Consider the multiple regression model: y = Bo + B,X1 + B2X2 + ... + BAX + 8 To test the null hypothesis Ho: B. = B2 = ... = Bk = 0 against the alternative hypothesis H : at least one B; + 0 at a significance level a, we use the decision rule reject Ho: if FK..-K-1 MSR > F-K-14 (12.23) where FK.n-k-1a is the critical value of F from Appendix Table 9 for which P (Fn-K-1 > Fx.m-K-1, a) = a The computed random variable FX.-K-1 follows an F distribution with numera- tor degrees of freedom K and denominator degrees of freedom (n - K-1). x34 Example 12.8 Housing Price Prediction Model (Simultaneous Coefficient Testing) During the development of the housing price prediction model for Northern City, the analysts wanted to know if there was evidence that the combination of four predictor variables was not a significant predictor of housing price. That is, they wanted to test, at a 99% confidence level, the hypothesis H: B = B2 = B3 = B4 = 0