Home

Welcome to the EpiEstim wiki!

FAQ on EpiEstim

Why are the estimates of R from estimate_R different from what I expect?

estimate_R produces Bayesian estimates of R so depend on the data but also on the prior chosen (see here and here for details of the method). By default in estimate_R the prior is set to a mean of 5 and a standard deviation of 5. You can change these settings using the function make_config. It is recommended to check whether changing the prior dramatically affects the estimates, to assess whether results are primarily driven by the data or not.

Can I use EpiEstim to estimate R from coarsely aggregated data, e.g. weekly data?

At the moment EpiEstim only allows estimation of R using the same time unit for the incidence and the serial interval data. If you want to estimate R from weekly incidence data, you will therefore have to specify the distribution of the serial interval with week as the time unit.