A researcher wanted to determine the effects of nutritional status on tuberculosis treatment outcomes. There are BMI values and treatment outcome status on the TB register of previous 2 years.
1 What study design is best?
2 What is the dependent variable?
3 What is the biomarker?
4 Which multivariable model is appropriate for these analyses?
5 What are the outcome measures?
6 What assumptions due we need to check?
7 What is the measure of model fitness?
Initially do a simple linear regression of change in quantified radiological TB over the 2 years against BMI in first year.
dependent variable, outcome and biomarker is radiological TB change
depending on other data on the register or specifically obtained, some covariates in a multiple regression could be other diseases and their treatments, age,sex,actual type of treatment, actual diet, geographic region,socio economic factors, trweament compliance etc
check linearity, selection bias for register inclusion,quality of data
Rsq and residual analysis for model fitness.
- Badges
- Science topic
- Similar topics
- Biological Science
- Physiology
- Physiological Processes
- Stress