tmalsburg

library(lme4)

head(sleepstudy)
summary(sleepstudy)

# Relabel subjects:
d <- sleepstudy
d$Subject <- factor(rep(1:18, each=10))

# Fit model:

tmalsburg

\usepackage{xpatch}% or use http://tex.stackexchange.com/a/40705

\def\makenamesetup{%
  \def\bibnamedelima{~}%
  \def\bibnamedelimb{ }%
  \def\bibnamedelimc{ }%
  \def\bibnamedelimd{ }%
  \def\bibnamedelimi{ }%
  \def\bibinitperiod{.}%
  \def\bibinitdelim{~}%

tmalsburg

A potential pitfall when running Ibex experiments on Amazon Mechanical Turk

Ibex does Latin squares in a way that can potentially have serious unintended consequences in the form of spurious effects.

The problem: When you submit an experiment to Amazon Mechanical Turk, a lot of workers will immediately jump at it but the rate of participation quickly decays (the distribution over time often looks like an exponential decay). For every participant, Ibex selects a stimulus list based on an internal counter and this counter is incremented when a participant submits their results. Unfortunately, this means that the initial wave of participants all work on the same list of the Latin square and this list will therefore be strongly overrepresented. This can lead to strong spurious effects that are not due to the experimental manipulation but due to between-item differences. This is an easy-to-miss problem and I would not be surprised if some published results obtained with Ibex were false because of this prob

tmalsburg

How to correctly calculate worker compensation for Amazon Mechanical Turk

tl;dr: When calculating the average time it takes to complete a HIT, it may be more appropriate to use the geometric mean or the median instead of the arithmetic mean. You may otherwise spend considerably more money than necessary (in our case 50% more).

---

tmalsburg

(defun tmalsburg-rmarkdown-render ()
  "Compiles the current RMarkdown file to PDF and shows output of
the compiler process in a separate window."
  (interactive)
  (let* ((buf (get-buffer-create "*rmarkdown-render*"))
         (temp-window (or (get-buffer-window buf)
                          (split-window-below -10)))
         (command "Rscript -e 'library(rmarkdown); render(\"%s\", output_format=\"%s\")'")
         (command (format command (buffer-file-name) "pdf_document")))
    (set-window-buffer temp-window buf)

tmalsburg

This little project now lives in a GitHub repository: https://github.com/tmalsburg/binomialCRIs

tmalsburg

Foundations of Math

Agenda for today

tmalsburg

Compile this template by executing the following in a command shell:

  pdflatex test && biber test && pdflatex test && pdflatex test

This template uses biblatex and biber instead of good old BibTeX. The bibliography files (*.bib) can have the same format (although biblatex allows using some interesting extensions). However, the biblatex+biber combo is much more powerful than good-old BibTeX (e.g. support for multiple bibliographies in one document) and comes with great documentation.

Suggestions for improvements welcome.

tmalsburg

Predict vs simulate in lme4

For this investigation we are going to use the sleepdata data set from the lme4 package. Here is the head of the data frame:

tmalsburg

import nltk
from statistics import mean, stdev, median, mode

nltk.download('brown')
tokens = nltk.corpus.brown.tagged_words(tagset="universal")
types  = list(dict.fromkeys(tokens))

# Lengths of tokens / types but ignoring punctuation, numbers, and X
# which is mostly foreign words (German, French, Latin) but strangely
# also a small number of common English words: