Free Data Analyst Interview Prep

Data Analyst Interview Questions

19 practice questions across 13 skills — each with what the interviewer is really listening for. Prepare with intent, not guesswork.

Free · No signup · Grouped by skill

How to use this page

Don't memorise answers. For each question, read what the interviewer is looking for, then practise answering out loud in your own words with a real example. The notes describe strong answers and common red flags — they are for your prep, not a script.

SQL

2 questions
  1. What is the difference between a WHERE clause and a HAVING clause in SQL?

    Basic

    What the interviewer is looking for: A strong answer explains that WHERE filters rows before aggregation and HAVING filters groups after, with an example using GROUP BY. Using them interchangeably or not mentioning aggregation is a red flag.

  2. Write a query to find customers who placed more than three orders last month. Walk me through it.

    Intermediate

    What the interviewer is looking for: Look for correct date filtering, GROUP BY with COUNT, and HAVING for the threshold. Red flags include filtering on the aggregate in WHERE or ignoring the date boundary logic.

Excel

2 questions
  1. How do you handle a dataset with missing values in Excel before analysis?

    Basic

    What the interviewer is looking for: Strong answers first understand WHY data is missing, then choose between removal, imputation, or flagging based on impact, rather than blindly filling zeros. Deleting rows without considering bias is a red flag.

  2. When would you use INDEX/MATCH or XLOOKUP instead of VLOOKUP?

    Intermediate

    What the interviewer is looking for: Look for awareness that VLOOKUP breaks on left-lookups and column insertions, while INDEX/MATCH and XLOOKUP are more flexible and robust. Not knowing VLOOKUP's limitations suggests limited hands-on spreadsheet work.

Python

1 question
  1. How would you use Python to clean and summarise a messy CSV of sales data?

    Intermediate

    What the interviewer is looking for: A good answer walks through loading with pandas, inspecting dtypes and nulls, standardising formats, and grouping to summarise. Red flags are jumping to analysis before validating the data or not mentioning pandas.

Data Visualization

2 questions
  1. You need to present the same insight to an engineer and to a VP of Sales. How does your visualization change?

    Intermediate

    What the interviewer is looking for: Strong answers tailor detail and framing to the audience — the VP wants the 'so what' and business impact, the engineer wants the method. Using identical dense charts for both audiences is a red flag.

  2. What makes a chart misleading, and how do you avoid it?

    Intermediate

    What the interviewer is looking for: Look for truncated axes, cherry-picked ranges, dual axes, and inappropriate chart types, plus a commitment to honest defaults. A candidate who cannot name a single common distortion has limited critical awareness.

Power BI

1 question
  1. Explain the difference between a calculated column and a measure in Power BI.

    Intermediate

    What the interviewer is looking for: A strong answer notes calculated columns are computed row-by-row and stored, while measures are evaluated at query time based on filter context. Confusing the two leads to wrong aggregations and is a common red flag.

Tableau

1 question
  1. How do you decide which chart type to use when building a Tableau dashboard?

    Basic

    What the interviewer is looking for: Look for matching chart to intent — trends over time, comparison, distribution, or part-to-whole — and prioritising clarity over decoration. Choosing charts for visual appeal rather than the question is a red flag.

Statistics

2 questions
  1. What is the difference between correlation and causation, and why does it matter in your reports?

    Intermediate

    What the interviewer is looking for: Strong candidates explain that correlation does not imply causation, cite confounders, and describe how they caveat findings. Presenting a correlation as proof of cause is a serious red flag for an analyst.

  2. A stakeholder says 'the average order value is fine.' Why might the mean mislead here?

    Intermediate

    What the interviewer is looking for: Look for mention of skew and outliers, and using median or distribution instead. A candidate who trusts the mean without checking the distribution shows a shallow statistical instinct.

Data Cleaning

1 question
  1. You receive a dataset with duplicate rows and inconsistent date formats. What is your process?

    Intermediate

    What the interviewer is looking for: A strong answer profiles the data first, defines what a duplicate means for this context, standardises formats, and documents the steps for reproducibility. Ad-hoc manual fixes with no record is a red flag.

Data Storytelling

1 question
  1. Walk me through how you would turn a query result into a recommendation leadership can act on.

    Intermediate

    What the interviewer is looking for: Look for structure — the question, the finding, the 'so what', and a clear recommendation — not just a data dump. Ending at the chart without a recommendation is the classic analyst red flag.

Communication

1 question
  1. How do you make sure a non-technical stakeholder actually understands your analysis?

    Basic

    What the interviewer is looking for: Strong answers use plain language, lead with the conclusion, check for understanding, and avoid jargon. Blaming the stakeholder for not understanding is a red flag.

Critical Thinking

1 question
  1. A metric suddenly dropped 20% overnight. How do you investigate whether it is real?

    Advanced

    What the interviewer is looking for: Look for checking data pipeline/tracking issues first, segmenting the drop, and forming hypotheses before alarming stakeholders. Immediately reporting the drop as real without validating the data is a red flag.

A/B Testing

1 question
  1. How would you design an A/B test to evaluate a new checkout button colour?

    Advanced

    What the interviewer is looking for: Strong answers define a hypothesis and success metric, randomise, estimate sample size, and wait for significance rather than peeking early. Calling a winner after a day or ignoring sample size is a red flag.

Pandas

1 question
  1. How do you use pandas to join two datasets and validate the join worked correctly?

    Intermediate

    What the interviewer is looking for: Look for choosing the right merge type, checking row counts before and after, and watching for unexpected many-to-many blow-ups or nulls. Merging without validating the result is a red flag.

Behavioural & role-general

2 questions
  1. Tell me about an analysis where your recommendation changed a decision. What was the impact?

    Basic

    What the interviewer is looking for: Strong answers connect the analysis to a concrete business outcome and show ownership of the recommendation. Vague stories with no measurable result or no clear personal role are red flags.

  2. How do you prioritise when three stakeholders each want their analysis done first?

    Basic

    What the interviewer is looking for: Look for clarifying business impact and deadlines, negotiating scope, and communicating trade-offs transparently. Simply doing whoever shouts loudest, or trying to do everything at once, are red flags.

Before the interview, close the skill gaps first

Upload your resume and see your Data Analyst Skill Score, the exact skills you're missing, and a free learning path for each one — so you walk in prepared.