Hello,
I am a beginner when it comes to SAS and this is my first project using SAS. I want to make sure that my interpretation of the odd ratio is accurate. I attached the output of my analysis and I also captured the effects table.
Response variable = "Age appropriate sleep duration" is the Response variable and it is binary i.e Child sleeps recommended age appropriate hours or Child did not sleep age appropriate recommended hours
Predictors :
1) ADHD Severity with two levels:
a Mild
b Moderate/Severe
Analysis was stratified based on ADHD Severity
2) Read to with 3 levels
a) 0-3 days
b) 4-6 days
c) Every day.
Analysis of Maximum Likelihood Estimates | ||||||
Parameter |
| HrsSleep_1617 | Estimate | Standard | t Value | Pr > |t| |
Intercept |
| Child sleeps recommended age-appropriate hours | 0.3499 | 0.4741 | 0.74 | 0.4687 |
readto_1617 | 0 -3 days | Child sleeps recommended age-appropriate hours | -1.1681 | 0.6242 | -1.87 | 0.0753 |
readto_1617 | 4-6 days | Child sleeps recommended age-appropriate hours | -1.1306 | 0.8286 | -1.36 | 0.1869 |
NOTE: The degrees of freedom for the t tests is 21. |
Odds Ratio Estimates | ||||
Effect | HrsSleep_1617 | Point Estimate | 95% Confidence Limits | |
readto_1617 0 -3 days vs Every day | Child sleeps recommended age-appropriate hours | 0.311 | 0.085 | 1.139 |
readto_1617 4-6 days vs Every day | Child sleeps recommended age-appropriate hours | 0.323 | 0.058 | 1.809 |
NOTE: The degrees of freedom in computing the confidence limits is 21. |
Interpretation:
In children diagnosed with mild ADHD the odds of child sleeps recommended age appropriate hours in children read to 0-3 days is 0.689 less compared to children read to everyday.
Is this interpretation accurate? Thank you for the anticipated response.
You haven't shown the results of the test for the proportional odds assumption, which indicates whether you have a valid model. You might like to study the annotated output given here:
https://stats.idre.ucla.edu/sas/output/ordered-logistic-regression/
Build your skills. Make connections. Enjoy creative freedom. Maybe change the world. Registration is now open through August 30th. Visit the SAS Hackathon homepage.
Register today!Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.