red", "blue", "red", "blue", "cyan"), |
show_legend |
boolean show legend |
NULL.
pdt::AB_permutation_test_plot( as.factor(c(rep("A",20), rep("B",20))), 1:40, c(rnorm(20), rnorm(20)+2), test_statistic_function="mean", de_A_trend=TRUE, detrend_A_position="center", show_de_A_trended=TRUE, de_B_trend=TRUE, detrend_B_position="center", show_de_B_trended=TRUE, show_plot_header="", xlab="", ylab="", ylim=NULL, labels=NULL, line_colors=c("blue", "red", "blue", "red", "blue", "cyan"), show_legend=TRUE)pdt::AB_permutation_test_plot( as.factor(c(rep("A",20), rep("B",20))), 1:40, c(rnorm(20), rnorm(20)+2), test_statistic_function="mean", de_A_trend=TRUE, detrend_A_position="center", show_de_A_trended=TRUE, de_B_trend=TRUE, detrend_B_position="center", show_de_B_trended=TRUE, show_plot_header="", xlab="", ylab="", ylim=NULL, labels=NULL, line_colors=c("blue", "red", "blue", "red", "blue", "cyan"), show_legend=TRUE)
Detrends the phase A part of time series y. detrend A is optional and not validated. The mean of the detrended signal will be set to the predicted value based on detrend_A_position: detrend_A_position = "first" : take predicted value for first valid observation detrend_A_position = "center" : take predicted value for center observation detrend_A_position = "last" : take predicted value for last valid observation.
detrend_A(x, x_values, y, detrend_A_position = "center")detrend_A(x, x_values, y, detrend_A_position = "center")
x |
factor vector to indicate conditions or phases (e.g., "A" and "B") |
x_values |
numerical vector with distance (time markers) between observations |
y |
numeric vector with the observed y-values |
detrend_A_position |
character to indicate the mean |
List with the trend and the detrended y-values: x_values_A_trend = vector with distance (time markers) between A-detrended signal, y_A_trend = vector with computed A-trend, y_detrended = vector with computed A-detrended y values.
pdt::detrend_A(as.factor(c(rep("A",20), rep("B",20))), 1:40, c(rnorm(20), rnorm(20)+2), detrend_A_position="center")pdt::detrend_A(as.factor(c(rep("A",20), rep("B",20))), 1:40, c(rnorm(20), rnorm(20)+2), detrend_A_position="center")
Detrends the phase B part of time series y. detrend B is optional and not validated. The mean of the detrended signal will be set to the predicted value based on detrend_B_position: detrend_B_position = "first" : take predicted value for first valid observation detrend_B_position = "center" : take predicted value for center observation detrend_B_position = "last" : take predicted value for last valid observation.
detrend_B(x, x_values, y, detrend_B_position = "center")detrend_B(x, x_values, y, detrend_B_position = "center")
x |
factor vector to indicate conditions or phases (e.g., "A" and "B") |
x_values |
numerical vector with distance (time markers) between observations |
y |
numeric vector with the observed y-values |
detrend_B_position |
character to indicate the mean |
List with the trend and the detrended y values: x_values_B_trend = vector with distance (time markers) between B-detrended signal, y_B_trend = vector with computed B-trend, y_detrended = vector with computed B-detrended y values.
pdt::detrend_B(as.factor(c(rep("A",20), rep("B",20))), 1:40, c(rnorm(20), rnorm(20)+2), detrend_B_position="center")pdt::detrend_B(as.factor(c(rep("A",20), rep("B",20))), 1:40, c(rnorm(20), rnorm(20)+2), detrend_B_position="center")
Remove series of more than k succeeding NA's in x, y, and x_values. This function is recommended before performing a permutation distancing test.
do_remove_NA_series_above_k(x, y, k, x_values = NULL)do_remove_NA_series_above_k(x, y, k, x_values = NULL)
x |
factor vector to indicate conditions or phases (e.g., "A" and "B") |
y |
numeric vector with the observed y-values |
k |
maximum allowed number of NA's |
x_values |
numerical vector with distance (time markers) between observations |
List with the modified x, y, x_values: x = factor vector with conditions (e.g., "A" and "B"). y = vector with observed values. x_values = vector with distance (time markers) between observations x,y.
pdt::do_remove_NA_series_above_k(as.factor(c("A","A","A","B","B","B")), c(1.1,NA,NA,7.1,8.3,9.8), 1, c(1,2,4,5,6,8))pdt::do_remove_NA_series_above_k(as.factor(c("A","A","A","B","B","B")), c(1.1,NA,NA,7.1,8.3,9.8), 1, c(1,2,4,5,6,8))
Makes the input time series equidistant. This is recommended before performing a permutation distancing test. This function first inserts NA's for missing x_values, then it tries to shift double value to previous or next NA's, finally it aggregates the remaining identical x_values.
insert_NA_and_try_to_shift(x, x_values, y)insert_NA_and_try_to_shift(x, x_values, y)
x |
factor vector to indicate conditions or phases (e.g., "A" and "B") |
x_values |
numerical vector with distance (time markers) between observations |
y |
numeric vector with the observed y-values |
List with the modified x, x_values, y: x = factor vector with conditions or phases (e.g., "A" and "B"). x_values = (optional) vector with distance (time markers) between observations. y = vector with observed values.
pdt::insert_NA_and_try_to_shift(as.factor(c("A","A","A","B","B","B")), c(1,2,4,5,6,8), c(1.1,3.2,5.3,7.1,8.3,9.8))pdt::insert_NA_and_try_to_shift(as.factor(c("A","A","A","B","B","B")), c(1,2,4,5,6,8), c(1.1,3.2,5.3,7.1,8.3,9.8))