Deck 8: The Chi-Square Test of Association Between Variables

Question 1

In chi-square analysis, degrees of freedom provide a way of adjusting for:

A) the size of the research sample.
B) the number of cells that contribute to the chi-square value.
C) the difference between observed and expected frequencies.
D) the difference between nominal and ordinal level measurement.

Answer 1

the number of cells that contribute to the chi-square value.

Question 2

When conducting chi-square analysis, "collapsing" refers to:

A) adding one or more additional variables to the analysis.
B) combining cells to be able to meet the requirements for using the chi-square formula.
C) combining the expected frequencies and the observed frequencies in each cell.
D) calculating the mean for the observed and expected frequencies for each cell.

Answer 2

combining cells to be able to meet the requirements for using the chi-square formula.

Question 3

In reporting the results of chi-square analysis, it is a good idea to also report one or more measures of association such as Yules Q or phi. What additional information do they give the reader of a research report?

A) The probability that sampling error may have produced a relationship between variables.
B) The probability that sampling bias may have produced a relationship between variables.
C) An estimate of the strength of the relationship between variables.
D) all of the above

Answer 3

An estimate of the strength of the relationship between variables.

Question 4

In chi-square analysis, the numbers that best reflects the null hypothesis are the:

A) column totals.
B) row totals.
C) observed frequencies.
D) expected frequencies.

Question 5

If the requirements for use of chi-square cannot be met, what statistical test can be substituted for it?

A) the median test
B) McNemar's test
C) Fisher's exact
D) Cramer's V

Question 6

A dummy table uses asterisks to indicate where there will be disproportionately large frequencies if:

A) requirements for using chi-square cannot be met.
B) there is support for a one-tailed research hypothesis.
C) there is support for a two-tailed research hypothesis.
D) there is support for the null research hypothesis.

Question 7

Chi-square determines if there is support for a relationship between variables by comparing:

A) a sample mean with a population mean.
B) the mean of two research samples.
C) observed frequencies and expected frequencies.
D) observed frequencies and degrees of freedom.

Question 8

Chi-square is a test for between variables.

A) cause and effect.
B) correlation.
C) association.
D) all of the above

Question 9

How many degrees of freedom are there in a 2 X 3 crosstabulation table?

A) 6
B) 3
C) 2
D) 1

Question 10

When conducting chi-square analysis, it is possible to examine the effect of a third, control variable by using:

A) the median test.
B) McNemar's test.
C) multiple crosstabulation tables.
D) Lambda.

Question 11

When the effect of a control variable is examined:

A) the relationship between the independent and dependent variables may be stronger.
B) the relationship between the independent and dependent variables may be weaker.
C) the relationship between the independent and dependent variables may be unchanged.
D) all of the above

Question 12

When using chi-square, statistically significant but very weak relationships between variables are likely to occur if:

A) samples sizes are large.
B) sample sizes are small.
C) the independent variable contains many different value categories.
D) the dependent variable contains many different value categories.

Question 13

The Yates correction factor for continuity is a mathematical correction that is made to the chi-square formula when:

A) the sample size is very large.
B) the sample size is small.
C) there are only four cells in the crosstabulation table.
D) The observed frequencies in one or more cells is less than 5.

Question 14

Should a researcher ever use chi-square to examine the relationship between two variables that are interval level and normally distributed?

A) Yes, since chi-square can be computed with any level of data.
B) Yes, since it can produce a significant saving in data analysis time.
C) Yes, since it is more powerful than tests designed for use with higher levels of level.
D) No, because it wastes the available precision of measurement, and can result in a Type II error.

Question 15

What is a requirement for the use of chi-square?

A) a 2 X 2 cross tabulation table.
B) an expected frequency of 5 or more in at least 80% of the cells.
C) an observed frequency of 5 or more in at least 80% of the cells.
D) a sample size of at least 100.