Author: Petra Klepac; Adam J Kucharski; Andrew JK Conlan; Stephen Kissler; Maria Tang; Hannah Fry; Julia R Gog
Title: Contacts in context: large-scale setting-specific social mixing matrices from the BBC Pandemic project Document date: 2020_2_19
ID: fugb778l_15
Snippet: Finally, we compared reported household size with social contacts for participants that had at least one reported physical or conversational contact (n=40,575). To explore the relationship between household size, average density of GPS tracks and social contacts, we used a generalized additive model [30] . The model was defined as g(E(y)) = b + f (x) + a, where y was the binary outcome variable (i.e. reported contacts made), x was the predictor (.....
Document: Finally, we compared reported household size with social contacts for participants that had at least one reported physical or conversational contact (n=40,575). To explore the relationship between household size, average density of GPS tracks and social contacts, we used a generalized additive model [30] . The model was defined as g(E(y)) = b + f (x) + a, where y was the binary outcome variable (i.e. reported contacts made), x was the predictor (i.e. household size or average density of GPS tracks on log 10 scale), g was the link function, b was the intercept, a was age (to adjust for possible confounding), and f was a smooth function represented by a penalized regression spline. Results for fitted GAMs are shown for a = 30.
Search related documents:
Co phrase search for related documents- outcome variable and social contact: 1
- participant social contact and social contact: 1
Co phrase search for related documents, hyperlinks ordered by date