Chapter 11: Chi Squared Tests For Association.

Question 1

How do you calculate the Expected Values in a Contingency Table from the Observed Values?

Without a calculator?

Answer 1

Expected Value = [(Row Total) x (Column Total)]/ Grand Total.

Question 2

What hypothesis do you state for a Chi Squared (χ²) Test?

Answer 2

• H0: There is no association between the 2 variables (independent).
• H1: There is an association between the 2 variables. (dependent).

(Always this way round).

Question 3

What do all the expected frequencies need to be greater than to work?

Answer 3

Greater than 5. Otherwise you have to combine the rows and columns again.

Question 4

How do you calculate the degrees of freedom (v)?

Answer 4

v = (Row length -1) x (Column length -1).

Question 5

Once you have a table of Expected Frequences, what do you have to find?

Answer 5

The Test Statistic (χ²). This is done by [(O-E)²]/E.

Your calculator should already give you this value along with d.f.

Question 6

Once you’ve found the Test Statistic, what do you need to find?

Answer 6

The Critical Value.

Question 7

How do you find the Critical Value for a Chi Squared Distribution?

Answer 7

Chi –> InvC
* Area = Level of Significance.
* d.f = Degrees of Freedom.
* That gives you xInv = a, where a is the Critical Value.

Question 8

If your Test Statistic is in the critical region, do you Accept or Reject H0?

Answer 8

Reject H0.

Question 9

If your Test Statistic is not in the critical region, do you Accept or Reject H0?

Answer 9

Accept H0.

Question 10

If the p-value is greater than the Significance Level, do we Accept or Reject H0?

Answer 10

Accept H0 - Insignificant Evidence…