Quiz 3: Loglinear models

Test your knowledge of the material on loglinear models in the following quiz.

1. What is a loglinear model for frequency tables in categorical data analysis?

1. A linear regression model for categorical data
2. A logistic regression model for categorical data
3. A statistical model for analyzing the relationship between categorical variables
4. A model for predicting binary outcomes from categorical predictors

2. How do you test for goodness of fit of a loglinear model for a two-way frequency table?

1. By using a chi-squared test
2. By using a likelihood ratio test
3. By using a Cochran-Mantel-Haenszel test
4. By using Cohen’s kappa.

3. What is the main difference between a glm() loglinear model and the chi-squared test for independence in two-way frequency tables?

1. glm() models allow for different types of associations among variables while chi-squared test only tests for independence
2. glm() models allow for non-normal data while chi-squared test do not
3. glm() models apply in small sample size while chi-squared test require large sample size
4. glm() models allow for estimation of parameters for interactions among variables and also for non-normal data while chi-squared test only tests for independence

4. How does a loglinear model differ from a logit model?

1. Loglinear models are linear while logit models are non-linear
2. Logit models handle only binary outcomes while loglinear models handle more than 2 outcomes
3. Loglinear models are used for continuous data while logit models are used for categorical data
4. Logit models estimate probabilities while loglinear models estimate frequencies

5. What is the difference between a loglinear model fit by loglm() and one fit using glm()?

1. loglm() requires large samples while glm() can be used for smaller samples
2. loglm() only estimates fitted values while glm() estimates parameters
3. loglm() uses an interative process while glm() provides an exact solution
4. loglm() gives the Pearson chi-square test while glm() gives the likelihood ratio test

6. What are the advantages of a loglinear model fit using glm() over one fit using loglm()

1. glm() estimates parameters while loglm() estimates only fitted values
2. glm() can handle ordinal and quantitative predictors while loglm() cannot
3. glm() can accommodate over-dispersion while loglm() cannot
4. All of the above

7. How can you extend a loglinear model for frequency tables to handle multi-way contingency tables?

1. By adding association terms to the model
2. By fitting separate loglinear models for each combination of predictors
3. By using a multivariate linear regression model
4. By using a multinomial logistic regression model

8. For a three-way frequency table what is the interpretation of the model symbolized by [A B] [A C]

1. A and B are conditionally independent given C
2. B and C are conditionally independent given A
3. A and B are mutually independent
4. The association between A and B is the same for all levels of C