Chi Square

Question 1

Chi square is sometimes used to determine what in regards to two variables??

Answer 1

Whether or not two variables are independent of each other or if they are related to each other.

Question 2

What is a contingency table?

Answer 2

A two way table showing the contingency between two variables where the variables have been classified into mutually exclusive categories and the cell entries are frequencies.

Question 3

Define contingency!

Answer 3

An event that may, but is not certain to occur aka something that may happen.

Question 4

What is a parametric test?

Answer 4

One that depends considerably on population characteristics or parameters for its use. (mean, SD etc)

Question 5

If nonparametric tests like Chi Square do not carry many assumptions and characteristics then why not use them all of the time.

Answer 5

Parametric tests are much more powerful and more versatile than nonparametric tests like Chi Square because they use more information in the calculation (more than just frequency).

Question 6

What is the statistical inference used most often with nominal data?
Hint: It is the only test we will cover in this class for nominal data.

Answer 6

The nonparametric test = chi square (X^2)

Question 7

What are the steps for calculating Chi Square?

Answer 7

Take the sum of the square of each observed frequency less the expectived frequency and divide by the expected frequency.

x^{2 =} ∑ (Oi - Ei)² / Ei

Question 8

What are the two types of statistical tests?

Answer 8

1. Parametric 2. Nonparametric

Question 9

What are the two assumptions of a parametric test?

Answer 9

1. The scores of the population are normally distributed
2. The variance across groups is homogenous.

Question 10

What level of data is used for X^2?

Answer 10

When dealing with nominal (categorical data).

Question 11

What are the three assumptions underlying Chi Square?

Answer 11

1. There is independence between each observation recorded in the contingency table. A) each subject may have only one entry in the table
2. Sample size must be large enough that the expected frequency in each cell is at least five for tables where there are more than two rows or columns
3. Normally used with nominal data A) however, can be used with ordinal, interval or ratio data.

Question 12

Is the following hypothesis a research or null hypothesis?

There is no difference in satisfied verses dissatisfied couples with respect to the number of unresolved arguments.

Answer 12

This is a null hypothesis or Ho, A null hypothesis indicates that there is no difference.

Question 13

Describe what the frequency expected ( fe) is ??

Answer 13

Expected frequency under the assumption sampling is random from the population. It is what we expect to get in each cell.

Question 14

Describe what the frequency observed is! (fo)?

Answer 14

This is the observed frequency for a particular cell.

Question 15

X^2 allows analysis of the difference scores between ___ and ____.

Answer 15

frequency expected and frequency observed.

Question 16

True or False
You can only use the Chi Square Test for nominal data?

Answer 16

False

You can treat ordinal or interval data as categorical and perform a Chi Square Test.

Question 17

When is a Chi Square Test useful in terms of NOIR?

Answer 17

1. For nominal data.
2. For higher levels of data when the distribution is skewed or kurtotic (positve skew, negative skew, leptokurtic, platykurtic).
3. If the group sizes are unequal. (Some parametric tests are sensitive to sample size).