Week 12

Question 1

parametric tests

Answer 1

tests that concern parameters and require assumptions about parameters

Question 2

nonparametric tests

Answer 2

do not require a distribution to meet required assumptions (distribution-free tests)

Question 3

observed frequency (Chi-square test goodness of fit )

Answer 3

number of individuals from the sample who are classified in a particular category
- only one category per individual

Question 4

expected frequency (Chi-square test goodness of fit)

Answer 4

value that is predicted from proportions in H0 and n
- the expected frequencies define an ideal sample distribution that would be obtained if the sample proportions were in perfect agreement with proportions in H0
- ƒe = p x n

Question 5

small value for chi-square goodness of fit

Answer 5

fail to reject H0

Question 6

large value for chi-square goodness of fit

Answer 6

reject H0

Question 7

chi-square test for goodness of fit

Answer 7

uses sample data to test hypotheses about the shape or proportions of population distribution

Question 8

chi-square test for independence

Answer 8

uses frequency data from a sample to evaluate the relationship between 2 variables in the population

Question 9

Cohen’s W

Answer 9

• measurement for effect size in chi-square
• po = observed proportion = ƒo ÷ n
• pe = expected proportion = ƒe ÷ n
• W = 0.10 – small effect, W = 0.30 – medium effect, W = 0.90 – large effect

Question 10

phi-coefficient

Answer 10

for dichotomous variables (= both variables have 2 values), in a 2x2 matrix
- ϕ = √x^2 / n
- ϕ = 0.10 – small effect, ϕ = 0.30 – medium effect, ϕ = 0.90 – large effect

Question 11

Cramer’s V

Answer 11

phi-coefficient for larger matrices

Question 12

assumptions and restrictions for chi-square tests

Answer 12

• independence of observations: each observed frequency is generated by a different individual
• size of expected frequencies: expected frequencies of any cell has to be at least 5