Feeling Blue
In statistics, the acronym BLUE stands for Best Linear Unbiased Estimator. For a while I didn’t know this and wondered why the stats paper I was reading kept using capitalized colors to describe a regression.
A blog about programming and math
In statistics, the acronym BLUE stands for Best Linear Unbiased Estimator. For a while I didn’t know this and wondered why the stats paper I was reading kept using capitalized colors to describe a regression.
Despite what academics might have you believe, science and especially social science has gotten increasingly political these days. It’s a pretty big problem that throws into question the validity of social science results.
Before you continue reading below, take a guess which math class(es) I am most often requested to tutor. No peeking!
I’m trying to come up with a cute, terse way to illustrate the phenomenon of conditioning on a collider and I’m actually having a hard time summarizing it. Mostly because I just read a rigorous academic paper discussing all the insiduous details of colliders, and I absolutely love rigor and details and want to tell you all about it! But I’ll suppress the urge. This is the cliff notes version. Enjoy.
If two random variables are independent, can they be correlated? If another two random variables have zero correlation, can they be dependent?
Languages may come and go, but theory is forever. Most of the definitions are copied from Wikipedia.
My height is in the 5th percentile for women my age. Which percentile do you think I’m in for weight?
a. 5th percentile
b. 10th percentile, so I should lose 5 pounds to get down to the 5th
c. 10th percentile, which is probably close to average for my height
d. A lady never tells
Generalizing to higher dimensions is one area where mathematicians have usually excelled. While others fear what they cannot visualize, mathematicians bravely add another coordinate or change a two to a three and BOOM!
I’m reading a book called Clean Code and it is fantastic.
I asked a friend to explain the difference between frequentism and bayesianism and he directed me to this very educational work of art:
For any continuous random variable X, if we apply the cumulative distribution function (cdf) of X to X itself we obtain a uniform random variable on the interval [0,1].
Every Simpson’s paradox involves at least three variables: