Write your results chapter in APA style

You now have all the results. The final step is to present them so that an examiner can follow your reasoning without opening your data. A good results chapter is predictable: it follows the order of your research questions, reports each test in a standard format and keeps interpretation for the discussion chapter.

A structure that works

1. Data screening: cases removed and why, missing data, outliers, assumption checks (or put these in the methods chapter, as your department prefers).
2. Descriptive statistics: participants (Table 1) and the means, SDs and reliabilities of the study variables, often with the correlation matrix (Table 2).
3. Hypothesis tests, in the order of the research questions, each with a short heading.
4. Additional or exploratory analyses, clearly labelled as such.

APA 7 rules for numbers and statistics

• Statistical symbols are italic: M, SD, t, F, p, r, d, N. Greek letters (α, β, η², χ²) are not italicised.
• Report exact p-values to two or three decimals (p = .037), except p < .001. Never write p = .000.
• No leading zero for statistics that cannot exceed 1 (p, r, α, β, R²): r = −.32, not −0.32. Use a leading zero otherwise: d = 0.39, M = 0.33.
• Round most statistics to two decimals; report degrees of freedom in parentheses after the symbol: t(238), F(3, 236), χ²(1, N = 240).
• Always give an effect size and, where possible, a 95% confidence interval.

Tables

APA tables have a bold number (Table 1), an italic title in title case on the next line, horizontal rules only above and below the column headings and at the bottom, no vertical lines, and a note that starts with Note. Every table must be mentioned in the text, and the text should highlight the main findings rather than repeat every number.

The course results, assembled

Here is how the findings from this course read as a compact results section. Use it as a model for the length and tone of each paragraph.

Preliminary analyses. After removing three duplicate submissions, the sample comprised 240 students (55.8% female; M_age = 21.98, SD = 2.14). Missing data were minimal (fewer than 0.2% of values). Stress (α = .85) and social support (α = .81) showed good internal consistency. Study hours were positively skewed and were analysed with non-parametric tests; all other variables were approximately normal. Descriptive statistics and correlations are shown in Tables 1 and 2.

Gender and stress (H1). Female students (M = 3.49, SD = 0.84) reported higher stress than male students (M = 3.16, SD = 0.87), t(238) = 2.97, p = .003, d = 0.39. H1 was supported.

Faculty and stress (H2). Stress differed between faculties, F(3, 236) = 2.87, p = .037, η² = .035, although no pairwise Tukey comparison was significant. H2 was partially supported.

Gender and counselling use (H3). Female students were more likely than male students to have used counselling (41.8% vs. 23.6%), χ²(1, N = 240) = 8.77, p = .003, V = .19. H3 was supported.

Predictors of exam performance (H4). Study hours, sleep, stress and support together explained 19.9% of the variance in final scores, F(4, 233) = 14.44, p < .001. Study hours (β = .31) and stress (β = −.36) were significant predictors (both p < .001); sleep and support were not. In a logistic regression, study hours (OR = 1.08) and stress (OR = 0.51) also predicted passing the exam.

Mediation (H5). Social support had a significant indirect effect on final scores through reduced stress, ab = 2.01, 95% CI [1.06, 3.22], with a non-significant direct effect, indicating indirect-only mediation. H5 was supported.

Results versus discussion

The results chapter states what you found; the discussion chapter explains what it means, compares it with previous research, and discusses limitations. Avoid phrases like “this proves” or “this shows that stress causes poor grades” in the results. Do mention non-significant results with the same detail as significant ones; they answer your research questions too.

Final checklist

• Every research question and hypothesis has a result, in the planned order.
• Each test reports the statistic, degrees of freedom, p, an effect size and, ideally, a CI.
• Descriptive statistics come before inferential tests.
• Tables are numbered, titled, mentioned in the text and formatted in APA style.
• Assumption checks and data screening decisions are reported.
• The software is cited. Each tool page shows a citation, such as “Xavier, B. (2026). FreeStatisticalTools.com: Free online statistical tools [Web application].”

Congratulations: you have taken a dataset from a messy export to a finished results chapter. The final assessment checks the whole course; pass it to get your certificate.