...partial F test. Comparing complete vs Reduced model. [SSE(reduced) – SSE(complete)]/ (p-q) F* = ------------------------------------------------------MSE(complete) SSR(Extra Variables)/(p-q) F* = --------------------------------------------------------MSE(complete) Multicollinearity Diagnosis, detection, VIF Qualitative variables Qualitative variables with two or more levels, indicator/dummy variables, interpretation of regression parameters, model with both qualitative variables and quantitative variables • Some Problems: 1. The following data gives R2, MSE statistic for different models. (p-1) R-Square MSE Model ---------------------------------------------------------------1 0.3555 3.94511 x2 1 0.3227 4.14604 x5 1 0.2839 4.38337 x6 1 0.1904 4.95545 x4 1 0.1538 5.17958 x8 1 0.1262 5.34868 x3 1 0.1140 5.42338 x7 1 0.0682 5.70378 x1 ---------------------------------------------------------------2 0.4927...
Words: 825 - Pages: 4
...Journal of Data Science 2(2004), 329-346 Estimating Optimal Transformations for Multiple Regression Using the ACE Algorithm Duolao Wang1 and Michael Murphy2 School of Hygiene and Tropical Medicine and 2 London School of Economics 1 London Abstract: This paper introduces the alternating conditional expectation (ACE) algorithm of Breiman and Friedman (1985) for estimating the transformations of a response and a set of predictor variables in multiple regression that produce the maximum linear effect between the (transformed) independent variables and the (transformed) response variable. These transformations can give the data analyst insight into the relationships between these variables so that relationship between them can be best described and non-linear relationships can be uncovered. The power and usefulness of ACE guided transformation in multivariate analysis are illustrated using a simulated data set as well as a real data set. The results from these examples clearly demonstrate that ACE is able to identify the correct functional forms, to reveal more accurate relationships, and to improve the model fit considerably compared to the conventional linear model. Key words: Alternating conditional expectation (ACE) algorithm, nonparametric regression, transformation. 1. Introduction In regression analysis, we try to explain the effect of one or more independent variables (predictors or covariates) on a dependent variable (response). The initial stages of data analysis...
Words: 6000 - Pages: 24
...As the new VP of Marketing at Clipboard Tablet Co., it is my duty to both analyze the results of the previous VP, and offer my own analysis on product performance for the X5, X6, and X7 tablets. Specifically, I will focus on the products themselves, their life cycles, and how they stack up in terms of price and performance. A financial review of each product will be undertaken as well, focusing on sales, costs, profitability, prices, and unit margins. I will then conduct a market review which will cover subjects ranging from new sales, previous sales, and market saturation. Finally, I will propose an alternate strategy, specifically in terms of pricing and R&D allocations. Initial observations indicate the previous VP of Marketing, Mr. Joe Schmoe, was satisfied with his opening assessment of the three products and was therefore content with keeping the project on autopilot. His satisfaction was ultimately unworthy and premature, as the CEO, Ms. Sally Smothers, does not believe these products are being developed and marketed to their fullest potential. There are a few key areas in which I can find fault with Mr. Schmoe. First, his inclination to disregard changing market forces. This is demonstrated by lack of motivation to make any changes whatsoever, despite making observations that each product performs differently. He is also negligent to make any adjustments based on future predictions and estimates. Areas in which he could have made an impact include R&D, manufacturing...
Words: 1512 - Pages: 7
...Problem 1: Answer1 The next BEST move for A would be D. If A is maximizing player then the next level would be minimum and then the next would be maximum and so on. MAX: MAX(E)=Minmax(L,M)=MINMAX(RESULT (7,8))=7 MAX(F)=Minmax(N,O)=MINMAX(RESULT (5,8))=8 MAX(G)=Minmax(P,Q)=MINMAX(RESULT (2,3))=3 MAX(H)=Minmax(R,S)=MINMAX(RESULT (0,-2))=0 MAX(I)=Minmax(T,U)=MINMAX(RESULT (6,2))=6 MAX(J)=Minmax(V,W)=MINMAX(RESULT (5,8))=8 MAX(K)=Minmax(X,Y)=MINMAX(RESULT (9,2))=9 MIN: MIN(B)=MINMAX(E,F,G)=MINMAX(7,8,3)=3 MIN(C)=MINMAX(H,I)=MINMAX(0,6)=0 MIN(D)=MINMAX(J,K)=MINMAX(8,9)=8 MAX: MAX(A)=Minmax(A,B,C)=MINMAX(RESULT (3,0,8))=8 Answer 2 Nodes that should not be examined while alpha beta pruning are: Node O, node P, node Q, node T ,node U, node Y Initially at Node A: v=-∞ (since A is max) then it traverses to Node B where(α,β)=( -∞ , +∞ ). Node B: v=+∞ (since B is min) then it traverses to Node E where(α,β)=( -∞ , +∞ ). Node E: v=-∞ (since E is max) then it traverses to leaf Node L where(α,β)=( 7 , +∞ ) (since 7 is better than -∞) leaf Node M where(α,β)=( 7 , +∞ ) (since 7 is better than 6) so at Node E: v=7 In the already explored path at Node B: v=7 where(α,β)=( -∞ , +∞ ) Node F: v=+∞ then it traverses to Leaf Node N where(α,β)=( 8 , +∞ ) (since 8 is better than 7) Here the maximizer compares the value with other alpha values. O,P, Q ,T ,U and Y nodes need not be expanded as the alpha-beta pruning algorithm is an alternative...
Words: 996 - Pages: 4
...VINSUN INFRA-ERP Case Study VINSUN INFRA-ERP Case Study 2015 GMP 2015-16 8/22/2015 2015 GMP 2015-16 8/22/2015 Akanksha Bhatnagar (G15005) Anshul Agrawal (G15012) Rajeev Ranjan (G15043) Rejith M Rajan (G15045) Swapnil Nitin Rughani (G15056) Akanksha Bhatnagar (G15005) Anshul Agrawal (G15012) Rajeev Ranjan (G15043) Rejith M Rajan (G15045) Swapnil Nitin Rughani (G15056) Vinsun ERP Problem 1. Evaluate the Total Cost of Ownership (TCO) for the available options for a period of five year The Total cost of ownership for the three options ie Bluechip’s on Premise ERP solution, Codeautomation’s on Premise ERP solution and Codeautomation’s on Cloud ERP solution, available with Vinsun are given in the table below: Item | Bluechip's on Premise ERP | Codeautomation Premise ERP | Codeautomation Cloud ERP | Workstation x6 | 209700 | 209700 | 209700 | Workstation UPS x6 | 22290 | 22290 | 22290 | Laptops x2 | 132488 | 132488 | 132488 | Server | 100000 | 70000 | | Backup up server | 100000 | 70000 | | Server UPS x2 | 7750 | 7750 | | Initial Hardware cost | 572228 | 512228 | 364478 | Hardware AMC(yr 1) | 57222.8 | 51222.8 | 36447.8 | | | | | ERP Software x8 | 960000 | 240000 | | Consulting | 80000 | | | Deployment cost | 520000 | 200000 | | Training | 180000 | | | Service Fee x8 x12 | | | 192000 | Data Storage Cost | | | 60000 | Software Cost | 1740000 | 440000 | 192000 | Software AMC(yr 1) | 172800...
Words: 634 - Pages: 3
...analysis of the financial performance and marketing data for each of the three PDA models that Handheld Corporation manufacturers, recommendations are presented within this paper as potential strategic options the company can take given the challenges they are facing today. This is an analysis that will not center on a given aspect of strategy yet will seek to find an integrative strategy based on the concepts of open systems theory (Negandhi, 1973) for Handheld to pursue that will seek to optimize their investment in new products and continually grow existing products performing well both from a financial and marketing standpoint. Concerns over the X7 New Product Strategy After analyzing the financial, market and product data from the Models X5, X6 and X7, the role of the latest product to be introduced, the X7 has been launched as a low-end product entry for the company. From an analysis of the financial and marketing data on the Model X7, it is clear that Handheld believed they could gain disproportionately higher sales with a low-end version of their PDAs. In effect, Handheld was attempting to capitalize on the elasticity curve of the market (Haley, Goldberg, 2008) and price a product on or below that curve, to achieve disproportionately higher sales. As is evidenced by an analysis of their financial and marketing data, the elasticity curve for PDAs in the price class of the X7 is flat and doesn’t seem to show any signs of elasticity within the $200 range. The X7 product launch...
Words: 1083 - Pages: 5
...STUDENT ID: 13000357 | ER3S72 | GLOBAL BUSINESS MANAGEMENT REPORT ELECDYNE | | PROFESSOR JOHN DAVIDSON | JANUARY 2014Abstract This report is meant for Japanese SME Elecdyne and by the use of analytical frameworks to analyse the internal and external business environment of the electronic industry, aims to provide Elecdyne with and conclude the most suitable country to internationalize in. The later part of the report will cover the different types of FDI and through critical evaluation, the most suitable type of FDI will be decided on. In this report, academic references are used to provide a basic understanding of internationalization and the purpose of analytical frameworks such as the STEEP analysis, the SWOT analysis as well as the PEST analysis. Abstract This report is meant for Japanese SME Elecdyne and by the use of analytical frameworks to analyse the internal and external business environment of the electronic industry, aims to provide Elecdyne with and conclude the most suitable country to internationalize in. The later part of the report will cover the different types of FDI and through critical evaluation, the most suitable type of FDI will be decided on. In this report, academic references are used to provide a basic understanding of internationalization and the purpose of analytical frameworks such as the STEEP analysis, the SWOT analysis as well as the PEST analysis. Key words: internationalization, STEEP, SWOT, PESTAL, electronics industry,...
Words: 3926 - Pages: 16
...I. Description of issues and challenges A. Home Depot should adjust their strategies to employees, vendors and especially to customer services. Through strategic realignment to enhance customer service, grab market shares and increase share price. 1. Justifications According to the case, we can see that during the Nardelli era the feedback of customer service is the worst ever in Home Depot history. And also because of the continued share price stagnation and declining housing market, Home Depot need to adjust its strategies to maintain its position in the home improvement market. II. Alternative Solutions A. Solution 1 Focus on cutting the cost of all the processes and use lower price product to grab market share. Maintain Nardelli’s centralized strategies and stop using the Six Sigma method in store operation. Hire knowledgeable full-time person, maintain the balance between full-time and part-time employees and keep implement the employee bonus program. 1. Pros: λ Centralized strategies on merchandise and purchase has advantages on build a uniform and consistent brand image and reduce cost. λ Centralized strategies are more convenience for headquarter to give instructions and unified management. λ Hire knowledgeable full-time person will improve the quality of customer service. λ Maintain the balance between full-time employees and part-time employee and keep implement the employee bonus program will stimulate the enthusiasm of employees, ensure the quality...
Words: 792 - Pages: 4
...is varied through different outlets. Superfoods has carried out investigations so as to be able to find out the best way in optimising its display space, which eventually means optimising its profits. Likewise, the company wants to increase its goodwill and the way they do business. An important problem nowadays in the sales of supermarket that has become evident is optimising display space to maximise profit. This study describes a computational approach with the use of an important tool in Operational Research known as Solver. The investigations carried out consist of two main experiments. Experiment 1: This experiment is about the variation of the layout of Superfoods products on their shelves with the help of 48 sample retailers. This involved making controlled changes in the location of products on display and measuring directly, by checking stores’ records for purchases and stock (also with the agreement and cooperation of the retailers) the effects of display variations on sales. Experiment 2: In this experiment, Superfoods investigated the effect of increased sales force merchandising activity on the display of its products. As a result of the first Display Experiment, Superfoods has gained an understanding of the effects on sales of different products of having them on display in different locations in the shop, and has been able to work out the best way to arrange Superfoods products with the display space available. The main effect of increased merchandising...
Words: 1654 - Pages: 7
...A Scalable Method for Multiagent Constraint Optimization Adrian Petcu and Boi Faltings {adrian.petcu, boi.faltings}@epfl.ch http://liawww.epfl.ch/ Artificial Intelligence Laboratory Ecole Polytechnique F´ d´ rale de Lausanne (EPFL) e e IN (Ecublens), CH-1015 Lausanne, Switzerland Abstract We present in this paper a new, complete method for distributed constraint optimization, based on dynamic programming. It is a utility propagation method, inspired by the sum-product algorithm, which is correct only for tree-shaped constraint networks. In this paper, we show how to extend that algorithm to arbitrary topologies using a pseudotree arrangement of the problem graph. Our algorithm requires a linear number of messages, whose maximal size depends on the induced width along the particular pseudotree chosen. We compare our algorithm with backtracking algorithms, and present experimental results. For some problem types we report orders of magnitude fewer messages, and the ability to deal with arbitrarily large problems. Our algorithm is formulated for optimization problems, but can be easily applied to satisfaction problems as well. 1 Introduction Distributed Constraint Satisfaction (DisCSP) was first studied by Yokoo [Yokoo et al., 1992] and has recently attracted increasing interest. In distributed constraint satisfaction each variable and constraint is owned by an agent. Systematic search algorithms for solving DisCSP are generally derived from depth-first search algorithms based on...
Words: 5452 - Pages: 22
...LINEAR PROGRAMMING FORMULATION PROBLEMS AND SOLUTIONS 7-14 The Electrocomp Corporation manufactures two electrical products: air conditioners and large fans. The assembly process for each is similar in that both require a certain amount of wiring and drilling. Each air conditioner takes 3 hours of wiring and 2 hours of drilling. Each fan must go through 2 hours of wiring and 1 hour of drilling. During the next production period, 240 hours of wiring time are available and up to 140 hours of drilling time maybe used. Each air conditioner sold yields a profit of $25. Each fan assembled may be sold for a $15 profit. Formulate and solve this LP production mix situation to find the best combination of air conditioners and fans that yields the highest profit. Use the corner point graphical approach. Let X1 = the number of air conditioners scheduled to be produced X2 = the number of fans scheduled to be produced Maximize | 25X1 | + | 15X2 | | | (maximize profit) | Subject to: | 3X1 | + | 2X2 | ≤ | 240 | (wiring capacity constraint) | | 2X1 | + | X2 | ≤ | 140 | (drilling capacity constraint) | | | | X1, X2 | ≥ | 0 | (non-negativity constraints) | Optimal Solution: X1 = 40 X2 = 60 Profit = $1,900 7-15 Electrocomp’s management realizes that it forgot to include two critical constraints (see Problem 7-14). In particular, management decides that to ensure an adequate supply of air conditioners for a contract, at least 20 air conditioners should...
Words: 4454 - Pages: 18
...Differential Evolution in Constrained Numerical Optimization. An Empirical Study Efr´n Mezura-Montesa,, Mariana Edith Miranda-Varelab , Rub´ del Carmen e ı c G´mez-Ram´n o o Laboratorio Nacional de Inform´tica Avanzada (LANIA A.C.) R´bsamen 80, Centro, a e Xalapa, Veracruz, 91000, MEXICO. b Universidad del Istmo, Campus Ixtepec. Ciudad Universitaria s/n, Cd. Ixtepec, Oaxaca, 70110, MEXICO c Universidad del Carmen. C. 56 #4, Ciudad del Carmen, Campeche, 24180, MEXICO a Abstract Motivated by the recent success of diverse approaches based on Differential Evolution (DE) to solve constrained numerical optimization problems, in this paper, the performance of this novel evolutionary algorithm is evaluated. Three experiments are designed to study the behavior of different DE variants on a set of benchmark problems by using different performance measures proposed in the specialized literature. The first experiment analyzes the behavior of four DE variants in 24 test functions considering dimensionality and the type of constraints of the problem. The second experiment presents a more in-depth analysis on two DE variants by varying two parameters (the scale factor F and the population size NP ), which control the convergence of the algorithm. From the results obtained, a simple but competitive combination of two DE variants is proposed and compared against state-of-the-art DE-based algorithms for constrained optimization in the third experiment. The study in this paper shows (1) important...
Words: 22303 - Pages: 90
...compilation © 2008 Blackwell Publishing Ltd Oxford, 20083Blackwell Publishing Ltd Research Article Research D Ghosh Article A Loose Coupling Technique for Integrating GIS and Multi-Criteria Decision Making A Loose Coupling Technique for Integrating GIS and Multi-Criteria Decision Making Debasis Ghosh National Informatics Centre Ministry of Communications and Information Technology Calcutta, India Keywords Abstract Spatial decision making is characterized by problems associated with multiple and conflicting alternatives relating to geographical features and their attributes. As such, the search for the best possible alternative from a large set of such alternatives can be a daunting task. The aim of integrating GIS with Multi-Criteria Decision Making (MCDM) is to develop a well-defined process that can scan through such extensive fields of choice to arrive at the best possible solution. Goal Programming is one tool (developed in conjunction with MCDM) that can handle a problem with multiple, conflicting and incommensurable alternatives, and this article explains how the loose coupling technique can integrate MCDM with GIS to assist decision making among competing alternatives. As an example, this methodology has been applied for community development purposes in the Hooghly District of West Bengal, India. 1 Background The inclusion of Multi-Criteria Decision Making (MCDM) in spatial environments provides us with the basis for spatial decision support systems. Spatial...
Words: 3647 - Pages: 15
...Running Head: MANAGEMENT BRIEFING MEMORANDUM AND PROPOSAL FOR IMPLEMENTING 1st PROVIDERS CHOICE AC/PC® SOFTWARE SYSTEM Management Briefing Memorandum and Proposal For Implementing 1st Providers Choice AC/PC® Software System HCAD 610/9042 July 18, 2010 M E M O R A N D U M TO: President The Center for Physical Therapy, LLC FROM: Director of Operations DATE: July 18, 2010 Re: Proposal to Implement 1st Providers Choice AS/PC® Practice Management Software System Per our recent conversation concerning facilities operations and patient care, I would like to present to you a proposal for a new technological advance software system. This system would assist our physical therapy practice with improving efficiency, decreasing errors in treatment and processing of claims, and better delivery of appropriate physical therapy treatment to patients in our outpatient clinical setting. After completing extensive research, the software system that I recommend and propose for the management of your physical therapy practice is called 1st Providers Choice AS/PC® Practice Management Software System. The following proposal outlines the details of implementing this new software, including its necessity, the contents and features of the system, the benefits, the operational cost...
Words: 1717 - Pages: 7
...Chapter Nine: Multicriteria Decision Making PROBLEM SUMMARY 1. Model formulation, product mix 2. Model formulation, transportation, computer solution 3. Model formulation, urban recreation facility allocation 4. Model formulation, crop determination, computer solution 5. Model formulation, product mix, computer solution 6. Model formulation, OSHA safety compliance, computer solution 7. Computer solution; graphical solution 8. Computer solution; graphical solution 9. Computer solution 10. Model formulation, computer solution 11. Model formulation, product mix, computer solution 12. Model formulation, product mix, computer solution 13. Model formulation, clinic personnel selection, computer solution 14. Model formulation, production scheduling, computer solution, sensitivity analysis 15. Model formulation, employee scheduling, computer solution 16. Model formulation, R&D project selection 17. AHP, company takeover 18. Pairwise comparison (9–17) 19. AHP, faculty raises 20. Pairwise comparisons (9–19) 21. AHP, mutual funds 22. AHP (9–21) 23. AHP, utility vehicles 24. AHP, anchor persons 25. AHP, hotel selection 26. AHP, college selection 27. AHP, dating service 28. AHP, R&D projects 29. AHP, student selection 30. AHP, athletic facilities 136 2. a) 31. AHP, vacation locations 32. Pairwise comparisons (9–31) 33. AHP, major options 34. AHP, basketball players 35. AHP, school facilities 36. Student’s pairwise comparisons 37. AHP, emergency rooms 38. AHP, class sections 39. Student car...
Words: 3864 - Pages: 16