The Results Section: A Narrative of Discovery in Research Reports

You’ve designed your study, recruited participants, collected your data, and run your analyses. Now comes the moment where all of that work becomes visible to the reader – the Results section. This part of a psychology research report isn’t just a dump of numbers; it’s a carefully structured, factual account of what the data actually showed. Done well, it tells a clear story: what was measured, what was found, and whether the hypotheses held up. Understanding how to read and write this section is a foundational skill in psychological research.

What the results section actually does
Preliminary information: setting the stage
Descriptive statistics: what happened in your study
How to report descriptive statistics in APA format
Inferential statistics: testing your hypothesis
The p-value: what it does and doesn’t tell you
Reporting effect sizes and confidence intervals
Structuring the narrative: from numbers to clarity
Handling non-significant results
Tables and figures: when visuals add value
The results section as the backbone of the report

What the results section actually does

The results section has one core job: to report findings objectively, without interpretation. It presents the data derived from the methodology, stating only what the data shows – not why it matters. That distinction matters a lot. Any explanation of meaning, any connection back to theory, any judgment about whether findings are surprising or important – all of that belongs in the Discussion section, not here.

Each primary result is presented both in terms of statistical values and explained in plain words, so the findings are accessible even to a reader who skims over the numbers. The section follows a logical structure that mirrors the order of the research questions or hypotheses laid out in the introduction.

Preliminary information: setting the stage

Before diving into the main findings, the APA-style results section includes preliminary details about participants and data – specifically the number of participants at each stage of the study, any missing data and why it was excluded, and for clinical studies, any adverse events. This transparency is essential. The rationale for excluding any data should be described clearly, so other researchers can evaluate whether those exclusions were appropriate.

Preliminary details may also cover how multiple responses were combined into a single variable, whether a manipulation check confirmed the independent variable worked as intended, and – in studies using psychological scales – measures of reliability such as Cronbach’s alpha. These aren’t filler; they establish that the data is trustworthy before the main results are presented.

Descriptive statistics: what happened in your study

Descriptive statistics are the foundation of the results section. They summarize the data – telling the reader, in concrete terms, what the scores looked like across groups or conditions. Descriptive statistics tell the story of what happened in a study. Although inferential statistics are also important, it is essential to understand the descriptive statistics first.

The most frequently reported descriptive statistics are sample size, mean, and standard deviation, because they form the basis for most inferential tests. For categorical data, proportions are used instead. The results section typically presents descriptive statistics followed by inferential statistics – reporting means, standard deviations, and 95% confidence intervals for each level of the independent variable.

When there are several variables or groups, a table is often the clearest way to present this information. Tables and graphs should add important information to the presentation, be as simple as possible, and be interpretable on their own. Crucially, raw data should never appear in the results section – only summarized, aggregated values belong here.

How to report descriptive statistics in APA format

In APA style, statistics are typically placed in parentheses to keep the prose readable. A sentence like “Participants in the treatment group scored higher on the anxiety scale (M = 34.32, SD = 10.45) than those in the control group (M = 21.45, SD = 9.22)” conveys the key information without becoming hard to follow. Means and standard deviations are the most commonly reported descriptive statistics in research papers, and the standard deviation should always accompany the mean – reporting a mean alone gives an incomplete picture of the data.

Inferential statistics: testing your hypothesis

Once descriptive statistics are reported, the results section moves into inferential territory. This is where the study’s hypotheses are directly addressed. Every statistical test reported should relate directly to a hypothesis. The results section begins by restating each hypothesis, then states whether results supported it, then provides the data and statistics that led to that conclusion.

According to APA guidelines, it is necessary to report all relevant hypothesis tests performed, estimates of effect sizes, and confidence intervals. Results should be presented in order – primary research questions first, then secondary questions, then any exploratory analyses. Importantly, relevant findings should not be omitted, even those that don’t support the study’s predictions. Selective reporting undermines the integrity of the research.

The p-value: what it does and doesn’t tell you

The p-value is central to inferential statistics. It represents the probability that the observed result occurred by chance, assuming the null hypothesis is true. Statistical significance is reached when the p-value falls below the chosen alpha level – typically .05 – leading the researcher to reject the null hypothesis. A p-value above that threshold means the null hypothesis is retained, not that nothing happened in the study.

It’s important to note that statistical significance alone doesn’t tell the full story. Effect size helps readers understand the magnitude of differences found, whereas statistical significance examines whether findings are likely due to chance. Both are essential for readers to understand the full impact of the work. A large sample can produce a statistically significant result for a trivially small difference – and without reporting effect size, readers can’t know whether the finding actually matters in practice.

Reporting effect sizes and confidence intervals

Effect sizes should be reported in a paper’s results section. An estimate of the effect size is often needed before even starting a study, to calculate the required sample size and ensure adequate statistical power. Common effect size measures include Cohen’s d for comparing means and Pearson’s r for correlations, with benchmarks of small (d = 0.2), medium (d = 0.5), and large (d = 0.8) effects.

Confidence intervals are useful for showing the variability around point estimates and should be included whenever population parameter estimates are reported. They give readers a sense of the precision of the result – a narrow confidence interval signals a more reliable estimate than a wide one.

Structuring the narrative: from numbers to clarity

A common mistake in writing results sections is letting the statistics do all the talking. Numbers alone don’t communicate clearly. Whenever a claim is made about a significant relationship between variables, the reader needs to be able to verify it by looking at the appropriate test statistic – but the surrounding prose must also explain what the numbers mean in plain terms.

In the results section, findings are merely presented to the reader with the briefest commentary on the data – interpretation is saved for the Discussion. The recommended structure is: state the hypothesis, report descriptive statistics, report the inferential test and its outcome, and then briefly note what the result indicates about the hypothesis. That four-step approach keeps the section organized and factual without spilling into interpretation.

Handling non-significant results

Not every hypothesis will be supported by the data – and that’s a legitimate scientific outcome. The goal of research is not to support a hypothesis, but to test it, and the answer to the test may be “no.” There is no shame in failing to support a hypothesis. When results are non-significant, the same structure applies: report the statistics fully and note that the null hypothesis was retained. The results section is not the place to explain why or offer alternative theories – again, that belongs in the Discussion.

Tables and figures: when visuals add value

Tables and figures are powerful tools in the results section, but they must earn their place. Unnecessary graphs that don’t link to the hypotheses and which could more easily be conveyed in a sentence should be avoided. Every table mentioned should be referred to at least once in the text – there is no point including a table that is never mentioned.

The general convention is that bar graphs are used when the variable on the x-axis is categorical, and line graphs are used when it is quantitative. Scatterplots display relationships between two quantitative variables. When a study involves multiple independent and dependent variables, a well-organized table presenting means and standard deviations across conditions is usually more efficient than describing each number in text.

The results section as the backbone of the report

Think of the results section as the evidentiary foundation of the research report. The introduction posed the questions, the method explained how answers would be sought, and now the results section provides those answers – factually and completely. It doesn’t speculate, advocate, or evaluate. It simply shows what the data revealed.

This factual clarity is what allows the Discussion section to do its job – interpreting findings, linking them back to existing theory, acknowledging limitations, and pointing toward future research. Without a clean, well-organized results section, the Discussion has nothing solid to stand on. The results section describes findings in an organized fashion, and each primary result is presented both in statistical terms and explained in words. That dual approach – numbers and language working together – is what makes research findings genuinely communicable.

What do you think? When reading a psychology study, do you find yourself paying closer attention to the p-values or to the effect sizes – and does knowing the difference change how you evaluate the findings? If a study fails to support its original hypothesis, does a well-reported results section make that outcome feel more or less meaningful to you as a reader?

How useful was this post?

Click on a star to rate it!

Average rating 0 / 5. Vote count: 0

No votes so far! Be the first to rate this post.

References

PDF 📄

Table of Contents

What the results section actually does 🔗

Preliminary information: setting the stage 🔗

Descriptive statistics: what happened in your study 🔗

How to report descriptive statistics in APA format 🔗

Inferential statistics: testing your hypothesis 🔗

The p-value: what it does and doesn’t tell you 🔗

Reporting effect sizes and confidence intervals 🔗

Structuring the narrative: from numbers to clarity 🔗

Handling non-significant results 🔗

Tables and figures: when visuals add value 🔗

The results section as the backbone of the report 🔗