1. In the spreadsheet tab Google Adwords , there is data from an advertisement campaign run by a retailer for one month . The retailer "bought " a set of adwords from Google and monitored the performance of those adwords over this time period . We have daily data on the following variables SALE - Whether any sale can be attributable to the adword (SALE [Yes =1 or No =0]) CLICKS - Number of Clicks generated by the adword IMPS - Number of impressions adword gets AvgPOS - The average position occupied by the adword We want to test whether the probability of getting a sale is related to any of these covariates Since the dependent variable here is a categorical variable (a binary variable ), hence we need to estimate a logistic regression where the dependent variable is SALE and the other variables are explanatory variables as in: PRSALE GOD 14 0609 If you want to estimate the coefficients using solver , or by installing statTools , or some other software , that's awesome but not necessary for this course and I've done the estimation for you here : Standard Wald Regression Coefficient p- Value Exp (Coef ) Coefficients Error Value Constant 2.043 0.026 77.726 0.000 0.130 CLICKS 0.089 0.001 62.399 0.000 1.093 Avg POS -0.142 0.006 22.357 0.000 0.868 Scaled -0.051 0.003 -19.933 0.000 0.950 Percent Classification Predicted Correct 2970 5404 85.47 % 841 40785 97.98 % Percent Summary Correct 87.51 % Base 83.25 % Improvement 25.42 %