Unit 4 · Relationships

How to run a simple linear regression in SPSS

Run a linear regression in SPSS, interpret R Square, B and Beta, and make predictions from the equation.

Free tutorialPro practiceAbout 5 minutes7 practice questions

Quick answer: How do you run a simple linear regression in SPSS?

  1. Click Analyze › Regression › Linear.
  2. Move the outcome into Dependent and the predictor into Independent(s).
  3. Click OK and read the Model Summary, ANOVA and Coefficients tables.

Report it in APA style: Revision hours predicted exam score, F(1, 48) = 20.26, p < .001, R² = .30; each extra hour predicted 1.52 more points.

Last updated November 2026 · Not sure this is the right test? Try the Which statistical test? tool.

What is linear regression?

Simple linear regression fits a straight line that predicts a Scale outcome (Y) from one predictor (X). It tells you how much Y changes for each one-unit change in X, and how much of the variation in Y the predictor explains.

When to use it

  • You want to predict an outcome or describe how it changes with a predictor.
  • Both variables are Scale (or the predictor is a two-category variable coded 0 and 1).

How it works

The equation is Ŷ = b0 + b1X. The constant (b0) is the predicted value when X = 0, and the slope (b1) is the change in Y for each one-unit increase in X. SPSS chooses the line that makes the squared prediction errors (residuals) as small as possible (least squares). R² is the proportion of variance in Y explained by X, and the ANOVA F tests whether the model predicts better than just using the mean.

Assumptions

  • A linear relationship.
  • Independent residuals.
  • Residuals roughly normal.
  • Equal spread of residuals at all predicted values (homoscedasticity).

Worked example

Predicted score = 44.50 + 1.52 × hours. Each extra hour of revision predicted 1.52 more points, and hours explained 30% of the variance, F(1, 48) = 20.26, p < .001.

Key terms

Predictor (IV)
The variable used to predict.
Outcome (DV)
The variable being predicted.
Residual
Actual minus predicted value.
R²
Proportion of variance explained.
b and β
Unstandardised slope (original units) and standardised slope (SD units).

Common mistakes

  • Predicting far outside the range of the data.
  • Interpreting the constant when X = 0 is impossible.
  • Assuming the predictor causes the outcome.

How to do it in SPSS

Linear Regression

Regression goes a step beyond correlation: it gives you an equation to predict one variable from another.

Linear Regression
Variables
Participant ID [id]
Age in years [age]
▶
Dependent:1
Exam score (%) [score]
Block 1 of 1
▶
Independent(s):2
Revision hours [hours]
Method: Enter3
Statistics…4Plots…Save…Options…Style…Bootstrap…
OKPasteResetCancelHelp
  1. 1
    DependentThe outcome you want to predict (Y), such as exam score.
  2. 2
    Independent(s)The predictor (X), such as revision hours. Add more for multiple regression.
  3. 3
    Method: EnterAll predictors go into the model at once. This is the default and the most common choice for student projects.
  4. 4
    Statistics…Estimates and Model fit are ticked by default. Add Descriptives, Collinearity diagnostics and Durbin-Watson for assumption checks.

Reading regression output

Three tables tell the whole story: how much is explained, whether the model works, and what the equation is.

Output1 [Document1] – SPSS Statistics Viewer
FileEditViewDataTransformAnalyzeGraphsUtilitiesExtensionsWindowHelp
Output
Log
Regression
Model Summary
ANOVA
Coefficients
Model Summary
ModelRR SquareAdjusted R SquareStd. Error of the Estimate
1.545.2971.28210.58

Predictors: (Constant), hours

ANOVA
ModelSum of SquaresdfMean SquareFSig.
Regression2266.2212266.2220.262.000
Residual5369.1648111.86
Total7635.3849

Dependent Variable: score

Coefficients
ModelBStd. ErrorBetatSig.
(Constant)44.5033.3913.13.000
hours1.5240.34.54554.50.000

Dependent Variable: score

  1. 1
    R SquareThe proportion of variance explained. .297 means revision hours explain about 30% of the differences in scores.
  2. 2
    ANOVA FTests whether the model predicts better than nothing. Sig. .000 means p < .001, so it does.
  3. 3
    Constant (B)The predicted score for someone who revised 0 hours: 44.50.
  4. 4
    Slope (B)Each extra hour of revision predicts 1.52 more points.
  5. 5
    BetaThe slope in standard deviation units, useful for comparing predictors. With one predictor it equals r.

The equation: predicted score = 44.50 + 1.52 × hours.

The SPSS syntax

Prefer typing to clicking? Open File › New › Syntax, paste this in, select it and choose Run › Selection. Every dialog's Paste button writes the same kind of code.

REGRESSION
  /STATISTICS COEFF OUTS CI(95) R ANOVA
  /DEPENDENT score
  /METHOD=ENTER hours.

Practice data

Download the file used in this lesson and run it yourself in SPSS: you should get the same results as the screens above.

Now practise it interactively →

Reading is only half of it. Tap through the real SPSS menus, read the output and pick the right write-up in 7 quick questions, with instant feedback on every answer.

Practice for this lesson is part of Pro, with every unit, unlimited hearts and saved progress.

More in Relationships