From 31dfc436a2a0226ba9c957e16129df1d726c861a Mon Sep 17 00:00:00 2001 From: Colin Bowers Date: Fri, 21 Sep 2018 21:11:50 +1000 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index b13e3d8..5e46e10 100644 --- a/README.md +++ b/README.md @@ -113,6 +113,6 @@ If the user wants the optimal block length using the method proposed in Patton, Now let `data::Matrix{Float64}`. -If the user wants the average optimal block length from each column of `data`, use `optblocklength(x, mean, blmethod=:ppw2009, )`. +If the user wants the median optimal block length from each column of `data`, use `optblocklength(data, blmethod=:ppw2009)`. If the user wants the average optimal block length use `optblocklength(data, blmethod=:ppw2009, fblocklengthcombine=mean)`. If the user wants the median of the test statistic that is the maximum of the sample mean of each column, using a stationary bootstrap with optimal block length, then use `dboot(data, flevel1=(x -> maximum(mean(x, 1))), flevel2=median)`. If `data::Vector{Vector{Float64}}` instead, and the user wanted the 95% confidence interval, use `dbootconf(data, flevel1=(x -> maximum([ mean(x[k]) for k = 1:length(x) ])))`.