AdvancedMultiple choice
Pricing houses in logs · Part 3 of 3
You build a model for house sale prices, regressing on and other features. The coefficient on log floor area is 0.8, and the residual standard deviation of log price is 0.3.
The model will set suggested listing prices across markets where homes range from 100,000 to 5 million. Which headline error metric should you present?
- ARMSE in currency, because it is in units everyone understands
- BR² on price levels, because it is scale-free
- CMedian absolute percentage error, with the share of homes within 10%
- DIn-sample MSE of the log price, since that is what the model minimised
The worked solution is in Premium
The answer, the full working and the one idea to take away – for this and all 1,322 questions in the bank. Answer it in practice and your working is marked, with a known mistake named when you make one.
Learn the method
Communicating: structuring an answer and defending an assumption
More research case studies questions
- You have finished describing your approach and have two minutes left.Applied
- You must present a forecast whose confidence interval is wide enough to include…Applied
- Midway through your case answer the interviewer says one of your key…Applied
- A Fermi estimate multiplies four independent factors, each uncertain to within…Advanced
- You are asked to "predict demand" for a bike-share operator. What do you say first?Foundation
- Ten observations: nine average 2 and one is 100.Foundation