Changes in version 0.99.0 (2023-04-23)
+ Submitted to Bioconductor

Changes in version 0.99.7 (2023-09-16)
+ Parallel now implemented with BiocParallel
+ Added validity tests

Changes in version 0.99.8 (2023-09-18)
+ Replaced RNAseqCovarImpute_data.RData with two individual rda files for example_DGE and example_data
+ Added documentation for the package (?RNAseqCovarImpute)
+ Added unit test structure and some basic unit tests

Changes in version 0.99.10 (2023-10-06)
+ No longer exports internal functions
+ License to GPL-3 + file LICENSE
+ Updated vignette introduction

Changes in version 0.99.11 (2023-10-06)
+ License to GPL-3

Changes in version 0.99.12 (2023-10-13)
+ limmavoom_imputed_data_list now returns results for all variables in model formula

Changes in version 1.0.1 (2023-10-26)
+ fixed bug in limmavoom_imputed_data_list_helper function where sigma values were not properly output

Changes in version 1.0.2 (2023-10-26)
+ fixed bug in combine_rubins where sigma values were not properly made into a numeric vector

Changes in version 1.1.3 (2024-04-12)
+ fixed bug in get_gene_bin_intervals where all genes were not included in some cases
+ fixed bug where dfs were Inf in cases where information loss due to missingness (lambda) was 0
+ Added MI PCA method where we 1) perform PCA on the log CPM values for all genes, 2) create M
  imputed datasets where the imputation predictor matrix includes all covariates and the optimum
  number of PCs to retain (e.g., based on Horn’s parallel analysis or the number of PCs that account
  for >80% explained variation), 3) conduct the standard limma-voom pipeline on each M imputed dataset,
  and 4) pool the results with Rubins’ rules to produce combined coefficients, standard errors, and P-values

Changes in version 1.1.4 (2024-04-29)
+ bug fix above where dfs were Inf fixed for df AND df_bayes