National EMSC Data Analysis Resource Center
Groups  Purpose  Conditions or Assumptions  Test  Descriptive Measures (also used to calculate CIs) 
Compare mean to historical or hypothetical (known) mean 
Standard deviation known or N large and approximate normality 
Onesample ztest 
Mean, std deviation, difference from historical mean 


Compare mean to historical or hypothetical (known) mean 
Standard deviation unknown; approximate normality 
Onesample ttest 
Mean, std deviation, difference from historical mean 
Compare means 
Approximate normality 
Twosample ttest 
Means, std deviations, pooled std deviation, difference in means 


Compare medians (Pr (X < Y)) 
Use for highly nonnormal outcomes 
Wilcoxon ranksum test MannWhitney U test 
Medians, quartiles, difference between medians 
Compare means (any or overall difference) 
Approximate normality 
Analysis of variance (ANOVA) 
Means, std deviations, pairwise differences in means 


Compare medians (outcome distributions) 
Use for highly nonnormal outcomes 
KruskalWallis test 
Medians, quartiles, pairwise differences in medians 
Evaluate whether mean of differences nonzero 
Approximate normality 
Paired ttest 
Mean of differences, std deviation of differences 


Evaluate whether median of differences nonzero 
Use for highly nonnormal outcomes 
Wilcoxon signrank test 
Median of differences, quartiles of differences 
Evaluate whether mean of differences nonzero 
Approximate normality 
Repeated measures ANOVA 
Mean of differences, std deviation of differences 


Evaluate whether median of differences nonzero 
Use for highly nonnormal outcomes 
Friedman test 
Median of differences, quartiles of differences 
Tweet
rev. 29Aug2016