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, with its hints. The 50 in the free sample can be answered and marked on the spot, no account needed; open 3 of their worked solutions to try, then all of them with a free account.
1,322 questions · page 18 of 34
Random question- 681Is the Sharpe ratio real?, part 1 of 3
FoundationStatistics and inference
- 682A hundred candidate signals, part 1 of 3
FoundationStatistics and inference
- 683Which statement about the central limit theorem is correct?
AppliedStatistics and inferenceJane StreetTwo SigmaD. E. ShawFree solution
- 684A strategy has a true Sharpe ratio of 0.5.
AppliedStatistics and inferenceTwo SigmaAQRPoint72 and Cubist
- 685You compute a 95% confidence interval of (2,8) for a mean. Which reading is correct?
AppliedStatistics and inferenceCitadelTwo SigmaD. E. Shaw
- 686You want to estimate a coin’s bias to within one percentage point at 95% confidence.
AppliedStatistics and inferenceCitadelTwo Sigma
- 687You test 200 signals with no edge at the 5% level.
AppliedStatistics and inferenceCitadelTwo SigmaD. E. Shaw
- 688A test returns p = 0.03. What does that mean?
AppliedStatistics and inferenceCitadelTwo SigmaPoint72 and Cubist
- 689The maximum likelihood estimator of a normal variance divides by n rather than n−1.
AppliedStatistics and inferenceCitadelTwo SigmaD. E. Shaw
- 690An estimator has a bias of 0.2 and a standard deviation of 0.3.
AppliedStatistics and inferenceCitadelTwo SigmaD. E. Shaw
- 691You lower your significance level from 5% to 1% without changing the sample. What happens?
AppliedStatistics and inferenceCitadelTwo SigmaD. E. Shaw
- 692You draw 1,000 bootstrap resamples and sort the statistics.
AppliedStatistics and inferenceCitadelTwo SigmaD. E. Shaw
- 693Your prior on a coin is Beta(2,2) and you observe 7 heads in 10 flips.
AppliedStatistics and inferenceJane StreetCitadelTwo Sigma
- 694What does a 95% credible interval say that a 95% confidence interval does not?
AppliedStatistics and inferenceCitadelTwo SigmaD. E. Shaw
- 695A fair die is rolled 100 times.
AppliedStatistics and inferenceJane StreetOptiverSIG (Susquehanna)
- 696A sample mean estimates μ = 2 with standard error 0.1.
AppliedStatistics and inferenceCitadelTwo Sigma
- 697One hundred waiting times are modelled as exponential with rate λ; their sample mean is 4.
AppliedStatistics and inferenceCitadelTwo Sigma
- 698A strategy won 220 of 400 trades.
AppliedStatistics and inferenceOptiverCitadelTwo Sigma
- 699Ten observations have sample standard deviation 2.
AppliedStatistics and inferenceCitadelTwo Sigma
- 700You compare two execution algorithms on the same 200 orders, measuring slippage…
AppliedStatistics and inferenceCitadelTwo Sigma
- 701A die is rolled 60 times, giving counts 5,8,9,8,10,20 for faces one to six.
AppliedStatistics and inferenceJane StreetTwo Sigma
- 702Five tests give p-values 0.001,0.008,0.012,0.04,0.2.
AppliedStatistics and inferenceCitadelTwo SigmaAQR
- 703You backtest 100 independent strategies, none with any edge, and call one a…
AppliedStatistics and inferenceCitadelTwo SigmaAQR
- 704A bootstrap sample draws 100 observations with replacement from 100.
AppliedStatistics and inferenceJane StreetTwo Sigma
- 705Your prior on a strategy’s alpha is normal with mean 0 and standard deviation 0.5%.
AppliedStatistics and inferenceCitadelTwo SigmaAQR
- 706Your prior on an event rate is Gamma with shape 2 and rate 1 (mean 2 per period).
AppliedStatistics and inferenceCitadelTwo Sigma
- 707An analyst checks an A/B test every day and stops the first time p < 0.05.
AppliedStatistics and inferenceJane StreetCitadelTwo Sigma
- 708An A/B test compares a 10% baseline conversion with a hoped-for 11%.
AppliedStatistics and inferenceCitadelTwo Sigma
- 709A hit rate with a prior, part 2 of 3
AppliedStatistics and inference
- 710Ten p-values in a row, part 2 of 3
AppliedStatistics and inference
- 711Twenty signals at five per cent, part 2 of 3
AppliedStatistics and inference
- 712Is the Sharpe ratio real?, part 2 of 3
AppliedStatistics and inference
- 713A hundred candidate signals, part 2 of 3
AppliedStatistics and inference
- 714You have screened 5,000 candidate features and want to hand a shortlist to a…
AdvancedStatistics and inferenceCitadelTwo SigmaAQR
- 715Twenty independent tests are run at the 5% level, all nulls true.
AdvancedStatistics and inference
- 716A two-sided test at α = 5% compares two arms of 64 with a true standardised effect of 0.5.
AdvancedStatistics and inferenceJane StreetCitadelTwo Sigma
- 717For which statistic does the ordinary bootstrap fail?
AdvancedStatistics and inferenceCitadelTwo SigmaD. E. Shaw
- 718An A/B test has 10,000 users per arm and a 5% baseline conversion rate.
AdvancedStatistics and inferenceCitadelTwo SigmaD. E. Shaw
- 719You average n independent standard Cauchy random variables.
AdvancedStatistics and inferenceJane StreetCitadelTwo Sigma
- 720Nineteen independent draws come from a uniform distribution on [0,θ], and the…
AdvancedStatistics and inferenceJane StreetSIG (Susquehanna)Two Sigma