All programs
Insight programs
What changed
Competitions

Contacts
Find people
Write a note

Learn
Drills
My answers
Markets
Resume review
Resources

Overview
Find your fit
Guides

Learn Drills My answers Markets Resume review Resources

Learn

Learn/Statistics and regression for researchers

Go to

Learn Statistics and regression for researchers

0 of 6 lessons, sign in to save

B Basic

Variance and covariance algebra10m
Estimators and standard errorsPro10m
Hypothesis tests and p-valuesPro11m

A Advanced

Linear regression, properlyPro12m
Overfitting and out of samplePro11m
Time series and backtest pitfallsPro12m

FlashcardsPro0/17
Basic quizPro80% passes
Advanced quizPro80% passes
Terms

Statistics and regression for researchers

0
of 6 lessons: 0
of 17 cards

Flashcards Start the first lesson

Variance algebra, standard errors, tests, regression, overfitting, and time series. What a research round checks before it trusts you with data.

BBasic3 lessons

1Variance and covariance algebraEvery risk number in a research interview comes from one formula: the variance of a weighted sum. Learn it once and portfolio, hedge, and signal questions all follow.10 min
2Estimators and standard errorsProEvery number estimated from data comes with noise. The standard error says how much, and it shrinks only with the square root of the sample.10 min
3Hypothesis tests and p-valuesProA test asks how surprising your data would be if nothing were going on. Researchers test thousands of ideas, so the false positives matter more than the formulas.11 min
Basic quizPro10 questions, 80% passes

AAdvanced3 lessons

4Linear regression, properlyProOrdinary least squares is the workhorse of quant research. Know where the slope comes from, what R squared measures, and what breaks it.12 min
5Overfitting and out of sampleProMarkets are noisy enough that a flexible model will fit noise first. The research job is mostly refusing to believe your own backtest.11 min
6Time series and backtest pitfallsProReturns are ordered in time, which changes how you scale risk, measure persistence, and test ideas. Most broken backtests break on time.12 min
Advanced quizPro10 questions, 80% passes