# Meta-Analysis Binary: Contrast

The Contrast dialog provides settings for controlling the contrast test for meta-analysis with binary outcomes on raw data that are provided in the active dataset for the estimation of the effect size.

- Variables
- The list display all available dataset variables. Select variables from the list and move them to the Contrast(s) list.
- Contrast(s)
- The list identifies coefficients that are stored as variables in the active data set. Multiple variables are allowed. String variables are not supported.
- User-Input Coefficient Values
- Provides settings for specifying coefficients of a user-supplied contrast. Only numeric values are allowed. To formulate a valid contrast test, the number of specified values must match that of the valid studies.
- Display exponentiated statistics
- Controls the inclusion of the exponential-form statistics. When the setting is selected, the output includes the exponential-form statistics, including the exponential effect size and confidence interval limits. The setting is available when the Effect Size is specified as Logs Odd Ratio, Peto's Logs Odd Ratio, or Log Risk Ratio.

## Defining Meta-Analysis Binary contrast settings

- From the menus choose:
- In the Meta-Analysis Binary dialog, click Contrast.
- Select and define the appropriate contrast settings.
- Click Continue.