Publications by Wingfeet
Stone Flakes V, networks again
Last week I tried pcalg. This week deal (Learning Bayesian Networks with Mixed Variables). The aim n this post I want to try something new, a causal graphical model. The aim here is just as much to get myself a feel what these things do as to understand how the stone flakes data fit together. DataData are stone flakes data which I analyzed prev...
3838 sym 10 img
odfweave setup and counting logicals
Two short items in this blogpost. Since it was not obvious how to run odfWeave() in my particular setup, the call I am using. Then there were several people crosstabulating logical vectors, so I wanted to play along, 80 times faster than table().odfWeaveMy particular setup consists of R, 7-zip, libreoffice. Somehow they don’t 100% p...
4040 sym
Guns are cool – time effects
September last year I made a post using the shootingtracker data. It is attempted in shootingtracker to register all shootings with at least four victims, be they wounded or dead. The data starts January 1st 2013, which means that by now the amount of data has almost doubled. This surely is a dataset where I hope the makers find le...
6923 sym 10 img
Guns are Cool – States
Last week I looked at time effects of the shootingtracker database. This week I will look at the states. Some (smaller) states never made it on the database. Other states, far too frequently. The worst of these California. After correcting for population size, Washington DC with 0.8 shootings per year per 100000 inhabitants sticks out. Subsequent...
12432 sym 4 img
Guns are Cool – Differences between states
Last week my blog showed that there are differences between states in the shootingtracker database. This week it is attempted to understand why states are different. A number of variables were extracted from a few sources, among which gun laws, % gun owners and a few more general variables. It appeared that among the examined variables, % highsc...
8966 sym 4 img
Guns are cool – Regions
This was supposed to be a post in which General Social Surveys (GSS) data were used to understand a bit more about the causation of differences between states. Thus it was to give additioanl insight than my previous post; Guns are Cool – Differences between states. Unfortunately, that did not work so good, and it ended as a kind of...
6779 sym 4 img
Quicksort speed, just in time compiling and vectorizing
I was reading the Julia documentation the other day. They do speed comparisons to other languages. Obviously R does not come out very well. The R code for quicksort is here and I noticed it was not vectorized at all. So I wondered if it could be improved. A quick check on wikipedia showed that the algorithm displayed by wikipedia is ...
9053 sym 8 img
JAGS and Stan
During the last year I have been running some estimations in both JAGS and Stan. In that period I have seen one example where JAGS could not get me decent samples (in the sense of low Rhat and high number of effective samples) but that was data which I could not blog about. When two weeks ago I had a problem where part of my model did...
19871 sym 4 img
Beta binomial revisited
I got some comments on my priors of last week’s post where better priors were proposed. Hence this week’s post looks at them. After some minor adaptations, since I have nine beta parameters and beta needs to be fairly high, I can conclude that these priors provide significant improvements. Especially the model which has p(alpha,be...
12120 sym
Mapping products in a space
I have read about people doing a Bayesian PCA at some points and always wondered how that would work. Then, at some point I thought of a way to do so. As ideas evolved my interest became not PCA as such, but rather in a prefmap. As a first step in that this post contains the mapping from a sensory space to a two dimensional space. For...
5416 sym 8 img