index.md

Nowcaster

nowcaster is an R package for “nowcasting” epidemiological time-series on individual level data.

Every single system of notification has an intrinsic delay between the date of onset of the event and the date of report. nowcaster can estimate how many counts of any epidemiological data of interest (i.e., daily cases and deaths counts) by fitting a negative binomial model to the time steps of delay between onset date of the event, (i.e., date of first symptoms for cases or date of occurrence of death) and the date of report (i.e., date of notification of the case or death).

Installing

After have a proper INLA installation to install nowcaster package simply run the code below in R:

devtools::install_github("https://github.com/covid19br/nowcaster")

If you have any problem installing, please refer to next section on the dependencies of the package.

Dependencies

nowcaster is based on the R-INLA and INLA packages for “Integrated Nested Laplace Approximation” algorithm to Bayesian inference. INLA is a fast alternative to others methods for Bayesian inference like MCMC. An introduction to INLA can be found here.

nowcaster it was built for epidemiological emergency use, it was constructed for the Brazilian Severe Acute Respiratory Illness (SARI) surveillance system (SIVEP-Gripe), at the time of Covid-19 pandemic.

Before installing the package certify you have an active installation of INLA, to do so you can run the following code:

install.packages("INLA",
                 repos=c(getOption("repos"),
                         INLA="https://inla.r-inla-download.org/R/stable"), 
                 dep=TRUE)

If you want more detail on other possible installations of INLA, please refer to the official page of the package.

Similar Initiatives

There are other alternative packages, that can produce nowcasting estimation, here it is some options:

• Epinow2
• Surveillance