Publications by xi'an
Custom Amazon EC2 config for Rstudio
IntroductionThis post is a work in progress building on the previous post. It’s my attempt to simultaneously learn Amazon’s AWS tools and set up R and Rstudio Server on a customized “cloud” instance. I look forward to testing some R jobs that have large memory requirements or are very parallelizable in the future. To start, I followed ...
3979 sym Python (1282 sym/2 pcs)
ABC in Roma [R lab #1]
Here are the R codes of the R labs organised by Serena Arima in supplement of my lectures. This is quite impressive and helpful to the students, as illustrated by the first example below (using the abc software). ### Example 1: Conjugate model (Normal-Inverse Gamma) ### y1,y2,...,yn ~N(mu,sigma2) ### mu|sigma2 ~ N(0,sigma2), sigma2 ~IG(1/2,1/2) ...
892 sym R (1692 sym/1 pcs) 16 img
ABC in Roma [R lab #2]
Here are the R codes of the second R lab organised by Serena Arima in supplement of my lectures (now completed!). This morning I covered ABC model choice and the following example is the benchmark used in the course (and in the paper) about the impact of summary statistics. (Warning! It takes a while to run…) n.iter=10000 n=c(10,100,1000) n.sim...
988 sym Python (4021 sym/1 pcs) 16 img
di Roma
It has been a wonderful week in Roma, a mix of pleasant work and enjoyable free-time! I gave the ABC advanced course for the second time in a month so it did not require much in terms of preparation and there was a good sized audience with attentive (if too silent!) students and friends as well. The addition of the R labs was a clear bonus and I ...
1886 sym 22 img
IS vs. self-normalised IS
I was grading my Master projects this morning and came upon this graph: which compares the variability of an importance-sampling estimator versus its self-normalised alternative… This is an interesting case in that self-normalisation does considerably degrade the quality of the approximation in that setting. In other cases, self-normalisation m...
1576 sym Python (645 sym/1 pcs) 20 img
simulated annealing for Sudokus [2]
On Tuesday, Eric Chi and Kenneth Lange arXived a paper on a comparison of numerical techniques for solving sudokus. (The very Kenneth Lange who wrote this fantastic book on numerical analysis.) One of these techniques is the simulated annealing approach I had played with a long while ago. They seem to use the same penalisation function as mine,...
2184 sym R (1243 sym/1 pcs) 18 img
What are the distributions on the positive k-dimensional quadrant with parametrizable covariance matrix? (bis)
Wondering about the question I posted on Friday (on StackExchange, no satisfactory answer so far!), I looked further at the special case of the gamma distribution I suggested at the end. Starting from the moment conditions, and the solution is (hopefully) given by the system The resolution of this system obviously imposes conditions on those m...
759 sym 10 img
What are the distributions on the positive k-dimensional quadrant with parametrizable covariance matrix? (solved)
Paulo (from the Instituto de Matemática e Estatística, Universidade de São Paulo, Brazil) has posted an answer to my earlier question both as a comment on the ‘Og and as a solution on StackOverflow (with a much more readable LaTeX output). His solution is based on the observation that the multidimensional log-normal distribution still allows...
1530 sym R (523 sym/1 pcs) 18 img
[not] Le Monde puzzle (solution)
Following the question on dinner table permutations on StackExchange (mathematics) and the reply that the right number was six, provided by hardmath, I was looking for a constructive solution how to build the resolvable 2-(20,5,1) covering. A few hours later. hardmath again came up with an answer, found in the paper Equitable Resolvable Covering...
1334 sym R (1148 sym/2 pcs) 16 img
mad statistic
In the motivating toy example to our ABC model choice paper, we compare summary statistics, mean, median, variance, and… median absolute deviation (mad). The latest is the only one able to discriminate between our normal and Laplace models (as now discussed on Cross Validated!). When rerunning simulations to produce nicer graphical outcomes (fo...
1291 sym R (222 sym/1 pcs) 18 img