When you read a clinical psychology research paper, the results section is filled with numbers and symbols. To succeed in your psychology entrance exams, you must know how to interpret these statistics.
In this topic, we will break down the most common statistical findings used to measure how well exercise treats depression.
1. Statistical Significance (The p-value)
The p-value tells you if the results of a study are likely due to the treatment or just random chance.
- The Rule: In psychology, a result is usually considered ”statistically significant” if the p-value is less than 0.05 (p < 0.05).
- What it means: If a study finds that strength training reduces depression with a p-value of 0.03, there is only a 3% probability that these results happened by random chance. We can confidently say the strength training likely caused the change.
- If p > 0.05: The results are not statistically significant. We cannot prove the treatment worked better than doing nothing.
2. Effect Size (Cohen’s d)
While the p-value tells you if a treatment works, the effect size tells you how well it works. This is a very common topic on entrance exams.
Researchers often use a measurement called Cohen’s d to show the size of the difference between two groups (for example, an exercise group and a control group).
- Small effect: d = 0.2
- Medium effect: d = 0.5
- Large effect: d = 0.8 or higher
Example: A study compares a yoga program to a standard SSRI medication for treating depression. The results show an effect size of d = 0.1. This means the difference between the two treatments is very small. Both treatments might be effective, but one is not vastly superior to the other.
3. Confidence Intervals (CI)
A Confidence Interval (CI) gives you a range of values where the true result is likely to fall. Studies usually report a 95% Confidence Interval.
Example: A study finds that running three times a week lowers scores on a depression questionnaire by an average of 6 points. The 95% CI is [4, 8].
- Interpretation: We are 95% confident that if we gave this running program to the entire population of people with depression, their scores would drop by somewhere between 4 and 8 points.
Exam Tip: If a 95% Confidence Interval for a difference between two groups includes the number zero (e.g., [-2, 4]), the result is not statistically significant. It means there is a chance there is zero difference between the groups.
4. Statistical vs. Clinical Significance
This is a critical distinction in clinical psychology.
- Statistical Significance: The math proves that a change happened and it was not due to chance (p < 0.05).
- Clinical Significance: The change is actually meaningful to the patient’s daily life.
Example: Imagine a study tests a 5-minute daily stretching routine for severe depression. The study includes 10,000 people. The stretching group’s depression score drops by 0.5 points on a 60-point scale. Because the study is so large, this tiny drop might have a p-value of 0.01 (statistically significant). However, a 0.5-point drop will not make a depressed patient feel any better in their real life. Therefore, the treatment is not clinically significant.
Summary for Your Exam
When analyzing study results, ask yourself these three questions:
- Is it real? Look at the p-value (p < 0.05).
- How big is the impact? Look at the effect size (Cohen’s d).
- Does it matter to the patient? Consider the clinical significance.