stats_power_solve | Solves the power equation of a t, z, ANOVA F, regression F or chi-square goodness-of-fit test for whichever one of effect_size, nobs, alpha and power is left null: the sample size for a target power, the power of a given sample, or the minimum detectable effect. | |
stats_power_curve | Power as a function of sample size for one or more effect sizes (one curve each), for the same tests as stats_power_solve. | |
stats_proportion_sample_size | Sample size and power for proportions: the n that gives a confidence interval of a given half-width, the group-1 size needed to detect a difference between two proportions at a target power (or the power of given group sizes), and the n for a one-tailed normal test of a difference. | |
stats_equivalence_power | Power of the two one-sided tests (TOST) for a proportion to show it lies inside [low, upp] when the true proportion is p_alt, at each sample size: exact binomial or normal approximation. | |
