Below you are given a partial computer output from a multiple regression analysis based on a sample of 16 observations.
Coefficients Standard Error
Constant 12.924 4.425
x1 -3.682 2.630
x2 45.216 12.560
Analysis of Variance
Source of Degrees of Sum of Mean
Variation Freedom Squares Square F
Regression 4853 2426.5
Error 485.3
We want to test whether the variable x1 is significant. The critical value obtained from ttable at the 1% level is:_______.
1. ±2.650.
2. ±2.921.
3. ± 2.977.
4. ± 3.012.

You need to test at 1% if the variable is significant, this means, if the slope for X₁ is different from zero (β₁≠0) using the t-statistic and the critical value approach.

The hypotheses are:

H₀: β₁= 0

H₁: β₁≠ 0

α: 0.01

[tex]t= \frac{b_1-\beta_1}{Sb_1} ~t_{n_1-3}[/tex]

The degrees of freedom "n₁-3" are determined by the number of parameters that you estimate for the multiple regression, in this case there are three "β₁" "β₂" and "δ²e"

The rejection region for this test is two-tailed, the critical values are:

±[tex]t_{n-3;1-\alpha /2}= t_{13;0.995}= 3.012[/tex]

I hope this helps!