Please enable JavaScript.
Coggle requires JavaScript to display documents.
Data analysis, 👉 How to interpret results:, 🔹 Interpretation Tips for…
Data analysis
Describe sample or participants
Quantitative
.
What's next?
Inferential statistics
: Tests hypotheses
Is the data normally distributed?
Parametric Tests (assumes normality):
t-test, ANOVA, regression
Is the data
not
normally distributed?
Nonparametric Tests (used if data not normal):
Mann-Whitney U, Wilcoxon, Kruskal-Wallis
Descriptive statistics
: Summarises data
Is the data normally distributed?
Mean and standard deviation
Is the data
not
normally distributed?
Median and Interquartile range
(Look for histograms, Shapiro-Wilk test, skewness/kurtosis, or explicit mention)
Qualitative
Other approaches
Grounded theory development
Narrative analysis
Content analysis
Units of analysis: frequency of content
Identify the categories or themes: How was data grouped?
Interpretation of meaning
Thematic analysis
What themes were identified?
How are quotes used to support findings?
Are participant voices represented clearly?
Do themes answer the research question?
Any theory or framework used to interpret results?
Mixed Methods
Quantitative results presented as above
Qualitative results presented as above
Integration
Results by joint display
One result explaining the next
Are quantitative and qualitative findings compared, contrasted, or merged?
👉 How to interpret results:
p-values: Is the result statistically significant (e.g., p < 0.05)? Indicates the probability that the result happened by chance. But significance doesn't always mean importance.
Confidence intervals (CI): What range of values are plausible for the true effect? Shows the range in which the true value likely falls (often 95%). If CI for OR/RR does not cross 1, the result is likely significant.
Narrow CI = precise; wide CI = less precise.
Effect sizes (e.g., Cohen’s d): How large or meaningful is the result? Describes how big the difference or relationship is. Small effect = minimal impact; Large effect = more meaningful. Important for understanding clinical relevance.
.
.
Correlation (Association) vs Causation: Correlation means things move together, not that one causes the other. Only randomised trials can establish causation.
🔹 Interpretation Tips for Students
✅ Always ask:
What is the main finding in this section?
How does this result answer the research question?
Are the findings clearly presented and supported?
What are the implications?