The NPAR1WAY Procedure

Overview: NPAR1WAY Procedure

The NPAR1WAY procedure performs nonparametric tests for location and scale differences across a one-way classification. PROC NPAR1WAY also provides a standard analysis of variance on the raw data, empirical distribution function statistics, pairwise multiple comparison analysis, and stratified analysis.

PROC NPAR1WAY performs tests for location and scale differences based on the following rank-based scores of a response variable: Wilcoxon, median, Van der Waerden (normal), Savage, Siegel-Tukey, Ansari-Bradley, Klotz, Mood, and Conover. In addition, PROC NPAR1WAY provides tests that use the raw input data as scores. When the data are classified into two samples, tests are based on simple linear rank statistics. When the data are classified into more than two samples, tests are based on one-way analysis of variance (ANOVA) statistics. Both asymptotic and exact p-values are available for these tests. PROC NPAR1WAY also provides Hodges-Lehmann estimation of the location shift (with exact confidence limits) and the Fligner-Policello test for two-sample data.

PROC NPAR1WAY provides stratified analysis for two-sample data based on the following scores: Wilcoxon, median, Van der Waerden (normal), Savage, and raw data scores. Rank-based scores can be computed by using within-stratum ranks or overall ranks; strata can be weighted by stratum size or by equal weights. PROC NPAR1WAY also provides alignment by strata.

PROC NPAR1WAY computes empirical distribution function (EDF) statistics, which test whether the distribution of a variable is the same across different groups. These statistics include the Kolmogorov-Smirnov test, the Cramér–von Mises test, and the Kuiper test. Exact p-values are available for the two-sample Kolmogorov-Smirnov test.

PROC NPAR1WAY uses ODS Graphics to create graphs as part of its output. For general information about ODS Graphics, see Chapter 21: Statistical Graphics Using ODS. For more information about the statistical graphics that PROC NPAR1WAY produces, see the PLOTS= option in the PROC NPAR1WAY statement and the section ODS Graphics.