TESTING FOR THE SIGNIFICANCE OF A SUBSET OF COEFFICIENTS-THE WALD TEST (UNRESTRICTED) MODEL MODEL A reg price sqft bedrms Source Model Residual SS df MS Number of obs F (3, 10) 3. 28371.6473 Prob > F 10.1670.00687 R-squared Adj R-squared 13 7831.9239 Root MSE 85114.94 16700.07 Total 101815 price Coef. sqft bedrms baths _cons baths Std. Err. 0.1548 .0319404 -21.5875 27.02933 -12.1928 43.25 129.0616 88.30326 t P>t 4.85 -0.80 -0.28 1.46 0.001 0.443 0.784 0.175 14 16.99 0.0003 0.836 0.7868 40.866 [95% Conf. Interval] 0.083632 -81.8126 -108.56 -67.6903 0.225968 38.63758 84.17425 325.8136 Wald Test: test bedrms baths ( 1) bedrms = 0 ( 2) baths = 0 F( 2, 10) = 0.47 Prob > F = 0.6375 EXPLANATION OF THE TEST: Wald test here is used to test the joint significance of a subset of coefficients, namely, bedrms and baths. These two variables are individually insignificant based on t-tests with very high p values. But before dropping them together, we may want to test the joint significance of them using Wald test. The command test bedrms baths tests whether baths and bedrms are insignificant jointly. Since the null says they are, and F-stat’s p-value=0.6375, then we cannot reject the null. DROP both baths and bedrms from the regression equation. They don’t belong to the model. SPECIAL WALD TEST: This is an F-test for the significance of all variables in the model, i.e. sqft, bedrms and baths. Hence, the null states betas of all variables in the model are set equal to zero. Null H 0 : sqft bedrms baths 0 Alternative H A : At least some are non zero. test bedrms baths sqft ( 1) bedrms = 0 ( 2) baths = 0 ( 3) sqft = 0 F( 3, 10) = 16.99 Prob > F = 0.0003 Notice that F-test p-value is 0.0003, which is lower than 1% of . Hence, we can reject the null and at least some variables in this trio is significant. This variable is SQFT! (based on the t-test). RESTRICTED MODEL MODEL B reg price sqft Source SS df Number of obs MS F( 1, 12) 14 54.86 Model 83541.4429 1 83541.4429 Residual 18273.5678 12 1522.79731 R-squared 0.8205 Total 101815.011 13 7831.9239 Adj R-squared Root MSE 0.8056 39.023 price sqft cons Coef. Std. Err. 0.1387503 .0187329 52.3509 37.28549 t Prob > F P>t 7.41 0 1.40 0.186 [95% Conf. 0 Interval] 0.0979349 0.179566 -28.88719 133.589