Error tripped:

Error in functional_boxplot(dts, depth_values = tvd, emp_factor = emp_factor_tvd, : Argument 'central_region' must be greater than 0 and less than 1.

First if statement is where I believe the error is:

if (length(shape_boxstats$out) != 0) {
  shape_outliers <- which(mss %in% shape_boxstats$out[shape_boxstats$out < mean(mss)])
  dts <- dts[-shape_outliers, ]
  tvd <- tvd[-shape_outliers]
  index <- index[-shape_outliers]
}

The issue is that an MSS value may be outlying positively (above the median), which makes the initial if statement TRUE. But then shape_outliers returns integer (empty). Thus, when indexing dts and tvd with shape_outliers, it gives back an empty data set.

Finally, this causes an issue when calling functional_boxplot because now central_region = 0.

I think this could be resolved easily by adding another condition to the if statement like so:

if (length(shape_boxstats$out) != 0 & shape_boxstats$out < mean(mss)) {
  ...
}

Edit: that solution^ did not work. I think the second part of the if statement needs to be another if statement inside the first.

if (length(shape_boxstats$out) != 0) {
  if (any(shape_boxstats$out < mean(mss))) {
    ...
  }
}

Edit2: sloppy coding by me today... added any for the inner if statement, considering shape_boxstats$out could be a vector of length > 1.

Hi Segun,

First things first, thank you for the great work!

I found that the aproximation of the degrees of freedom for large dimension provides values smaller than dimension+1. Then the quantile of the F distribution cannot be computed. Find attached an R code with a visualization of the problem.

To solve the issue, I modified the function croux_hesbroeck_asymptotic.R to use the asyntotic m value when this happends. I add the following at the end of the function assuming that for large p and n the asyntotic is a good estimator.

if(m >= dimension){
cutoff <- qf(0.993, dimension, m - dimension + 1)
}else{ #for large dimension and m, we assume that the m_asy is a good estimator
m <- m_asy
}

I will create a pull request.