Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
16 Cards in this Set
- Front
- Back
|
What is the purpose of the chi-square test?
|
To determine whether a distribution of cases in your data matches an expected pattern
|
|
|
For what type of variable is chi-square used?
|
Nominal/categorical variables
|
|
|
When do you use goodness-of-fit chi-square?
|
When you are comparing the observed and expected distributions of cases for a single nominal variable
|
|
|
How do you determine the expected frequencies for a goodness-of-fit chi-square if you are not given a population distribution?
|
Assume that the cases are divided evenly among all categories ( E = N / # of categories )
|
|
|
How do you determine expected frequencies for goodness-of-fit chi-square if you are given a population distribution?
|
Multiply the proportion for each category in the population by the total number of cases in the sample. The result is the expected frequency for that category in the sample.
|
|
|
How do you determine the degrees of freedom for a goodness-of-fit chi-square?
|
df = # of categories - 1
|
|
|
What do we mean when we say that two variables are statistically independent?
|
There is no statistical association between the variables.
|
|
|
What is a contingency table?
|
A table that displays the breakdown of cases across two nominal variables at the same time.
|
|
|
How do you determine degrees of freedom for independence chi-square?
|
df = (# rows - 1)(# columns - 1)
|
|
|
What is population one in all chi-square problems?
|
The population like the cases in the sample.
|
|
|
What is the research hypothesis for all chi-square problems?
|
Cases are distributed differently between populations.
|
|
|
What is population two for independence chi-square?
|
The population in which the two variables are unrelated. (Remember to specify what the two variables are!)
|
|
|
When do we use independence chi-square?
|
When trying to determine if there is an association between two nominal/categorical variables.
|
|
|
How would you describe the chi-square distribution?
|
Unimodal with a positive skew.
|
|
|
How do you calculate the expected frequencies for cells in the independence chi-square?
|
Either: Multiply that cell's row marginal (R) by the column marginal (C) and dividing the product by the total number of cases (N). OR Divide that cell's row marginal (R) by the total number of cases (N), then multiply that quotient by the column marginal (C).
|
|
|
How do you calculate the chi-square statistic?
|
For each category/cell, subtract the expected frequency from the observed frequency, then square the result. Divide the squared result by the expected frequency for each category/cell, then add up the answers to get the chi-square figure.
|
