Technical Interview Questions

Question 1

What are you Excel skills like?

Answer 1

I am confident using excel and I actually use Excel or Google sheets on a daily basis for personal use whether this be creates GANNT charts, exercise routines, or monthly goals with conditional formatting applied.

I used Excel consistently throughout university including on my internship at the advanced wellbeing research centre where I created an extensive Excel spreadsheet, applied data validation, and transferred over 500 rows of raw data.

I also consolidated my knowledge in a recent data analysis bootcamp where I passed the assignment which included the use of formulas and data visualisation.

Question 2

What are some considerations when approaching data?

Answer 2

1. The classifications of the data such as internal/ external, the sensitivity of the data.
2. The ethics and data ownership. Data rights. The usage of the data.
3. Data security - encryption, authorised access.
4. Data integrity - reliability, accuracy, data redundancy, validity, consistency.

Question 3

What are methods of collecting data?

Answer 3

• Primary data (surveys, questionnaires, sensors - collecting the data yourself).
• Secondary data (meta-analysis)
• Acquiring existing data from a company data base etc.
• Web APIs
• Web scraping if permissiable

Question 4

What are methods of organising data?

Answer 4

Databases (relational to improve data scaling, integrity, query performance further down the line) compared to a spreadsheet.

Question 5

What are methods of aggregating data?

Answer 5

Aggregation involves summarising and combining individual data points into groups or categories. It’s useful for condensing large datasets into manageable summaries and extract meaningful insights.

• Summation
• Averaging
• Count or Count Distinct
• Minimum
• Maximum
• Attribute
• Variance

Question 6

What are key methods or types when analysing data?

Answer 6

• Descriptive analysis: summarise the main features of data set such as mean and range, etc.
• Inferential statistics: make inferences or predictions of population based on sample, hypothesis testing, confidence intervals, regression analysis.
• Exploratory analysis: visually exploring and summarising data to uncover patterns (box plots, histograms, scatter plot, etc.).
• Predictive modelling: use statistical models and machine learning algorithms to forecast future outcomes based on historical data (linear regression, logistic regression, neural networks).

Question 7

How can we improve data quality?

Answer 7

Data quality is essential for reliable analysis and should be considered when decision making.

Seven pillars of data quality:

1. Completeness: null data?
2. Conformity: unstandardised format (diff units etc)?
3. Uniqueness: repeated data?
4. Accuracy: 0 values/ outdated data?
5. Validity: Data filled out correctly?
6. Consistency: correct data/ no conflicting data for same row?
7. Integrity: Invalid/ missing primary key (unique identifier)?

Question 8

How can we drive automation?

Answer 8

Driving automation involves leveraging technology to streamline processes, increase efficiency, and reduce manual intervention.

Strategies include:
- Identifying automation opportunities : conduct a thorough assessment of existing processes to identify tasks and workflows that can be automated.

• Look for repetitive, rule-based tasks with clear inputs, outputs and decision points.