Professional References
Statistical Analysis Expertise
Samuel R. Friedman  supervisor at NDRI for a decade. I worked with Sam and his colleagues on several large grants to advise, develop and apply statistical data analysis techniques to the grant writing process. Specific data analysis techniques applied include: OLS regression, logistic regression, multinomial logistic regression, ordinal logistic regression, factor analysis, cluster analysis, hierarchical linear models, power analysis, box plots, strip plots, dot plots, mosaic plots, scatterplots. Together we published many peerreviewed articles.
Leslie Prichep  was my supervisor at BrainScope. I worked with Leslie to develop data analysis techniques to support here research. Careful application of logistic regression, discriminant analysis, genetic algorithms, box plots and classification trees helped distinguish people with various conditions on the basis of electroencephalographic data.
Anjali Sharma  At SUNY Downstate, some of my most involved work has been with Anjali analyzing data about epilepsy. In addition to logistic regression we used OLS regression and hierarchical linear models to support and advance Anjali's research.
Agnes Perenyi  Collegue at SUNY downstate who I worked with on research data about neonatology. I helped Agnes implement a combination of fundamental statistical analysis techniques as well as ANOVA and chisquare."
Featured Posts

[latexpage] In regression models of various kinds (e.g.

Regression refers to a collection of techniques for modeling one variable (the dependent variable or DV), as a...

This is a talk that I gave at NDRI. I also gave a version of this talk at Yale and at BrainScope

I will be giving a 4 hour course at SESUG in Savannah this fall. The course is titled: Lies, damn lies...

In this article I showed some problems with the average or arithmetic mean and in this one I discussed...

Sir Ronald Fisher famously said:
"To call in the statistician after the experiment is done may be...

In an earlier article, we looked at simple linear regression, which involves one independent variable (IV) and...

If you picture the data as a 2 x 2 crosstab, then quasicomplete separation occurs when one of the cells is...

Lately, across the statistical blogosphere, the repeating discussion of R vs. SAS has started up again. In...

When you have two numeric variables and are interested in the relationship between them, the basic statistical...

Cluster analysis is a set of methods for finding subjects (people, corporations, drugs, whatever) that "go...

In a previous article I looked at how to go wrong with the mean. Today, I will look at a set of alternative...