[INTERNAL] Sample size for correlation computation
[INTERNAL] Sample size for correlation computation
[INTERNAL] Depending on how missing data is handled in correlation matrix computation, the number of samples used is returned. If all.obs is specified the number of rows (i.e. samples) of the original data is returned. If pairwise.complete.obs is specified the crossproduct of a matrix indicating the non-NA values is returned as matrix. This implementation was adopted from corAndPvalue.
Source
Method to calculate samples in pairwise.complete.obs adopted and improved from corAndPvalue
measurement_data: [data.frame] Data frame containing the respective raw data (e.g. mRNA expression data, protein abundance, etc.) to the adjacency matrix. Analyzed components (e.g. genes) in rows, samples (e.g. patients) in columns.
handling_missing_data: ["all.obs"|"pairwise.complete.obs"] Specifying the handling of missing data during correlation matrix computation. (default: all.obs)
Returns
For 'all.obs' returns an integer indicating the number of samples in the supplied matrix (i.e. number of rows). For 'pairwise.complete.obs' returns a matrix in the same size of the correlation matrix indicating the number of samples for each correlation calculation.