Poisson Regression

Term Paper # 115607

Poisson Regression

An overview of poisson regression analysis and its application to an exploration of the relationship between adequacies of sleep and injuries sustained by children between 18 months and 4 years of age.

2,405 words () | 11 sources | APA | 2009 Philippines

Paper Summary:

This paper provides a brief description on regression models and how they share the same elements, the dependent variable, the independent variables and the error term. In particular, the paper focuses on what to do when the variable to be predicted is a count data and how the appropriate modeling technique to be used is poisson regression. Poisson regression assumes that the dependent variable Y comes from a poisson distribution. To demonstrate an application of the poisson regression the paper "Inadequate Sleep and Unintentional Injuries in Young Children" by Koulouglioti, C., Cole, R., and Kitzman is presented and analysed.

Outline:
Introduction
Basic Concepts
Generalized Linear Models
Poisson Regression
Model Fitting
Assessing Model Adequacy
Sample Article
Background
Objective
Dependent Variable
Independent Variables
Analysis and Results
Conclusion

From the Paper:

"There are cases when the dependent variable Y can take only several discreet values. When a model's objective is to predict a new business venture's success based on several factors, the dependent variable Y can only be any of the values 'Successful' or 'Not Successful'. In a similar fashion, if the model's objective is to predict the number of appliances that will be broken down while being shipped to a warehouse, it is not logical to have predicted values that are not count data. A value of 3.5, 1.03 or 4.2 will not make any sense. In this case the predicted values of the dependent variable to be given by the models should be constrained to non-negative integers."

Sample of Sources Used:

Draper, N.R. and Smith, H. 1998. Applied Regression Analysis, 3rd edn. New York, NY: John Wiley & Sons
Paulson, Daryl S. 2007. Handbook of regression and Modelling: applications for the clinical and pharmaceutical industries. New York: Taylor & Francis Group, LLC
Ross, Sheldon M. 2004. Introduction to Probability and Statistics for Engineers and Scientists, 3rd edn. New York: Elsevier Inc.
Ryan, Thomas P. 2007. Modern Engineering Statistics. Hoboken, New Jersey: John Wiley & Sons
Juran, J. M. and Godfrey. 1999. A. B. Juran's Quality Handbook, 5th edn. New York: Mc Graw-Hill