statpsych version 1.5.0 (Release date: 2023/12/11)
Changes:
New functions:
ci.cv1 – Computes confidence interval for a single coefficient of variation
ci.ratio.cv2 – Computes confidence interval for a ratio of coefficients of variation
ci.pv – Computes confidence intervals for positive and negative predictive values with retrospective sampling
ci.2x2.stdmean.ws – Computes confidence intervals of standardized effects in a 2x2 within-subjects design
ci.2x2.stdmean.mixed – Computes confidence intervals of standardized effects in a 2x2 mixed design
ci.2x2.median.ws – Computes confidence intervals of effects in a 2x2 within-subjects design for medians
ci.2x2.median.mixed – Computes confidence intervals of effects in a 2x2 mixed design
for medians
spearmanbrown – Computes the reliability of a scale with r2 measurements given the reliability of a scale with r1 measurements
size.ci.spear – Computes the sample size requirement for a Spearman correlation confidence interval
size.ci.pbcor – Computes the sample size requirement for a point-biserial correlation confidence interval
size.ci.mape1 – Computes the sample size requirement for a mean absolute prediction error confidence interval
Error Corrections:
corrected CI error in ci.cramer
corrected SE error in ci.lc.stdmean.ws
Modifications:
both biased and bias adjusted estimates are now reported in ci.stdmean1, ci.stdmean2, ci.stdmean.ps, ci.stdmean.strat, and ci.2x2.stdmean.bs
ci.mape has been renamed ci.mape1
statpsych version 1.4.0 (Release date: 2023/06/26)2023-06-14
Changes:
New functions:
power.prop1 – Computes power for 1-sample test of proportion for a planned sample size
power.prop2 – Computes power for 2-sample test of proportion for planned sample sizes
power.prop.ps – Computes power for paired-samples test of proportion for a planned sample size
power.mean1 – Computes power for 1-sample t-test for a planned sample size
power.mean2 – Computes power for 2-sample t-test for planned sample sizes
power.mean.ps – Computes power for paired-samples t-test for a planned sample size
power.lc.mean.bs – Computes power of a test for a linear contrast of means for planned sample sizes in a between-subjects design
power.cor1 – Computes power for 1-sample test of correlation for a planned sample size
power.cor2 – Computes power for 2-sample test of correlations for planned sample sizes
ci.cqv1 – Computes confidence interval for a population coefficient of qualitative variation
ci.prop1.inv – Computes confidence interval for a population proportion using inverse
sampling
ci.prop2.inv – Computes confidence interval for a difference in population proportions using inverse sampling
ci.agree.3rater – Computes confidence intervals for a 3-rater design with dichotomous ratings
ci.ratio.sd2 – Computes robust confidence interval for ratio of standard deviations in a 2-group design
size.test.cor2 – Computes sample size for a test of equal Pearson or partial correlation in a 2-group design
size.test.cronbach2 – Computes sample size to test equality of Cronbach reliability
coefficients in a 2-group design
size.ci.cronbach2 – Computes sample size for a 2-group Cronbach reliability difference confidence interval
size.ci.etasqr – Computes sample size for an eta-squared confidence interval
size.ci.indirect – Computes sample size for an indirect effect confidence interval
ci.mape2 – Computes confidence interval for a ratio of mean absolute prediction errors in a 2-group design
ci.rel2 – Computes confidence interval for a 2-group reliability difference
ci.cronbach2 – Computes confidence interval for a difference in Cronbach reliabilities in
a 2-group design
ci.2x2.stdmean.bs – Computes confidence intervals of standardized effects in a 2x2 between-subjects design for means
ci.2x2.median.bs – Computes confidence intervals of effects in a 2x2 between-subjects design for medians
pi.var.upper – Computes upper prediction limit for an estimated variance
ci.bayes.normal – Computes Bayesian credible interval for any parameter estimator with a normal sampling distributuion using a Normal prior distribution
ci.bayes.prop1 – Computes Bayesian credible interval for a single proportion using a Beta prior distribution
Modifications:
Corrected Example output in ci.reliability and ci.prop.ps
SE added to output in: ci.cronbach, ci.oddsratio, ci.yule, ci.etasqr, ci.rsqr, ci.spear2, ci.cor2, ci.cor.dep, ci.cod1, ci.mad1, ci.mape, ci.agree2, ci.pbcor, and ci.tetra
Improved accuracy in size.ci.rsqr
Three generalized Yule coefficients added to ci.yule
The ci.prop.ps, ci.ratio.prop.ps, and ci.2x2.prop.mixed functions now define proportions for the y = 1 category rather than the y = 0 category.
ci.2x2.mean.bs - Confidence intervals for effects in a 2x2 between-subjects design for means
ci.2x2.mean.ws - Confidence intervals for effects in a 2x2 within-subjects design for means
ci.2x2.mean.mixed - Confidence intervals for effects in a 2x2 mixed design for means
ci.2x2.prop.bs - Confidence intervals for effects in a 2x2 between-subjects design for proportions
ci.2x2.prop.mixed - Confidence intervals for effects in a 2x2 mixed design for proportions
sim.ci.mean1 – Simulation of confidence interval for a single mean
sim.ci.mean2 – Simulation of confidence interval for mean difference in a two-group design
sim.ci.mean.ps – Simulation of confidence interval for mean difference in a paired-samples design
sim.ci.median1 – Simulation of confidence interval for a single median
sim.ci.cor – Simulation of confidence interval for a Pearson correlation
sim.ci.spear – Simulation of confidence interval for a Spearman correlation
Modifications:
The ci.prop.ps function now outputs an adjusted point estimate of the proportion difference, as stated in the documentation, rather than an unadjusted estimate
The ci.cor, ci.cor2, and ci.cor.dep functions now uses a bias adjustment to reduce the bias of the Fisher transformed correlations
The ci.median1 function now uses the same standard error formula as the ci.median2, ci.ratio.median2, and ci.median.ps functions
Error Correction:
Corrected an error for the standard error computation in the ci.indirect function