# Quiz 16: Regression

Psychology

Q 1Q 1

Regression is to _____ as correlation is to _____.
A) association; causation
B) causation; association
C) relation; prediction
D) prediction; relation

Free

Multiple Choice

D

Q 2Q 2

Simple linear regression allows one to:
A) determine the relation among four or more variables.
B) predict an individual's score on a dependent variable from her score on multiple independent variables.
C) predict an individual's score on the dependent variable from her score on the independent variable.
D) infer the direction of causal relations.

Free

Multiple Choice

C

Q 3Q 3

Which statistical tool allows one to predict a dependent score based on information about an independent variable?
A) t test
B) correlation
C) regression
D) standardization

Free

Multiple Choice

C

Q 4Q 4

Regression cannot prove causation, but it can:
A) provide specific quantitative predictions that help explain relations among variables.
B) provide stronger evidence for association than does correlation.
C) predict people's behaviors on variables that may seem impossible to measure.
D) serve as a substitute for good experimental design.

Free

Multiple Choice

Q 5Q 5

Which sentence does NOT state a limitation of using regression?
A) The presence of confounding variables may limit confidence in the findings.
B) The data used are rarely from a true experiment.
C) Regression is only appropriate with linear data.
D) Regression allows one to determine an equation for a straight line.

Free

Multiple Choice

Q 6Q 6

What is the formula for predicting an individual's z score on the dependent variable from the z score on the independent variable using the correlation coefficient?
A)

_{ }_{ }B) C) D)Free

Multiple Choice

Q 7Q 7

Y is the symbol for a(n) _____, and Ŷ is the symbol for a(n) _____.
A) predicted score on the independent variable; observed score on the independent variable
B) observed score on the dependent variable; predicted score on the dependent variable
C) observed score on the independent variable; predicted score on the dependent variable
D) predicted score on the dependent variable; observed score on the independent variable

Free

Multiple Choice

Q 8Q 8

The correlation between the number of ounces of candy a child consumes weekly and the number of cavities the child has at the age of 13 is 0.78.If a child has a z score of -0.85 on the candy-consumed variable, the z score on the variable number of cavities would be predicted to be:
A) -0.66.
B) -0.92.
C) 0.66.
D) 0.92.

Free

Multiple Choice

Q 9Q 9

If the correlation between the number of beers consumed over a semester and the GPA for the semester is -0.56, what would be the predicted z score for a person who has a z score of -0.95 for the number of beers consumed?
A) 0.59
B) -0.59
C) 0.53
D) -0.53

Free

Multiple Choice

Q 10Q 10

The predicted z score for the dependent variable will always be _____ the individual's z score for the independent variable.
A) more than
B) the same as
C) two times
D) less than

Free

Multiple Choice

Q 11Q 11

The tendency of scores that are particularly high or low to drift toward the mean over time is called:
A) simple linear regression.
B) standard error of the mean.
C) regression to the mean.
D) standard error of the estimate.

Free

Multiple Choice

Q 12Q 12

In the formula Ŷ = a + b(X), a is the:
A) slope.
B) intercept.
C) predicted value for the dependent variable.
D) observed value on the independent variable.

Free

Multiple Choice

Q 13Q 13

In the formula Ŷ = a + b(X), b is the:
A) slope.
B) intercept.
C) predicted value for the dependent variable.
D) observed value on the independent variable.

Free

Multiple Choice

Q 14Q 14

In the equation for a regression line, the intercept is the:
A) value for X when Y is equal to 0.
B) predicted value for Y when X is equal to 0.
C) amount that Y is predicted to increase for a one-unit increase in X.
D) z score of the amount that Y is predicted to increase as X increases.

Free

Multiple Choice

Q 15Q 15

In the equation for a regression line, the slope is the:
A) value for X when Y is equal to 0.
B) predicted value for Y when X is equal to 0.
C) amount that Y is predicted to increase for a one-unit increase in X.
D) z score of the amount that Y is predicted to increase as X increases.

Free

Multiple Choice

Q 16Q 16

Data from the World Health Organization in 2013 were used to predict the life expectancy for men in a country from the life expectancy of women in the country.The resulting regression equation was Ŷ = 3.73 + 0.88(X).Using the regression equation, what would be the predicted life expectancy of men in a country in which the life expectancy for women is 70 years?
A) 57.87 years
B) 60.93 years
C) 65.33 years
D) 69.61 years

Free

Multiple Choice

Q 17Q 17

Data from the World Health Organization in 2013 were used to predict the life expectancy for men in a country from the life expectancy of women in the country.The resulting regression equation was Ŷ = 3.73 + 0.88(X).This regression equation implies that:
A) when a woman's life expectancy increases by 1 year, a man's life expectancy increases by 3.73 years.
B) women live 0.88 times as long as men do.
C) when a woman's life expectancy increases by 1 year, a man's life expectancy increases by 0.88 of a year.
D) the average life expectancy for men in some countries is 3.73.

Free

Multiple Choice

Q 18Q 18

In a 2008 article by Hsiu-Ling Lee, data from 147 colleges from 1995 to 2005 were used to predict endowments to a college from the average SAT score of students attending the college, among other variables.The resulting regression equation for just these variables was Ŷ = -20.46 + 4.06(X).Using the regression equation, what would be predicted to be the endowments (in billions) to a college whose students' average SAT score is 1020?
A) 3.6 billion
B) 4,120.74 billion
C) 4,161.66 billion
D) 20,865.14 billion

Free

Multiple Choice

Q 19Q 19

Data from 147 colleges from 1995 to 2005 (Lee, 2008) were used to predict the endowments (in billions) to a college from the average SAT score of students attending the college.The resulting regression equation was Ŷ = -20.46 + 4.06(X).This regression indicates that:
A) most colleges have very high endowments.
B) for every one-point increase in SAT scores, a college can expect 4.06 billion more in endowments.
C) for every one-dollar increase in endowments, the college can expect a half-point increase in SAT scores.
D) for every one-point increase in SAT scores, a college can expect 20.46 billion fewer in endowments.

Free

Multiple Choice

Q 20Q 20

Which statement about the slope of the simple linear regression line is true?
A) It has the same sign as the correlation.
B) It is expressed as a standardized value.
C) The square of the slope is the proportion of variation in Y explained by X.
D) It is the value of Y when X is zero.

Free

Multiple Choice

Q 21Q 21

The regression line is the line that:
A) minimizes error in predicting scores on the dependent variable.
B) is the mean of the dependent variable.
C) minimizes error in predicting scores on the independent variable.
D) minimizes the correlation coefficient.

Free

Multiple Choice

Q 22Q 22

The standardized regression coefficient expresses the:
A) relation between the independent and dependent variable in terms of squared units.
B) strength of the correlation between the two variables that are now incorporated into a regression analysis.
C) predicted change in the dependent variable in terms of standard deviations for an increase of 1 standard deviation in the independent variable.
D) likelihood of rejecting the null hypothesis with a regression analysis.

Free

Multiple Choice

Q 23Q 23

The standardized regression coefficient expresses a predicted change in the dependent variable in terms of:
A) standard deviation units.
B) slope.
C) a one-unit change in the independent variable.
D) error units.

Free

Multiple Choice

Q 24Q 24

For a simple linear regression, the standardized regression coefficient is:
A) the square of the r statistic.
B) equal to the Pearson correlation coefficient.
C) the square root of the slope.
D) unrelated to the correlation value.

Free

Multiple Choice

Q 25Q 25

The standard error of the estimate indicates:
A) how far two regression lines are from each other.
B) how far, on average, the regression line is from the mean.
C) how much error there is in any single prediction made from a given regression equation.
D) the typical distance between the regression line and each of the observed data points.

Free

Multiple Choice

Q 26Q 26

A high standard error of the estimate indicates that the:
A) mean is not a good representation of the sample data.
B) observed Ys will vary greatly from the predicted Ys.
C) sample mean is not a good representation of the population mean.
D) observed Ys will cluster closely around the regression line.

Free

Multiple Choice

Q 27Q 27

The standard error of estimate could be thought of as the:
A) standard deviation of the data points around the regression line.
B) standard deviation of the independent variable on the regression line.
C) standard deviation of the dependent variable.
D) amount of error made in random selection.

Free

Multiple Choice

Q 28Q 28

If the standard error of the estimate is zero, the relation between two variables is:
A) curvilinear.
B) imperfect.
C) perfect.
D) unknown.

Free

Multiple Choice

Q 29Q 29

Under what circumstance, unlikely as it might be, would the standard error of estimate be zero?
A) The proportionate reduction in error is zero.
B) The correlation coefficient is zero.
C) The correlation coefficient is either 1.00 or -1.00.
D) The proportionate reduction in error is 1.

Free

Multiple Choice

Q 30Q 30

As the standard error of estimate becomes larger, predictions become:
A) less accurate.
B) more accurate.
C) larger.
D) smaller.

Free

Multiple Choice

Q 31Q 31

As r

^{2}increases, the standard error of the estimate: A) increases. B) decreases. C) stays the same. D) gets closer to 1.Free

Multiple Choice

Q 32Q 32

Use the following to answer questions
The scatterplot and regression line on the left depict the relation between a state's expenditure per student and the average SAT scores for students in the state.The scatterplot and regression line on the right depict the relation between students' SAT Verbal and SAT Quantitative scores.
Figure: Standard Error Comparisons
-(Figure: Standard Error Comparisons) For which prediction is the standard error of the estimate greater?
A) state expenditure per student from composite SAT scores
B) composite SAT scores from the state's expenditure per student
C) SAT Quantitative scores from SAT Verbal scores
D) SAT Verbal scores from SAT Quantitative scores

Free

Multiple Choice

Q 33Q 33

Use the following to answer questions
The scatterplot and regression line on the left depict the relation between a state's expenditure per student and the average SAT scores for students in the state.The scatterplot and regression line on the right depict the relation between students' SAT Verbal and SAT Quantitative scores.
Figure: Standard Error Comparisons
-(Figure: Standard Error Comparisons) Based on the scatterplots, for which prediction is the r

^{2}greater? A) state expenditure per student from composite SAT scores B) composite SAT scores from the state's expenditure per student C) SAT Quantitative scores from SAT Verbal scores D) SAT Verbal scores from SAT Quantitative scoresFree

Multiple Choice

Q 34Q 34

A man and woman who are both tall (he is 6 feet tall and she is 5 feet, 10 inches) have four children; which child represents regression to the mean for height?
A) Janet who is 5 feet tall
B) Amy who is 5 feet, 1 inch tall
C) Laura who is 5 feet, 5 inches tall
D) John who is 6 feet, 2 inches tall

Free

Multiple Choice

Q 35Q 35

Every year it seems as though last season's baseball rookie of the year fails to live up to expectations for his sophomore season.What might explain this phenomenon?
A) regression to the mean
B) overestimation of effect size
C) standard error of the estimation
D) proportionate reduction in error

Free

Multiple Choice

Q 36Q 36

Which statistic quantifies the improvement in ability to predict a person's score when using the regression line rather than the mean?
A) standard error of the estimation
B) standard deviation
C) slope
D) proportionate reduction in error

Free

Multiple Choice

Q 37Q 37

The proportionate reduction in error is a measure of the:
A) amount of variance in the dependent variable explained by the independent variable.
B) correlation between two variables.
C) amount of variance in the independent variable explained by the dependent variable.
D) slope of a regression line.

Free

Multiple Choice

Q 38Q 38

Which is the correct formula for the proportionate reduction in error?
A) (b)
B)
C) a + bX
D)

Free

Multiple Choice

Free

Multiple Choice

Q 40Q 40

A simple way to calculate proportionate reduction in error is by:
A) taking the square root of the correlation coefficient.
B) squaring SS

_{total}. C) squaring the correlation coefficient. D) adding the slope and y intercept.Free

Multiple Choice

Q 41Q 41

As the correlation coefficient becomes stronger, proportionate reduction in error:
A) becomes smaller.
B) becomes larger.
C) is unaffected.
D) becomes more variable.

Free

Multiple Choice

Q 42Q 42

An independent variable that makes a unique contribution to the prediction of a dependent variable is a(n) _____ variable.
A) orthogonal
B) latent
C) manifest
D) unique

Free

Multiple Choice

Q 43Q 43

If two variables, independently, can help predict the outcome of a third variable, they are:
A) autonomous.
B) orthogonal.
C) standardized.
D) proportionate.

Free

Multiple Choice

Q 44Q 44

To predict a single dependent variable from more than one independent variable, which statistical technique should be used?
A) multiple regression
B) structural equation modeling
C) simple linear regression
D) correlation

Free

Multiple Choice

Q 45Q 45

A researcher wants to be able to predict first-semester grade point average with as much accuracy as possible, so she would like to use both high school grade point average and SAT score as predictor variables.Which technique would be most appropriate to make this prediction?
A) simple linear regression
B) proportionate reduction in error
C) multiple regression
D) standardized regression coefficient

Free

Multiple Choice

Q 46Q 46

In the equation Ŷ = 130 + 5(X

_{1}) + 3(X_{2}), what is the y intercept? A) 130 B) 8 C) 5 D) 3Free

Multiple Choice

Q 47Q 47

For the equation Ŷ = 130 + 5(X

_{1}) + 3(X_{2}), which statement is true? A) 130 is the slope of the line. B) This is a simple linear regression equation. C) There are two slopes. D) The y intercept is 8.Free

Multiple Choice

Q 48Q 48

In a study designed to predict blood cholesterol levels from amount of daily saturated fat in grams (X

_{1}) and number of hours of daily exercise (X_{2}), the slope of X_{1}is 5, the slope of X_{2}is -4, and the y intercept is 130.Which formula is the regression equation for these data? A) Ŷ = 130 + 5(X_{1}) - 4(X_{2}) B) Ŷ = 130 - 4(X_{1}) - 5(X_{2}) C) Ŷ = 130 + 5(X_{1}) + 4(X_{2}) D) Ŷ = 130 + 1(X)Free

Multiple Choice

Q 49Q 49

In the equation Ŷ = 98 + 4.30(X

_{1}) + 7.20(X_{2}), what is/are the slope(s)? A) 98 B) 98 and 4.30 C) 4.30 D) 4.30 and 7.20Free

Multiple Choice

Q 50Q 50

What information do the slopes in a multiple regression equation provide about the correlation coefficient?
A) The slopes tell us nothing about the correlation coefficient.
B) The sign of the slope (positive or negative) tells us the direction of the correlation.
C) The slope sign is inversely related to the direction of the correlation.
D) The magnitude of the slope tells us how strong the correlation coefficient is.

Free

Multiple Choice

Q 51Q 51

In the computer printouts presented in the text, information for the multiple regression equation can be found in the column labeled:
A) standardized coefficients.
B) B under unstandardized coefficients.
C) beta under standardized coefficients.
D) sig.

Free

Multiple Choice

Q 52Q 52

If someone reports that she typically eats 15 grams of saturated fat daily and exercises 1 hour daily, what would her cholesterol level be predicted to be?
A) 75
B) 145
C) 180
D) 201

Free

Multiple Choice

Q 53Q 53

Structural equation modeling involves:
A) quantifying how well data fit a specified theory.
B) using a single independent variable to predict multiple dependent variables.
C) using multiple independent variables to predict a single dependent variable.
D) determining the amount of error present in a regression.

Free

Multiple Choice

Q 54Q 54

A latent variable is:
A) an idea or construct we cannot directly observe, but still wish to measure.
B) a variable that can be directly observed and is measured in a research study.
C) the dependent variable when performing structural equation modeling.
D) the dependent variable when performing multiple regression.

Free

Multiple Choice

Q 55Q 55

A manifest variable is:
A) an idea or construct we cannot directly observe, but still wish to measure.
B) a variable that can be directly observed and is measured in a research study.
C) the dependent variable when performing structural equation modeling.
D) the dependent variable when performing multiple regression.

Free

Multiple Choice

Q 56Q 56

Carrico, Gifford, and Moos (2007) studied the relation between a substance abuser's spirituality/religiosity and her participation in a 12-step program.Participants in the study rated their agreement, on a scale from 1 to 5, with statements such as, "In my life I experience the presence of the divine." In this study, spirituality/religiosity is the _____ and participants' ratings of agreement to the specific statements are the _____.
A) dependent variable; independent variables
B) independent variable; dependent variables
C) manifest variable; latent variables
D) latent variable; manifest variables

Free

Multiple Choice

Q 57Q 57

The arrows in a structural equation model indicate the:
A) causal direction of a relation.
B) strength and direction of a predictive relation.
C) number of variables that determine the prediction equation.
D) latent variables.

Free

Multiple Choice

Free

True False

Q 59Q 59

Regression capitalizes on correlation by using what is known about the relation between two variables to make predictions beyond those variables.

Free

True False

Q 60Q 60

The predicted z score on the dependent variable will always be closer to its mean than the z score for the independent variable.

Free

True False

Q 61Q 61

The predicted z score on the dependent variable will always be closer to the z score for the independent variable than its mean.

Free

True False

Free

True False

Free

True False

Free

True False

Free

True False

Free

True False

Free

True False

Free

True False

Free

True False

Free

True False

Q 71Q 71

The standard error of estimate is a measure of how accurately we predict using the regression equation or line of best fit.

Free

True False

Free

True False

Q 73Q 73

Like correlation, regression cannot prove causal direction of a relation between two variables.

Free

True False

Q 74Q 74

Unlike correlation, regression can prove causal direction of a relation between two variables.

Free

True False

Q 75Q 75

It is impossible for the regression line to do a poorer job than the mean of predicting the dependent variable.

Free

True False

Q 76Q 76

Correlation coefficient and proportionate reduction in error are inversely related; that is, as the correlation coefficient increases, proportion reduction in error decreases.

Free

True False

Q 77Q 77

Simple linear regression is a statistical technique that includes two or more predictor variables in a prediction equation.

Free

True False

Q 78Q 78

It is inappropriate to use structural equation modeling if there is not an a priori theoretical idea regarding the pattern of relations among the variables being measured.

Free

True False

Free

True False

Free

True False

Free

True False

Free

True False

Q 83Q 83

You want to predict your score on the statistics final exam using your grade point average for the semester.Which statistical technique is best for this type of analysis?
A) bar graph
B) correlation
C) simple linear regression
D) standardized z scores

Free

Multiple Choice

Q 84Q 84

Regression is a type of statistical analysis that is most useful for:
A) calculating z scores.
B) predicting behavior.
C) determining standard deviations.
D) finding the direction and strength of a relation between two variables.

Free

Multiple Choice

Q 85Q 85

In the equation for a line in statistics, the _____ is the predicted amount of increase for Y when X is increased by 1, and the _____ is the predicted value for Y when X crosses the y-axis (X = 0).
A) intercept; slope
B) intercept; standard error
C) slope; standard error
D) slope; intercept

Free

Multiple Choice

Q 86Q 86

Penny is figuring the regression line for some data but needs help in first figuring the predicted value of Y.She knows that the slope is 3 and the intercept is 4.What is the predicted Y value for an X score of 7?
A) 17
B) 19
C) 25
D) 31

Free

Multiple Choice

Q 87Q 87

If shyness is negatively correlated with the number of friendships a person has, which statement regarding the line of best fit, or regression line, would be true?
A) The line will start in the lower left corner of the graph and end in the upper right corner.
B) The line will start in upper left corner of the graph and end in the lower right corner.
C) Because the correlation is negative, a regression line cannot be drawn.
D) The y intercept will be negative.

Free

Multiple Choice

Q 88Q 88

When a regression equation includes just one independent variable, the value of the standardized regression coefficient is:
A) equal to the slope of the regression equation.
B) the inverse of the correlation coefficient.
C) the same as the Pearson correlation coefficient.
D) equal to the y-intercept of the regression equation.

Free

Multiple Choice

Q 89Q 89

The statistic that describes the variability of a set of data points to the line of best fit in a linear regression is the standard:
A) deviation.
B) deviation of the estimate.
C) error of the estimate.
D) error.

Free

Multiple Choice

Q 90Q 90

If the points on a scatterplot are all close to the regression line:
A) the standard error of the estimate is small.
B) r is a positive number.
C) r is close to 0.
D) the standard error of the estimate is large.

Free

Multiple Choice

Q 91Q 91

There is an extremely high negative correlation between altitude and the percentage of oxygen in the air.Is it correct to say that high altitudes cause low amounts of oxygen in the air based on a linear regression equation and the Pearson correlation coefficient?
A) yes, because the regression analysis reveals a strong correlation
B) yes, because the correlation is negative
C) no, because the correlation is negative
D) no, because regression analysis does not imply causation

Free

Multiple Choice

Q 92Q 92

Desmond thinks his new tutoring methods are highly effective compared to commercially available methods.He selects the worst students in his statistics class and tries his new tutoring strategy.Which statement describes a threat to the validity of his hypothesis even if the students do very well after the tutoring sessions?
A) Instrumentation errors will skew the results.
B) Regression to the mean is likely to occur.
C) Confirmation bias is likely to occur.
D) The testing sequence is a confounding factor.

Free

Multiple Choice

Q 93Q 93

If the points on a scatterplot are all far away from the regression line:
A) the standard error of the estimate is small.
B) r is a positive number.
C) r is close to 0.
D) the standard error of the estimate is large.

Free

Multiple Choice

Q 94Q 94

_____ refers to the accuracy of a prediction based on the regression equation or the amount of error that is eliminated compared to predictions based on the mean of the dependent variable.
A) Predictive validity
B) Orthogonal regression coefficient
C) Reliability
D) Proportionate reduction in error

Free

Multiple Choice

Q 95Q 95

Multiple regression differs from simple linear regression because it:
A) repeats a linear regression several times, which can improve the results by averaging.
B) uses more than one independent variable to make predictions.
C) uses higher order polynomials to make predictions.
D) employs the mathematical framework of calculus.

Free

Multiple Choice

Q 96Q 96

A multiple regression analysis revealed the following equation relating the time (in hours) it takes to complete a puzzle based on the number and size of pieces: Ŷ = 1.5 + 0.014 (X

_{number of pieces}) - 1.2 (Y_{size of pieces}).If a puzzle has 500 pieces, with a size value of 0.5 inches, how long will it take to complete? A) 6.3 hours B) 7.1 hours C) 7.9 hours D) 9.3 hoursFree

Multiple Choice

Q 97Q 97

Structural equation modeling graphs depict a _____ among several variables, demonstrating how all of the variables combine to create a _____.
A) network of relations; statistical model
B) causal chain; correlation
C) box plot; theory
D) scatterplot; theoretical model

Free

Multiple Choice

Q 98Q 98

A multiple regression analysis revealed the following equation relating the time (in hours) it takes to complete a puzzle based on the number and size of pieces: Ŷ = 1.5 + 0.014 (X

_{number of pieces}) - 1.2 (Y_{size of pie}_{ces}).If a puzzle has 1000 pieces, with a size value of 0.5 inches, how long will it take to complete? A) 6.3 hours B) 7.9 hours C) 11.9 hours D) 14.9 hoursFree

Multiple Choice

Q 99Q 99

_____ is a useful statistical analysis for predicting behavior, and _____ is a useful technique for finding the direction and strength of a relation between two variables.
A) Psychometrics; correlation
B) Correlation; regression
C) Regression; correlation
D) Psychometrics; regression

Free

Multiple Choice

Q 100Q 100

If a person's score on a(n) _____ variable is known, the person's score on the _____ variable can be predicted using simple linear regression.
A) dependent; independent
B) independent; dependent
C) scale; nominal
D) nominal; z score

Free

Multiple Choice

Q 101Q 101

Good physical fitness has been correlated with many medical benefits, particularly in relation to blood pressure.A regression equation predicting an individual's blood pressure based on physical fitness level results in a negatively sloped line of best fit.What does this statement mean?
A) People who are physically fit are predicted to have low blood pressure, while people who have low fitness levels are predicted to have high blood pressure.
B) People who have low fitness levels have low blood pressure, while people who are highly active probably have high blood pressure.
C) There is no correlation between blood pressure and physical fitness.
D) Low fitness levels cause high blood pressure; high fitness levels cause low blood pressure.

Free

Multiple Choice

Q 102Q 102

In looking at a graph of data, there seems to be a curved pattern, possibly because of the influence of a third variable.Should simple linear regression be used?
A) Yes; the data are linear.
B) Yes; the data are nonlinear.
C) No; the date are linear.
D) No; the data are nonlinear.

Free

Multiple Choice

Q 103Q 103

Dr.Garoule is trying to determine which of his patients has the highest likelihood of depression.He calculates a linear regression equation with the scores on an anxiety measure, which are positively correlated with scores on a scale measuring depression.Dr.Garoule converts patient D's anxiety score to a z score and predicts the z score for the depression scale to be -0.35.Is patient D's raw score for depression above or below the mean and why?
A) It is below the mean because the z score is negative.
B) It is above the mean because the z score is negative.
C) It is below the mean because the z score is positive.
D) It is above the mean because the z score is positive.

Free

Multiple Choice

Q 104Q 104

Dr.Garoule is trying to determine which of his patients has the highest likelihood of depression.He calculates a linear regression equation with the scores on an anxiety measure, which are positively correlated with scores on a scale measuring depression.Dr.Garoule converts patient D's anxiety score to a z score and predicts the z score for the depression scale to be 0.65.Is patient D's raw score for depression above or below the mean and why?
A) It is below the mean because the z score is negative.
B) It is above the mean because the z score is negative.
C) It is below the mean because the z score is positive.
D) It is above the mean because the z score is positive.

Free

Multiple Choice

Q 105Q 105

Assume a positive correlation is found between the number of hours students spend studying for an exam and their grade on the exam.If the regression equation for these data is calculated and the y intercept is 65, what conclusion can be drawn?
A) The standard error of the estimate is low.
B) The regression line crosses the x-axis at a score of 65.
C) The slope of the regression line is 65 when students do not study at all.
D) When students do not study at all, we would predict a score of 65 on the exam.

Free

Multiple Choice

Q 106Q 106

When drawing a line of best fit, it is "best" to use _____ point(s) of _____ value(s).
A) 1; low
B) 2; high and medium
C) 3; low
D) at least 2; low and high

Free

Multiple Choice

Q 107Q 107

The standardized regression coefficient, which is equal to the Pearson correlation coefficient in a simply linear regression, is also called:
A) alpha.
B) standardized deviation prediction.
C) beta weight.
D) slope.

Free

Multiple Choice

Q 108Q 108

Body weight can be predicted based on the amount of calories consumed by an individual due to the positive correlation between the two variables.When looking at the line of best fit for the linear regression, the data points are clustered close together.Predicted shyness based on the number of friendships a person has is also correlated, but the data points are more scattered around the line of best fit, showing a general negative correlation.Which has the higher predictive power and why?
A) calories consumed and body weight, because it is a positive correlation
B) calories consumed and body weight, because the variance is lower
C) shyness and number of friendships, because it is a negative correlation
D) shyness and number of friendships, because the variance is lower

Free

Multiple Choice

Q 109Q 109

According to the text, a good statistician examines the data points before proceeding and questions causality after the statistical analysis.What would that statistician be doing during each of these two phases of a regression analysis?
A) Before the test, examine for linearity, and after the test, consider confounding variables that might help to understand cause.
B) Before the test, examine for errors in the data, and after the test, conjecture about possible causes using the ABC model.
C) Before the test, check for outliers, and after the test, run an experiment to reveal causal relations.
D) Before the test, create appealing visual displays of data, and after the test, create theories about causation.

Free

Multiple Choice

Q 110Q 110

The idea that patterns of extreme scores will balance out if sampling continues indefinitely or trends are looked at over the long run is known as:
A) attrition.
B) regression to the mean.
C) history of the mean.
D) correlation.

Free

Multiple Choice

Q 111Q 111

Dr.Kim thinks his regression equation is very accurate, but he wonders if perhaps the mean is just as good at predicting scores as the regression equation.He knows that the correlation coefficient (r) for the two variables is quite high, -0.82.Should Dr.Kim use the mean or the regression equation to predict scores?
A) He should use the regression equation because the proportionate reduction in error (r

^{2}) is low. B) He should use the regression equation because the proportionate reduction in error (r^{2}) is high. C) He should use the mean because the proportionate reduction in error (r^{2}) is low. D) He should use the mean because the proportionate reduction in error (r^{2}) is high.Free

Multiple Choice

Q 112Q 112

Predicting an individual's IQ score from two variables, for example, socioeconomic status and education level, would involve the use of:
A) bivariate regression.
B) simple linear regression.
C) multiple regression.
D) nonlinear correlation.

Free

Multiple Choice

Q 113Q 113

In the social sciences, there are numerous variables that can be discussed and considered as important phenomena, but they cannot be observed directly.These are called _____ variables.However, _____ variables, which can be observed and measured, are used to assess the intangible variables.
A) intangible; tangible
B) latent; manifest
C) tangible; intangible
D) manifest; latent

Free

Multiple Choice