"Anova makes the assumption that each level of a categorical variable has a normal distribution for the response variable with equal variances. Why notoriously robust, I would look at the data on a trellis-style graph before doing an ANOVA.…"
"Oldies but Goodies
The New S Language, 1988. Richard Becker, John Chambers, Allan Wilks
good if you need the origins of the S/R world
Understanding Robust and Exploratory Data Analysis, 1983
David Hoaglin, Frederick Mosteller,…"
"If you are not willing to do it via key words or phrases, you could construct a "Spam" filter by training it on the most important documents. You would then come up with a score, and your email program would need to recognize it and sort…"
Are there algorithms or techniques for scoring email besides key word filters? I found myself talking to managers who claim they get hundreds of email a day from the field. Is there any way to create threads that push a high-priority email above a bulk or unimportant one?See More
"As Matt states below, Generalized Linear Model techniques transform a response into a continuous range, so the response and coefficients on the right side look like a linear regression model--a linear combination of coefficients multiplied by the…"
We are talking about models that fit a survival response with an assumed hazard function and a set of covariates. I thought this was parametric survival analysis. Since there is only one response, event duration, not a vector it isn't a multivariate model. I don't want to make a big deal about this but it seems like, new, inappropriate, nomenclature.
"Some federal jobs may allow green card holders. I know California is having problems but you could try state jobs since you are in Sacramento. Also there are probably a lot of quasi--governmental research groups in that area. If you can leave…"
Owner, Direct Effects. LLC. I launched the business in 2006. My recent area of expertise is laboratory and clinical data analysis for consumer products and pharmaceuticals. I have also worked in survey research and response analytics. I am advanced SAS user and working knowledge of other software. Most importantly I am good at communicating quantitative concepts and their impact.
I hold a Masters in Statistics from Rutgers and a B.A. from Cornell.