Deck 9: Logistic Regression

Question 1

The relationship between the odds at one value of the independent variable compared with the odds at the next lower value of the independent variable is called the ______.

A) common logarithm
B) likelihood function
C) logit
D) odds ratio

Answer 1

D

Question 2

MLE compares the probability of a correct guess between two models by ______ the logged likelihood of Model 1 ______ Model 2.

A) adding; to
B) subtracting; from
C) multiplying; and
D) dividing; and

Answer 2

B

Question 3

The natural log of a correct guess is called the ______ in logistic regression.

A) logged likelihood
B) maximum likelihood
C) pseudo R-square
D) outcome

Answer 3

A

Question 4

______ expresses a number as an exponent of some constant or base.

A) Common logarithms
B) Logged odds
C) Odds
D) Probability

Question 5

If both the independent and dependent variables are ______ level, then ordinary least squares (OLS) regression would most likely be applied.

A) nominal
B) ordinal
C) ratio
D) interval

Question 6

Suppose the probability of voting equals .6 and the probability of not voting equals .4. What are the odds of voting?

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

Question 7

As we move from one value of the independent variable to the next, we describe the relationship between it and a change in the category of the dependent variable as the ______.

A) probability
B) logged odds
C) exponent
D) odds ratio

Question 8

A natural logarithm is approximately equal to ______.

A) 2
B) 2.5
C) 2.72
D) 2.83

Question 9

Which of the following tells the researcher how completely the independent variable explains the dependent variable.

A) Z-score
B) $\chi$ ²
C) Pearson's r
D) R-square

Question 10

The ______ of an outcome are a ratio of the number of expected occurrences to the number of occurrences of other outcome(s).

A) probability
B) odds
C) proportion
D) chances

Question 11

Logistic regression is designed to predict the ______ of an event occurring.

A) proportion
B) variability
C) probability
D) category

Question 12

Logistic regression estimates the ______ effects at the means when using more than one independent variable.

A) marginal
B) maximum
C) minimum
D) micro

Question 13

A variable coded as voted/not voted is an example of a ______ variable.

A) hypothetical
B) maximized
C) logistic
D) binary

Question 14

If there is a .10 probability of an event happening, there is a .90 chance of the event not happening and the odds of the event are ______.

A) .02
B) .07
C) .11
D) .57

Question 15

MERs stands for ______ effects at representative values.

A) minimal
B) maximum
C) marginal
D) multiple

Question 16

Logistic regression uses natural logarithms known as ______.

A) Base-10
B) Base-e
C) Base-2
D) Base-b

Question 17

The probability of an event can be expressed as a percentage between 0 and ______.

A) 10
B) 50
C) 75
D) 100

Question 18

MEMs stands for ______ effects at the means.

A) maximum
B) marginal
C) minimal
D) multiple

Question 19

The ______ of an event is equal to the number of times it occurs divided by the total number of chances for it to occur.

A) odds
B) probability
C) logged odds
D) proportion

Question 20

To use logistic regression with a categorical dependent variable, at least one independent variable must be measured at the ______ level.

A) nominal
B) ordinal
C) ratio
D) interval

Question 21

MLE stands for maximum likelihood estimation.

Question 22

Marginal effects at the means and marginal effects at representative values are not mutually exclusive strategies for analyzing probabilities.

Question 23

The likelihood function can take on any value between 0 and 100.

Question 24

Switchover points and full effects can be especially valuable interpretive tools in comparing marginal effects at representative values.

Question 25

Logistic regression produces a $\chi$ ² statistic we can use to determine the significance of the association between the variables.

Question 26

A number that summarizes how well a model's predictions fit the observed data is called an estimator.

Question 27

Both OLS and logistic regression are flexible in that they permit the use of multiple independent variables, including dummy independent variables.

Question 28

Common logarithms are used widely in electronics and experimental sciences.

Question 29

A binary variable is one that can assume only two values.

Question 30

The maximum likelihood estimation employs the same approach as the proportional reduction error.

Question 31

Dummy variables can be used with logistic regression.

Question 32

Logistic regression can only be used with one dependent and one independent variable.

Question 33

Maximum likelihood estimation (MLE) is the heart and soul of logistic regression.

Question 34

The marginal effects at the medium approach is useful when more than one independent variable is measured at the interval-level and researches want to convey the effect of one interval-level independent variable on the probability of the outcome, while other interval-level independent variables are help constant at their mean values.

Question 35

Logistic regression works well with multiple independent variables regardless of the level of measurement.