We’re going to start by loading the following libraries. However, the “hits” in the logistic question can’t be understood without further conducting the Poisson regression. This is why logistic and Poisson regressions go together in research: there is a dichotomous outcome inherent in a Poisson distribution. Using our count variables from above, this could be a sample that contains individuals with and without heart disease: those without heart disease cause a disproportionate amount of zeros in the data and those with heart disease trail off in a tail to the right with increasing amounts of heart attacks. Sometimes two processes may be at work: one that determines whether or not an event happens at all and another that determines how many times the event happens when it does.
The Poisson distribution is unique in that its mean and its variance are equal. Poisson regression, also known as a log-linear model, is what you use when your outcome variable is a count (i.e., numeric, but not quite so wide in range as a continuous variable.) Examples of count variables in research include how many heart attacks or strokes one’s had, how many days in the past month one’s used, or, as in survival analysis, how many days from outbreak until infection.
1.2 Why would you do a Poisson regression?
0 kommentar(er)
