Guide

Analyze Your Thesis Data in JASP: Start to Finish

You have a data file, a deadline, and a supervisor who said "just run the analysis." This guide takes you through the analysis in JASP (free, point-and-click, and built to produce APA-style output), from opening your CSV to writing the results sentence. Every step links to the StatsCapybara lesson that explains the why, and there is a practice dataset to follow along with.

Why JASP

JASP is free, open-source statistics software developed at the University of Amsterdam. It has three advantages for a thesis. Its menus are organized by type of analysis. Its output updates as soon as you tick an option, so you can try things out freely. And its tables are already close to APA format. If your department requires SPSS, the companion guide From SPSS Output to APA Results covers the same steps.

Follow along: this guide uses sleep-experiment.csv from our practice datasets: 80 volunteers randomly assigned to a normal night's sleep or a night restricted to four hours, then scored on attention lapses. Download it and every number below will appear on your own screen.

Step 0: Start tidy, keep the raw file sacred

JASP analyzes whatever is in your spreadsheet, errors included. Two rules apply before you open it:

  • One row per observation, one column per variable, one value per cell. No merged cells, no color-coding-as-data, no two variables squeezed into one column. If your file breaks these rules, fix it first. The Tidy Data lesson shows the common problems and how to fix each one. If your export needs more work than that, go through Clean Your Survey Data, Step by Step and then come back here.
  • Never edit the raw export. Copy it, clean the copy, and keep a note of what you changed. You, and anyone who checks your thesis, may need to go back to the original. The Cleaning Workflow lesson sets out a routine for this.

Also make sure every column name has a line in a codebook: what it measures, its units, and how missing values are marked. Blank cells are the safest missing-value marker. A numeric code like -99 is averaged in as a real value unless you declare it missing.

Step 1: Import, then check the variable types

In JASP: ☰ menu → Open → Computer, and pick your .csv (JASP also reads SPSS .sav and Excel files). The data appear in a spreadsheet view.

Next, check the small icon in each column header. It shows the measurement level JASP guessed for that variable. Groups coded as numbers are the usual mistake: a condition coded 1/2 is read as a continuous number. Click the icon to fix it: the ruler means scale (continuous), the ordered bars mean ordinal, the overlapping circles mean nominal. If the levels are unclear, the Types of Data lesson explains them in about five minutes.

For sleep-experiment.csv: condition should be nominal, errors scale, and participant_id is only a label, so mark it nominal and JASP will not average it.

Step 2: Descriptives first, always

Before any test: Descriptives in the ribbon, drag your outcome into Variables, and (for a group design) drag the grouping variable into Split. Under Plots, tick Distribution plots and Boxplots.

You're looking for three things:

  • Sanity. Is n what it should be? Are the minimum and maximum possible values for your measure? An age of 511 or a reaction time of 3 ms is a data-entry error. The validation lesson shows how such errors get into a file.
  • Shape. Roughly symmetric, or badly skewed? One hump or two? This shows whether the assumption checks in Step 3 are likely to find a problem.
  • Outliers. Points far beyond the boxplot whiskers need to be investigated, not deleted without comment. Outliers: Detect, Investigate, Decide gives the rules for deciding.

For the sleep data you should see: normal sleep M = 20.07, SD = 5.92; restricted sleep M = 22.77, SD = 6.02, with 40 people per group and no impossible values. (Want the same numbers without opening JASP? Paste a column into our descriptives calculator.)

Step 3: Check the assumptions

Every classical test makes assumptions, and JASP checks the main ones inside the analysis itself. For a t-test, tick Assumption checks to get normality tests and Levene's test for equal variances in the same output panel.

Read them with two rules, both explained in ANOVA & t-Test Assumptions. First, trust the plots more than the p-values. With large samples, normality tests flag departures too small to matter, and with small samples they miss serious ones. Look at the Q-Q plot instead: if the points stay close to the line, the data are normal enough. Second, know your fallback. If the variances are unequal, use the Welch row (many statisticians always use it). If the data are badly skewed and the sample is small, use one of the non-parametric alternatives, which lose a little power but do not assume normality.

For the sleep data, the two groups' spreads are nearly identical (Levene's F(1, 78) = 0.10, p = .758), so assuming equal variances is reasonable here.

Step 4: Confirm you're running the right test

Ideally you chose the test before collecting data (if you did not, read why planning first matters). The choice depends on your outcome type, your group structure, and whether the same people were measured more than once. Two tools on this site help you decide: the quick Which test should I use? chooser, and Plan My Analysis, which turns your answers into a printable plan with a sample-size estimate. The full reasoning is in Choosing Statistics for Your Dissertation.

The example here is the simplest case. One continuous outcome (errors) and two independent groups (condition) call for an independent-samples t-test.

Step 5: Run it

In JASP: T-Tests → Independent Samples T-Test. Drag errors into Dependent Variables and condition into Grouping Variable. Under Tests, tick Welch alongside Student; under Additional Statistics, tick Descriptives and Effect size (Cohen's d); tick the Assumption checks. The output appears instantly:

Step 6: Read the output like an examiner

  • t and df: the test statistic and its degrees of freedom (here 78 = 40 + 40 − 2). The df in your write-up must match your n, and examiners check it.
  • p: two-tailed by default, and a two-tailed test is almost always what you want. p = 0.047 means: if sleep restriction had no effect, data at least this extreme would turn up about 5% of the time. It is not the probability that the effect is real. Hypothesis-Testing Logic explains the difference.
  • Cohen's d: the size of the effect in standard-deviation units, and the number to interpret in your discussion. d = 0.45 is a little below Cohen's medium benchmark of 0.5. Effect Size & Power explains the benchmarks and their limits, and the effect-size converter shows d as the overlap between the two groups' distributions.

Step 7: Write it up

A results sentence gives what was compared, the descriptives, then the statistics. Write it in the past tense and leave the interpretation for the Discussion, as From Output to Results Section recommends:

Participants in the restricted-sleep condition made more attention lapses (M = 22.77, SD = 6.02) than participants who slept normally (M = 20.07, SD = 5.92), t(78) = 2.02, p = .047, d = 0.45.

Mind the typography: Latin statistical symbols (t, p, d, M, SD) are italic, p gets no leading zero, and p is reported exactly — never as p = .000. The full rules are in Reporting Statistics in APA Style, and the APA results formatter builds such a sentence from your numbers and checks it.

When things don't go to plan

  • p = .06. Do not call it "a trend toward significance." Report the exact p, the effect size and its confidence interval. Writing About Non-Significant Results shows how to interpret the result, and why a non-significant thesis is not a failed thesis.
  • Assumptions failed. Unequal variances → Welch row (already in your output). Serious non-normality with small n → the matching non-parametric test (for two independent groups, Mann–Whitney; it's one tick away in the same JASP panel).
  • An outlier is driving everything. Run the analysis with and without it, report both, and justify your decision. The outlier triage lesson gives the decision rules. Never delete a point without reporting it.
  • You're tempted to try "just one more" analysis. Every extra analysis raises the chance of a false positive. The Replication Crisis shows the consequences. Label any extra analyses as exploratory.

The whole path: tidy file → import → fix variable types → descriptives and plots → assumption checks → the planned test → effect size → APA sentence. None of the eight steps is hard, but do them in this order.

Keep going