PROPHET StatGuide: Testing equality of means or locations

• One-sample tests:

  • t test (test whether population mean is equal to hypothesized value)
  • sign test (test the hypothesis that the probability of a random value from the population being above the specified value is equal to the probability of a random value being below the specified value)
  • Wilcoxon signed rank test (test whether population median is equal to hypothesized value)

• Paired two-sample tests:

  • t test (test whether population mean of paired differences is 0)
  • sign test (test the hypothesis that the probability of a paired difference being above 0 is equal to the probability of a paired difference being below 0)
  • Wilcoxon signed rank test (test whether population median of paired differences is 0)
  • McNemar's Q (test whether population median of paired differences is 0 --dichotomous outcome variable, counted data arranged in "contingency" table)

• Two-sample (unpaired) tests:

  • t test (test whether two population means are equal)
  • Mann-Whitney rank sum test (test whether two population distribution functions are identical against the alternative that they differ by location)

• Multi-sample one-way tests:

  • Unblocked

    • One-way ANOVA (unblocked) (test whether several treatment effects (means) are equal)
    • Kruskal-Wallis test (test whether several population distribution functions are identical against the alternative that they differ by location)

  • Blocked

    • One-way ANOVA (blocked) (test whether several treatment effects (means) are equal)
    • Friedman's test (test whether several treatment effects ( locations) are equal)
    • Cochran's Q (test whether several treatment effects ( locations) are equal --dichotomous outcome variable)

• Multi-factor ANOVA

  • Multi-factor ANOVA (test simultaneously the significance of the effect of multiple factors on treatment means)

Examine the glossary.

Do a keyword search of PROPHET StatGuide.

Back to StatGuide home page.

Last modified: March 17, 1997