Pavel V. Dimens

That's a very good point I had not considered. It could, in theory, have a kwarg of a Bool to specify the handling of `missing` as the ignore or include-as-1...

@nignatiadis the committed change suggests a method accounting for the scenarios your describe: ```julia julia> a = [0.1, 0.2, missing, 0.4] ; julia> adjust(a, Holm()) 4-element Array{Union{Missing, Float64},1}: 0.30000000000000004 0.4...

Thinking about it some more, maybe something like a `findall` for the `missing` values, get an array of those indices, then omit the `missing` with `skipmmissing(array) |> collect` , calculate...

Here is how I handled the situation in my own code. I don't know if it would merit adding to your package: ``` # make a copy without the missing...

That's a pretty fair question. The p-values were generated with a chi-squared test. When performed on all the data, it works ok, but if the data is partitioned by group,...

Having learned quite a bit since opening this issue, the PR submitted performs this **a lot** more elegantly than the code suggested above.

One (possibly outrageous) proposal would be to use the `Pair` syntax for the first two positional arguments, where the pair would be `dataframe => :col` (or `[:col1, :col2, ...]`). I...

In my mind's eye, I see 2-4 overarching groups like `global` `module`, etc. No idea what the internals of that would look like

I have also gotten reports like this for my data. Is there any insight into what could be happening here? ``` Read1 before filtering: total reads: 1778364 total bases: 238806338...

This seems like a completely sane and clean implementation of a feature a lot of people are already comfortable with.