Multivariate Analysis: Tests to Evaluate Relationships

Autor: James E. De Muth
Rok vydání: 2019
Předmět:
Zdroj: Practical Statistics for Pharmaceutical Analysis ISBN: 9783030339883
DOI: 10.1007/978-3-030-33989-0_6
Popis: Sometimes a researcher wishes to determine if variables are associated with each other. If one variable increases, what is the effect on a second variable? This chapter explores inferential statistical tests that evaluate the relationship between two or more variables. The tests will determine the strength of the relationship and if the relationship is strong enough to show statistical significance. Selection of the test will depend on whether the variables are continuous or discrete. For continuous variables, tests covered in this chapter include the correlation, linear regression, multiple regression, and logistic regression. For discrete variables, chi square and related tests are discussed including tests for goodness-of-fit and independence. Additional tests related to chi square are introduced in the chapter. Minitab applications for evaluating the strength of these relationships are presented.
Databáze: OpenAIRE