About this question
Medium · Statistics & Regression · Quant Trader interview question · hypothesis-testing, statistical-power, type-ii-error, sample-size
You are evaluating a trading strategy that aims to exploit short-term mean reversion in a stock. You formulate a null hypothesis that the strategy has no edge (i.e., the expected return is zero). You then perform a hypothesis test using a sample of the strategy's historical trades. Define the power of this hypothesis test. How does increasing the sample size (number of trades) generally affect the power of the test, assuming all other factors remain constant?