Association between Sedentary Time and Hypoglycemic Events in a 7-Day Analysis

[James Loyd]

Greetings to the community,

I am conducting a study aiming to determine whether repetitive sedentary time over 7 consecutive days is associated with hypoglycemic events during the same period. Here are my variables:

• Independent Variable: Sedentary time (measured over 7 days using accelerometry)
• Dependent Variable: Hypoglycemic events, daily average blood glucose levels (measured over the same 7 days using continuous glucose monitoring)
• Covariates: Daily insulin dosage, daily carbohydrate intake

I would like to gather opinions or suggestions on the most appropriate statistical approach to analyze these associations. Any advice on specific statistical models or additional considerations I should take into account would be highly appreciated.

Thank you in advance for any insights you may provide.

Best regards,

[Nick Cox]

Cross-posted at https://stats.stackexchange.com/ques...7-day-analysis

Please note our policy on cross-posting, which is that you are asked to tell us about it. https://www.statalist.org/forums/help#crossposting

[Carlo Lazzaro]

James:
welcome to this forum.
As an aside to Nick's recommendation, is your query related to a study or an assignment (https://www.statalist.org/forums/help#adviceextras #4)?
It sounds strange that you have to elaborate a statistical plan by yourself without the contribution of other pros/scholars.
That said, since you have repeated measurements and your dependent variable seems to take on integer values (that is, the number of hypoglycemic events), you may want to take a look at -xtpoisson-.
Otherwise, a semi-parametric or a parametric survival regression model (faillure=hypoglycemic event) might be worth considering.