Web services
Blog categories
Top blog posts
Stats
- 17,128 hits
Pseudoreplication is a serious and often neglected problem in many statistical analyses. Hurlbert defined in 1984 (1) pseudoreplication as the “use of inferential statistics to test for treatment effects with data from experiments where either treatments are not replicated (though samples maybe) or replicates are not statistically independent”. Similar problems occur in clinical research, for [...]
It is well known that results generated by repeated hypothesis testing are less reliable than indicated by the significance level. A common method to adjust the p-value for the multiplicity effects is called the Bonferroni method. It consists simply in dividing the nominal significance level by the number of tests performed. This protects the type-1 [...]
As a statistics student during the 1970′s and independent consultant during the 1990′s I worked with several different software packages, mostly SPSS, SAS, BMDP, and GLIM. SPSS is probably the package that has been mot successful in terms of number of academic licenses. However, I personally stopped using it more than 10 years ago. Both [...]
R can be installed with Ubuntu 11.10 Oneiric Ocelot the same way as with Ubuntu 11.04 Natty Narwhal, see here.
I installed Stata v12 with Ubuntu 11.10 the same way as with Ubuntu 11.04, see this link. In brief, two libraries are missing, libgtksourceview and libgnomeprint. Link to libgtksourceview and install libgnomeprint (before or after installing Stata) by opening a terminal window and running: sudo ln -s /usr/lib/libgtksourceview-2.0.so.0 /usr/lib/libgtksourceview-1.0.so.0 sudo apt-get install libgnomeprint2.2-0
Recent comments