LongDat R package takes longitudinal dataset as input data and analyzes if there is significant change of the features over time (proxy for treatments), while detects and controls for confounders at the same time. LongDat is able to take in several data types as input, including count, proportion, binary, ordinal and continuous data. The output table contains p values, effect sizes and confounders of each feature, making the downstream analysis easy.

A poster introducing LongDat can be found here.


Install LongDat by typing install.packages("LongDat") in R.


Tutorials for the analysis on continuous time variable (e.g. days) can be found here.

Tutorials for the analysis on discrete time variable (e.g. before/after treatment) can be found here.

Alternatively, you can type browseVignettes(“LongDat”) in R after installing LongDat to access these tutorials.


The paper will be added once it is published. Before that, please cite:
Chen et al., ( 2022 ). LongDat: an R package for confounder-sensitive longitudinal analysis on multi-omics data.