问题如下:
Suppose you fit a model where both t-statistics are exactly +1.0. Could an F-statistic lead to rejection in this circumstance? Use a diagram to help explain why or why not.
选项:
解释:
Yes. When the regressors are very positively correlated, then this can happen. The t-stats are small because the variables are highly co-linear, so that the variation in the left-hand-side variable cannot be uniquely attributed to either. However, the F-stat is a joint test and so if there is an effect in at least one, the F can reject even if the t-stats do not. See the image below that shows the region where the F would fail to reject, and the two t-stats.
看不懂这个figure