casallas

\usepackage{stringstrings} % \capitalize, \caselower
\newcommand{\sentencecase}[1]{\caselower[e]{#1}\capitalize{\thestring}}

casallas

To install

1. Install jags: in the terminal using homebrew brew install jags
2. Install rjags: in R

install.packages("rjags")
library(rjags)

Potential issues

casallas

Writing

Jones, Simon. How to write a great research paper: Seven simple suggestions. Great talk, mostly focused on CS, but applicable in other disciplines. https://www.youtube.com/watch?v=g3dkRsTqdDA

Goodson, Patricia. "Becoming an Academic Writer 50 Exercises for Paced, Productive, and Powerful Writing". General (e.g. get in the habit of writing) and concrete (i.e. per section) exercises to become a better writer. Additional book resources (writing log, article template). http://www.sagepub.com/goodson/study/resources.htm

Silvia, Paul. "How to write a lot"

Strunk, William. Elements of Style. Ithaca, N.Y.: Priv. print. [Geneva, N.Y.: Press of W.P. Humphrey], 1918; Bartleby.com, 1999. www.bartleby.com/141/. [Date of Printout].

casallas

Package	Ordinal	Multinomial	Partial proportional odds	Scale Effects	Random Effects
nnet	no	multinom	N/A	N/A	No
MASS	polr	No	No	No	No
ordinal	clm/clm2	all X's in nominal (may not converge)	offending X's in nominal	via scale	clmm/clmm2
VGAM	yes	?	?	?	No
MCMCglmm	yes	?	?	?	?
Mixcat	yes	?	?		npmlt
mlogit	?	mlogit	N/A	N/

casallas

These tricks require BibTool, which can be installed using homebrew.

To extract only the used fields call bibtool -x on a .aux file, e.g.

bibtool -x doc.aux -o output.bib

To delete fields that you don't want to share, e.g. notes and file locations,

bibtool -- "delete.field {annote}" -i input.bib -o output.bib

casallas

NHST

• Descriptions and myths: http://yatani.jp/HCIstats/NHST
• Statistical significance
  • Marginal significance: http://andrewgelman.com/2013/11/06/marginally-significant/
  • Gelman: p-values and multiple comparisons http://www.slate.com/articles/health_and_science/science/2013/07/statistics_and_psychology_multiple_comparisons_give_spurious_results.single.html
  • Gelman: vs. Bayesian inference http://andrewgelman.com/2013/10/29/talk-amsterdam-tomorrow-wed-29-oct-can-use-bayesian-methods-resolve-current-crisis-statistically-significant-research-findings-dont-hold/
  • Gelman. (2013) The problem with p-values is how they're used. http://www.stat.columbia.edu/~gelman/research/published/murtaugh2.pdf
    • (note that Gelman says that the same problem can be found on the usage of AIC and CIs). Some background on this article can be found in this blog post
  • Dance of the p-values https://www.youtube.com/watch?v=ez4DgdurRPg

casallas

I found this method http://www.r-bloggers.com/a-quick-way-to-do-row-repeat-and-col-repeat-rep-row-rep-col/

rep.row <- function(x, n){
   matrix(rep(x, each = n), nrow = n)
}

And it seemed sensible if the matrices are stored by column major, however, it seems like filling by rows is quicker

casallas

lmm

Assumptions

Code based on: http://pages.stat.wisc.edu/~fyang/stat572/disc9.R

Homoscedasticity

# checking that e_i all have the same variance:
gsame_var <- function(flmer){

casallas

Mavericks

gnutar

gnutar is no longer shipped with Mavericks, this may cause some issues, e.g. when running R devtools.Solution, based on this blogpost:

brew install gnu-tar
cd /usr/bin
sudo ln -s  `brew --prefix gnu-tar`/libexec/gnubin/tar /usr/bin/gnutar

casallas

This is introduced in Ch. ? from Gelman and Hill (2007). The following presentation offers some insight on that (and in general a tutorial for mixed-effects models) Slides: http://madere.biol.mcgill.ca/cchivers/rstats/linear_mixed_effects/Multilevel%20Models%20in%20R.pdf Code, data, ...: https://sites.google.com/site/mcgillbgsa/workshops/mixed-effects