Answer Happy

A researcher collected data to study the effect of smoking on the risk of a heart attack. The variables were: X-a categorical variable with the categories: (1) Present smoker (2) Past smoker (smoked but quit) (3) Non-smoker Y-a binary variable defined by: Y = 1 if the person had a heart attack Y = 0 if the person didn't have a heart attack Since the X-variables are categorical, the researcher coded the X-variable by two dummy variables: X1 = X2 S 1 1 If present smoker otherwise If past smoker otherwise 0 Since Y is a binary variable, the researcher chose to use a logistic regression model. (a) Write the general form of the logistic regression equation with the two X-variables. (b) The researcher ran the logistic regression, and the parameter estimates came out to be: bo= -2.197, b1 = 1.578, b2 = 2.117. Estimate the probability of getting a heart attack for each of the categories of X. (turn the page)
If you did Part (b) correctly, then you found that a past smoker has a higher probability of getting a heart attack than a present smoker. The researcher therefore wrote in his report: "The regression analysis shows that people who quit smoking have a higher risk of getting a heart attack than people who presently smoke. Therefore, my conclusion is: People who smoke cigarettes should not quit smoking !!" Is this conclusion valid? If not, then what is wrong? How would you explain these findings?