# T-Test of a Regression Coefficient

Where ${\displaystyle {\hat {\beta }}}$ is a coefficient, ${\displaystyle n}$ is the effective number of observations (note that this is different to the effective sample size where repeated observations exist for each respondent) and ${\displaystyle se_{\beta }}$ is the standard error of the coefficient, the test statistic is:
${\displaystyle t={\frac {\hat {\beta }}{se_{\beta }}}}$,
${\displaystyle p=2\Pr(t_{n-k}\geq |t|)}$,
${\displaystyle k}$ is the number of parameters, including the intercept (where applicable).