Descriptives
Descriptives gives the sample size, minimum, maximum, mean and standard deviation (and optionally variance, skewness and kurtosis) of numeric variables in one compact table.
Menu: Analyze → Descriptive Statistics → Descriptives…
When should I use Descriptives?
- Summarising scale variables such as age, scores or income.
- Creating z-scores (Save standardized values).
What are the assumptions?
- Mean and SD are most meaningful for roughly symmetric scale data; for skewed data also report the median (Explore).
How do I run it in StatLab?
- Choose numeric variables.
- Tick “Variance, skewness and kurtosis” for shape statistics.
- Tick “Save standardized values” to add Z-score variables (Z + name).
How do I read the output?
| Output | Meaning |
|---|---|
| N | Valid cases for that variable. |
| Mean / Std. Deviation | Average and sample standard deviation (n − 1 denominator). |
| Skewness (SE) | Bias-corrected G1. Rough rule: |skewness / SE| > 2 suggests noticeable asymmetry. |
| Kurtosis (SE) | Bias-corrected excess kurtosis G2 (0 for a normal distribution). |
| Valid N (listwise) | Cases with valid values on every listed variable. |
Worked example
For age in the bundled sample dataset (File → Sample dataset: 150 survey respondents with gender, programme group, age, pre/post test scores, five satisfaction items, income, smoking and education): N = 150, mean = 41.25, SD = 15.17, range 18–65.
How would I report it in APA style?
Participants were aged 18–65 years (M = 41.25, SD = 15.17); wellbeing scores averaged 69.50 (SD = 7.94).
Numbers above were computed by StatLab’s validated engine from the sample dataset when this page was built.
What are common mistakes?
- Reporting means of nominal codes (e.g. “mean gender = 1.54”).
- Confusing the standard deviation with the standard error of the mean.