In: Statistics and Probability
9. The data presented in Problem 7 are analyzed using muliple linear regression analysis and the models are shown here. In the models, the data are coded as 1= new treatment and 0= standard treatment, and age greater than 65 is coded as 1= yes and 0= no.
y= 53.85- 23.54 (Treatment)
y= 45.31- 19.88 (Treatment) + 14.64 (Age > 65)
y= 45.51 - 20.21 (Treatment) + 14.29 (Age> 65) + .75 (Treatment X Age > 65)
Patients < 65 y= 45.51 -20.21 (Treatment)
Patients 65 + y = 59.80 -19.47 (Treatment)
Does it appear that there is effect modification by age? Justify your response using the preceeding models.
Based on your answers to Problem 8 and Problem 9, how should the effect of treatment be summarized? Should results be reported separetly by age group or combined? Should the effect of treatment be adjusted for age? Justify your response use the models presented in the above problem.
Problem 8 answer is 7.56>3.84 at 1 degree of freedom, so null hypothesis gets rejected. The age and treatment are not independent.