How would you test for statistical significance when performing a regression analysis using a t-test?

What will be an ideal response?

a. For small samples we use the t-distribution; as the sample grows past 30 or 40 the t-distribution increasingly approximates the standard normal. A general practice is to compute t statistics for each coefficient and compare the observed value with a critical t (or z) based on N – K – 1 degrees of freedom. The observed t values are calculated, as the coefficient divided by its standard error. The t can be checked against a critical value obtained from a t table by choosing the appropriate alpha level and number of tails. If the absolute value of the t score is greater than the t critical value, the result is statistically significant.