Generalized Linear Models (or GLMs) extend the ordinary regression framework to situations where the observations of the response variate do not follow a Normal distribution, or where a transformation needs to be applied before a linear model can be fitted. The Generalized Linear Models dialog can be used to fit a range of models including log-linear models and logistic regression. In addition there are menus for ordinal regression and all subset regression.

- After you have imported your data, from the menu select

**Stats | Regression Analysis | Generalized Linear Models**. - Fill in the fields as required then click
**Run**.

You can set additional Options then after running, you can save the results by clicking Save.

## Generalized linear models dialog

The following range of models can be fitted using the Generalized Linear Models dialog. Note that the General Model can be used a fit a wide range of models by specifying a model formula, distribution and link function.

- Log-linear modelling
- Modelling binomial proportions
- Probit analysis
- General model
- Multinomial regression
- Further Output for additional output subsequent to analysis
- Predictions from Generalized Linear Model
- Plot table of predictions
- Further Output
- Change Regression Model
- Saving Results
- Save Individual Regression Terms dialog
- Multiple Comparisons options
- Least Significant Intervals Plot Options dialog

See also

- Linear regression for fitting linear models
- Standard curves for fitting standard non-linear curves
- Linear regression for fitting linear models with correlated errors
- Standard curves for fitting standard non-linear curves with correlated errors
- Ordinal regression
- All subset regression
- Quantile regression menu
- Functional linear regression menu