{lvmisc} contains a group of useful functions to compute basic indices of accuracy. These functions can be divided in those which compute element-wise values and those which compute average values:
error()
error_abs()
error_pct()
error_abs_pct()
error_sqr()
mean_error()
mean_error_abs()
mean_error_pct()
mean_error_abs_pct()
mean_error_sqr()
mean_error_sqr_root()
bias()
loa()
You may notice that the majority of these functions have common
prefixes (error_
and mean_error_
), intended to
facilitate the use, as most text editors have an auto-complete feature.
Also all of the accuracy indices functions take actual
and
predicted
as arguments, and the functions that return
average values have na.rm = TRUE
in addition.
Let’s now see how each function computes its results
error()
It simply subtracts the predicted
from the
actual
values.
Formula: ai−pi
error_abs()
It returns the absolute values of the error()
function.
Formula: |ai−pi|
error_pct()
Divides the error by the actual
values.
Formula: ai−piai⋅100
error_abs_pct()
Returns the absolute values of the error_pct()
function.
Formula: |ai−pi||ai|⋅100
error_sqr()
It squares the values of the error()
function.
Formula: (ai−pi)2
mean_error()
It is the average of the error.
Formula: 1NN∑i=1(ai−pi)
mean_error_abs()
Computes the average of the absolute error.
Formula: 1NN∑i=1|ai−pi|
mean_error_pct()
The average of the percent error.
Formula: 1NN∑i=1ai−piai⋅100
mean_error_abs_pct()
It is the average of the absolute percent error.
Formula: 1NN∑i=1|ai−pi||ai|⋅100
mean_error_sqr()
Averages the mean squared error.
Formula: 1NN∑i=1(ai−pi)2
mean_error_sqr_root()
It takes the square root of the mean squared error.
Formula: √1NN∑i=1(ai−pi)2
bias()
Alias to mean_error()
.
loa()
Formula: bias±1.96σ
Where σ is the standard deviation.