Top 20 Question For Data Analyst Interview

The term data has been there with us for ages. For decades, analysts have utilized the data or raw information to extract insights that might help in business decisions. Now, with advanced tools and technologies, it is possible to even predict future trends, analyze the raw form of data to increase customer experience, and extract other useful information.

Owing to the importance of data analysis, many young minds aspire to enter the field and become a data analyst. For all the budding data analysts, we have prepared a list of 20 questions that may help you outshine the interview process.

Read more for 20 data analysts interview questions:

1. Explain the Process of Data Analysis.

Data analysis is a concept that allows analysts to collect, inspect, cleanse, transform, and model data so that valuable information can be extracted.

  • The data collection refers to the process of storing data and cleaning it so that it can be utilized for analysis and insights.


  • The data analysis analyzes the data to extract valuable information based on the problem analysts are trying to solve. This model is repeatedly modified to reach the desired outcome and the best possible prediction.


  • Based on the analysis, reports are formed so that business stakeholders can utilize this information for better business decisions.


2. Explain the Difference Between Data Analysis and Mining.

Data mining is a process of determining patterns present in a given dataset. It is achieved with cleaned, documented data but the final interpretation of the information is not easy.

Data analysis, on the other hand, organizes data to extract meaning from it. It is achieved with raw data as the cleaning of data is one of the major steps of the process. The end-results can be easily interpreted by business stakeholders.

3. Explain the Difference Between Data Profiling and Mining.

The responsibility of data mining is to find out unusual patterns in structured data. It looks for interdependencies, clusters, or usual information.

Data profiling analyses and evaluates the attributes corresponding to the data. It focuses on aspects such as frequency, data type, etc.

4. Explain Data Cleansing and Its Best Practices.

When data is received or collected by organizations from various sources, it contains several errors. Removing these errors such as incorrect data, repetitive information, anomalies, etc. is known as data cleansing.

Some of the industry best practices followed by businesses for data cleaning are:

  • Median and mean
  • Dummy variables to be used for empty spaces
  • Finding similarities and correlations

5. Explain Important Steps of Data Validation.

The process involving the validation of a given dataset is necessary for ensuring the quality of data. It contains two steps:

  • Data screening for finding out inaccurate data present in the dataset with the help of various algorithms.


  • Data verification involves analyzing each value for a set of use cases, which helps decide which value should be added or removed.


6. Explain the Concept of Interquartile Range.

The interquartile range is utilized to measure the data dispersion in the form of a box plot, which is nothing but the difference in the lower and upper quartile.

7. How Can You Say That A Data Model Is Bad or Good?

Although the answer to this question may vary from individual to individual, there are a few aspects that help determine the quality of the data model.

  • Predictable performance corresponds to a good data model as it helps in predicting future trends.
  • When the business environment and minor factors change, a good model adjusts to the changing demands.
  • Good models scale according to the changes in the dataset.
  • A good model is finally able to offer actionable insights and outcomes to the business stakeholders.

8. Explain KNN Imputation.

The KNN imputation is a concept of finding out missing data values. This is achieved by analyzing and evaluating similar values to missing attribute value. The distance function is used to determine the similarities in attributes.

9. Explain the Waterfall Chart.

The waterfall chart achieves the final value with the help of both negative and positive values. For example, finding the net income of a company. The waterfall chart for this aspect will show how the final net income is achieved.

10.  Is It Possible to Make A Pivot Table Using Multiple Tables?

Yes, it is possible to make a pivot table with multiple tables. Go to Insert> Pivot Table> Add Table1> Add this data to the data model> Select All from PivotTable Fields.

11. How Would Set Print Area in Excel?

Go to Page Layout Tab> Print Area> Set Print Area.

12. Is It Possible to Sort More Than One Column at A Time In Excel?

Yes, multiple columns can be sorted at one time in Excel. Go to Sort Dialog Box> Select data to be sorted> Data Tab> Sort. Now, specify details and use Add Level for various columns.

13. Explain A/B Testing.

The A/B testing is a statistical model which tests two different webpages to find out which one performs better. This type of testing is also known as split testing.

14. Explain Nominal Distribution.

The nominal distribution is utilized to find out the measure of the difference in mean and standard deviations of various values.

15. Explain the Alternative Hypothesis.

The alternative hypothesis assumes that the observations have occurred due to a real effect but there may be some chance of variance.

16. Differentiate Between Bivariate, Univariate, And Multivariate Analysis.

In the bivariate analysis, two variables are used so that the difference in these variables can be achieved.

The univariate analysis finds out the number of variables present for a given instance.

In multivariate analysis, more than two variables are studied to know the effect and impact of these variables on the corresponding response.

17. What Is the Difference Between Covariance and Variance?

While the variance in the data spread around the mean value, covariance is the direct relationship formed between two variables.

18. What Challenges You May Face During Data Analysis?

Various issues can occur during data analysis such as formatted files, duplicate entries, inconsistent entries, or poor data representation.

19. Explain outlier.

The values diverged from a given pattern or far away from each other are known as an outlier. There are two types of outliers: multivariate and univariate.

20. Explain MapReduce.

MapReduce is a process of splitting datasets and analyzing these datasets. Finally, these subsets are processed and combined for an output.

Most of the frequently asked questions are placed in this article to increase the understanding of the data analysis in the candidate. Additionally, it is recommended to learn about ongoing industry trends and tools such as SAS, R, Tableau, etc. for specific knowledge.