mi (version 0.10-2)

typecast: Variables type

Description

Function for determinig the variable type.

Usage

typecast( object )
  ## S3 method for class 'ANY':
typecast( object )
  ## S3 method for class 'matrix':
typecast( object )
  ## S3 method for class 'data.frame':
typecast( object )  
  ## S3 method for class 'list':
typecast( object )

Arguments

object

Vector, matrix, or data frame of data to determin the type of.

Value

• fixed
  varaibles that contain only one value.
• binary
  variables that contain two values.
• ordered-categorical
  variables that contain 3 to 5 postive values.
• unorderd-categorial
  variables that contain characters or more than 5 postive levels
• positive-continuous
  variables that contain more than 5 postive values, NOT including 0s.
• nonnegative
  variables that contain more than 5 postive values, including 0s.
• continuous
  variables that are not belong to any of the above types.
• log-continuous
  log-scaled continuous variable

Details

The variable type of a vector, or vector of variable types for each variable in the dataset.

References

Yu-Sung Su, Andrew Gelman, Jennifer Hill, Masanao Yajima. (2011). Multiple Imputation with Diagnostics (mi) in R: Opening Windows into the Black Box. Journal of Statistical Software 45(2).

See Also

mi

Examples

data(CHAIN)
class(CHAIN)

typecast(CHAIN[,1]) # for vector

typecast(as.matrix(CHAIN))# for matrix

typecast(CHAIN) # for data.frame