Hypothesis Testing Flashcards
What is the purpose of a chi-square test of independence?
To find out if one categorical variable is independent of another categorical variable.
For example: Is race and force used independent?
When do you use a chi-square goodness of fit test?
When you have one categorical variable and you want to test a hypothesis about its distribution.
Examples: Is the manufacturer’s claim about the distribution of M & M colors true?
Is the die fair?
When do you use a t-test?
When you have two groups and you want to compare the population means.
For example: Do people taking the new drug have lower blood pressure than people who take the old drug?
What is the null hypothesis for a chi-square test of independence?
The variables are independent.
What is the alternative hypothesis for a chi-square test of independence?
The variables are not independent.
How do you calculate the degrees of freedom for a chi square test of independence? For example:
df=(#Rows - 1) (#Columns-1)
How do you calculate the expected values from a contingency table? For example:
(Row total * Column Total)/Grand Total
What is the null hypothesis for a t-test for two means?
What is the alternative hypothesis for a two-tailed t-test?
What is the alternative hypothesis for a one-tailed t-test?
What is the null hypothesis for a chi-square goodness of fit test?
The variable follows the expected distribution.
What is the alternative hypothesis for a chi-square goodness of fit test?
The variable does not follow the expected distribution.
What are the calculator steps for a chi-square test of independence?
1) Enter your data into matrix A (2nd, Matrix, Edit, [A])
2) Run the test (Stat, TESTS, C: X^2 Test)
What are the calculator steps for a t-test?
-1) Enter the data (Stat, Enter, enter group 1 data into L1 and group 2 data into L2)
2) Run the test (Stat, TESTS, 4:2-Samp-T-Test)
What are the calculator steps for a chi-square goodness of fit test?
1) Enter the data (Stat, enter, observed vals go in L1 and expected vals go in L2)
2) Run the test (Stat, TESTS, D: X^2GOF TEST)
How do you decide whether to accept or reject the null hypothesis?
T-test for two means,what should you select?
pooled: NO or YES
pooled: YES
(The reason for this is because on the IB exam, they always give data with equal variances. You will learn more on this if you take more stats in college.)
