The general manager of QuickFix, a chain of quick-service, no appointment auto repair shops, wants to develop a model to forecast monthly vehicles served at any particular shop based on four factors: garage bays, population within 5-mile radius (Population in 1,000s), interstate highway access (Access equals 1 if convenient, 0 otherwise), and time of year (Winter equals 1 if winter, 0 otherwise). He believes that, all else equal, shops near an interstate will service more vehicles and that more vehicles will be serviced in the winter due to battery and tire issues. A sample of 19 locations has been obtained. A portion of the data is shown in the accompanying table.
a. Estimate the regression equation relating vehicles serviced to the four explanatory variables.
b. Interpret each of the slope coefficients.
c. At the 5% significance level, are the explanatory variables jointly significant? Are they individually significant?
d. What about at the 10% significance level? What proportion of the variability in vehicles served is explained by the four explanatory variables?
e. Predict vehicles serviced in a non-winter month for a particular location with 5 garage bays, a population of 40,000, and convenient interstate access.
Vehicles Served Garage Bays Population Access Winter 200 3 15 351 3 22 464 74 1 1
> Consider the following sample regressions for the linear and quadratic models along with their respective R2 and adjusted R2. a. Use the appropriate goodness-of-fit measure to justify which model fits the data best. b. Given the best-fitting model, pr
> Consider the following sample regressions for the linear and quadratic models along with their respective R2 and adjusted R2. a. Use the appropriate goodness-of-fit measure to justify which model fits the data best. b. Given the best-fitting model, pre
> Consider the following three models: For each of the estimated models, predict y when x equals 10 and 15. ŷ = 80 + 1.2x ŷ = 200 + 2.1x – 0.6x? ŷ = 100 + 16x – 2.2x² + 0.08x³
> Consider the following two estimated models: For each of the estimated models, predict y when x equals 5 and 10. ŷ = 25 + 1.2x ŷ = 30 + 1.4x – 0.12x²
> The Chartered Financial Analyst (CFA) designation is fast becoming a requirement for serious investment professionals. Although it requires successfully completing three levels of grueling exams, it also promises great careers with lucrative salaries. Su
> Jack Sprague is the relocation specialist for a real estate firm in the town of Arlington, Massachusetts. He has been working with a client who wishes to purchase a single-family home in Arlington. After seeing the information that Jack provided, the cli
> A study examined “sidewalk rage” in an attempt to find insight into anger’s origins and offer suggestions for anger-management treatments (The Wall Street Journal, February 15, 2011). â€
> Refer to the previous exercise for a description of the data set. Previous exercise: More and more parole boards are using risk assessment tools when trying to determine an individual’s likelihood of returning to crime (The Boston Gl
> More and more parole boards are using risk assessment tools when trying to determine an individual’s likelihood of returning to crime (The Boston Globe, February 20, 2011). Most of these models are based on a range of character traits a
> Refer to the previous exercise for a description of the data set. Estimate the logit probability model where admission is a function of the SAT score and high school GPA. Previous exercise: Seton Hall University is a Roman Catholic university situated
> Consider the following sample information: k = 3 and H = 4.5. a. Specify the competing hypotheses to test whether some differences exist between the medians. b. At the 10% significance level, do some medians differ? Explain
> Seton Hall University is a Roman Catholic university situated in New Jersey, with easy access to New York City. Like most universities, it uses SAT scores and high school GPA as primary criteria for admission. The accompanying table shows a portion of da
> Since assembly line work can be tedious and repetitive, it is not suited for everybody. Consequently, a production manager is developing a binary choice regression model to predict whether a newly hired worker will stay in the job for at least one year (
> To encourage performance, loyalty, and continuing education, the human resources department at a large company wants to develop a regression-based compensation model (Comp in $ per year) for mid-level managers based on three variables: (1) business unit
> According to the U.S. Department of Health and Human Services, African American women have the highest rates of being overweight compared to other groups in the United States. Individuals are considered overweight if their body mass index (BMI) is 25 or
> The manager of a diner wants to reevaluate his staffing needs depending on variations in customer traffic during the day. He collects data on the number of customers served, along with four dummy variables representing the morning, afternoon, evening, an
> According to the Center for Disease Control and Prevention, life expectancy at age 65 in America is about 18.7 years. Medical researchers have argued that while excessive drinking is detrimental to health, drinking a little alcohol every day, especially
> A researcher in the education department wants to determine if the number of hours that business students study per week at a state university varies by term. He conducts a survey where business students are asked how much they study per week in each of
> An analyst studies quarterly data on the relationship between retail sales (y, in $ millions), gross national product (x, in $ billions), and a quarterly dummy d that equals 1 if the sales are for the 4th quarter, 0 otherwise. He estimates the model y =
> In a seminal study, researchers documented race-based hiring in the Boston and Chicago labor markets (American Economic Review, September 2004). They sent out identical resumes to employers, half with traditionally African American names and the other ha
> A financial analyst would like to determine whether the return on Fidelity’s Magellan mutual fund varies depending on the quarter; that is, if there is a seasonal component describing return. He collects 10 years of quarterly return dat
> Researchers at the Wharton School of Business have found that men and women shop for different reasons. While women enjoy the shopping experience, men are on a mission to get the job done. Men do not shop as frequently, but when they do, they make big pu
> Refer to the previous exercise for a description of the data set. Estimate the logit model where divorce depends on age, income, and the number of children. Previous exercise: According to an estimate, the divorce rate in England has fallen to a 26yea
> According to an estimate, the divorce rate in England has fallen to a 26year low (The Guardian, August 29, 2008). However, it is documented that the rate of divorce is more than twice as high for men and women aged 25 to 29. John Haddock is a sociologist
> Refer to the previous exercise for a description of the data set. Estimate the logit model where insurance coverage depends on premium percentage and income. Consider an individual with an income of $60,000. What is the probability that she has insurance
> Nearly nine out of 10 Americans now have health insurance since the Affordable Care Act (also known as “Obamacare”) took effect in 2014 (www.cnn.com, April 13, 2015). However, 22% of those making less than $36,000 stil
> Refer to the previous exercise for a description of the data set. Estimate the logit model where the Under Armour purchase depends on age. Previous exercise: FILE Purchase. Annabel, a retail analyst, has been following Under Armour, Inc., the pioneer
> FILE Purchase. Annabel, a retail analyst, has been following Under Armour, Inc., the pioneer in the compression-gear market. Compression garments are meant to keep moisture away from a wearer’s body during athletic activities in warm and cool weather. An
> Using 40 observations, the following output was obtained when estimating the logit model. a. What is the predicted probability when x1 = 15, x2 = 10, and x3 = −2? b. At the 5% significance level, which of the explanatory variables ar
> Using 30 observations, the following output was obtained when estimating the logit model. a. What is the predicted probability when x = 0.40? b. Is x significant at the 5% level? Predictor Coef SE Constant -0.188 0.083 2.27 0.024 3.852 1.771 2.18
> Using 30 observations, the following regression output is obtained from estimating the linear probability model y = β0 + β1x + ε. a. What is the predicted probability when x = 20? b. Is x significant at the 5% leve
> Consider a binary response variable y and two explanatory variables x1 and x2. The following table contains the parameter estimates of the linear probability model (LPM) and the logit model, with the associated p-values shown in parentheses. a. Comment
> According to the Organization of Economic Cooperation and Development, South Koreans spend more hours per year on the job than people in any other developed country (The Wall Street Journal, March 1, 2010). Suppose 10 workers in South Korea and 10 worker
> Consider a binary response variable y and an explanatory variable x. The following table contains the parameter estimates of the linear probability model (LPM) and the logit model, with the associated p-values shown in parentheses. a. Use both models t
> Consider a binary response variable y and an explanatory variable x. The following table contains the parameter estimates of the linear probability model (LPM) and the logit model, with the associated p-values shown in parentheses. a. Test for the sign
> Consider a binary response variable y and an explanatory variable x that varies between 0 and 50. The linear probability model is estimated as. a. Compute the estimated probability for x = 25 and x = 40. b. For what values of x is the estimated proba
> Mechanics Consider a binary response variable y and an explanatory variable x that varies between 0 and 4. The linear model is estimated as. a. Compute the estimated probability for x = 2 and x = 3. b. For what values of x is the estimated probabilit
> The following table shows a portion of monthly data on the personal savings rate (Savings in %) and personal disposable income (Income in $ billions) in the U.S. from January 2007 to November 2010. a. Estimate and interpret a log-log model, ln (Savings
> One of the theories regarding initial public offering (IPO) pricing is that the initial return (the percentage change from offer to open price) on an IPO depends on the price revision (the percentage change from pre-offer to offer price). Another factor
> The distribution center for an online retailer has been experiencing quite a few “pick errors” (i.e., retrieving the wrong item). Although the warehouse manager thinks most errors are due to inexperienced workers, she
> . According to the World Health Organization, obesity has reached epidemic proportions globally. While obesity has generally been linked with chronic disease and disability, researchers argue that it may also affect wages. In other words, the body mass i
> A sociologist is looking at the relationship between consumption expenditures of families in the United States (Consumption in $), family income (Income in $), and whether or not the family lives in an urban or rural community (Urban = 1 if urban, 0 othe
> House price y is estimated as a function of the square footage of a house x; a dummy variable d that equals 1 if the house has ocean views and 0 otherwise; and the interaction variable xd. The estimated house price, measured in $1,000s, is given by a.
> An analysis of census data suggests that married men have a higher median income than unmarried men (The Boston Globe, January 19, 2010). Suppose the incomes (in $1,000s) of six married men and seven unmarried men produce the following results: a. Set
> A random sample of eight drugstores shows the following prices (in $) for a popular pain reliever: a. Specify the competing hypotheses to determine whether the median price is less than $6.00. b. Calculate the value of the test statistic. c. The p-va
> The annual salary of an employee y (in $1,000s) is estimated as a function of years of experience x; a dummy variable d that equals 1 for college graduates and 0 for those graduating from high school but not college; and the interaction variable xd. The
> Using 20 observations, the following regression output is obtained from estimating y = β0 + β1x + β2d + β3xd + ε. a. Compute for x = 10 and d = 1; compute for x = 10 and d = 0. b. Are the du
> Consider a linear regression model where y represents the response variable and x and d are the explanatory variables; d is a dummy variable assuming values 1 or 0. A model with the dummy variable d and the interaction variable xd is estimated as ŷ
> A government researcher is analyzing the relationship between retail sales (in $ millions) and the gross national product (GNP in $ billions). He also wonders whether there are significant differences in retail sales related to the quarters of the year.
> The issues regarding executive compensation have received extensive media attention (The New York Times, February 9, 2009). Consider a regression model that links CEO compensation (in $ millions) with the total assets of the firm (in $ millions) and the
> In an attempt to “time the market,” a financial analyst studies the quarterly returns of a stock. He uses the model y = β0 + β1d1 + β2d2 + β3d3 + ε where y i
> A manager at an ice cream store is trying to determine how many customers to expect on any given day. Overall business has been relatively steady over the past several years, but the customer count seems to have ups and downs. He collects data over 30 da
> Use the accompanying data to estimate a linear regression model with Math as the response variable and GPA and Female as the explanatory variables. a. Compute the predicted math score for a male student with a GPA of 3.5. Repeat the computation for a fe
> The SAT has gone through many revisions over the years. People argue that female students generally do worse on math tests but better on writing tests. Consider the following portion of data on 20 students who took the SAT test last year. Information inc
> A professor teaches two sections of an introductory statistics course. He gives each section the same final and wonders if any significant differences exist between the medians of these sections. He draws a sample of seven scores from Section A and six s
> In the United States, baseball has always been a favorite pastime and is rife with statistics and theories. While baseball purists may disagree, to an applied statistician no topic in baseball is too small or hypothesis too unlikely. Researchers at Wayne
> A researcher wonders whether males get paid more, on average, than females at a large firm. She interviews 50 employees and collects data on each employee’s hourly wage (Wage in $), years of higher education (EDUC), years of experience
> According to the World Health Organization, obesity has reached epidemic proportions globally. While obesity has generally been linked with chronic disease and disability, researchers argue that it may also affect salaries. In other words, the body mass
> One of the theories regarding initial public offering (IPO) pricing is that the initial return y (the percentage change from offer to open price) on an IPO depends on the price revision x (the percentage change from pre-offer to offer price). Another fac
> A sociologist is studying the relationship between consumption expenditures of families in the United States (Consumption in $), family income (Income in $), and whether or not the family lives in an urban or rural community (Urban = 1 if urban, 0 otherw
> House price y is estimated as a function of the square footage of a house x and a dummy variable d that equals 1 if the house has ocean views. The estimated house price, measured in $1,000s, is given by = 118.90 + 0.12x + 52.60d. a. Compute the predicte
> Applications An executive researcher wants to better understand the factors that explain differences in salaries for marketing majors. He decides to estimate two models: y = β0 + β1d1 + ε (Model 1) and y = β0 + β1d1 + β2d2 + ε (Model 2). Here y represent
> Using 50 observations, the following regression output is obtained from estimating y = β0 + β1x + β2d1 + β3d2 + ε. a. Compute for x = 250, d1 = 1, and d2 = 0; compute for x = 250, d1 = 0, and
> Consider a linear regression model where y represents the response variable and d1 and d2 are dummy variables. The model is estimated as ŷ = 160 + 15d, + 32dz- a. Compute î for d1 = 1 and d2 = 1. b. Compute i for d1 = 0 and d2 = 0. %3D
> Mechanics Consider a linear regression model where y represents the response variable, x is a quantitative explanatory variable, and d is a dummy variable. The model is estimated as ŷ = 14.8 + 4.4x – 3.8d a. Interpret the dummy variable coefficient.
> A bank employs two appraisers. When approving borrowers for mortgages, it is imperative that the appraisers value the same types of properties consistently. To make sure that this is the case, the bank asks the appraisers to value 10 different properties
> The consumption function is one of the key relationships in economics, where consumption (y) depends on disposable income (x). Consider the following table, which presents a portion of quarterly data on personal consumption expenditure and disposable inc
> The S&P 500 Index is a value-weighted index of prices of 500 large-cap common stocks actively traded in the United States. A research analyst at an investment firm is attempting to forecast the daily stock price of Genzyme Corporation, one of the wor
> The following data represent a portion of quarterly net sales (in $ millions) of Lowe’s Companies, Inc., over five years. a. Estimate a linear trend model with seasonal dummy variables and compute MSE and MAD. b. Estimate an exponent
> Refer to the previous exercise for a description of the data set. Previous exercise: Revenue passenger-miles are calculated by multiplying the number of paying passengers by the distance flown in thousands. The accompanying table shows a portion of mon
> Revenue passenger-miles are calculated by multiplying the number of paying passengers by the distance flown in thousands. The accompanying table shows a portion of monthly data on revenue passenger-miles (in millions) from January 2006 through September
> While U.S. inventory levels remain low, there is a slight indication of an increase in the U.S. business inventory-to-sales ratio, due to higher sales (The Wall Street Journal, December 15, 2010). The accompanying table shows a portion of seasonally adju
> Consider the following portion of data on real estate loans granted by FDIC insured Commercial Banks in the United States (in $ billions, base = 2007) from 1972 to 2007. Year ………………………………………………………………………………………………… Loans 1972 ……………………………………………………………………………
> Consider the following portion of monthly data on price per gallon of regular unleaded gasoline in the United States from January 2009 to December 2010. Date …………………………………………………………………………………… Price Per Gallon Jan-09 ………………………………………………………………………………………………….
> Tourism was hit hard by the international financial crisis that began in the fall of 2008. According to the Bureau of Economic Analysis (December 20, 2010), tourism spending has picked up, but it still remains below its peak, which occurred in 2007. The
> The following table lists a portion of the percentage (share) of total shipment of music that falls in the category of country and rap/hip-hop rock music from 1990–2008. a. Plot each of the series and comment on the respective trend.
> A diet center claims that it has the most effective weight loss program in the region. Its advertisement says, “Participants in our program really lose weight.” Five clients of this program are weighed on the first day
> The U.S. housing market remains fragile despite historically low mortgage rates (AARP, July 2, 2010). Since the rate on 30-year mortgages is tied to the 10-year yield on Treasury bonds, it is important to be able to predict this yield accurately. The acc
> A research analyst at an investment firm is attempting to forecast the daily stock price of Home Depot, using causal models. The following table shows a portion of the daily adjusted closing prices of Home Depot y and the Dow Jones Industrial Average x f
> The Phillips curve is regarded as a reliable tool for forecasting inflation. It captures the inverse relation between the rate of unemployment and the rate of inflation; the lower the unemployment in an economy, the higher is the inflation rate. Consider
> Hiroshi Sato, an owner of a sushi restaurant in San Francisco, has been following an aggressive marketing campaign to thwart the effect of rising unemployment rates on business. He used monthly data on sales ($1,000s), advertising costs ($), and the unem
> Consider the following portion of data on y and x. a. Estimate yt = β0 + β1xt−1 + εt. b. Estimate yt = β0 + β1yt−1 + εt. c. Estimate yt = &I
> Consider the following portion of data on y and x. a. Estimate yt = β0 + β1xt−1 + εt to make a one-step-ahead forecast for period 13. b. Estimate yt = β0 + β1ytâˆ
> Consider the following portion of data on the variable y. t ………………………………………………………………………………………………………… y 1 …………………………………………………………………………………………………… 29.32 2 ………………………………………………………………………………………………… 30.96 ⋮ ………………………………………………………………………………………………………… ⋮ 24 ………………………
> Consider the following portion of data on the response variable y and the explanatory variable x. a. Estimate yt = β0 + β1xt−1 + εt and yt = β0 + β1xt−1 +
> Refer to the previous exercise for a description of the data set. Fit an appropriate polynomial trend model along with seasonal dummies to make a forecast for November and December of 2010. Previous exercise: The following table lists a portion of the
> The following table lists a portion of the University of Michigan’s Consumer Sentiment Index. This index is normalized to have a value of 100 in 1965 and is used to record changes in consumer morale. Date ……………………………………………………………………………. Consumer Sentimen
> Suppose eight college-bound students take a mock SAT, complete a three-month test-prep course, and then take the real SAT . A portion of the data is shown in the accompanying table. a. Specify the competing hypotheses to determine whether the median sc
> Refer to the previous exercise for a description of the data set. Previous exercise: Blockbuster Inc. faced challenges by the growing online market (CNNMoney.com, March 3, 2009). Its revenue from rental stores sagged as customers increasingly got thei
> Blockbuster Inc. faced challenges by the growing online market (CNNMoney.com, March 3, 2009). Its revenue from rental stores sagged as customers increasingly got their movies through the mail or high-speed Internet connections. The following table contai
> The controller of a small construction company is attempting to forecast expenses for the next year. He collects quarterly data on expenses (in $1,000s) over the past five years, a portion of which is shown in the accompanying table. a. Estimate a line
> Refer to the previous exercise for a description of the data set. Estimate a linear trend model with seasonal dummy variables to make forecasts for the first three months of 2011. FILE Expenses. The controller Previous exercise: Consider a portion of m
> Consider a portion of monthly return data (in %) on 20-year Treasury Bonds from 2006–2010. Date ……………………………………………………………………………………………… Return Jan-06 ……………………………………………………………………………………………… 4.65 Feb-06 ……………………………………………………………………………………………… 4.73 ⋮ …………………………………
> Hybrid cars have gained popularity because of their fuel economy and the uncertainty regarding the price of gasoline. All automakers, including the Ford Motor Co., have planned to significantly expand their hybrid vehicle lineup (CNN.com, November 9, 200
> The accompanying data file contains monthly observations for 5 years. Use it to estimate (a) a linear trend model with seasonal dummies, and (b) an exponential trend model with seasonal dummies. Which of the two models has a lower MSE and MAD? Use the ap
> The accompanying data file contains monthly observations for 5 years. a. Construct the seasonal indices for the data. b. Plot the seasonally adjusted series to recommend the appropriate trend model. c. Use the trend and seasonal estimates to make fore
> The accompanying data file contains quarterly observations for 5 years. a. Plot the series and discuss its trend and seasonal components. b. Use decomposition analysis to make in-sample forecasts with the exponential trend and seasonal indices. Compute
> The accompanying data file contains monthly observations for 5 years. Calculate and interpret the seasonal indices for April and November.
> The following data are provided for two samples drawn from independent populations: W = 545, n1 = 25, and n2 = 25. Suppose the distribution of W is approximately normal. a. Calculate the mean and the standard deviation of the distribution of W. b. Spec
> The accompanying data file contains quarterly observations for 5 years. Calculate and interpret the seasonal indices for quarters 1 and 4.