Interview practice

Data Analyst

0–2 years · Junior — SQL · Excel · Power BI / Tableau · Statistics · Python · Stakeholder reporting

scenario Data Quality 1 of 6

You receive a dataset with missing values that is needed for an urgent report. How do you handle this situation in the first thirty minutes?

What a strong answer covers

Identifies the extent and pattern of missing data; prioritises fields critical to the analysis; applies appropriate imputation methods or flags the missing data; communicates implications of missing data to stakeholders; decides whether to proceed with analysis or delay for complete data.

The follow-up you would get

You discover that the missing data is due to a reporting error. How do you prevent this issue from recurring?

Could you have answered that?

technical Statistical Analysis 2 of 6

You have a dataset with two variables: advertising spend and sales revenue. How do you determine if there is a significant correlation between them?

What a strong answer covers

Calculates the correlation coefficient using Pearson’s method; visualises data with a scatter plot; checks for linearity and outliers; conducts a hypothesis test for significance; considers the coefficient of determination for explained variance.

The follow-up you would get

What would you do if you find a high correlation but low causation?

Could you have answered that?

scenario Performance Metrics 3 of 6

A key performance indicator (KPI) shows a sudden drop, but you are not sure why. How do you investigate this in the first hour?

What a strong answer covers

Analyzes time series data for patterns or anomalies; checks for recent changes in data collection methods or processes; reviews relevant external factors affecting performance; discusses findings with team members; documents any findings for follow-up.

The follow-up you would get

You find that a change in the data source caused the drop. How do you communicate this to the stakeholders?

Could you have answered that?

ownership Handling conflicting reports 4 of 6

Tell me about a time you encountered two reports that disagreed, and how you approached resolving this.

What a strong answer covers

Describes the nature of the disagreement, including data sources; outlines steps taken to investigate the discrepancy; specifies how they communicated findings to relevant parties; reflects on the impact of their resolution.

The follow-up you would get

What did you learn about the data that you didn't know before?

Could you have answered that?

technical Data Cleaning 5 of 6

You notice that your sales dataset contains duplicate entries. What steps do you take to identify and remove these duplicates?

What a strong answer covers

Uses the DISTINCT keyword in SQL or the Remove Duplicates feature in Excel; checks for duplicate rows based on key fields; considers implementing data validation rules; reviews the source of duplicates to prevent future occurrences; documents the cleaning process for transparency.

The follow-up you would get

What if some duplicates contain different values for the same key? How would you handle that?

Could you have answered that?

technical SQL Querying 6 of 6

You have a table of sales data with a column for sales date and a column for sales amount. How would you write a query to find the total sales for each month in the last year?

What a strong answer covers

Uses the DATE_TRUNC function to group by month; aggregates sales amount using SUM; filters for the last year with a WHERE clause; orders results by month; ensures proper handling of NULL values if necessary.

The follow-up you would get

What if the sales data includes multiple years? How would you adjust your query?

Could you have answered that?

That is this set.

Load six more — you will get questions you have not seen first.

Give me six more →

Say your answer out loud before revealing. Reading the answer first feels like learning and is not.