Blog


Correlation is not causation

posted May 12, 2014, 11:42 AM by Rach   [ updated May 12, 2014, 11:43 AM ]

Yes please, part 2

posted Mar 27, 2014, 12:39 PM by Rach

Another amazing discovery in the world of data visualization: Wes Anderson-style plots

Time to graduate

posted Mar 27, 2014, 12:26 PM by Rach   [ updated Mar 27, 2014, 12:33 PM ]

A look at how much tuition costs have shot up compared to 30 years ago. Yikes. 

Couple that with the average jobseeker's 9 months of unemployment, and that leaves me with just enough money to buy a box of tissues and pint of ice cream.

The Great Language Game

posted Mar 21, 2014, 2:03 PM by Rach   [ updated Mar 21, 2014, 2:04 PM ]

Neat article about language confusion using 16 million guesses from the great language game. Poor Kannada.

Yes please

posted Mar 21, 2014, 11:43 AM by Rach

Thanks to this article, I just learned that Matlab has an xkcd visualization function. Haha. Yes please!

March Madness redone

posted Mar 20, 2014, 12:18 PM by Rach

Neat post on using stats to do your bracket. Let's see how far Nate Silver gets me this year. My usual against-the-odds choice is already out (Georgetown, whyyy) so Louisville? Why not.

surPrise

posted Feb 21, 2014, 5:37 AM by Rach   [ updated Feb 21, 2014, 3:56 PM ]

No p-hacking here! A good example of the complexities in data analysis:

"Critics also bemoan the way that P values can encourage muddled thinking. A prime example is their tendency to deflect attention from the actual size of an effect. Last year, for example, a study of more than 19,000 people showed8 that those who meet their spouses online are less likely to divorce (p < 0.002) and more likely to have high marital satisfaction (p < 0.001) than those who meet offline (see Nature http://doi.org/rcg; 2013). That might have sounded impressive, but the effects were actually tiny: meeting online nudged the divorce rate from 7.67% down to 5.96%, and barely budged happiness from 5.48 to 5.64 on a 7-point scale. To pounce on tiny P values and ignore the larger question is to fall prey to the “seductive certainty of significance”, says Geoff Cumming, an emeritus psychologist at La Trobe University in Melbourne, Australia. But significance is no indicator of practical relevance, he says: “We should be asking, 'How much of an effect is there?', not 'Is there an effect?'”

Another reason why I am wary of things like this for anything more than preliminary exploration.

Twice random, once mixed

posted Feb 11, 2014, 3:55 PM by Rach

Just came across this article, which very nicely describes the benefits of mixed models over ANOVA. Linguists, take note!

The kick-off

posted Feb 2, 2014, 12:47 PM by Rach   [ updated Feb 2, 2014, 12:52 PM ]

I know as my dissertation defense draw closer, I will field more and more questions along the lines of "why are you leaving academia?" and "you aren't applying to postdocs?!". 

While I have enjoyed my time in graduate school immensely, while I have learned more than I ever thought possible, while I am impressed with the acumen and devotion of my fellow researchers...I am ready to move onto the next challenge. Which, for me, lies outside of academia. 

I really urge everyone to peruse this interesting read. I think there is a whole lot that I was looking for in academia, and there is a whole lot I still haven't found. Hopefully I will find it elsewhere.

1-9 of 9