Home Analytics SPSS SPSS Statistics Regression IBM SPSS Regression
Predict categorical outcomes and apply nonlinear regression procedures. Test this function with a full-feature SPSS trial or explore pricing options
Try SPSS Statistics at no cost See pricing options
Unlock advanced data insights with SPSS Regression

IBM® SPSS® Regression enables you to predict categorical outcomes and apply various nonlinear regression procedures when studying consumer buying habits, treatment response, credit risk analysis, and other common situations where ordinary regression techniques are limiting or inappropriate.

Find out how to run regression analysis in IBM® SPSS® Statistics
Industry use cases Do you build predictive models but find the usual tools for conducting regression analysis too limiting? If so, SPSS is a versatile, intuitive software that can be used to conduct regression analysis across industries including: Marketing

Study consumer buying habits. Optimize marketing strategies and customer satisfaction.

Healthcare

Analyze dosage responses to improve care quality and achieve better patient outcomes.

Banking and finance

Assess credit risks and enhance customer relationships through targeted offers.

Education

Measure academic achievement tests and support institutional research.

Retail

Examine customer behavior to curate personalized offers.

Government

Improve citizen services and safety. Assess tax payment compliance, minimize fraud and mitigate threats.

What you can do
Binary logistic regression

Predict the presence or absence of a characteristic or binary outcome based on values of a set of predictor variables.

Logit response models

Use the logit link function to model the dependence of a polytomous ordinal response on a set of predictors.

Multinomial logistic regression

Classify subjects based on values of a set of predictor variables. This type of regression is like logistic regression, but it is more general because the dependent variable is not restricted to two categories.

Nonlinear regression

Find a nonlinear model of the relationship between the dependent variable and a set of independent variables.

Probit response analysis

Use probit and logit response modeling to analyze the potency of responses to stimuli such as medicine doses, prices or incentives. This procedure measures the relationship between the strength of a stimulus and the proportion of cases exhibiting a certain response to the stimulus.

Two-stage least squares

In the first stage, use instrumental variables that are uncorrelated with the error terms to compute the estimated values of one or more problematic predictors. In the second stage, use those computed values to estimate a linear regression model of the dependent variable.

Weighted least squares

Control the correlations between the predictor variables and error terms that can occur with time-based data. The weight estimation procedure tests a range of weight transformations and indicates which gives the best fit to the data.

Elastic net

The new linear elastic net extension procedure estimates regularized linear regression models for a dependent variable on one or more independent variables.

Lasso

The new linear lasso extension estimates L1 loss in regularized linear regression models for a dependent variable on one or more independent variables.

Ridge

The new linear ridge extension procedure estimates L2 or squared loss regularized linear regression models for a dependent variable on one or more independent variables.

Product reviews*

Choose from a subscription or one-time purchase, with multiple options for capabilities based on your needs.

Starting at USD 99* per month Buy online

Purchase SPSS Statistics and the add-ons you need online, whether monthly or annually, and start your analysis right away.

Buy online Save 10% Explore more
Purchase with a seller

Select between Base, Standard, Professional and Premium packages with options to customize your configuration, whether it is a perpetual or 12-month subscription license.

Purchase with a seller Explore more
Are you a student or a teacher?

Choose the edition that meets your requirements and buy it from IBM-selected vendors to receive the best support.