Confidence intervals is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Read the full entry →Research Wiki · Methods Lab
Statistical inference and hypothesis testing
Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions.
Methods family
Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions.
Use methods only after defining the estimand, data structure, assumptions, validation plan and decision consequence.
Margin of error is an interval around a sample estimate that reflects uncertainty from probability sampling under stated assumptions. It does not capture coverage error, non-response bias, measurement error or model misspecification.
Read the full entry →Statistical power is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Read the full entry →Power analysis is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Read the full entry →Effect-size analysis is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Read the full entry →One-sample t-test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Read the full entry →An independent-samples t-test compares the means of two independent groups under assumptions about sampling, outcome scale and variance. The result should be reported with an effect size and confidence interval, not only a p-value.
Read the full entry →A paired-samples t-test evaluates the mean of within-pair differences, such as before-and-after measures on the same people. Pairing must be retained in the analysis.
Read the full entry →Z-test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
A chi-square test evaluates whether observed categorical counts differ from expected counts under a null model. Sparse cells can invalidate the approximation and may require exact or alternative methods.
Fisher’s exact test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
McNemar’s test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Cochran’s Q test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
One-way ANOVA tests whether at least one group mean differs across three or more independent groups under model assumptions. Post-hoc comparisons and effect sizes are needed to locate and interpret differences.
Two-way ANOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Factorial ANOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Repeated-measures ANOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Mixed-design ANOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
MANOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
MANCOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
ANCOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Welch’s ANOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Kruskal-Wallis test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Mann-Whitney U test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Wilcoxon signed-rank test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Friedman test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Sign test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Kolmogorov-Smirnov test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Shapiro-Wilk test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Levene’s test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Bartlett’s test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Post-hoc testing is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Tukey HSD is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Bonferroni correction is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Holm correction is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
False discovery rate is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Equivalence testing is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Non-inferiority testing is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Superiority testing is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Bayesian hypothesis testing is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Browse linked method entries
Confidence intervals
Confidence intervals is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodMargin of error
Margin of error is an interval around a sample estimate that reflects uncertainty from probability sampling under stated assumptions. It does not capture coverage error, non-response bias, measurement error or model misspecification.
Open methodStatistical power
Statistical power is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodPower analysis
Power analysis is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodEffect-size analysis
Effect-size analysis is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodOne-sample t-test
One-sample t-test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodIndependent-samples t-test
An independent-samples t-test compares the means of two independent groups under assumptions about sampling, outcome scale and variance. The result should be reported with an effect size and confidence interval, not only a p-value.
Open methodPaired-samples t-test
A paired-samples t-test evaluates the mean of within-pair differences, such as before-and-after measures on the same people. Pairing must be retained in the analysis.
Open methodZ-test
Z-test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodChi-square test
A chi-square test evaluates whether observed categorical counts differ from expected counts under a null model. Sparse cells can invalidate the approximation and may require exact or alternative methods.
Open methodFisher’s exact test
Fisher’s exact test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodMcNemar’s test
McNemar’s test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodCochran’s Q test
Cochran’s Q test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodOne-way ANOVA
One-way ANOVA tests whether at least one group mean differs across three or more independent groups under model assumptions. Post-hoc comparisons and effect sizes are needed to locate and interpret differences.
Open methodTwo-way ANOVA
Two-way ANOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodFactorial ANOVA
Factorial ANOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodRepeated-measures ANOVA
Repeated-measures ANOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodMixed-design ANOVA
Mixed-design ANOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodMANOVA
MANOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodMANCOVA
MANCOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodANCOVA
ANCOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodWelch’s ANOVA
Welch’s ANOVA is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodKruskal-Wallis test
Kruskal-Wallis test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodMann-Whitney U test
Mann-Whitney U test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodWilcoxon signed-rank test
Wilcoxon signed-rank test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodFriedman test
Friedman test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodSign test
Sign test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodKolmogorov-Smirnov test
Kolmogorov-Smirnov test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodShapiro-Wilk test
Shapiro-Wilk test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodLevene’s test
Levene’s test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodBartlett’s test
Bartlett’s test is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodPost-hoc testing
Post-hoc testing is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodTukey HSD
Tukey HSD is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodBonferroni correction
Bonferroni correction is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodHolm correction
Holm correction is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodFalse discovery rate
False discovery rate is a statistical or analytical concept within statistical inference and hypothesis testing. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodEquivalence testing
Equivalence testing is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodNon-inferiority testing
Non-inferiority testing is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodSuperiority testing
Superiority testing is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodBayesian hypothesis testing
Bayesian hypothesis testing is a method within statistical inference and hypothesis testing. Methods for quantifying uncertainty and testing whether observed differences are compatible with sampling variation and model assumptions. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodNo entries match this search.