I have longitudinal data with 2 follow ups at year 1 and 3. At baseline we have measure of endothelial function and we want to calculate the relation ship between endothelial function and diabetes type II. at follow up, the incidence of diabetes is recorded with self reported diagnosis or use of medication as the follow up was only done through interviews and questionnaire. we dont have the exact date of incidence of diabetes. which analysis method will be best to use for this type of data. survival analysis or mixed model? I understand for survival analysis I would need exact date of diagnosis of diabetes. but is there other assumptions that can make it possible to use it?
You likely want a longitudinal model. Full details can be found in the notes at this link:
https://www4.stat.ncsu.edu/~davidian/st732/notes.html
Prof. Davidian is a leading expert. Best, D. Booth
The reflex here is to put in age as a covariate. The alternative, which makes better use of your age variable, is to use age as the time variable in a survival analysis. Participants enter at the age at which they were first surveyed and exit at the last survey age. This allows you to calculate the effect of your risk factor using a hazard function that starts at the earliest observed entry and ends at the last exit.
Ed Korn has a very good paper on this: Korn EL, Graubard BI, Midthune D. Time-to-event analysis of longitudinal follow-up of a survey: choice of the time-scale. Am J Epidemiol. 1997 Jan 1;145(1):72–80.
Ronán Michael Conroy David Eugene Booth
thank you for both of your suggestions. I will look into them
Edit: I have around 2000 participants. their endothelial function was measured with FHR ( continuous values). we have other information about their history of diabetes and other cardiovascular diseases etc. the participants were followed up at year 1 and than at year 3(after 3 yrs of baseline) through phone interviews and paper questionnaires. we asked their medical history, use of medication etc. we want to find an association between endothelial function and incidence of diabetes. so we exclude people who have diabetes at baseline so I am hypothesizing that :people who have bad endothelial function at baseline will get diabetes at follow up.
independent variable; endothelial function (continuous variable) dependent variable: diabetes type 2 incidence (dichotomous , calculated through weather participant get diagnosis for diabetes at follow up, or if they are using medication of diabetes.)
I want to find this association and show its significance using statistical analysis. but for the incidence of diabetes, we dont have exact dates, but only weather they have diabetes or not at one of the follow up.
In absence of exact date of diagnosis of diabetes, which is needed for survival analysis, either you can use followup date as incidence date or try to get approximate date of incidence and use it. For example if you come to know that a particular person was diagnosed in one of the followup time, try to explore approximate date by provoking him/her to get closer date, if not exact date, by questions related to signs, symptoms, treatment etc related to diabetes .
Kandasamy Ravichandran thank you for your suggestions. However, its not possible to get in touch of participant as it was done in 2010. We do have an approximation date but wouldn’t it effect the credibility of the answer. do you suggest we go for any other model? Like mixed model etc?
i read about “interval censoring data”. Do you think it is applicable method for my study?
- Badges
- Science topic
- Similar topics
- Medicine
- Disease
- Metabolic Diseases
- Glucose Metabolism Disorders
- Diabetes