similar to: possible changed organization of help files in 1.5.0?

My search site, http://finzi.psych.upenn.edu, has had several problems recently, all my fault, for which I apologize. But it now seems to be running reliably, on a new computer that is much faster than the old one. It uses htdig to permit search of the Rhelp mailing list, R documents, R functions, and various combinations of these. Search has several options, including Boolean search (with AND,

First, my site will be down December 27-28 because of a network upgrade at Penn. It will also be down at least one day before that, while I upgrade the operating system. (And another day some time in January because of a planned power outage.) Second, I have replaced the search engine in my R site: http://finzi.psych.upenn.edu/ I am now using Namazu instead of HtDig. The direct link to the

Two improvements at http://finzi.psych.upenn.edu 1. I have added all packages from CRAN, including contributed packages, so you can look for a package that does X. Check out the "Limit search to" box on the right, as well as "Sort by". 2. The new (beta) version of htdig (which I use) will search by phrases as well as words (so long as the phrases are made of words, it

Unfortunately, I am unable to get this search site working again. (The message below explains why I had to rebuild it.) The computer worked for the better part of a day downloading and installing all the help files from all CRAN packages. Somehow it failed to get the vignettes this time. But I pushed ahead and ran the part of namazu that makes the search indices: mknmz. And you can see the

For my R page at http://finzi.psych.upenn.edu/ (also the target of RSiteSearch()), I'm trying to find a way to get the html versions of the help pages without actually installing packages. This will allow me to include packages that don't install. And it will also vastly speed up the monthly update, and make it easier to replicate everything in case of disaster. I have made a modified

I've made a few changes in the indices in my R search site. http://finzi.psych.upenn.edu is the general URL, and RSiteSearch takes you to http://finzi.psych.upenn.edu/search.html, which is equivalent to http://finzi.psych.upenn.edu/nmz.html. The main change is that I have eliminated "Previous message" and "Next message" from each page. (I still have "Next in

The Goodman/Kruskal gamma is a nice descriptive rank-order correlation statistic, often used in psychology. It is nice because it is easy to understand. It takes all pairs of values of each variable and asks whether they are congruent (S+ is the number in the same order for both variables) or discordant (S-, opposite ranking). The statistic is (S+ - S-)/(S+ + S-). It is like tau except for the

Does anyone know how to read a SYSTAT .syd file on Linux? (Splus 6 does it, but it is easier to find a Windows box with Systat than to download their demo. I'm wondering if there is a better way than either of these options.) Jon -- Jonathan Baron, Professor of Psychology, University of Pennsylvania Home page: http://www.sas.upenn.edu/~baron R search page:

Inspired by the functions that Barry Rawlingson and Dave Forrest posted for searching Rwiki and R-help archive, I've made up a function that does the search on Prof. Baron's site (Thanks to Prof. Baron's help on setting up the query string!): RSiteSearch <- function(string, restrict="Rhelp", format="long", sortby="score",

I have always avoided missing data by keeping my distance from the real world. But I have a student who is doing a study of real patients. We're trying to test regression models using multiple imputation. We did the following (roughly): f <- aregImpute(~ [list of 32 variables, separated by + signs], n.impute=20, defaultLinear=T, data=t1) # I read that 20 is better than the default of

It used to be that, whenever I added or updated a new package, the file /usr/lib/R/doc/html/packages.html would be updated (on Linux). Now I find that this does not happen anymore. So I found this function make.packages.html, which seems to do what I think should be done automatically. But it puts its output in a file in /tmp/..., which I then have to move, in an extra step, to where it should

On 9/8/2016 5:01 AM, Jonathan Baron wrote: > OK. It is sort of fixed and sort of works. > > We'll keep it for now, but this is not going to work forever. When > namazu fails completely I will not have the time to install a new > search engine. > > One option is to use google. For a site like this, I think they will > want some money, but I'm not sure, and I do not

The RPM for Fedora Core 2 seems to work just fine on Core 3. (The graphics window got smaller, but I'm sure there is a setting for that.) Jon -- Jonathan Baron, Professor of Psychology, University of Pennsylvania Home page: http://www.sas.upenn.edu/~baron R search page: http://finzi.psych.upenn.edu/

The RPM for Fedora Core 2 seems to work just fine on Core 3. (The graphics window got smaller, but I'm sure there is a setting for that.) Jon -- Jonathan Baron, Professor of Psychology, University of Pennsylvania Home page: http://www.sas.upenn.edu/~baron R search page: http://finzi.psych.upenn.edu/

I'd like to generate 00Index.html for a bunch of libraries for my R search page. I have now almost all the html help files for individual functions, even for packages that won't install on my computer (e.g., because they are specific to Windows). I made these using Rdconv. But that won't make the 00Index file, and neither will Rdindex, which makes a text file. I'm probably

Any hints on how to do a significance test using gee? Is the "robust z" the thing to use? There is apparently another implementation of gee called yags (http://www.biostat.harvard.edu/~carey), but I can't figure out how to install it. I think it does significance tests. -- Jonathan Baron, Professor of Psychology, University of Pennsylvania Home page:

The search site at http://finzi.psych.upenn.edu/ is back up. This allows you to search mailing list archives, R functions from most packages, and documents. You can also use the R function RSiteSearch() in R itself, which opens the results in your browser. I'm sorry the site was down for so long. I plan to work out a system that will allow faster restoration if this happens again (mutual

Yuelin Li and I have made some revisions in our introductory document, "Notes on the use of R for psychology experiments and questionnaires," which is still available through my R page (below) in html or pdf. We fixed typos. We updated and organized the list of commands. ("Re"-organized isn't quite right.) We made a few other additions throughout. And we revised the

For maintaining my R search page at http://finzi.psych.upenn.edu (also used for RSiteSearch(), I have been extracting only the html help pages and the vignettes from most packages. (Many will not compile on Linux. And, more generally, this saves wear and tear on the computer and me.) I wrote a version of the old INSTALL script that does this. I removed various parts of it, not fully

I would like to impute missing data in a set of correlated variables (columns of a matrix). It looks like transcan() from Hmisc is roughly what I want. It says, "transcan automatically transforms continuous and categorical variables to have maximum correlation with the best linear combination of the other variables." And, "By default, transcan imputes NAs with "best