In this 3-part video series, Jarlath Quinn introduces the fundamentals of Poisson Regression and shows how to run the procedure and interpret the output in IBM SPSS Statistics. Poisson Regression is often used with data that records counts, such as the number of events occurring within a fixed period. Examples include predicting the frequency of traffic accidents at an intersection based on factors like weather conditions and time of day or the hourly number of customers contacting a helpline based on the day of the week and recent product sales. Poisson regression can also be used to predict rates, such as the rate of disease incidence in different populations. In the video series Jarlath discusses:
- The properties of the Poisson Distribution
- Running Poisson Regression and making sense of the results
- Modelling mortality in a population based on age group and tobacco usage
- Comparing Poisson Regression results to those obtained by alternative methods