Grubbs test for outliers

[ArnoStrouwen]

Implements the "type = 10" Grubbs test from R Outliers.

The (p = 2 - p) part is needed to match results of two-sided tests, but I can't figure out why that is a good idea, instead of just putting it to 1.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 61.11111% with 14 lines in your changes missing coverage. Please review.

Project coverage is 93.88%. Comparing base (c440511) to head (6be062d).

Files with missing lines	Patch %	Lines
src/grubbs.jl	61.11%	14 Missing :warning:

Additional details and impacted files

@@            Coverage Diff             @@
##           master     #345      +/-   ##
==========================================
- Coverage   94.52%   93.88%   -0.65%     
==========================================
  Files          29       30       +1     
  Lines        1827     1863      +36     
==========================================
+ Hits         1727     1749      +22     
- Misses        100      114      +14     

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

:rocket: New features to boost your workflow:

• :snowflake: Test Analytics: Detect flaky tests, report on failures, and find test suite problems.