Spot the False Statement About Regression p-Values

Reported in interviews at Picnic Ericsson

Problem statement

Which statement about regression p-values is false? You regress $y$ on $x_1$ and $x_2$ and test whether each coefficient is zero using a two-sided test. The p-values are 0.01 for $x_1$ and 0.10 for $x_2$.

A. The coefficient of $x_1$ is significant at the 5% level. B. A p-value measures the probability of a test statistic at least as extreme as observed, assuming the null is true. C. A p-value measures that probability assuming the null is false. D. The coefficient of $x_2$ may be zero.

Show hint

What exactly is a p-value conditioned on: the null being true, the null being false, or the observed data?

Relevant roles: Data Scientist, Applied Scientist and Research Scientist.

Related free problems