You clicked OK and SPSS produced six pages of tables. Which numbers go into your thesis? Usually fewer than a third of them. The SPSS output viewer prints every statistic a procedure can produce, and much of it is there for checking, not reporting. This guide explains how to read SPSS output for the eight tables that appear in most quantitative theses, column by column, and how to turn each one into results text.
This article is part of our guide How to Write a Master’s Thesis by the Mastermind PhD team and relates to our Statistical Analysis service. Sources last checked: November 2026.
What is SPSS output? SPSS output is the set of pivot tables, charts and notes that IBM SPSS Statistics displays in the Output Viewer after a procedure runs. Each table has a title, row and column labels, the statistics, and footnotes that explain conditions such as violated assumptions or flagged correlations. The left pane of the viewer lists every item as an outline you can navigate, hide or delete.
General rules before you read any table
- Sig. is the p value. Recent versions print One-Sided p and Two-Sided p; use the two-sided value unless you planned a one-sided test.
- .000 is not zero. It means p < .0005, reported as p < .001.
- Check N first. If N is smaller than your sample, cases were excluded because of missing data.
- Read the footnotes. They report problems such as small expected counts or a constant variable.
- Double-click a table to edit it, or use File, then Export, to send output to Word. Thesis tables are then rebuilt in APA format, not pasted as they are.
1. Frequencies
The table shows Frequency, Percent, Valid Percent and Cumulative Percent for each category. Percent includes missing cases in the denominator; Valid Percent excludes them. Report Valid Percent in the sample profile and state the number missing. Cumulative Percent matters only for ordered categories.
📱 Ask a statistician about your data — Send a short description of your instrument and sample size on WhatsApp and get a suitable analysis plan. Every analysis comes with the raw SPSS file and a results report.
2. Descriptive Statistics
Columns: N, Minimum, Maximum, Mean and Std. Deviation, with Valid N (listwise) at the bottom. Check that minimum and maximum fall within the possible range; a maximum of 55 on a 1-to-5 item is an entry error. Report M and SD with two decimals.
3. Reliability Statistics and Item-Total Statistics
Reliability Statistics gives Cronbach’s Alpha and N of Items; report alpha for each scale. Item-Total Statistics shows the Corrected Item-Total Correlation (items below about .30 deserve a look) and Cronbach’s Alpha if Item Deleted. A negative item-total correlation usually means an item was not reverse-coded.
4. Tests of Normality
Both Kolmogorov-Smirnov (with the Lilliefors correction) and Shapiro-Wilk are printed, each with Statistic, df and Sig. Sig. above .05 means the test did not detect a departure from normality. In large samples these tests flag trivial deviations, so read them with skewness, kurtosis and the plots.
5. Independent Samples Test
This SPSS output is read in two steps. First, Levene’s Test for Equality of Variances: if its Sig. is above .05, read the row Equal variances assumed; otherwise read Equal variances not assumed. Second, from the chosen row take t, df, the two-sided p, the mean difference and its 95% confidence interval. The effect size (Cohen’s d) appears in a separate table when requested.
6. ANOVA
The one-way ANOVA table has rows Between Groups, Within Groups and Total, and columns Sum of Squares, df, Mean Square, F and Sig. Report F with two degrees of freedom, for example F(2, 297) = 6.84, p = .001. A significant F says the groups differ somewhere; the Multiple Comparisons table (Tukey or Games-Howell) shows which pairs differ.
7. Correlations
Each cell of the matrix contains Pearson Correlation, Sig. (2-tailed) and N. The matrix is symmetrical, so read only one triangle. One asterisk marks correlations significant at .05 and two asterisks at .01. In the thesis, report r with two decimals and no leading zero, for example r(248) = .42, p < .001.
8. Regression: Model Summary, ANOVA and Coefficients
Linear regression SPSS output has three main tables:
| Table | What to read | What to report |
|---|---|---|
| Model Summary | R, R Square, Adjusted R Square | R² and adjusted R² |
| ANOVA | F, df (Regression, Residual), Sig. | Whether the model as a whole is significant |
| Coefficients | B, Std. Error, Beta, t, Sig., Tolerance, VIF | B, SE, β, t and p for each predictor; VIF for collinearity |
B is the change in the outcome for one unit of the predictor; Beta is the standardized coefficient for comparing predictors measured on different scales. VIF values above about 5 to 10 signal collinearity.
Bonus: Chi-Square Tests
For crosstabs, read the Pearson Chi-Square row: Value, df and Asymptotic Significance (2-sided). The footnote reports how many cells have an expected count below 5; if more than 20% do, use Fisher’s exact test for 2 × 2 tables or merge categories. Add Cramér’s V from Symmetric Measures as the effect size.
Five reading mistakes examiners notice
- Reading the wrong row of the Independent Samples Test without checking Levene’s test.
- Reporting Percent instead of Valid Percent when some respondents skipped a demographic question, so the percentages no longer match the sample described.
- Treating B as Beta. Unstandardized coefficients cannot be compared across predictors measured on different scales; use Beta for that comparison.
- Ignoring the Multiple Comparisons table after a significant ANOVA and writing that “all groups differ”.
- Copying both normality tests and contradicting them in the text. Decide in advance which test and which indicators you rely on, and say so.
Each of these comes from reading the SPSS output too quickly rather than from a wrong analysis, so a second, slower read before you write saves a round of corrections.
From SPSS output to the results chapter
A results paragraph built from SPSS output usually follows one pattern: the research question, the test used, the key statistics in APA format, the effect size, and one sentence of interpretation. For example (illustrative values): “Job satisfaction differed by years of experience, F(2, 297) = 6.84, p = .001, ηp² = .04. Tukey tests showed that teachers with more than ten years reported higher satisfaction than those with less than five.”
Report only what the question needs: the test statistic, its degrees of freedom, the p value, the effect size and, where useful, the confidence interval. Keep the original SPSS output file (.spv) and the syntax with your data. Examiners and supervisors sometimes ask to see where a number came from.
📱 Ask on WhatsApp now — 5 years of experience across all disciplines and 14 academic services. Two-stage payment (80/20); revisions are free until supervisor approval, within 30% of the chapter.
Frequently asked questions
Why does my SPSS output show fewer cases than my sample?
Cases with missing values on any variable in the analysis are excluded listwise by default. Check the Case Processing Summary or the N column and report the number used.
What do numbers like 1.2E-5 mean?
That is scientific notation: 1.2 × 10⁻⁵, or 0.000012. Double-click the cell to see more decimals.
Should I paste SPSS output tables directly into my thesis?
No. Rebuild them in Word following APA style or your faculty’s format, keeping only the statistics you report. Raw output belongs, if anywhere, in an appendix.
What is the difference between Sig. and Asymp. Sig.?
Both are p values. Asymp. Sig. is based on a large-sample approximation, while Exact Sig. is computed exactly; for small samples or sparse tables, exact values are preferable.
Can I change the number of decimals in SPSS output?
Yes. Double-click the table, select the cells and use Cell Properties to set the decimals. Changing the display does not change the stored values.
Sources
- Field, A. (2018). Discovering Statistics Using IBM SPSS Statistics (5th ed.). SAGE.
- Pallant, J. (2020). SPSS Survival Manual (7th ed.). Open University Press.
- IBM. IBM SPSS Statistics documentation: Working with output. https://www.ibm.com/docs/en/spss-statistics
- American Psychological Association. (2020). Publication Manual of the American Psychological Association (7th ed.); Journal Article Reporting Standards: Quantitative. https://apastyle.apa.org/jars/quantitative
- Laerd Statistics. SPSS Statistics tutorials and statistical guides. https://statistics.laerd.com/
Sources last checked: November 2026. This article is general educational guidance and does not replace your university regulations or your supervisor’s instructions. How we prepare our content.