tmsImpute: Missing data imputation

In fernandoPalluzzi/tmsClassifier: Random Forest Classifiers for Transcranial Magnetic Stimulation Data

Description

Impute missing Transcranial Magnetic Stimulation (TMS) values, using the K-nearest neighbours (KNN) algorithm from impute.knn (Troyanskaya, 2001).

Usage

tmsImpute(tms, sici.icf = 1:7, sai = 8:11, lici = 12:14,
  max.na = 7, max.r = 0.5, max.c = 0.8, k = 10)

Arguments

tms	A matrix or data.frame containing subjects as rows and TMS values as columns.
sici.icf	Numeric vector determining the position of temporally-ordered SICI-ICF columns (SICI: short-interval intracortical inhibition; ICF: intracortical facilitation). By default, they should be the first 7 measures (sici.icf = 1:7; 4 for SICI and 3 for ICF), taken at times (interstimulus intervals): 1, 2, 3, 5, 7, 10, 15 ms. Set sici.icf to NULL to exclude these values from classification.
sai	Numeric vector determining the position of temporally-ordered SAI (short-latency afferent inhibition) columns. By default, they should be the 4 columns following sici.icf (sai = 8:11), taken at time steps (interstimulus intervals): -4, 0, 4, 8 ms. Set sai to NULL to exclude these values from classification.
lici	Numeric vector determining the position of temporally-ordered LICI (long-interval intracortical inhibition) columns. By default, they should be the 3 columns following sai (lici = 12:14), taken at time steps (interstimulus intervals): 50, 100, 150 ms. Set lici to NULL to exclude these values from classification.
max.na	Maximum number of missing values per row (default max.na = 7).
max.r	Maximum percentage of missing values per row (default max.r = 0.5).
max.c	Maximum percentage of missing values per column (default max.c = 0.8).
k	Number of nearest neighbours to perform imputation.

Value

The original data.frame with imputed missing values.

References

Troyanskaya O, Cantor M, Sherlock G, Brown P, Hastie T, Tibshirani R, Botstein D, Altman RB (2001). Missing value estimation methods for DNA microarrays. Bioinformatics, 17(6):520-525. https://doi.org/10.1093/bioinformatics/17.6.520

See Also

impute.knn for further details on KNN imputation.

fernandoPalluzzi/tmsClassifier documentation built on Feb. 3, 2021, 12:31 p.m.