Relationship Between t-Statistic and F-Statistic in Simple Regression
Problem statement
In ordinary least squares with a single predictor, you fit the model
$$Y_i = \beta_0 + \beta_1 X_i + \varepsilon_i$$
and want to test $H_0: \beta_1 = 0$ against $H_1: \beta_1 \neq 0$.
You compute both the $t$-statistic $T_s$ for the coefficient $\beta_1$ and the $F$-statistic $F_s$ for the overall regression (comparing the full model to the intercept-only model).
What is the exact mathematical relationship between $T_s$ and $F_s$? Prove it.
Show hint
Which common ingredients (slope estimate, spread of $X$, residual sum of squares) could you express both test statistics in?
Relevant roles: Data Scientist, Applied Scientist and ML Engineer.