IBM SPSS Exact Tests
Two minute module overview
What’s in the Exact Tests module?
IBM SPSS Exact Tests enables you to use small samples and still feel confident about the results. With the money saved using smaller sample sizes, you can conduct surveys or test direct marketing programs more often. Stay ahead of the competition by using these resources to find new opportunities.
- IBM SPSS Exact Tests is easy to use. You can perform a test any time, with just a click of a button – during your original analysis or when you rerun it. With IBM SPSS Exact Tests, there is no steep learning curve, because you don’t need to learn any new statistical theories or procedures. You simply interpret the exact tests results the same way you already interpret the results in IBM SPSS Statistics Base.
- You’ll always have the right statistical test for your data situation. IBM SPSS Exact Tests provides more than 30 exact tests, which cover the entire spectrum of nonparametric and categorical data problems for small or large datasets. These tests include one-sample, two-sample and K-sample tests on independent or related samples, goodness-of-fit tests, tests of independence in RxC contingency tables and on measures of association.
- Both the client and server versions of IBM SPSS Exact Tests are available on Mac® and Linux®, as well as on Windows® operating systems.
The IBM SPSS Exact Tests module provides additional methods for calculating the significance levels for the statistical tests available through the Crosstabs and the Nonparametric Tests menus. Using the standard tests in IBM SPSS Base (known as asymptotic tests) can lead to misleading or inaccurate results when working with small datasets or sparse groups in the sample data. IBM SPSS Exact Tests enables users to obtain an accurate significance level without relying on assumptions that might not be met by the data.
- Exact Tests however are not necessary when working with reasonably large data files and in fact may use too much computational resource or take too long to calculate the result.
- Exact Tests offers two extra methods of calculating probabilities on top of the normal asymptotic methods in SPSS Base.
- Asymptotic: The asymptotic significance is based on the assumption that the data set is large. If the data set is small or poorly distributed, this may not be a good indication of significance.
- Monte Carlo Estimate: An unbiased estimate of the exact significance level. This method is most useful when the data set is too large to compute exact significance but the data do not meet the assumptions of the asymptotic method.
- Exact: The probability of the observed outcome or an outcome more extreme is calculated exactly.