empirical_confint

Confidence intervals for sample statistics based on estimated empirical null distribution

Syntax

   [xup,xlo] = empirical_confint(alpha,X,ptails,ksmooth)

Arguments

See also Common variable names and data structures.

input

   alpha      significance level (scalar)
   X          matrix of sample statistics
   ptails     Pareto tails lower and upper probabilities (default: no Pareto tails)
   ksmooth    use kernel smoothing to estimate cdf (default: no smoothing)

output

   xup        matrix of upper confidence bounds
   xlo        matrix of lower confidence bounds

Description

Return upper and lower confidence bounds [xup,xlo] at significance level alpha based on the empirical distributions in X (derived e.g. from a bootstrap). The first dimension of X must index samples. NaN s are ignored. See empirical_cdfi for details of other parameters.

See also

empirical_cdf | empirical_cdfi | empirical_pval | empirical_cval mvgc_demo_confint