Fits an additive model for multidimensional array, using Tukey's median polish procedure.
Usage
## S3 method for class 'ConstructMPst'
MedianPolishM(data, eps, maxiter, na.rm, ...)
Arguments
data
class ConstructMPst.
eps
real number greater than 0, default 0.01. A tolerance for convergence: see Details
maxiter
the maximum number of iterations. Default 10.
na.rm
logical. If the data contains NA's. Default TRUE.
...
ignored.
Details
The model fitted is additive μ +α _{a} + β _{b} + ξ _{c} + τ _{t}, where μ is an overall mean, α_{a} is the a-th row effect, β_{b} is the effect b-th column effect, ξ_{c} is the c-th layer effect, τ _{t} is the t-th time effect. The algorithm works by alternately removing medians of every spatio - temporal dimensions, and continues until the proportional reduction in the sum of absolute residuals is less than eps or until there have been maxiter iterations. If na.rm is FALSE the presence of any NA value in x will cause an error, otherwise NA values are ignored. MedianPolishM returns an object of class MedianPolishM (see below). There is a plotting method for this class, plot.MedianPolishM.
Value
An object of class medpolish with the following named components in a list:
residuals
the residuals.
overall
the fitted constant term.
effects
the fitted every space - time effects.
iter
number of iterations used in the range maxiter.
References
Hoaglin, D. C., Mosteller, F., & Tukey, J. W. (Eds.). (2011). Exploring data tables, trends, and shapes (Vol. 101). John Wiley & Sons.[link]