accu {riskyr} | R Documentation |
A list containing current accuracy information.
Description
accu
contains current accuracy information
returned by the corresponding generating function
comp_accu_prob
.
Usage
accu
Format
An object of class list
of length 5.
Details
Current metrics include:
-
acc
: Overall accuracy as the probability (or proportion) of correctly classifying cases or ofdec_cor
cases:See
acc
for definition and explanations.acc
values range from 0 (no correct prediction) to 1 (perfect prediction). -
wacc
: Weighted accuracy, as a weighted average of the sensitivitysens
(aka. hit rateHR
,TPR
,power
orrecall
) and the the specificityspec
(aka.TNR
) in whichsens
is multiplied by a weighting parameterw
(ranging from 0 to 1) andspec
is multiplied byw
's complement(1 - w)
:wacc = (w * sens) + ((1 - w) * spec)
If
w = .50
,wacc
becomes balanced accuracybacc
. -
mcc
: The Matthews correlation coefficient (with values ranging from -1 to +1):mcc = ((hi * cr) - (fa * mi)) / sqrt((hi + fa) * (hi + mi) * (cr + fa) * (cr + mi))
A value of
mcc = 0
implies random performance;mcc = 1
implies perfect performance.See Wikipedia: Matthews correlation coefficient for additional information.
-
f1s
: The harmonic mean of the positive predictive valuePPV
(aka.precision
) and the sensitivitysens
(aka. hit rateHR
,TPR
,power
orrecall
):f1s = 2 * (PPV * sens) / (PPV + sens)
See Wikipedia: F1 score for additional information.
Notes:
Accuracy metrics describe the correspondence of decisions (or predictions) to actual conditions (or truth).
There are several possible interpretations of accuracy:
Computing exact accuracy values based on probabilities (by
comp_accu_prob
) may differ from accuracy values computed from (possibly rounded) frequencies (bycomp_accu_freq
).When frequencies are rounded to integers (see the default of
round = TRUE
incomp_freq
andcomp_freq_prob
) the accuracy metrics computed bycomp_accu_freq
correspond to these rounded values. Usecomp_accu_prob
to obtain exact accuracy metrics from probabilities.
See Also
The corresponding generating function comp_accu_prob
computes exact accuracy metrics from probabilities;
acc
defines accuracy as a probability;
comp_accu_freq
computes accuracy metrics from frequencies;
num
for basic numeric parameters;
freq
for current frequency information;
prob
for current probability information;
txt
for current text settings.
Other lists containing current scenario information:
freq
,
num
,
pal_bwp
,
pal_bw
,
pal_kn
,
pal_mbw
,
pal_mod
,
pal_org
,
pal_rgb
,
pal_unikn
,
pal_vir
,
pal
,
prob
,
txt_TF
,
txt_org
,
txt
Other metrics:
acc
,
comp_accu_freq()
,
comp_accu_prob()
,
comp_acc()
,
comp_err()
,
err
Examples
accu <- comp_accu_prob() # => compute exact accuracy metrics (from probabilities)
accu # => current accuracy information
## Contrasting comp_accu_freq and comp_accu_prob:
# (a) comp_accu_freq (based on rounded frequencies):
freq1 <- comp_freq(N = 10, prev = 1/3, sens = 2/3, spec = 3/4) # => rounded frequencies!
accu1 <- comp_accu_freq(freq1$hi, freq1$mi, freq1$fa, freq1$cr) # => accu1 (based on rounded freq).
# accu1
#
# (b) comp_accu_prob (based on probabilities):
accu2 <- comp_accu_prob(prev = 1/3, sens = 2/3, spec = 3/4) # => exact accu (based on prob).
# accu2
all.equal(accu1, accu2) # => 4 differences!
#
# (c) comp_accu_freq (exact values, i.e., without rounding):
freq3 <- comp_freq(N = 10, prev = 1/3, sens = 2/3, spec = 3/4, round = FALSE)
accu3 <- comp_accu_freq(freq3$hi, freq3$mi, freq3$fa, freq3$cr) # => accu3 (based on EXACT freq).
# accu3
all.equal(accu2, accu3) # => TRUE (qed).