data · Fresher-friendly
Data Analyst interview questions on SQL, Python, statistics, and dashboarding tools asked at Indian analytics and tech companies.
Write a SQL query to find the second-highest salary from an Employee table.
Tip: Use LIMIT with OFFSET, or a subquery with MAX(salary) WHERE salary < MAX. Mention edge cases: what if two employees share the highest salary?
What is the difference between INNER JOIN and LEFT JOIN?
Tip: INNER JOIN returns only matching rows. LEFT JOIN returns all rows from the left table with NULLs for non-matching right rows. Draw a Venn diagram mentally as you explain.
What is the difference between GROUP BY and HAVING? Can you use HAVING without GROUP BY?
Tip: GROUP BY groups rows; HAVING filters those groups. Yes, HAVING without GROUP BY treats the entire table as one group — rarely useful but valid SQL.
How do you handle missing values (NULLs) in a dataset? Give at least three strategies.
Tip: Deletion (if <5% missing), mean/median/mode imputation, forward-fill for time series, or model-based imputation. State when you would choose each.
What is the difference between supervised and unsupervised learning?
Tip: Supervised: labelled data, learns a mapping (classification/regression). Unsupervised: no labels, finds patterns (clustering, dimensionality reduction). Give one example each.
What does a p-value of 0.03 mean in a hypothesis test?
Tip: It means there's a 3% probability of observing this result (or more extreme) if the null hypothesis were true. Do NOT say 'there is a 97% chance the hypothesis is correct' — that is wrong.
Tell me about a data analysis project you have worked on. What was the business impact?
Tip: Quantify the impact wherever possible (e.g., "reduced churn by 12%"). Describe the problem, your approach, tools used, and the decision it enabled.
How would you explain a complex analysis result to a non-technical business stakeholder?
Tip: Lead with the 'so what': the business recommendation. Use visuals. Avoid jargon. Validate understanding by asking what decisions they'll make with the insight.
What data visualisation tools have you used, and how do you decide which chart type to use?
Tip: Mention tools (Tableau, Power BI, Python matplotlib/seaborn). Chart type choice: comparison → bar; trend → line; distribution → histogram; proportion → pie (sparingly).
What would you do if your analysis result directly contradicts what the business team expects?
Tip: First verify your own analysis for errors. Then present findings objectively with full methodology. Data should inform decisions, not tell people what to do. Offer to investigate further.
Practice, not just reading
Upload your resume and practice a full Data Analyst mock interview with AI-generated questions and rubric-based scoring across 5 dimensions — free to start.