In ksboxer/CDIPATools: CDI Predictive Analytics Tools

library(CDIPATools)
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

Linear Interpolation Concept

The linear interpolation equation to be used in the base function is below. The y₀ and y₁ would be either BMI or Media exposure variable. The x₀ and x₁ would be the time variable.

The y variable is the missing value we are looking for at time x. For BMI variable, the x corresponds to a time from Media exposure that is missing between the x₀ and the x₁ intervals. The inverse can be said of the Media Exposure variable to BMI as well.

Source: Linear Interpolation, Wikipedia

2-D Linear Interpolation

For 2-D Linear Interpolation, we have to provide 2 pairs of (x,y) coordinates and 1 coordinate point corresponding to the missing value.

missing.y <- LinInterpolate(3,5,1,3,2)

ksboxer/CDIPATools documentation built on June 5, 2019, 8:29 a.m.