Question 1

A regression model applied to autocorrelated data will have ________________________ .

Accepted Answer

A) errors that are independent 
B) residuals with no pattern over time 
C) a Durbin-Watson D that is not close to 2 
D) an invalid test for the slope of the regression line 
E) no way to reduce the autocorrelation 
A) errors that are independent 
B) residuals with no pattern over time 
C) a Durbin-Watson D that is not close to 2 
D) an invalid test for the slope of the regression line 
E) no way to reduce the autocorrelation C

Question 2

A regression model was developed relating fiber and potassium content for a sample of cereals.The circled observation is ________________________ .

Accepted Answer

A) an outlier and leverage point 
B) an outlier and influential point 
C) a leverage and influential point 
D) an influential point only 
E) an outlier only 
A) an outlier and leverage point 
B) an outlier and influential point 
C) a leverage and influential point 
D) an influential point only 
E) an outlier only A

Question 3

The analysis of unusually large or small residuals can help us to ________________________ .

Accepted Answer

A) discover groups in our data 
B) identify unusual or extreme observations 
C) explore other factors in the relationship 
D) All of these. 
E) None of these. 
A) discover groups in our data 
B) identify unusual or extreme observations 
C) explore other factors in the relationship 
D) All of these. 
E) None of these. D

Question 4

A residual analysis results in the finding that there are many residuals clustered closely around 0, but there is also some predicted values that have very large (>0) residuals and some that have very small (<0) residuals.This may indicate that ________________________ .

Accepted Answer

A) there are groups that should be analyzed separately 
B) a linear model is not appropriate for this data 
C) there is a positive autocorrelation. 
D) a transformation is necessary. 
E) the regression model is providing good estimates. 
A) there are groups that should be analyzed separately 
B) a linear model is not appropriate for this data 
C) there is a positive autocorrelation. 
D) a transformation is necessary. 
E) the regression model is providing good estimates.

Question 5

A regression model was developed relating average annual pay to the percentage of women employed for a sample of companies.Below is the plot of residuals versus predicted values.Which of the following re-expression of the data would be appropriate?

Accepted Answer

A) Square the data values. 
B) Cube the data values. 
C) Use a logarithmic transformation. 
D) Use a geometric transformation. 
E) The data should not be transformed. 
A) Square the data values. 
B) Cube the data values. 
C) Use a logarithmic transformation. 
D) Use a geometric transformation. 
E) The data should not be transformed.

Question 6

A regression model was estimated to describe the trend in closing stock prices over 8 months.The Durbin Watson statistic was calculated as 0.5626.Using α = .01 we can conclude that there is evidence of ________________________ .

Accepted Answer

A) positive autocorrelation 
B) negative autocorrelation 
C) positive or negative autocorrelation 
D) an outlier 
E) an inconclusive test 
A) positive autocorrelation 
B) negative autocorrelation 
C) positive or negative autocorrelation 
D) an outlier 
E) an inconclusive test

Question 7

A linear regression model was estimated to describe the trend in world population over time.Below is the plot of residuals versus predicted values.Which of the following re-expression of the data would be appropriate?

Accepted Answer

A) Square the data values. 
B) Cube the data values. 
C) Use a logarithmic transformation. 
D) Use a geometric transformation. 
E) The data should not be transformed. 
A) Square the data values. 
B) Cube the data values. 
C) Use a logarithmic transformation. 
D) Use a geometric transformation. 
E) The data should not be transformed.

Question 8

Which of the following statements about the Ladder of Powers is true?

Accepted Answer

A) Moving further down the Ladder has a weaker effect on the data. 
B) If you go too far, you cannot back up the Ladder of Powers 
C) Will always change the direction of the relationship 
D) Using the Ladder of Powers can improve an analysis of relationships 
E) None of these is true. 
A) Moving further down the Ladder has a weaker effect on the data. 
B) If you go too far, you cannot back up the Ladder of Powers 
C) Will always change the direction of the relationship 
D) Using the Ladder of Powers can improve an analysis of relationships 
E) None of these is true.

Question 9

A data point with a large, positive residual ________________________ .

Accepted Answer

A) should always be removed from further analysis 
B) is one that should be explored as a possible outlier 
C) indicates that the regression model has provided an underestimate for the value 
D) B and C 
E) All of these. 
A) should always be removed from further analysis 
B) is one that should be explored as a possible outlier 
C) indicates that the regression model has provided an underestimate for the value 
D) B and C 
E) All of these.

Question 10

Transformation (re-expression) is NOT done to make the ________________________ .

Accepted Answer

A) relationship between x and y look better 
B) distribution of a variable more symmetric 
C) spread of several groups more alike 
D) form of a scatterplot more nearly linear 
E) scatter in a scatterplot or residual plot spread out evenly rather than following a fan shape 
A) relationship between x and y look better 
B) distribution of a variable more symmetric 
C) spread of several groups more alike 
D) form of a scatterplot more nearly linear 
E) scatter in a scatterplot or residual plot spread out evenly rather than following a fan shape

Question 11

When working with scatterplots of summary values ________________________ .

Accepted Answer

A) we get a good representation of the variation in the data 
B) conclusions will be the same as a random sample of individual data values 
C) data appears more variable than data collected on individuals 
D) the strength of a relationship can be inflated 
E) None of these. 
A) we get a good representation of the variation in the data 
B) conclusions will be the same as a random sample of individual data values 
C) data appears more variable than data collected on individuals 
D) the strength of a relationship can be inflated 
E) None of these.

Question 12

A high leverage point ________________________ .

Accepted Answer

A) can hide in plots of residuals 
B) can be informative about the relationship between x and y 
C) should probably be omitted 
D) can pull the regression line, making the slope appear smaller 
E) All of these, 
A) can hide in plots of residuals 
B) can be informative about the relationship between x and y 
C) should probably be omitted 
D) can pull the regression line, making the slope appear smaller 
E) All of these,

Question 13

Data on internet usage (per 100 inhabitants) and population were collected for a sample of 52 countries whose populations ranged from 0 to 40 million.Suppose the linear model fit to these data is used to determine Internet usage in India, a country with a population of 1,153,230,948.This would be called ________________________ .

Accepted Answer

A) an accurate prediction 
B) an extrapolation 
C) a time series prediction 
D) an exaggeration 
E) a residual 
A) an accurate prediction 
B) an extrapolation 
C) a time series prediction 
D) an exaggeration 
E) a residual

Question 14

Which of the following plots can be used to indicate that there may be different groups in the data that should be considered separately?

Accepted Answer

A) Histogram of the residuals. 
B) Residuals vs predicted values. 
C) A scatterplot showing regression lines for each group. 
D) All of these. 
E) None of these. 
A) Histogram of the residuals. 
B) Residuals vs predicted values. 
C) A scatterplot showing regression lines for each group. 
D) All of these. 
E) None of these.

Question 15

An outlier is a point with ________________________ .

Accepted Answer

A) a y-value far from the regression model 
B) an x-value far from the mean of the x-values 
C) a value that, upon removal, results in a very different model 
D) an extremely high y-value 
E) an extremely high x-value 
A) a y-value far from the regression model 
B) an x-value far from the mean of the x-values 
C) a value that, upon removal, results in a very different model 
D) an extremely high y-value 
E) an extremely high x-value

Question 16

Data were collected for a sample of companies regarding their investment in quality improvement efforts and cost savings realized as a result (both measured as a percentage of sales revenue).The R2 for the regression is 0.833.If the data were collected for individual departments within companies rather than at the company level, we would expect ________________________ .

Accepted Answer

A) a higher R2 
B) a lower R2 
C) the same R2 
D) fewer outliers in the data 
E) None of the above. 
A) a higher R2 
B) a lower R2 
C) the same R2 
D) fewer outliers in the data 
E) None of the above.

Question 17

Quarterly figures for e-commerce retail sales were obtained from the first quarter of 2001 through the fourth quarter of 2007.A regression model was estimated to describe the trend in e-commerce retail sales over time.The Durbin Watson statistic was calculated as 1.727.Using α = .01 we can conclude that there is ________________________ .

Accepted Answer

A) evidence of positive autocorrelation 
B) evidence of negative autocorrelation 
C) no evidence of positive or negative autocorrelation 
D) evidence of an outlier 
E) an inconclusive test 
A) evidence of positive autocorrelation 
B) evidence of negative autocorrelation 
C) no evidence of positive or negative autocorrelation 
D) evidence of an outlier 
E) an inconclusive test

Question 18

Which of the following Ladder of Powers is a good place to start if you are dealing with counted data?

Accepted Answer

A) The (negative) square root. 
B) The (negative) reciprocal square root. 
C) Square of the data values. 
D) Square root of the data values. 
E) Base-10 Log. 
A) The (negative) square root. 
B) The (negative) reciprocal square root. 
C) Square of the data values. 
D) Square root of the data values. 
E) Base-10 Log.

Question 19

A regression model that showed good fit was developed recently to predict average annual pay for companies based on the percentage of female employees.Companies included in the analysis had between 40% and 80% of employees who were female.This model could safely be used to estimate average annual pay for companies ________________________ .

Accepted Answer

A) with ¾ of female employees 
B) owned and operated in the 18th century 
C) with 10% of female employees 
D) that will start up in the next 20 years 
E) regardless of the number of females or annual pay 
A) with ¾ of female employees 
B) owned and operated in the 18th century 
C) with 10% of female employees 
D) that will start up in the next 20 years 
E) regardless of the number of females or annual pay

Exam 17: Understanding Residuals

A regression model applied to autocorrelated data will have ________________________ .

A regression model was developed relating fiber and potassium content for a sample of cereals.The circled observation is ________________________ .

The analysis of unusually large or small residuals can help us to ________________________ .

A residual analysis results in the finding that there are many residuals clustered closely around 0, but there is also some predicted values that have very large (>0) residuals and some that have very small (<0) residuals.This may indicate that ________________________ .

A regression model was developed relating average annual pay to the percentage of women employed for a sample of companies.Below is the plot of residuals versus predicted values.Which of the following re-expression of the data would be appropriate?

A regression model was estimated to describe the trend in closing stock prices over 8 months.The Durbin Watson statistic was calculated as 0.5626.Using α = .01 we can conclude that there is evidence of ________________________ .

A linear regression model was estimated to describe the trend in world population over time.Below is the plot of residuals versus predicted values.Which of the following re-expression of the data would be appropriate?

Which of the following statements about the Ladder of Powers is true?

A data point with a large, positive residual ________________________ .

Transformation (re-expression) is NOT done to make the ________________________ .

When working with scatterplots of summary values ________________________ .

A high leverage point ________________________ .

Which of the following plots can be used to indicate that there may be different groups in the data that should be considered separately?

An outlier is a point with ________________________ .

Which of the following Ladder of Powers is a good place to start if you are dealing with counted data?

Data and Decisions

Visualizing and Describing Categorical Data

Describing, Displaying, and Visualizing Quantitative Data

Correlation and Linear Regression

Randomness and Probability

Random Variables and Probability Models

The Normal and Other Continuous Distributions

Data Sources: Observational Studies and Surveys

Data Sources: Experiments

Sampling Distributions and Confidence Intervals for Proportio

Confidence Intervals for Means

Testing Hypotheses

More About Tests and Intervals

Comparing Two Means

Inference for Counts: Chi-Square Tests

Inference for Regression

Multiple Regression

Building Multiple Regression Models

Time Series Analysis

Introduction to Data Mining

Quality Control

Nonparametric Methods

Decision Making and Risk

Analysis of Experiments and Observational Studies

Statistics and Data Analysis

Filters