Acknowledgments
Download 3.57 Mb.
|
This was the three-category case. However, this case can be generalized into a multiple category case. Suppose that you have a categorical variable with n possible categories you wish to incorporate in the multiple regression model. Thus, it would entail creating  dummy variables. Consequently, adding only one categorical variable alone can add numerous predictors to a model [2].
CHAPTER 3 DISTRIBUTIONS When analyzing a set of data it is essential to estimate the underlying distribution. Many of the tests and methods assume that the data has a normal underlying distribution. However, there are instances when this is not always the case. There are numerous different kinds of distributions that can be used to describe the particular data set. A few are Normal, Hypergeometric, Poisson, Gamma, Beta, Multinomial, and Chi-Square Distributions. Each distribution must be handled with various methods [1]. NORMAL DISTRIBUTION Since many of the measurements of variables are approximately normally distributed, the normal distribution is one of the most important distributions in statistical analysis. A random variable, x, is normally distributed if its corresponding probability density function is defined as  ,  ,
Download 3.57 Mb. Share with your friends:
|