Question: 1

Logistic regression is used when you want to?

Predict a dichotomous variable from continuous or dichotomous variables.

Predict a continuous variable from dichotomous ones.

Predict any categorical variable from other categorical variables.

Predict a continuous variable from dichotomous or continuous variables.

Question: 2

In logistic regression, the values of the parameters are estimated using?

Maximum-likelihood estimation

Maximum-likelihood probability

Minimum-likelihood estimation

Minimum-likelihood probability

Question 3

Very high standard errors in parameter estimates in logistic regression suggest evidence of?

Multicollinearity

Shrinkage

An outlier

A dummy variable

Question 4

Large log-likelihood values donotshow or represent?

That the model is a good fit.

The extent of the relationship between independent and dependent variables.

That there are a large number of unexplained observations in the data.

That there is a large measure of deviance.

Question 5

Which of the following isnota research question that should be investigated with logistic regression?

Differences between groups

Strength of association between criterion and predictors

Interaction between predictors

Prediction of group membership

Question 6

A marketing consultant would like to analyze whether an advertisement is recalled or not by a group of consumers, predicted by the number of hours of television they watch. He has received various pieces of advice from colleagues. Which should he listen to?

Logistic regression is perfectly acceptable for this model.

Logistic regression is not suitable with this predictor variable.

Logistic regression is not suitable as the dependent variable only has two categories.

Logistic regression is not suitable as only one predictor variable is postulated.

Question 7

To predict a person's occupation by their income, lawyers are coded as 0 and accountants as 1. If there are 100 cases and 40 are accountants, what is the mean of the variable?

0.4

40

2.5

25

9.

Question 8

To predict a person's occupation by their income, lawyers are coded as 0 and accountants as 1. If there are 100 cases and 40 are accountants, the mean is also equal to?

The probability of randomly drawing an accountant

The probability of drawing a lawyer

The mode

The median

Question 9

A researcher is interested in predicting whether a company might attempt to buy out a competitor (score = 1) or not (score = 0), using market share (%) as an independent variable. She establishes that the value of 'exp(B)' is 2.56. How should she interpret this?

If two companies have a market share that differs by 1 unit, then the odds of the company with the higher score attempting a takeover are 2.56 higher than for the other company.

2.56 times more companies who attempted takeovers scored highly on market share.

If two companies have market share scores that differ by 1 unit, then the odds of the company with the higher score attempting a takeover are 2.56 lower than for the other company.

Takeover rates are 2.56 times as high in companies with a large share of their market.

Question 10

You are proofreading a new business statistics book for a close friend. He lists the following as functions of logistic regression, but you suspect one is not accurate. Which?

Rank the relative importance of independent variables

Predict a dependent variable on the basis of several independent variables

Determine the variance in the dependent variable explained by the independent variables

Assess the impact of covariate control variables