Computing Phase (stressassignRDATA File)

1. You are asked to a. obtain appropriate graphs and descriptive statistics (for central tendency, and dispersion) for the non-dichotomous variables used (for dichotomies a table or barplot will be sufficient); b. obtain two two-way tables, with an odds ratio and a value of Q for each; these crosstabs should be between sex and himal, then sleepok and himal; obtain two further tables with himal by sleepok, one including Ms only, and one including Fs only c. obtain a doubledecker, using himal as dependent, with sex and sleepok as predictors; and d. run regression equations. initially, you should try to predict malaise from age, sex, papers, gradesat, sleepok, financesok, sociasci and nurssci. If a predictor appears to be unnecessary, you should drop it in a second equation. As usual, you should hand in the syntax you have used to do this. (35 points) Writeup Phase Your written report should include: 2. a statement of what your crosstabs, the ORs and Qs associated with them, and your doubledecker tell us. (Don't just report statistics - say what they mean.) (16 points) 3. an explanation of why some variables were dropped from regression, if this has been done, or why none were dropped. (Saying that something was or wasn't 'statistically significant' is only the beginning of a full answer.) (6 points) 4. a table showing the coefficients from your final equation, in presentation form. This is illustrated in the text (pp. 240-41). Please, no more than 3 digits to the right of the decimal point. (8 points) 5. a set of brief explanations of the following elements of your regression output: SEE (or, as R refers to it, the 'residual standard error'), R-squared, and b. Just explain what measure each of these refers to, and how we interpret itsvalue for these data. (10 points) 6. a discussion of the message of your regression results. Specifically, what does the value of each of the individual bs in your final equation tell us? Among the dichotomous predictors, which seems to have the greatest impact? By how much? (17 points) Data The data for this assignment are found in the file stressassign.rdata, which may be downloaded from the course Blackboard site. Variables The dependent variable for the regressions is malaise, which has been created by summing the scores for five variables, having to do with headaches, anxiety, irritability, feeling stressed and feeling overwhelmed. As is typically done with scales constructed in this way, you can treat malaise as an interval variable. It has been coded so that higher scores mean greater malaise. Other variables are coded as follows: himal, a dichotomized version of malaise, is coded 0 = below the median, 1 = at or above the median age: 1 = 18-19 ; 2 = 20-21 ; 3 = 22-23 ; 4 = 24-25 ; 5 = 26 and over sex: 1 = M, 2 = F papers = number of papers to be written in the remainder of the term gradesat, coded 1 = very dissatisfied with grades through to 5 = very satisfied financesok, coded 0 = having financial difficulties, 1 = financial situation is OK sleepok, coded 0 = not getting the right amount of sleep, 1 = getting the right amount sociasci, coded 0 = not enrolled in the social sciences, 1 = in the social sciences nurssci, coded 0 = not enrolled in Nursing, 1 = enrolled in Nursing