VB-Stan: Black-box black-box variational Bayes

February 18, 2015
By

Alp Kucukelbir, Rajesh Ranganath, Dave Blei, and I write: We describe an automatic variational inference method for approximating the posterior of differentiable probability models. Automatic means that the statistician only needs to define a model; the method forms a variational approximation, computes gradients using automatic differentiation and approximates expectations via Monte Carlo integration. Stochastic gradient […] The post VB-Stan: Black-box black-box variational Bayes appeared first on Statistical Modeling, Causal Inference,…

Read more »

An unsuccessful adaptation of a classic

February 18, 2015
By
An unsuccessful adaptation of a classic

Found this chart in Hemispheres magazine on board a United flight: A quick self-sufficiency test reveals the biggest shortcoming of this visual presentation. What would you guess is the difference in areas between the two white-ish sectors (pointing at 9...

Read more »

What’s in a Combine?

February 18, 2015
By
What’s in a Combine?

They sprint, they jump, they lift. Does any of it matter come draft day? Click through to read my take on the matter. Predicting NFL draft picks based on their combine results!

Read more »

Monitor the progress of a long-running SAS/IML program

February 18, 2015
By
Monitor the progress of a long-running SAS/IML program

When you have a long-running SAS/IML program, it is sometimes useful to be able to monitor the progress of the program. For example, suppose you need to computing statistics for 1,000 different data sets and each computation takes between 5 and 30 seconds. You might want to output a message […]

Read more »

Larry David (4) vs. Thomas Hobbes

February 17, 2015
By

Yesterday‘s winner is Chris Rock. “There’s math. And then everything else is debatable.” And now, for today, we have a misanthropists’ version of yesterday’s contest: the grumpy comedian battling it out with the consummate realist political philosopher. Nasty, brutish, and short, indeed. It’s a bit scary how appropriate this matchup is, considering they were all […] The post Larry David (4) vs. Thomas Hobbes appeared first on Statistical Modeling, Causal…

Read more »

Non-Existent Instruments

February 17, 2015
By
Non-Existent Instruments

Consider the following abstract for an econometrics paper:"The method of instrumental variables (IV) and the generalized method of moments (GMM), and their applications to the estimation of errors-in-variables and simultaneous equations models in econo...

Read more »

Bayesian survival analysis with horseshoe priors—in Stan!

February 17, 2015
By
Bayesian survival analysis with horseshoe priors—in Stan!

Tomi Peltola, Aki Havulinna, Veikko Salomaa, and Aki Vehtari write: This paper describes an application of Bayesian linear survival regression . . . We compare the Gaussian, Laplace and horseshoe shrinkage priors, and find that the last has the best predictive performance and shrinks strong predictors less than the others. . . . And here’s […] The post Bayesian survival analysis with horseshoe priors—in Stan! appeared first on Statistical Modeling,…

Read more »

Bayesian survival analysis with horseshoe priors—in Stan!

February 17, 2015
By
Bayesian survival analysis with horseshoe priors—in Stan!

Tomi Peltola, Aki Havulinna, Veikko Salomaa, and Aki Vehtari write: This paper describes an application of Bayesian linear survival regression . . . We compare the Gaussian, Laplace and horseshoe shrinkage priors, and find that the last has the best predictive performance and shrinks strong predictors less than the others. . . . And here’s […] The post Bayesian survival analysis with horseshoe priors—in Stan! appeared first on Statistical Modeling,…

Read more »

Reading Arduino data directly into R

February 17, 2015
By
Reading Arduino data directly into R

I have experimented with reading an Arduino signal into R in the past, using Rserve and Processing. Actually, it is much easier. I can read the output of my Arduino directly into R with the scan function. Here is my temperature sensor example again:And...

Read more »

R. A. Fisher: How an Outsider Revolutionized Statistics (Aris Spanos)

February 17, 2015
By
R. A. Fisher: How an Outsider Revolutionized Statistics (Aris Spanos)

In recognition of R.A. Fisher’s birthday…. ‘R. A. Fisher: How an Outsider Revolutionized Statistics’ by Aris Spanos Few statisticians will dispute that R. A. Fisher (February 17, 1890 – July 29, 1962) is the father of modern statistics; see Savage (1976), Rao (1992). Inspired by William Gosset’s (1908) paper on the Student’s t finite sampling […]

Read more »

R.A. Fisher: ‘Two New Properties of Mathematical Likelihood’: Just before breaking up (with N-P)

February 16, 2015
By
R.A. Fisher: ‘Two New Properties of Mathematical Likelihood’: Just before breaking up (with N-P)

In recognition of R.A. Fisher’s birthday tomorrow, I will post several entries on him. I find this (1934) paper to be intriguing –immediately before the conflicts with Neyman and Pearson erupted. It represents essentially the last time he could take their work at face value, without the professional animosities that almost entirely caused, rather than being caused by, the apparent […]

Read more »

Continuing the discussion on truncation, Bayesian convergence and testing of priors

February 16, 2015
By
Continuing the discussion on truncation, Bayesian convergence and testing of priors

My post “What’s wrong with taking (1 – β)/α, as a likelihood ratio comparing H0 and H1?” gave rise to a set of comments that were mostly off topic but interesting in their own right. Being too long to follow, I put what appears to be the last group of comments here, starting with Matloff’s query. […]

Read more »

Continuing the discussion on truncation, Bayesian convergence and testing of priors

February 16, 2015
By
Continuing the discussion on truncation, Bayesian convergence and testing of priors

My post “What’s wrong with taking (1 – β)/α, as a likelihood ratio comparing H0 and H1?” gave rise to a set of comments that were mostly off topic but interesting in their own right. Being too long to follow, I put what appears to be the last group of comments here, starting with Matloff’s query. […]

Read more »

Chris Rock (3) vs. Jean-Jacques Rousseau

February 16, 2015
By

At first I thought yesterday‘s bout would be hard to score. But, after reading all the comments, it was easy. Beauvoir, and it’s not even close. My reasoning isn’t based on any single comment, but rather that there was a lot more passion in the comments about Beauvoir, pro and con. I think it’s fair […] The post Chris Rock (3) vs. Jean-Jacques Rousseau appeared first on Statistical Modeling, Causal…

Read more »

The Econometric Game, 2015

February 16, 2015
By
The Econometric Game, 2015

If you're a grad. student with an interest in econometrics, you've probably heard about The Econometric Game. It's been covered before on this blog (e.g., here, last year).The 2015 Econometric Game is the sixteenth in the series, and it will take place...

Read more »

James Watson sez: Cancer cure is coming in minus 14 years!

February 16, 2015
By

From a recent news article by Laura Helmuth, I learned this amusing fact about DNA-discoverer James Watson: “he told a New York Times reporter 16 years ago that a researcher was ‘going to cure cancer in two years.'” Here’s the link to the NYT story, dated 3 May 1998: Within a year, if all goes […] The post James Watson sez: Cancer cure is coming in minus 14 years! appeared…

Read more »

On deck this week

February 16, 2015
By

Mon: James Watson sez: Cancer cure is coming in minus 14 years! Chris Rock (3) vs. Jean-Jacques Rousseau Tues: Bayesian survival analysis with horseshoe priors—in Stan! Larry David (4) vs. Thomas Hobbes Wed: VB-Stan: Black-box black-box variational Bayes Jesus (1) vs. Leo Tolstoy Thurs: Another example of why centering predictors can be good idea Mohandas […] The post On deck this week appeared first on Statistical Modeling, Causal Inference, and…

Read more »

Heroic Econometrics Teachers: Tom Rothenberg and Dennis Sargan

February 16, 2015
By

I'm not sure why this popped into my head just now. There have been many fine graduate econometrics teachers/mentors; their armies of well-trained students now populate top universities.  But two seem to me to have transcended the rest, achieving ...

Read more »

Friends don’t let friends concatenate results inside a loop

February 16, 2015
By
Friends don’t let friends concatenate results inside a loop

Friends have to look out for each other. Sometimes this can be slightly embarrassing. At lunch you might need to tell a friend that he has some tomato sauce on his chin. Or that she has a little spinach stuck between her teeth. Or you might need to tell your […]

Read more »

pacman 0.2.0: Initial CRAN Release

February 16, 2015
By
pacman 0.2.0: Initial CRAN Release

We’re please to announce the first CRAN release of pacman v. 0.2.0. pacman is the combined work of Dason Kurkiewicz & Tyler Rinker. pacman is an R package management tool that combines the functionality of base library related functions into intuitively … Continue reading →

Read more »

pacman 0.2.0: Initial CRAN Release

February 16, 2015
By
pacman 0.2.0: Initial CRAN Release

We’re please to announce the first CRAN release of pacman v. 0.2.0. pacman is the combined work of Dason Kurkiewicz & Tyler Rinker. pacman is an R package management tool that combines the functionality of base library related functions into intuitively … Continue reading →

Read more »

Stan Down Under

February 15, 2015
By
Stan Down Under

I (Bob, not Andrew) am in Australia until April 30. I’ll be giving some Stan-related and some data annotation talks, several of which have yet to be concretely scheduled. I’ll keep this page updated with what I’ll be up to. All of the talks other than summer school will be open to the public (the […] The post Stan Down Under appeared first on Statistical Modeling, Causal Inference, and Social…

Read more »

Testing for Multivariate Normality

February 15, 2015
By
Testing for Multivariate Normality

The assumption that multivariate data are (multivariate) normally distributed is central to many statistical techniques. The need to test the validity of this assumption is of paramount importance, and a number of tests are available.A recently release...

Read more »


Subscribe

Email:

  Subscribe