About this question
Hard · Statistics & Regression · Quant Trader interview question · statistics, likelihood-ratio-test, hypothesis-testing, asymptotic-distribution
Suppose you are building a statistical model to predict stock returns. You want to compare two nested models using the Likelihood Ratio Test (LRT). Model 0 is the simpler model with $p$ parameters, and Model 1 is a more complex model with $p + k$ parameters. Let $L_0$ be the maximized likelihood of Model 0, and $L_1$ be the maximized likelihood of Model 1. The likelihood ratio test statistic is defined as $Λ = -2 \ln(L_0 / L_1)$. Under the null hypothesis ($H_0$) that the simpler model (Model 0