Fit Linear Regression: Analyze Economic Impact of Coefficients
Overview
This question evaluates understanding of linear regression modeling, coefficient estimation and economic interpretation, hypothesis testing using t-statistics and p-values, nested F-tests for model comparison, and the ability to connect estimated betas to economic meaning in a financial tabular dataset.
Voleon Group
Aug 4, 2025, 10:55 AM
Data Scientist
Technical Screen
Machine Learning
0
0
Scenario
You are given a tabular financial dataset df where the column target is the dependent variable (e.g., next-period return or excess return), and all other columns are candidate predictors/features.
Task
- Fit an Ordinary Least Squares (OLS) regression with target as the dependent variable and all other columns as predictors.
- Report each estimated coefficient (beta) and interpret its economic meaning.
- Describe how you would sequentially test the marginal contribution of each feature (i.e., whether adding/removing a feature improves the model), referencing t-tests and nested F-tests.
Notes
- Use Python statsmodels OLS.
- Refer to summary(), t-statistics, p-values, adjusted R², and nested F-tests. Stepwise procedures are acceptable if justified.
Solution
Login required
Show