BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
dkcundiffMD
Quartz | Level 8

To finish the Bradford Hill criteria results of this new nutritional epidemiology methodology: (1) strength BMI formula versus BMI: r= 0.907 (95% CI: 0.903 to 0.911) p<0.0001), (2) experiment: 20/20 bootstrap BMI formulas (each n=100 cohorts) have the 25 risk factors with the same risk factor signs as the worldwide BMI formula, (3) consistency: absolute difference between 37 mean BMI and BMI formula outputs < 0.300 BMI units. (4) Dose-response: the absolute differences between 4 mean BMI and BMI formula dose-response outputs < 0.300. (5) temporality: BMI trend formula r≥0.500, p<0.0001. (6) analogy: low density lipoprotein cholesterol (LDL-C) correlates very strongly with the BMI formula (r=0.808, 95% CI 0.800 to 0.816, p<0.0001) and with BMI (r=0.759 95% CI 0.747 to 0.766, p<0.0001). (7) plausibility all 25 BMI formula risk factors are plausible according to literature reviews. (8) specificity: BMI formula is unique and fits no other health outcome. (9) coherence: all evidence supports that the BMI formula accurately models BMI worldwide.

 

PaigeMiller
Diamond | Level 26

I really don't understand why you are telling me all of this.

 

PLS (and ordinary least squares regression, and similar methods) are empirical. The modeling algorithms don't know, and they don't care, about any previous results found or what the true BMI formula is. It simply finds correlations between x-variables and y-variables and then finds a predictive model to use that fits the data as well as it can.

 

If you are going to do this, you should definitely read the article, but the syntax for PROC PLS in that article is old and doesn't work. The correct syntax is at https://documentation.sas.com/?cdcId=pgmsascdc&cdcVersion=9.4_3.4&docsetId=statug&docsetTarget=statu...

--
Paige Miller

SAS Innovate 2025: Save the Date

 SAS Innovate 2025 is scheduled for May 6-9 in Orlando, FL. Sign up to be first to learn about the agenda and registration!

Save the date!

How to choose a machine learning algorithm

Use this tutorial as a handy guide to weigh the pros and cons of these commonly used machine learning algorithms.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 18 replies
  • 7692 views
  • 10 likes
  • 3 in conversation