A study was conducted to assess the association between certain pollutants/behaviors and respiratory function.The response measured was chronic respiratory disease status where subjects were assigned to one of four possible categories (Level 1 = no symptoms, Level 2 = cough or phlegm 3 months per year, Level 3 = cough or phlegm > 3 months per year, Level 4 = cough or phlegm and shortness of breath > 3 months per year).The explanatory variables of interest are Air Pollution (air = low, high), Job Exposure to Pollution (exposure = no, yes), and Smoking Status (smoking = non, ex, current).The SAS data step for this data set is given below:

Construct a proportional odds model using level as the response variable. Select only the appropriate predictors in the final model.After the final model is constructed, compare each level of response against the level 1 symptom group.Based on the final model, report summary findings - include hypotheses, descriptive statistics, interpret the parameters, discuss your findings, and provide conclusion.Two-sided alpha is set at 0.05.

data respire;

input air $ exposure $ smoking $ level count @@;

datalines;

0 0 0 1 158

0 0 0 2 9

0 0 1 1 167

0 0 1 2 19

0 0 2 1 307

0 0 2 2 102

0 1 0 1 26

0 1 0 2 5

0 1 1 1 38

0 1 1 2 12

0 1 2 1 94

0 1 2 2 48

1 0 0 1 94

1 0 0 2 7

1 0 1 1 67

1 0 1 2 8

1 0 2 1 184

1 0 2 2 65

1 1 0 1 32

1 1 0 2 3

1 1 1 1 39

1 1 1 2 11

1 1 2 1 77

1 1 2 2 48

0 0 0 3 5

0 0 0 4 0

0 0 1 3 5

0 0 1 4 3

0 0 2 3 83

0 0 2 4 68

0 1 0 3 5

0 1 0 4 1

0 1 1 3 4

0 1 1 4 4

0 1 2 3 46

0 1 2 4 60

1 0 0 3 5

1 0 0 4 1

1 0 1 3 4

1 0 1 4 3

1 0 2 3 33

1 0 2 4 36

1 1 0 3 6

1 1 0 4 1

1 1 1 3 4

1 1 1 4 2

1 1 2 3 39

1 1 2 4 51

;

run;

PROC Logistic order= data;

class air (ref='0') / param = ref;

class exposure (ref='0') / param = ref;

class smoking (ref='0') / param = ref;

model level = air exposure smoking / link =clogit;

run;

Dataset Summary of Variables in Dataset:

• The first explanatory variable of interest is the Air variable. If air is 0 then air pollution is low and if air pollution is high then it is 1.
• The second explanatory variable of interest is job exposure to pollution which is 0 if exposure is no, and if exposure is yes then it is 1.
• The smoking variable is 0 if the participants are non-smokers, 1 if they are ex-smokers, and 2 if they are current smokers.

Level outcome: the response measured was chronic respiratory disease status where subjects were assigned to one of four possible categories (Level 1 = no symptoms, Level 2 = cough or phlegm 3 months per year, Level 3 = cough or phlegm > 3 months per year, Level 4 = cough or phlegm and shortness of breath > 3 months per year)