superb comes with a few built-in measures of
precisions. All SE.fct() functions produces an interval width;
all CI.fct() produces the lower and upper limits of an interval.
See (Harding et al. 2014; Harding et al. 2015)
for more.
"superbPlot-compatible" precision measures must have these parameters:
SE.mean(x)
CI.mean(x, gamma)
SE.median(x)
CI.median(x, gamma)
SE.hmean(x)
CI.hmean(x, gamma)
SE.gmean(x)
CI.gmean(x, gamma)
SE.var(x)
CI.var(x, gamma)
SE.sd(x)
CI.sd(x, gamma)
SE.MAD(x)
CI.MAD(x, gamma)
SE.IQR(x)
CI.IQR(x, gamma)
SE.fisherskew(x)
CI.fisherskew(x, gamma)
SE.pearsonskew(x)
CI.pearsonskew(x, gamma)
SE.fisherkurtosis(x)
CI.fisherkurtosis(x, gamma)a vector of numbers, the sample data (mandatory);
a confidence level for CI (default 0.95).
a measure of precision (SE) or an interval of precision (CI).
Harding B, Tremblay C, Cousineau D (2014).
“Standard errors: A review and evaluation of standard error estimators using Monte Carlo simulations.”
The Quantitative Methods for Psychology, 10(2), 107--123.
Harding B, Tremblay C, Cousineau D (2015).
“The standard error of the Pearson skew.”
The Quantitative Methods for Psychology, 11(1), 32--36.
# the confidence interval of the mean for default 95% and 90% confidence level
CI.mean( c(1,2,3) )
#> [1] -0.4841377 4.4841377
CI.mean( c(1,2,3), gamma = 0.90)
#> [1] 0.3141455 3.6858545
# Standard errors for standard deviation, for MAD and for fisher skew
SE.sd( c(1,2,3) )
#> [1] 0.5
SE.MAD( c(1,2,3) )
#> [1] 0.4606589
SE.fisherskew( c(1,2,3) )
#> [1] 1.224745