Traditionally what statistical test has been used for a single variable, two group design? Why is it not appropriate for multiple groups or multiple variables?
What will be an ideal response?
The Student's t-test has traditionally been used for comparing two groups. It is not appropriate for multiple groups or multiple variables because the probability of a Type I error (rejecting the null hypothesis when you shouldn't) increases with each t-test you do; if you do multiple tests, you are more likely to reject the null when you shouldn't.
You might also like to view...
A majority of first-year college students are liberal or far left
Indicate whether this statement is true or false?
A law passed by Congress and the adoption of a regulation by an agency are examples of which of the following?
a. interest groups b. red tape c. public policies d. public opinion
Payroll tax is withheld from which of the following?
A. an employee's wages B. an employer's revenues C. the state government's savings D. the federal government's investments
Suppose you wanted to argue that the Supreme Court should have the right to exercise the power of judicial review. Which of these statements would provide the support for this thesis?
a. The use of judicial review opens up the Constitution to multiple and potentially conflicting interpretations. b. Trial courts cannot carry out their basic role in the legal system without the power of judicial review. c. The U.S. Constitution does not explicitly state that federal courts cannot exercise the power of judicial review. d. Without the power of judicial review, the Court would not be able to play much of a role in the system of checks and balances.