Concept explainers
The method for rating teams in Example 7.8 is based on actual and predicted point spreads. This method can be biased if some teams run up the score in a few games. An alternative possibility is to base the ratings only on wins and losses. For each game, you observe whether the home team wins. Then from the proposed ratings, you predict whether the home team will win. (You predict the home team will win if the home team advantage plus the home team’s rating is greater than the visitor team’s rating.) You want the ratings such that the number of predictions that match the actual outcomes is maximized. Try modeling this. Do you run into difficulties? (Remember that Solver doesn’t like IF functions.)
EXAMPLE 7.8 RATING NFL TEAMS9
We obtained the results of the 256 regular-season NFL games from the 2015 season (the 2016 season was still ongoing as we wrote this) and entered the data into a spreadsheet, shown at the bottom of Figure 7.38. See the file NFL Ratings Finished.xlsx. (Some of these results are hidden in Figure 7.38 to conserve space.) The teams are indexed 1 to 32, as shown at the top of the sheet. For example, team 1 is Arizona, team 2 is Atlanta, and so on. The first game entered (row 6) is team 19 New England versus team 25 Pittsburgh, played at New England. New England won the game by a score of 28 to 21, and the point spread (home team score minus visitor team score) is calculated in column J. A positive point spread in column J means that the home team won; a negative point spread indicates that the visiting team won. The goal is to determine a set of ratings for the 32 NFL teams that most accurately predicts the actual outcomes of the games played.
Want to see the full answer?
Check out a sample textbook solutionChapter 7 Solutions
Practical Management Science
- You want to take out a 450,000 loan on a 20-year mortgage with end-of-month payments. The annual rate of interest is 3%. Twenty years from now, you will need to make a 50,000 ending balloon payment. Because you expect your income to increase, you want to structure the loan so at the beginning of each year, your monthly payments increase by 2%. a. Determine the amount of each years monthly payment. You should use a lookup table to look up each years monthly payment and to look up the year based on the month (e.g., month 13 is year 2, etc.). b. Suppose payment each month is to be the same, and there is no balloon payment. Show that the monthly payment you can calculate from your spreadsheet matches the value given by the Excel PMT function PMT(0.03/12,240, 450000,0,0).arrow_forwardBased on Grossman and Hart (1983). A salesperson for Fuller Brush has three options: (1) quit, (2) put forth a low level of effort, or (3) put forth a high level of effort. Suppose for simplicity that each salesperson will sell 0, 5000, or 50,000 worth of brushes. The probability of each sales amount depends on the effort level as described in the file P07_71.xlsx. If a salesperson is paid w dollars, he or she regards this as a benefit of w1/2 units. In addition, low effort costs the salesperson 0 benefit units, whereas high effort costs 50 benefit units. If a salesperson were to quit Fuller and work elsewhere, he or she could earn a benefit of 20 units. Fuller wants all salespeople to put forth a high level of effort. The question is how to minimize the cost of encouraging them to do so. The company cannot observe the level of effort put forth by a salesperson, but it can observe the size of his or her sales. Thus, the wage paid to the salesperson is completely determined by the size of the sale. This means that Fuller must determine w0, the wage paid for sales of 0; w5000, the wage paid for sales of 5000; and w50,000, the wage paid for sales of 50,000. These wages must be set so that the salespeople value the expected benefit from high effort more than quitting and more than low effort. Determine how to minimize the expected cost of ensuring that all salespeople put forth high effort. (This problem is an example of agency theory.)arrow_forwardSuppose that GLC earns a 2000 profit each time a person buys a car. We want to determine how the expected profit earned from a customer depends on the quality of GLCs cars. We assume a typical customer will purchase 10 cars during her lifetime. She will purchase a car now (year 1) and then purchase a car every five yearsduring year 6, year 11, and so on. For simplicity, we assume that Hundo is GLCs only competitor. We also assume that if the consumer is satisfied with the car she purchases, she will buy her next car from the same company, but if she is not satisfied, she will buy her next car from the other company. Hundo produces cars that satisfy 80% of its customers. Currently, GLC produces cars that also satisfy 80% of its customers. Consider a customer whose first car is a GLC car. If profits are discounted at 10% annually, use simulation to estimate the value of this customer to GLC. Also estimate the value of a customer to GLC if it can raise its customer satisfaction rating to 85%, to 90%, or to 95%. You can interpret the satisfaction value as the probability that a customer will not switch companies.arrow_forward
- Based on Morrison and Wheat (1984). When his team is behind late in the game, a hockey coach usually waits until there is one minute left before pulling the goalie out of the game. Using simulation, it is possible to show that coaches should pull their goalies much sooner. Suppose that if both teams are at full strength, each team scores an average of 0.05 goal per minute. Also, suppose that if you pull your goalie you score an average of 0.08 goal per minute and your opponent scores an average of 0.12 goal per minute. Suppose you are one goal behind with five minutes left in the game. Consider the following two strategies: ■ Pull your goalie if you are behind at any point in the last five minutes of the game; put him back in if you tie the score. ■ Pull your goalie if you are behind at any point in the last minute of the game; put him back in if you tie the score. Which strategy maximizes your probability of winning or tying the game? Simulate the game using 10-second increments of…arrow_forwardHi is this correct?The management of an oil company is trying to decide whether to drill for oil in a particular fieldin the Gulf of Mexico. It costs the company $600 thousand to drill in the selected field. Themanagement believes that if oil is found in this field, its estimated value will be $3400 thousand. Atpresent, this oil company believes that there is a 45% chance that the selected field actually containsoil. Before drilling, the oil company can hire a team of geologists to perform seismographic tests at acost of $55 thousand. Based on similar tests in other fields, the tests have a 25% false negative rate(no oil predicted when oil is present) and a 15% false positive rate (oil predicted when no oil ispresent).A. Assume the oil company wants to maximize its expected net earnings. Please utilize decisiontree analysis to determine its optimal strategy.B. Calculate the expected value of the information (EVI/EVSI) provided by the team ofgeologists.C. Calculate and interpret EVPI…arrow_forwardA market analyst working for a small appliance manufacturer finds that if the firm produces and sells x blenders annually, a model for the total profit (in dollars) is P(x) = 8x + 0.3x2 − 0.001x3 − 372. Graph the function P in an appropriate viewing rectangle, and use the graph to answer the following questions. (a) When just a few blenders are manufactured, the firm loses money (profit is negative). (For example, P(10) = −263, so the firm loses $263.00 if it produces and sells only 10 blenders.) How many blenders must the firm produce to break even? (Round your answer to the nearest whole number.) blenders(b) Does profit increase indefinitely as more blenders are produced and sold? YesNo If not, what is the largest possible profit the firm could have? (If profit increases indefinitely, enter your answer as ∞. Otherwise, round your answer to the nearest cent.)arrow_forward
- Vladimir Ulanowsky is playing Keith Smithson in atwo-game chess match. Winning a game scores 1 match 19.4 Further Examples of Probabilistic Dynamic Programming Formulations 1029 point, and drawing a game scores 12match point. After thetwo games are played, the player with more match points isdeclared the champion. If the two players are tied after twogames, they continue playing until someone wins a game(the winner of that game will be the champion). Duringeach game, Ulanowsky can play one of two ways: boldly orconservatively. If he plays boldly, he has a 45% chance ofwinning the game and a 55% chance of losing the game. Ifhe plays conservatively, he has a 90% chance of drawing thegame and a 10% chance of losing the game. Ulanowsky’sgoal is to maximize his probability of winning the match.Use dynamic programming to help him accomplish thisgoal. If this problem is solved correctly, even thoughUlanowsky is the inferior player, his chance of winning the match is over 12. Explain this…arrow_forwardTRUE OR FALSE In a simplex maximization slack variable is added to convert the objective function to equation.arrow_forwardWe are considering investing in three stocks. The randomvariable Si represents the value one year from now of $1invested in stock i. We are given that E(S1) 1.15, E(S2) 1.21, E(S3) 1.09; var S1 0.09, var S2 0.04, var S3 0.01; cov(S1, S2) 0.006, cov(S1, S3) 0.004, and cov(S2,S3) 0.005. We have $100 to invest and want to have anexpected return of at least 15% during the next year.Formulate a QPP to find the portfolio of minimum variancethat attains an expected return of at least 15%.arrow_forward
- Please no written by hand and no emage John is an investor. His portfolio primarily tracks the standard and poor 500 (S & P 500) and John wants to add the stock of ABC corp. Before adding the stock to his portfolio, he wants to assess the directional relationship between the stock and the S & P 500. John does not want to increase the unsystematic risk of his portfolio. Thus he is not interested in owning securities in the portfolio that tends to move in the same direction. The prices obtained are summarized in the table that follows:Required: Calculate the covariance of John’s stocks. State the implication of the outcome in project management decisionsarrow_forwardIn the figure below, no probabilities are known for the occurrence of the nature states. For the matrix, solve every one of the subpoints with the respective formulas: Laplace Maximin(Minimax) Savage Hurwitz (assume that α=0.3)arrow_forwardAn investment manager is considering stocks X1, X2, and X3 for investment. Market research shows the following information (per stock) X1 X2 X3 cost $100 risk measure 8 price annual growth rate: 9% annual return: $14 cost $120 risk measure 10 price annual growth rate: 13% annual return: $15 cost $80 risk measure 7 price annual growth rate: 8% annual return: $20 Based on his experience, the manager has set the following priorities for the investment: (1) The total amount invested should be at least $90,000. (d1) (2) The minimum annual average growth rate in stock prices is 12%. (d2) (3) The risk factor of all stocks should not exceed a total of 5,000. (d3) (4) The total annual return should be $15,000. (d4) The constraint for the annual growth rate can be written as: 9X1 + 13X2 + 8X3 ≥ 12 [(9X1 + 13X2 + 8 X3)/(X1+ X2+ X3)] + d2- - d2+ ≥ 12 [(9X1 + 13X2 + 8X3)/(X1+ X2+ X3)] + d2- - d2+ ≤ 0 -3X1+ X2 - 4X3 + d2- - d2+ ≥ 12 -3X1 +…arrow_forward
- Practical Management ScienceOperations ManagementISBN:9781337406659Author:WINSTON, Wayne L.Publisher:Cengage,