Quant interview questions
1,322 questions in the style trading and research firms ask, from probability and brainteasers to options, statistics and coding. Every question is open to read; the 50 in the free sample show their worked solutions here.
378 questions · page 3 of 10 · Clear filters
- Regression residuals have a first-order autocorrelation of 0.4.Regression and econometrics · Foundation
- A treated group’s average outcome goes from 10 to 15 after a policy; a control…Regression and econometrics · Foundation
- A regression coefficient is 3.Regression and econometrics · Foundation
- In a logistic regression a coefficient is 0.7.Regression and econometrics · Foundation
- In a Poisson regression of trade counts, a regressor has coefficient 0.1.Regression and econometrics · Foundation
- You regress y on x and get a slope of 2.Regression and econometrics · Applied
- The tallest fathers tend to have sons shorter than themselves. What does this show?Regression and econometrics · Applied
- You regress fund returns on manager tenure and get a positive coefficient.Regression and econometrics · Applied
- You add a regressor of pure noise to a model. What happens to R² and to adjusted R²?Regression and econometrics · Applied
- A regression on 100 observations with 5 regressors has R² = 0.30.Regression and econometrics · Applied
- Your errors are heteroskedastic. What is still true of the OLS coefficients?Regression and econometrics · Applied
- Regressing x₁ on the other regressors gives R² = 0.9.Regression and econometrics · Applied
- Your regression residuals on a time series are strongly positively autocorrelated.Regression and econometrics · Applied
- With orthonormal regressors, the OLS coefficient is 2 and the ridge penalty is λ = 3.Regression and econometrics · Applied
- A logistic regression has intercept −2 and slope 0.5.Regression and econometrics · Applied
- A regression on 100 observations has an intercept and 5 other regressors.Regression and econometrics · Applied
- A regression has XᵀX = [[2, 1], [1, 2]] and Xᵀy = [4, 5].Regression and econometrics · Applied
- Which assumption is essential for the OLS coefficients to be unbiased?Regression and econometrics · Applied
- In a simple regression the error standard deviation is 2 and Σᵢ(xᵢ−x)² = 25.Regression and econometrics · Applied
- A regression with 4 regressors plus an intercept, fitted on 105 observations, has R² = 0.2.Regression and econometrics · Applied
- In a simple regression on 20 points with Σ(xᵢ−x)² = 18, one point has xᵢ−x = 3.Regression and econometrics · Applied
- The true model is y = x₁+2x₂+ε.Regression and econometrics · Applied
- The true slope is 2. The regressor is measured with independent noise of…Regression and econometrics · Applied
- In a panel of firms over many years, what does adding firm fixed effects to a…Regression and econometrics · Applied
- You accidentally duplicate every row of your data set and rerun OLS.Regression and econometrics · Applied
- With orthonormal regressors, the lasso minimising…Regression and econometrics · Applied
- With highly collinear regressors, ridge regression often predicts better out of…Regression and econometrics · Applied
- You add independent noise to a regressor x. What happens to its coefficient?Regression and econometrics · Advanced
- By the Frisch–Waugh–Lovell theorem, what does the coefficient on x₁ in a…Regression and econometrics · Advanced
- An instrument Z has Cov(Z,Y) = 0.6 and Cov(Z,X) = 0.4.Regression and econometrics · Advanced
- Your first-stage F-statistic is 4. What does that tell you about the IV estimate?Regression and econometrics · Advanced
- You model trade counts per venue where exposure times differ. What belongs in the model?Regression and econometrics · Advanced
- Two models are fitted on 100 observations.Regression and econometrics · Advanced
- You average 1,000 observations from an AR(1) process with autocorrelation 0.5.Regression and econometrics · Advanced
- A design matrix has squared singular values 9, 4 and 1.Regression and econometrics · Advanced
- Which of these is closest to being a stationary series?Time series · Foundation
- For white noise, sample autocorrelations have standard error about 1/√T.Time series · Foundation
- When is the AR(1) process xₜ = φxₜ₋₁+εₜ covariance stationary?Time series · Foundation
- A HAR model forecasts tomorrow’s realised volatility as 0.1+0.4 RV_d+0.3 RV_w+0.2 RVₘ.Time series · Foundation
- Your labels are each asset’s return over the next 10 trading days.Time series · Foundation