Question

Nonparametric tests should not be used when ______.

the associations being tested involve categorical variables

the dependent variables are ordinal scales

the assumptions of parametric tests are met

the population distribution is heavily skewed

The chi-square tests are used to analyze ______.

Medians

frequency of data

continuous variables

skewness

The ______ tests are more powerful than the ______ tests, which means the ______ is higher for nonparametric tests.

parametric; nonparametric; type II error

nonparametric; parametric; type I error

parametric; nonparametric; type I error

nonparametric; parametric; type II error

If a 3 × 3 table is presented, then you know that a study used ______ independent variables each with ______ categories.

nine; two

two; four

three; three

two; three

Expected frequencies are obtained in rows-by-columns table assuming that the row and column categorizations are ______.

independent of each other

equal

related to each other

dependent on each other

Which of the following is a possible null hypothesis for a chi-square test?

The two categorical variables are unrelated in the population.

The means of populations in two independent groups are equal.

The two categorical variables are related in the population.

The distribution of scores for the first population is different from the distribution of scores for the second population.

If you have a 5 × 5 frequency table, then the critical value of chi-square would be based on ______ degrees of freedom.

16

8

10

25

Below are the number of acts of graffiti that occur on walls painted white, painted blue, or covered with chalkboard. H_o is frequencies of graffiti are equal in the population. With N = 30, f_e = N/k = 30/3 = 10 for each category.

What is the critical value for this test?

White	Blue	Chalk
fo = 8	fo = 8	fo = 8
fe = 10	fe = 10	fe = 10

3.84

5.99

9.21

9.57

Below are the number of acts of graffiti that occur on walls painted white, painted blue, or covered with chalkboard. H_o is frequencies of graffiti are equal in the population. With N = 30, f_e = N/k = 30/3 = 10 for each category.

What is the appropriate obtained value for this test?

White	Blue	Chalk
fo = 8	fo = 8	fo = 8
fe = 10	fe = 10	fe = 10

7.80

2.60

3.90

5.99

Below are the number of acts of graffiti that occur on walls painted white, painted blue, or covered with chalkboard. H_o is frequencies of graffiti are equal in the population. With N = 30, f_e = N/k = 30/3 = 10 for each category.

In the population, we expect _____% of graffiti on white walls, _____% on blue walls, and _____% on chalkboard walls.

White	Blue	Chalk
fo = 8	fo = 8	fo = 8
fe = 10	fe = 10	fe = 10

58%; 21%; 19%

27%; 17%; 57%

50%; 25%; 25%

33%; 33%; 33%

Answer 1

1) Nonparametric tests are also called distribution-free tests because they are based on fewer assumptions. We should use nonparametric tests when your data don't meet the assumptions of the parametric test, especially the assumption about normally distributed data.

So, the answer is:

Nonparametric tests should not be used when the assumptions of parametric tests are met.

2) The chi-square test is used to analyze a contingency table consisting of rows and columns to determine if the observed cell frequencies differ significantly from the expected frequencies.

So, the correct answer is:

The chi-square tests are used to analyze frequency of data.

3) The assumptions for the nonparametric test are weaker than those for the parametric test, and it has been stated that when the assumptions are not met, it is better to use the nonparametric test. Nonparametric tests are more “liberal” (i.e., more likely to make a Type-I Error).

So, the correct answer is:

The Parametric tests are more powerful than the Non Parametric tests, which means the Type I error is higher for nonparametric tests.