OHDSI/Castor: Characterization and Analysis of Statistical Time series comprised Of Real-world data

Castor is an R package that facilitates exploratory analysis of temporal data in an observational database in the OMOP Common Data Model v5.x. It enables you to extract the desired data from your database and build univariate or multivariate time series objects. Each time series can represent either a single concept or a concept set. A concept set time series combines the data for multiple concepts into a single multivariate time series object. Non-parametric methods useful for supporting the following characaterization of a time series are supplied: moving average computation, trend determination, transition and change point detection, outlier detection, interval classification, and seasonality determination. Castor makes no distributional assumptions about the data and thus provides no methods for forecasting.

install.packages("remotes")
remotes::install_github("OHDSI/Castor")