What Does the Jury Ask in a Thesis Defense? Most Common Biostatistics Questions and Answers
A comprehensive guide to the most common biostatistics and data analysis questions asked during academic thesis defenses, with scientifically balanced answers and preparation tips.
A thesis defense is one of the most critical stages of master’s, PhD, and medical specialty (residency) theses. Jury members evaluate not only the results but also the methodology, data analysis process, and the appropriateness of statistical methods used in the study. In particular, biostatistics-related questions are among the most frequently asked topics in thesis defenses.
In this guide, we compiled the most common biostatistics questions asked by thesis defense committees, the scientific reasoning behind these questions, and strong sample answers you can use during your defense.
1. “How did you determine the sample size?”
This is one of the most frequently asked questions in thesis defenses. The jury wants to evaluate whether the study has sufficient statistical power and whether the number of participants is scientifically justified.
Incorrect Answers
“We included the number of patients we could reach in our clinic.”
“We roughly estimated it based on similar studies.”
Scientific Answer
“The sample size of our study was calculated using power analysis based on the primary outcome of the research. The calculation was performed using effect sizes derived from similar studies in the literature, with a statistical power of 80% or 90% and a Type I error rate of 5%. Additionally, the required sample size was increased by a certain percentage to account for potential dropouts.”
What the Jury Evaluates
Whether a proper power analysis was conducted
The risk of insufficient sample size affecting study validity
Whether the study design is scientifically grounded
2. “Why did you use parametric or non-parametric tests?”
This question aims to assess whether statistical tests were appropriately chosen according to the data structure.
Scientific Answer
“Before analysis, the distribution of continuous variables was assessed. Normality was evaluated using the Shapiro-Wilk test, histograms, Q-Q plots, and skewness-kurtosis values. When parametric assumptions were satisfied, Student’s t-test and ANOVA were used. When assumptions were violated, non-parametric alternatives such as Mann-Whitney U, Wilcoxon, or Kruskal-Wallis tests were applied.”
What the Jury Evaluates
Whether test selection was made consciously
Whether statistical assumptions were checked
Whether the correct method was applied to the data type
3. “What does a p-value less than 0.05 mean?”
The concept of p-value is one of the most frequently tested topics in thesis defenses. The jury wants to determine whether the candidate understands the concept rather than memorizing it.
Scientific Answer
“A p-value less than 0.05 indicates that, assuming the null hypothesis is true, the probability of observing the obtained result or a more extreme one is less than 5%. Therefore, there is sufficient statistical evidence to reject the null hypothesis. However, the p-value alone does not indicate clinical or practical significance.”
Important Note
In a strong thesis defense, not only the p-value but also:
Effect size
Confidence intervals
Clinical significance
should be discussed.
4. “Which post-hoc test did you use for multiple comparisons?”
This is a common question when more than two groups are compared.
Scientific Answer
“To evaluate overall group differences, ANOVA was used. After obtaining a significant result, post-hoc analyses were conducted to identify which groups differed. Since the assumption of homogeneity of variances was met, Tukey HSD or Bonferroni correction was applied to control for Type I error inflation due to multiple comparisons.”
What the Jury Evaluates
Awareness of multiple comparison problems
Handling of false positive risk
Reliability of reported results
5. “Why did you report effect size?”
In recent years, many jury members focus not only on p-values but also on effect size.
Scientific Answer
“While statistical significance indicates the likelihood that results occurred by chance, effect size measures the magnitude of the observed difference or relationship. Therefore, effect size metrics were reported to better evaluate the scientific and clinical importance of the findings.”
6. “Why are confidence intervals important?”
This question has become increasingly common in modern thesis defenses.
Scientific Answer
“Confidence intervals provide information not only about statistical significance but also about the range within which the true effect is likely to lie. Therefore, they are essential for evaluating the precision and uncertainty of the results.”
Final Advice for Thesis Defense
Success in a thesis defense is not about memorizing result tables. Jury members especially expect you to understand:
Sample size and power analysis
Proper identification of data types
Selection of parametric and non-parametric tests
P-values and statistical significance
Effect size and confidence intervals
Multiple comparisons and post-hoc analyses
Study limitations
A strong preparation requires being able to clearly explain why each statistical method was chosen and which assumptions were considered. This will significantly improve your performance and credibility during the defense.