Statistics and inference
A hundred candidate signals, part 3 of 3
A hundred candidate signals · Part 3 of 3
A researcher tests 100 independent candidate signals, each at the 5% level. In truth 90 have no predictive value and 10 are real, and each real signal is detected with probability 0.8, the power of its test. Take the false-discovery share to be the expected number of false positives divided by the expected number of discoveries.
Keep the 5% level, the 100 signals and power 0.8, but suppose that k of the signals are real. What is the smallest k for which the false-discovery share is at most 0.20?
Answer with a number. Fractions, powers and expressions like 23/6 or C(52,5) are read correctly in practice.
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.
Report an issue with this question
Learn the method
More statistics and inference questions
- You have 100 observations and a standard error of 0.4.Foundation · Free solution
- Which statement about the central limit theorem is correct?Applied · Free solution
- An estimator has a bias of 0.2 and a standard deviation of 0.3.Applied · Premium
- You lower your significance level from 5% to 1% without changing the sample. What happens?Applied · Premium
- You draw 1,000 bootstrap resamples and sort the statistics.Applied · Premium
- Your prior on a coin is Beta(2,2) and you observe 7 heads in 10 flips.Applied · Premium