Regression With R or Python | Dataford Interview Questions

How would you use R or Python to run regression and analyze results?

Using PostgreSQL tables, prepare the monthly observations that would be passed to R or Python and calculate the core regression statistics directly in SQL. Exclude incomplete observations and funds with fewer than three valid observations.

Output

One row per qualifying fund with fund_id, fund_name, observations, alpha_monthly, beta, r_squared, and r_squared_rank.
Use excess fund returns and excess benchmark returns, and rank funds by descending r_squared, breaking ties by fund_id.

Schema

funds

Column	Type	Description
fund_idPK	INT	Unique fund identifier
fund_name	VARCHAR(100)	Fund name
strategy	VARCHAR(60)	Investment strategy

portfolio_returns

Column	Type	Description
return_idPK	INT	Unique return record identifier
fund_id	INT	Referenced fund
month_start	DATE	First day of the return month
return_pct	DECIMAL(8,4)	Monthly fund return percentage

market_returns

Column	Type	Description
month_startPK	DATE	First day of the return month
benchmark_return_pct	DECIMAL(8,4)	Monthly benchmark return percentage
risk_free_pct	DECIMAL(8,4)	Monthly risk-free return percentage

Your question is Regression With R or Python. Start with the requirements and the three tables in the Question tab.

Run and submit as often as you like. When you're ready, talk me through your approach or go straight to the code.

Problem