**M**y friends Luke Bornn, Natesh Pillai and Dawn Woodard just arXived along with Aaron Smith a short note on the convergence properties of ABC. When compared with acceptance-rejection or regular MCMC. Unsurprisingly, ABC does worse in both cases. What is central to this note is that ABC can be (re)interpreted as a pseudo-marginal method where the data comparison step acts like an unbiased estimator of the true ABC target (not of the original ABC target, mind!). From there, it is mostly an application of Christophe Andrieu’s and Matti Vihola’s results in this setup. The authors also argue that using a single pseudo-data simulation per parameter value is the optimal strategy (as compared with using several), when considering asymptotic variance. This makes sense in terms of simulating in a larger dimensional space but what of the cost of producing those pseudo-datasets against the cost of producing a new parameter? There are a few (rare) cases where the datasets are much cheaper to produce.

## Archive for ranking

## a pseudo-marginal perspective on the ABC algorithm

Posted in Mountains, pictures, Statistics, University life with tags ABC, ABC-MCMC, acceptance rate, Alps, asymptotics, Chamonix, MCMSki IV, pseudo-data, ranking on May 5, 2014 by xi'an## author rank

Posted in Statistics with tags Amazon, books, Gainesville, George Casella, Ithaca, ranking on October 11, 2012 by xi'an**G**ot the following email from Amazon:

Today we have added a new feature, Amazon Author Rank, the definitive list of best-selling authors on Amazon.com. This list makes it easy for readers to discover the best-selling authors on Amazon.com overall and within a selection of major genres. Your Amazon Author Rank is 44,881 in Print Books.

**I**t is a new feature so, with a very limited past horizon, this rank seems to be moving wildly! (For instance, it is now 36,776, just a few hours later.) But so are the individual book sales. Hence a clear lack of smoothing in the indicator.

**A**nother interesting feature of this Author Central facility is the display of US sales by district, Not only because it shows that New York and San Francisco are the cities where I sell the most books (great!) but also because it uses the notion of “combined areas”, aggregating “the copies sold in these sparsely populated areas in order to obscure any single retailer’s sales”. A good display of data protection (even though the level of aggregation sounds too high to me, resulting in “combined areas” being the 3rd highest sale area. And including Gainesville, Florida and Ithaca, New York, the two latest locations of George Casella, in this combination!

## Posts of the year

Posted in Books, R, Statistics, University life with tags blog statistics, book reviews, Julien Cornebise, Og, R, ranking, Ross Ihaka, top posts on August 31, 2011 by xi'an**L**ike last year, here are the most popular posts since last August:

- Home page 92,982
- In{s}a(ne)!! 6,803
- “simply start over and build something better” 5,834
- Julien on R shortcomings 2,373
- Parallel processing of independent Metropolis-Hastings algorithms 1,455
- Do we need an integrated Bayesian/likelihood inference? 1,361
- Coincidence in lotteries 1,256
- #2 blog for the statistics geek?! 863
- ABC model choice not to be trusted 814
- Sudoku via simulated annealing 706
- Bayes on the Beach 2010 [2] 704
- News about speeding R up 688
- Solution manual for Introducing Monte Carlo Methods with R 688
- R exam 617
- Bayesian p-values 607
- Monte Carlo Statistical Methods third edition 577
- Le Monde puzzle [49] 499
- The foundations of Statistics: a simulation-based approach 493
- The mistborn trilogy 492
- Lack of confidence in ABC model choice 487
- Solution manual to Bayesian Core on-line 481
- Bayes’ Theorem 459
- Julian Besag 1945-2010 452
- Millenium 1 [movie] 448
- ABC lectures [finale] 436

**N**o major surprise in this ranking: R related blogs keep the upper part, partly thanks to being syndicated on R-bloggers, partly thanks to the tribunes contributed by Ross Ihaka and Julien Cornebise, even though I am surprised a rather low-key Le Monde puzzle made it to the list (maybe because it became part of my latest R exam?). Controversial books reviews are great traffic generators, even though the review of The foundations of Statistics: a simulation-based approach was posted less than a month ago. At last, it is comforting to see two of our major research papers for the 2010-2011 period on the list: the Parallel processing of independent Metropolis-Hastings algorithms with Pierre and Murray, and the more controversial Lack of confidence in ABC model choice with Jean-Michel and Natesh (twice). The outlier in the list is undoubtedly Bayes on the Beach 2010 [2] which got undeserved traffic for pointing out to Surfers Paradise , a highly popular entry! On my side unscientific entries, Saunderson’s Mistborn and Larson’s Millenium, McCarthy’s Border trilogy missing the top list by three entries…

## Posts of the year

Posted in Books, Kids, Statistics, Travel with tags Central Park, Introducing Monte Carlo Methods with R, ranking, The Search for Certainty on August 13, 2010 by xi'an**H**ere are the top posts since last August, before the ‘Og goes on a semi-vacation regime. Even though my attempt at news with the pictures from the tornado in Central Park was rather successful, I am pleased to see that my pet project of illustrating simulated annealing on sudokus attracted more attention over the period!

- Home page 50,619
- Sudoku via simulated annealing 1,306
- Tornado in Central Park 998
- Solution manual to Bayesian Core on-line 953
- The Search for Certainty 827
- Top 15 all-timers? 716
- t-walk on the banana side 592
- Bayes vs. SAS 570
- New Le Monde puzzle 556
- Incoherent inference 547
- A ridiculous email 524
- Of black swans and bleak prospects 486
- About 448
- Bayesian p-values 420
- Introducing Monte Carlo Methods with R: 415
- Solution manual for Introducing Monte Carlo Methods with R 400
- t-walk on the wild side 394
- “Introducing Monte Carlo Methods with R” 376
- Bayes’ Theorem 359
- “Introducing Monte Carlo Methods with R” 358
- plagiarism exposed! 356
- Morning visit to The Louvre 352
- Rites of love and math 306
- On resolving the Savage-Dickey paradox 299
- Particle MCMC discussion 280

**M**aybe the most surprising item is the Morning visit to The Louvre as it is fairly mundane and does not bring much information, only impressions from our quick stroll through the museum… Less surprising is the relative success of the controversial posts like the criticisms of Black Swans and The Search for Certainty, or of Templeton’s PNAS attack against (Bayeian) inference. And a clear interest in Introducing Monte Carlo Methods with R!