3,054 reputation
824
bio website dataorigami.net
location Ottawa
age
visits member for 2 years, 2 months
seen 7 hours ago

ex-quant doing data @shopify. We're hiring data analysts, scientists and statisticians! Screencaster at www.dataorigami.net


Aug
27
awarded  Taxonomist
Aug
4
comment Name for the Bayesian posterior probability that a regression coefficient is larger than zero
@Zen yes I was too hasty - you are correct.
Aug
3
comment Name for the Bayesian posterior probability that a regression coefficient is larger than zero
Bayesian one-sided p-value is the best choice. Alternatively, you can give human-readable context (I'm assuming this is for a report or article?): the posterior probability the coefficient is greater than 0 is... - no need for potentially misleading names
Jul
25
reviewed Approve suggested edit on Estimation of regression with autocorrelated errors
Jul
13
comment Plain english explanation of the Rayleigh distribution?
I think your second example, with the hazard rate, is terrific and something I did not know
Jul
8
answered How to prepare interactions of categorical variables in scikit-learn?
Jul
2
awarded  Curious
Jun
29
awarded  Nice Question
Jun
21
reviewed Approve suggested edit on If X and Y are correlated, but Y and Z are independent, is X and Z always independent?
Jun
11
accepted Percentile Loss Functions
Jun
11
comment Percentile Loss Functions
You've proved that pictures are worth 1000 words. Thanks @whuber =)
Jun
11
comment Percentile Loss Functions
Thanks, @Matthew, this is a great find. I like balancing out interpretation
Jun
11
asked Percentile Loss Functions
Jun
8
awarded  Yearling
Jun
8
awarded  Nice Answer
Jun
8
revised Survival Analysis tools in Python
added 19 characters in body
Jun
7
reviewed Approve suggested edit on What are the regularity conditions for Likelihood Ratio test
Jun
7
awarded  Revival
Jun
4
comment Metropolis Random Walk Algorithm in Python
This is a great, short article on this subject: darrenjw.wordpress.com/2012/06/04/…
Jun
1
comment MCMC Modelling - can this even be solved?
Of course: you can make C a pymc stochastic variable: C = pm.Beta('C', some_alpha, some_beta). The implication of doing this would be wider posteriors for N_T.