Some tranformation for making variables more normally distributed are

• Square/Cube Root
• Logarithmic
• Power
• Inverse
• Hyperbolic Arcsine
• Arcsine

This quick overview shows how/when to apply these transformations in SPSS and compares their results.

Quick guide on creating dummy variables in SPSS for categorical predictors in regression.

Intermediate tutorial with practice data, examples and a handy tool.

In this tutorial, we'll show a quick and simple way to extract leading digits from a string variable.

You can set missing values for string variables in SPSS but this doesn't work as it should. This tutorial walks you through some problems and fixes.

The right way to compute means over variables is SPSS’ MEAN function.

For example: COMPUTE MEAN_SCORE = MEAN(Q1 TO Q5). computes mean_score as the mean over variables Q1 to Q5. This method also works correctly if you there's any missing values in your data.

In some cases, one would like to calculate respondents' age given their birthday. As long as birthday is an actual date variable, age is readily calculated by using the DATEDIFF function.

Converting a string variable into an SPSS date variable isn’t hard if you combine the right tools. Step-by-step tutorial with downloadable data file.

SPSS has 2 types of variables:

• numeric variables contain only numbers and can be used for calculations;
• string variables contain text and cannot be used for calculations.

Numeric variables come in several formats such as plain numbers, dates and percentages. Working with SPSS becomes much faster and easier if you're aware of variable types and formats.

We'll look up SPSS data values with the Python spssdata module. We'll then have Python insert the values into SPSS syntax and create several Excel files.