Visualization and Estimation of Effect Sizes

[Up] [Top]

Documentation for package ‘esvis’ version 0.2.0

Help Pages

auc Calculate the area under the curve
benchmarks Synthetic benchmark screening data
binned_plot Quantile-binned effect size plot
cdfs Compute the empirical distribution functions for each of several groups.
coh_d Compute Cohen's _d_
col_hue Color hues
col_scheme Determine the color scheme to be used for the plotting
create_base_legend Create a base legend for a plot
create_cut_refs Create a set of reference lines according to a cut score
create_legend Create a legend for a plot
create_vec Create a named vector of all possible combinations
ecdf_plot Empirical Cumulative Distribution Plot
empty_plot Create an empty plot
hedg_g Compute Hedges' _g_ This function calculates effect sizes in terms of Hedges' _g_, also called the corrected (for sample size) effect size. See 'coh_d' for the uncorrected version. Also see Lakens (2013) for a discussion on different types of effect sizes and their interpretation. Note that missing data are removed from the calculations of the means and standard deviations.
pac Compute the proportion above a specific cut location
parse_form Parse formula
pooled_sd Compute pooled standard deviation
pp_annotate Annotation function to add AUC/V to a given plot
pp_calcs Produce calculations necessary for pp_plot.
pp_plot Produces the paired probability plot for two groups
probs Compute probabilities from the empirical CDFs of a grouping variable for each group.
qtile_es Compute effect sizes by quantile bins
qtile_mean_diffs Compute mean differences by various quantiles
qtile_n Compute sample size for each quantile bin for each group
seda Portion of the Stanford Educational Data Archive (SEDA).
seg_match Match segments on a plot
star Data from the Tennessee class size experiment
themes Theme settings
tpac Transformed proportion above the cut
v Calculate the V effect size statistic