The following model was fitted to data on 90 United Kingdom electronics companies." y= .819 +2.11x+96x-.059x+5.87x+.00226x (1.79) (1.94) (144) (4.08) (.00115) where figures in brackets are estimated standard errors, and R-410 y - Share price x Earnings per share * Funds Bow per share x Dividends per share x-Book value per share A measure of growth

(a) Test at the 10% level the null hypothesis that the coefficient on, is zero in the popu- lation regression, against the alternative that the true coefficient is positive.

(b) Test at the 10% level the null hypothesis that the coefficient on x is zero in the popu- lation regression, against the alternative that the true coefficient is positive.

(c) The variable.x, was dropped from the model, and the regression of y on (x. Ng, Xu, Xy) was estimated. The estimated coefficient on ; was then 3.10, with standard error.68. Next, the variable; was dropped from the original model, and the regression of y on (x) was estimated. The estimated coefficient on x was 2.95, with standard er- ror .63. How can these results be reconciled with the conclusions of parts

(a) and (b)?