In a conversational tone, Regression & Linear Modeling provides conceptual, user-friendly coverage of the generalized linear model (GLM). Readers will become familiar with applications of ordinary least squares (OLS) regression, binary and multinomial logistic regression, ordinal regression, Poisson regression, and loglinear models. The author returns to certain themes throughout the text, such as testing assumptions, examining data quality, and, where appropriate, nonlinear and non-additive effects modeled within different types of linear models.

Poisson Models: Low-Frequency Count Data as Dependent Variables

Advance Organizer

Count variables, particularly counts of relatively infrequent events, represent a different category of data that we have not fully explored to this point. Count data are often gathered in the social and behavioral sciences (e.g., how many cigarettes were smoked by adolescents during a day, how many times a student was held back a grade, or how many depressive symptoms were experienced in a given period). In general, count data can be analyzed via ordinary least squares (OLS) regression as long as the assumptions of OLS regression are met. When counts of things represent qualitatively different situations, multinomial regression is an inefficient but appropriate method of analysis. With a particular type of count data, in ...

  • Loading...
locked icon

Sign in to access this content

Get a 30 day FREE TRIAL

  • Watch videos from a variety of sources bringing classroom topics to life
  • Read modern, diverse business cases
  • Explore hundreds of books and reference titles