Significant PCs should show a p-value distribution that is strongly skewed to the left compared to the null distribution. The p-value for each PC is based on a proportion test comparing the number of features with a p-value below a particular threshold (score.thresh), compared with the proportion of features expected under a uniform distribution of p-values.
ScoreJackStraw(object, ...) # S3 method for JackStrawData ScoreJackStraw(object, dims = 1:5, score.thresh = 1e-05, ...) # S3 method for DimReduc ScoreJackStraw(object, dims = 1:5, score.thresh = 1e-05, ...) # S3 method for Seurat ScoreJackStraw( object, reduction = "pca", dims = 1:5, score.thresh = 1e-05, do.plot = FALSE, ... )
Arguments passed to other methods
Which dimensions to examine
Threshold to use for the proportion test of PC significance (see Details)
Reduction associated with JackStraw to score
Show plot. To return ggplot object, use
Returns a Seurat object