Analyst Application Summary Statistics
Table Analysis and Hypothesis Tests
Table Analysis
In the Table Analysis task, you can create and analyze two-way to n-way frequency tables. You can request various statistics such as Chi-square statistics, measures of association, Mantel-Haenszel statistics, and measures of agreement.
One-Sample Hypothesis Tests
In the One-Sample Hypothesis Test tasks, you can test whether a parameter of
a population is equal to the value specified in the null hypothesis. These tests include a Z-test for a mean,
t-test for a mean, test for a proportion, and test for a variance. You can compute confidence intervals, perform a
retrospective power analysis, and request plots such as bar charts and distribution plots.
Two-Sample Hypothesis Tests
In the Two-Sample Hypothesis tasks, you can test whether parameters of two populations are equal (or whether they differ by a specified amount). Two-sample data arise when two samples are observed, possibly with different sample sizes. These tests include a t-test for means, paired t-test for means, test for proportions, and test for variances. You can request that confidence intervals be produced and perform a retrospective power analysis. You can specify any of several types of plots to be produced depending on your analysis, including a box-and-whisker plot, a bar chart, a means and standard error plot, and a distribution plot.
Statistics and Operations Research Home Page | Analyst Application