Generalized Linear Models and Extensions

Regular price €78.99
A01=James W. Hardin
A01=Joseph M. Hilbe
Age Group_Uncategorized
Age Group_Uncategorized
Author_James W. Hardin
Author_Joseph M. Hilbe
automatic-update
Binomial Response Models
Category1=Non-Fiction
Category=PBT
Category=PBUH
Continuous Response Models
COP=United States
Count Response Models
Delivery_Delivery within 10-20 working days
eq_isMigrated=2
Foundations of Generalized Linear Models
Language_English
Multinomial Response Models
PA=Available
Price_€50 to €100
PS=Active
softlaunch

Product details

  • ISBN 9781597182256
  • Weight: 1192g
  • Dimensions: 191 x 235mm
  • Publication Date: 27 Apr 2018
  • Publisher: Stata Press
  • Publication City/Country: US
  • Product Form: Paperback
  • Language: English
Delivery/Collection within 10-20 working days

Our Delivery Time Frames Explained
2-4 Working Days: Available in-stock

10-20 Working Days
: On Backorder

Will Deliver When Available
: On Pre-Order or Reprinting

We ship your order once all items have arrived at our warehouse and are processed. Need those 2-4 day shipping items sooner? Just place a separate order for them!

Generalized linear models (GLMs) extend linear regression to models with a non-Gaussian, or even discrete, response. GLM theory is predicated on the exponential family of distributions—a class so rich that it includes the commonly used logit, probit, and Poisson models. Although one can fit these models in Stata by using specialized commands (for example, logit for logit models), fitting them as GLMs with Stata’s glm command offers some advantages. For example, model diagnostics may be calculated and interpreted similarly regardless of the assumed distribution.

This text thoroughly covers GLMs, both theoretically and computationally, with an emphasis on Stata. The theory consists of showing how the various GLMs are special cases of the exponential family, showing general properties of this family of distributions, and showing the derivation of maximum likelihood (ML) estimators and standard errors. Hardin and Hilbe show how iteratively reweighted least squares, another method of parameter estimation, are a consequence of ML estimation using Fisher scoring.

James W. Hardin is a professor and the Biostatistics division head in the Department of Epidemiology and Biostatistics at the University of South Carolina. He is also the associate dean for Faculty Affairs and Curriculum of the Arnold School of Public Health at the University of South Carolina.

Joseph M. Hilbe was a professor emeritus at the University of Hawaii and an adjunct professor of sociology and statistics at Arizona State University.