mid.importance()
calculates the MID importance of a fitted MID model.
Arguments
- object
a "mid" object.
- data
a data frame containing the observations to be used to calculate the MID importance. If
NULL
, thefitted.matrix
of the MID model is used.- weights
an optional numeric vector of sample weights.
- sort
logical. If
TRUE
, the output data frame is sorted by MID importance.- measure
an integer specifying the measure of the MID importance. Possible alternatives are
1
for the mean absolute effect,2
for the root mean square effect, and3
for the median absolute effect.- x
a "mid.importance" object to be printed.
- digits
an integer specifying the minimum number of significant digits to be printed.
- ...
additional parameters to be passed to
print.data.frame()
to print the importance of component functions.
Value
mid.importance()
returns an object of the class "mid.importance" containing the following components.
- importance
the data frame of calculated importances.
- predictions
the matrix of the fitted or predicted MID values.
- measure
the type of the importance measure.
Details
mid.importance()
returns an object of class "mid.importance".
The MID importance is defined for each component function of a MID model as the mean absolute effect in the given data
.
Examples
data(airquality, package = "datasets")
mid <- interpret(Ozone ~ .^2, airquality, lambda = 1)
#> 'model' not passed: response variable in 'data' is used
imp <- mid.importance(mid)
imp
#>
#> MID Importance based on 111 Observations
#>
#> Measure: Mean Absolute Deviation
#>
#> Importance:
#> term importance order
#> 1 Temp 13.94096 1
#> 2 Wind 10.50540 1
#> 3 Solar.R 5.57458 1
#> 4 Day 4.39277 1
#> 5 Month 2.27995 1
#> 6 Solar.R:Wind 0.44950 2
#> 7 Solar.R:Month 0.37623 2
#> 8 Temp:Day 0.37148 2
#> 9 Wind:Month 0.36905 2
#> 10 Wind:Day 0.36547 2
#> 11 Month:Day 0.32260 2
#> 12 Wind:Temp 0.28060 2
#> 13 Solar.R:Day 0.26646 2
#> 14 Solar.R:Temp 0.23464 2
#> 15 Temp:Month 0.12076 2