Chi- Squared Tests

Question 1

The ‘null’ and ‘alternative hypotheses’ generally take the following form

Answer 1

Ho: There is no difference between the observed and theoretical distribution.
H1: There is a difference between the observed and theoretical distribution.

Question 2

Goodness of fit

Answer 2

Is concerned with measuring how well an observed frequency distribution fits to a know distribution

Question 3

The measure of goodness of fit

Answer 3

Question 4

The Chi-squared family of distributions can be used to approximate…

Answer 4

chi squared as long as none of the expected values are below 5
- need to combine nearby table columns

Question 5

When calculating degrees of freedom

Answer 5

v = number of cells after combining - number of constraints

Question 6

When using chi squared tests, if any of the expected values are less than 5,

Answer 6

Then you have to combine frequencies in the data table until they are greater than 5

Question 7

When selecting which of the chi-squared family to use as an approximation for X^2,

Answer 7

You have to select the distribution which has ‘v’ equal to the number of degrees of freedom of your expected values.

Question 8

If chi squared exceeds the critical value,

Answer 8

it is unlikely that the null hypothesis is correct so you reject it in favour of the alternative hypothesis.

Question 9

If n is the number of cells after combining:

Answer 9

Question 10

For contingency tables:

Answer 10