Sampling of values for imputation — calculate

calculate_imputation is a helper function that is used in the impute function. Depending on the type of missingness and method, it samples values from a normal distribution that can be used for the imputation. Note: The input intensities should be log2 transformed.

calculate_imputation(
  min = NULL,
  noise = NULL,
  mean = NULL,
  sd,
  missingness = c("MNAR", "MAR"),
  method = c("ludovic", "noise"),
  skip_log2_transform_error = FALSE
)

Arguments

min: a numeric value specifying the minimal intensity value of the precursor/peptide. Is only required if method = "ludovic" and missingness = "MNAR".
noise: a numeric value specifying a noise value for the precursor/peptide. Is only required if method = "noise" and missingness = "MNAR".
mean: a numeric value specifying the mean intensity value of the condition with missing values for a given precursor/peptide. Is only required if missingness = "MAR".
sd: a numeric value specifying the mean of the standard deviation of all conditions for a given precursor/peptide.
missingness: a character value specifying the missingness type of the data determines how values for imputation are sampled. This can be "MAR" or "MNAR".
method: a character value specifying the method to be used for imputation. For method = "ludovic", MNAR missingness is sampled around a value that is three lower (log2) than the lowest intensity value recorded for the precursor/peptide. For method = "noise", MNAR missingness is sampled around the noise value for the precursor/peptide.
skip_log2_transform_error: a logical value, if FALSE a check is performed to validate that input values are log2 transformed. If input values are > 40 the test is failed and an error is returned.

Value

A value sampled from a normal distribution with the input parameters. Method specifics are applied to input parameters prior to sampling.