TJ Mahr tjmahr

Correlation is not causation (???)
No causation without manipulation. (Holland)
All models are wrong, some are useful. (Box)
Statistics is the science of uncertainty. (arguably Tukey)
Statistics is the science of learning from experience, especially experience that arrives a little bit at a time. (Efron)

If you were to give recommendations to your "little brother/sister" on things that they need to do to become a data scientist, what would those things be?

I think the "Data Science Venn Diagram" (http://drewconway.com/zia/2013/3/26/the-data-science-venn-diagram) is a great place to start. You need three things to be a good data scientist:

Statistical knowledge
Programming/hacking skills
Domain expertise

	# estimate covariance matrix with regression
	library(GGMnonreg)

	p = 20

	pcors = GGMnonreg::gen_net(p = p)

	y = MASS::mvrnorm(n = 500,
	mu = rep(0, p),
	Sigma = pcors$cors)

	---
	title: "Sympy Engine"
	output: html_notebook
	editor_options:
	chunk_output_type: inline
	---

	Assuming the "sympy" knitr engine has been registered:

	```{sympy, results='asis'}

	Mute these words in your settings here: https://twitter.com/settings/muted_keywords

	ActivityTweet
	generic_activity_highlights
	generic_activity_momentsbreaking
	RankedOrganicTweet
	suggest_activity
	suggest_activity_feed
	suggest_activity_highlights
	suggest_activity_tweet

	functions{
	// GP: computes noiseless Gaussian Process
	vector GP(real volatility, real amplitude, vector normal01, int n_x, real[] x ) {
	matrix[n_x,n_x] cov_mat ;
	real amplitude_sq_plus_jitter ;
	amplitude_sq_plus_jitter = amplitude^2 + 1e-6 ;
	cov_mat = cov_exp_quad(x, amplitude, 1/volatility) ;
	for(i in 1:n_x){
	cov_mat[i,i] = amplitude_sq_plus_jitter ;
	}

	// On the Last.FM website go to the page which lists the tracks that you have loved.
	// Open Chrome DevTools (or Firefox or any modern browser that has a built in Javacript Console)
	// and run the following command.
	// This basically clicks on all the delete buttons on the page and reloads the page.
	jQuery('.love-button--loved').each(function(_, b) {
	b.click();
	});
	location.reload();


	# Some fake data

	library(dplyr); library(rstan)

	# Write out the data generation with known parameters

	# Set the number of individuals
	n_ind <- 50

	.Rproj.user
	.Rhistory
	.RData
	*.Rproj
	*.html

TJ Mahr tjmahr

Statistical knowledge