What's new

YouTube T2-18 Regression: Significance Test of Slope Coefficient

Nicole Seaman

Director of FRM Operations
Staff member
The test statistic of the slope is given by (b1 - β)/SE(b1), although typically the null hypothesis is H(0):β = 0, such that the test statistic simply divides the regression coefficient by its own standard error (i.e., standard deviation of the estimate). This is compared to the student's t value with degrees of freedom equal to (n - k). In my example, the sample is small (n = 10) so that the d.f., = 10 - 2 = 8. We subtract two because there are two estimated coefficients (tip: df equals sample size minus the number of columns in the linest array).

Here is David's XLS: https://trtl.bz/2JS64qq