Exercise 6:    Create table 4 “Multiple regressions”

·         This exercise will use demo2 project. If you have not started demo2 project, click here to follow exercise 1: start the new project demo2

·         This exercise will use new variables. Click here to follow through Exercise 2:  Create new variables, code and label variables, if you have not done so.

Objectives:

·         Create multiple regressions table 1

·         Create multiple regressions table 2

·         Create multiple regressions table 3

================================================================================================

 

Objective 1: To create following table:

Multiple regressions 1

 

-

SBP

DBP

Crude

Body mass inex

0.1 (-0.6, 0.8) 0.807

0.0 (-0.3, 0.4) 0.854

Body mass inex tertiles

Low

0

0

Middle

-3.9 (-7.8, -0.1) 0.044

-1.9 (-3.8, 0.0) 0.053

High

-1.2 (-5.0, 2.7) 0.550

-1.0 (-2.9, 1.0) 0.323

Adjusted

Body mass inex

0.8 (0.2, 1.4) 0.011

0.3 (-0.1, 0.6) 0.114

Body mass inex tertiles

Low

0

0

Middle

-0.8 (-4.2, 2.6) 0.637

-0.7 (-2.6, 1.1) 0.422

High

2.2 (-1.2, 5.7) 0.202

0.2 (-1.7, 2.0) 0.845

 

ß(95%CI) p-value or OR/RR(95%CI) p-value

Outcome(Y): SBP and DBP, Risk factor(X): Body mass inex and Body mass inex tertiles, model each Y with each X respectively.

Crude: none adjusted

Adjusted: adjust for SEX, AGE, Education, Occupation, Cigarette smoking and Alcohol consumption

Each model use its available observations

 

Follow following steps to create the above table:

·         Click “Advanced analysis” -> “Multiple regressions”

·         Drag and drop variable SBP and DBP to “Select outcome variables (Y)”

·         Drag and drop BMI and BMI3 to “Select risk factors(X)”

·         Drag and drop SEX, AGE, EDUC, OCCU, SMK and ALH to “Model 2”.

·         Check box “outcomes” in “Design columns” panel.  Set rows sorted by “M: Models” and then “X: Exposures”

            

·         Click “View Table” button, wait for a few seconds, you will get the above table

 

Done!

 

Objective 2:  To create following table:

Multiple regressions 2

 

Body mass inex

Male

Female

Total

SBP

Crude

-0.6 (-1.6, 0.5) 0.275

0.7 (-0.2, 1.6) 0.134

0.2 (-0.5, 0.9) 0.611

Adjusted

-0.1 (-1.1, 0.8) 0.770

1.4 (0.6, 2.1) <0.001

0.8 (0.2, 1.4) 0.011

DBP

Crude

-0.4 (-1.0, 0.2) 0.171

0.3 (-0.1, 0.8) 0.136

0.0 (-0.3, 0.4) 0.821

Adjusted

-0.2 (-0.8, 0.3) 0.411

0.6 (0.2, 1.0) 0.005

0.3 (-0.1, 0.6) 0.114

 

ß(95%CI) p-value or OR/RR(95%CI) p-value

Outcome(Y): SBP and DBP, Risk factor(X): Body mass inex, model each Y with each X respectively.

Crude: none adjusted

Adjusted: adjust for AGE, Education, Occupation, Cigarette smoking and Alcohol consumption

Combined analysis adjust for SEX

Each model use its available observations

 

Follow following input screen shot to create the above table

·         Drag and drop variable SBP and DBP to “Select outcome variables (Y)”

·         Drag and drop BMI to “Select risk factors(X)”

·         Drag and drop AGE, EDUC, OCCU, SMK and ALH to “Model 2”.

·         Select SEX and check “By stratified groups, select stratified variable” as the design of columns.

·         Set rows sorted by “X: Exposures” and then “Y: Outcomes” and then “M: Models”

·         Click “View Table” button, wait for a few seconds, you will get the above table

 

Done!

 

Objective 3:  To create following table:

Multiple regressions 3

 

Body mass inex tertiles

N

Mean ± SD

beta

95% CI

P value

SBP

Low

263

132.0 ± 24.9

0.0

Middle

267

128.1 ± 20.4

-0.8

-4.2, 2.6

0.637

High

265

130.8 ± 22.0

2.2

-1.2, 5.7

0.202

DBP

Low

263

70.4 ± 12.4

0.0

Middle

267

68.5 ± 10.8

-0.7

-2.6, 1.1

0.422

High

265

69.5 ± 10.7

0.2

-1.7, 2.0

0.845

 

Outcome: SBP and DBP

Risk factor: Body mass inex tertiles

Adjust for: AGE, SEX, Education, Occupation, Cigarette smoking and Alcohol consumption

 

Follow following input screen shot to create the above table

·         Drag and drop variable SBP and DBP to “Select outcome variables (Y)”

·         Drag and drop BMI to “Select risk factors(X)”

·         Drag and drop AGE, SEX, EDUC, OCCU, SMK and ALH to “Model 1”.

·         Check “Show N(%)/ Mean(SD) and Regression Output” as the “design of columns”.

·         Set rows sorted by “Y: Outcomes” and then “X: Exposures”.

·         Click “View Table” button, wait for a few seconds, you will get the above table

 

Done!