| TruePrev {PoolTestR} | R Documentation |
A synthetic dataset for pooled testing
Description
This data.frame contains the 'true' values of prevalence for each, site,
village, region and year used to generate the synthetic dataset
ExampleData
Usage
TruePrev
Format
A data frame with 900 rows and 7 variables:
- Region
ID of the region the pool was taken from. "A", "B", or "C"
- Village
ID of village pool was taken from. Includes name of region e.g. "B-3" is village 3 from region B
- Site
ID of sampling site pool was taken from. Includes name of region and village e.g. "B-3-7" is site 7 from village 3 from region B
- Year
Year of sampling. Years are 0, 1, or 2
- PrevalenceRegion
'True' average prevalence in the region (in that year)
- PrevalenceVillage
'True' average prevalence in the village (in that year)
- PrevalenceSite
'True' prevalence at that site (in that year)
Details
The 'true' model can be summarised in formula notation as:
Result ~ Region + Year + (1|Village) + (0 + Year|Village) + (1|Site)
where the coefficient for Year is log(0.8), the standard deviation for intercept random effects for village and site are both 0.5, the standard deviation for the year random effect for village is 0.2 and the random effects are all uncorrelated/independent.