Statistics 802 Quantitative Methods Spring 2008 - PowerPoint PPT Presentation

Loading...

PPT – Statistics 802 Quantitative Methods Spring 2008 PowerPoint presentation | free to view - id: 4587b-ZDc1Z



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

Statistics 802 Quantitative Methods Spring 2008

Description:

A Multimethod Approach for Creating New Business Models: The General Motors OnStar Project ... Diet problem. Samples of Models. Location game theory ... – PowerPoint PPT presentation

Number of Views:116
Avg rating:3.0/5.0
Slides: 45
Provided by: howard80
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: Statistics 802 Quantitative Methods Spring 2008


1
Statistics 802 Quantitative
Methods Spring 2008
  • Final Thoughts

2
Goal (Syllabus)
  • To provide students with a description of the
    advanced quantitative techniques which are
    routinely used for managerial decision making

3
Goal (Syllabus)
  • To provide students with examples of the
    application of these models
  • Interfaces
  • Forecasting Project
  • AHP Guest Lecture

4
Companies in Interfaces presentations
The Ombudsman Reaping Benefits from Management
Research Lessons from the forecasting principles
project. Forecasting Software in Practice Use,
Satisfaction, and Performance Against Your Better
Judgment? How Organizations Can Improve Their Use
of Management Judgment in Forecasting Contract
Optimization at Texas Children's Hospital Using
Organizational Control Mechanisms to Enhance
Procurement Efficiency How GlaxoSmithKline
Improved the Effectiveness of E-Procurement Optimi
zation of the Production Planning and Trade of
Lily Flowers at Jan de Wit Company Improving
Volunteer Scheduling for Edmonton Folk
Festival Optimizing Highway Transportation at
United States Postal Service Staffing a
Centralized Appointment Scheduling Department in
Lourdes Hospital Building Marketing Models that
Make Money An Analysis of the Applications of
Neural Networks in Finance Improving Customer
Service Operations at Amazon.com Dell Uses a New
Production-Scheduling Algorithm to Accommodate
Increased Product Variety A Novel Problem for a
Vintage Technique Using Mixed-Integer
Programming to Match Wineries and Distributors A
Marketing-Decision-Support Model for Evaluating
and Selecting Concepts for New Products Developing
a Customized Decision-Support System for Brand
Managers Improve Their Use of Management Judgment
in Forecasting
5
Companies in Interfaces presentations
How Bayer Makes Decisions to Develop New
Drugs Improving Supply-Chain-Reconfiguration
Decisions at IBM Ranking US Army Generals of the
20th Century A Group Decision-Making Application
of the Analytic Hierarchy Process PLATO Helps
Athens Win Gold Olympic Games Knowledge Modeling
for Organizational Change and Resource
Management Research and Development Project
Valuation and Licensing Negotiations at
Phytopharm, PLC Pricing Analysis for Merrill
Lynch Integrated Choice A Multimethod Approach
for Creating New Business Models The General
Motors OnStar Project Chrysler Leverages Its
Suppliers' Improvement Suggestions Improving Car
Body Production at PSA Peugeot Citroën Managing
Credit Lines and Prices for Bank One Credit
Cards Applying Quantitative Marketing Techniques
to the Internet Merrill Lynch Improves Liquidity
Risk Management for Revolving Credit Lines Nestlé
Improves Its Financial Reporting with Management
Science Subject Pricing for Environmental
Compliance in the Auto Industry Achieving
Breakthrough Service Delivery through Dynamic
Asset Deployment Strategies The Kellogg Company
Optimizes Production, Inventory, and
Distribution Responding to Emergencies Lessons
Learned and the Need for Analysis Development of
a Codeshare Flight-Profitability System at Delta
Airlines Travelocity Becomes a Travel Retailer
6
Samples of Models (From Lectures, Text,
Homework, Greatest Hits and Exams)
  • Market share
  • Brand loyalty (Markov chain)
  • Advertising (Game)
  • Scheduling
  • 1 to 1 (Assignment)
  • 1 or many to many
  • Transportation
  • Integer Program (Set covering)

7
Samples of Models
  • Advertising
  • Media selection (linear programming)
  • Competitive
  • Game/Market Share/
  • Game/Price Guarantees Guarantees guarantee HIGH
    prices!

8
Samples of Models
  • Inventory planning
  • Newsboy problem (single period inventory model
    greeting cards example)
  • Decision table
  • Simulation
  • Production planning - linear programming
  • Bidding
  • Simulation (in notes, we did not get to it)
  • Capital budgeting - integer program

9
Samples of Models
  • Enrollment management/forecasting - Markov chain
  • Public services
  • Mail delivery, street cleaning/plowing
  • School bussing transportation
  • Finance/accounting
  • Cost/volume - simulation
  • Portfolio selection linear/integer programming

10
Samples of Models
  • Production
  • Product mix/resource allocation - linear
    programming
  • Blending - linear programming
  • Employee scheduling- related problems
  • Workforce scheduling
  • Workforce training
  • Assignment
  • Health
  • Diet problem

11
Samples of Models
  • Location game theory
  • Agricultural planning
  • Noncompetitive - linear programming
  • Competitive - non zero sum game

12
Bonus Models - Sports
  • Baseball
  • Assignment of pitchers - linear programming
  • Football
  • Fourth and goal - decision tree
  • Optimal sequential decisions and the content of
    the fourth-and goal
  • Desperation - decision analysis - maximax
  • Ice hockey
  • Pull the goalie sooner
  • Desperation - decision analysis - maximax
  • Basketball
  • Desperation - decision analysis - maximax

13
Models In Some Cases There Is One Specific Goal
  • Linear programming
  • Transportation
  • Assignment
  • Integer programming

14
Models In Some Cases There Is One Specific Goal
  • Networks
  • Spanning trees
  • Shortest path
  • Maximal flow
  • Traveling salesperson problem
  • Chinese postman problem
  • Analytic Hierarchy Process (AHP)

15
Models In Other Cases There May Be More Than One
Specific Goal/Measurement
  • Decision analysis
  • Expected (monetary) value
  • Maximin (conservative, pessimistic)
  • Maximax (optimistic, desperate)
  • Maximin regret (conservative, pessimistic)
  • Forecasting
  • Error measurement (technique evaluation)
  • Mad
  • Mean squared error (standard error)
  • Mean absolute percent error (MAPE)

16
Prescriptive Vs. Descriptive Models
  • Some models PRESCRIBE what action to take
  • Linear programming based
  • Transportation, assignment, integer programming,
    goal programming, game theory
  • Network based
  • Shortest path, maximal flow, minimum spanning
    tree, traveling salesperson, Chinese postman
  • AHP
  • Zero or constant sum games
  • Flip a coin!!!

17
Prescriptive Vs. Descriptive Models
  • Some models DESCRIBE the consequences of actions
    taken
  • Decision analysis
  • Forecasting
  • Markov chains
  • Simulation
  • Non zero sum games
  • Matching lowest price leads to high prices !
  • Competition leads to low prices

18
Probabilistic vs. Deterministic Models
  • Some models include probabilities
  • Markov Chains
  • Decision Analysis
  • Decision tables
  • Decision trees
  • Games
  • Forecast Ranges

19
Probabilistic vs. Deterministic Models
  • Other models are completely deterministic
  • Linear programming
  • Transportation
  • Assignment
  • Integer programming
  • Networks
  • AHP

20
Long Run
  • Some models/measures require steady state (long
    run) in order for the results to be useful
  • Games
  • Decision analysis
  • Expected value
  • Expected value of perfect information

21
Models Tradeoffs
  • Ease of use vs. flexibility/generality
  • Transportation (easier) vs. LP (more flexible)
  • Decision table (easier) vs. Decision tree (more
    flexible)
  • QM for windows (easier) vs. Excel (more flexible)
  • Model correctness vs. solvability
  • Integer programming/linear programming

22
Models Tradeoffs
  • Model Exactness vs. Flexibility
  • Analytical method vs. Simulation
  • Development Cost/Time vs. Exactness
  • Analytical method vs. Simulation

23
Model Sensitivity
  • Forecasting Simulation
  • Standard error/standard deviation
  • Linear Programming
  • Dual values/ranging table
  • Integer Programming
  • Change values 1 unit at a time
  • Decision Tables/Decision Trees
  • Data table (letting probabilities vary)

24
Data Table With a Decision Tree
25
Solving Backwards
  • Decision tree
  • Game tree (sequential decisions)
  • Lets make a deal

26
Models Number of Decision Makers
  • One
  • Most models
  • More than one
  • Games
  • Lets make a deal !!

27
Excel Addins
  • Solver
  • Linear integer programs
  • Networks (shortest path maximal flow)
  • Zero sum games
  • Decision trees
  • Crystal ball
  • Simulation/risk analysis
  • Will be used in your Fall Finance course

28
Excel Tools
  • Data analysis
  • Forecasting
  • Simulation
  • Can be used for generating random numbers
  • Scenarios
  • Data tables
  • Simulation
  • Decision tables
  • Decision trees

29
Computer Skills
  • Microsoft office
  • Word
  • Excel
  • PowerPoint
  • Blackboard
  • Listserv
  • Software
  • Download
  • Installation

30
Less important computer skills (but skills
nonetheless)
  • QM (POM-QM) for Windows
  • Will be used in MSOM 5806 Operations Mgt in
    Fall
  • Excel OM
  • Available for use in MSOM 5806

31
SURVEY/EVALUATION RESULTS CLASS OF 2009
32
Survey Results Forecasting Class of 2008/Class
of 2007/Class of 2006
  • Workload
  • Too much time 3/1/5
  • Just right 25/17/18
  • Too little time 1/0/0
  • Value
  • High 22/18/17
  • Medium 6/1/6
  • Low 1/0/0
  • Conclusion Maintain project as is.

33
Interfaces presentations
  • Workload
  • Too much time 2/1/2
  • Just right 26/18/20
  • Too little time 0/0/1
  • Value of reading listening
  • High 1210/106/7 6
  • Medium 1410/76/14 11
  • Low 33/11/2 1
  • Interfaces options
  • Discontinue 3/2/17
  • Continue as is 10/10/1
  • Continue w Power point 12/10/na

Conclusion Continue, but consider students using
ppt
34
LP interpretations self
  • Workload
  • Too much time 1/0/2
  • Just right 26/18/20
  • Too little time 2/0/0
  • Value
  • High 10/13/14
  • Medium 10/6/8
  • Low 0/0/0
  • Conclusion Continue as is

35
LP interpretations team
  • Workload
  • Too much time 2/1/7
  • Just right 26/17/16
  • Too little time 1/0/0
  • Value
  • High 10/11/12
  • Medium 17/5/8
  • Low 1/3/3
  • Conclusion Continue as is

36
Decision Tree - Team
  • Workload
  • Too much time 3
  • Just right 23
  • Too little time 2
  • Value
  • High 14
  • Medium 12
  • Low 3
  • Conclusion Continue as is

37
Group Take home exam
  • Workload
  • Too much time 2/2/6
  • Just right 24/16/17
  • Too little time 3/0/0
  • Value
  • High 22/16/21
  • Medium 7/3/2
  • Low 0/0/0
  • Conclusion Next years is already posted!

38
Homework/Exam
  • Workload
  • Too much time 5/2/14
  • Just right 18/12/8
  • Too little time 6/4/1
  • Value
  • High 15/12/14
  • Medium 13/7/7
  • Low 1/0/2
  • Conclusion Continue as is

39
Guest Lecture
  • Repeat next year 18/13/13
  • Do not repeat 9/6/9
  • Conclusion Continue

40
Overall Course Workload
  • Compared to Econ, Elective
  • Above average 13/7/15
  • Average 16/11/8
  • Below average 0/0/0
  • Compared to Stat 5800
  • Higher 13/3/6
  • Same 14/14/16
  • Lower 2/1/1
  • Conclusion Workload may be slightly high

41
THE FINAL EXAM GRADES
42
Final Exam
  • Howard, now is the time to return the exams!

base 120 Pct (Cl 07/06)
Mean 93.78 76 (75, 71)
Median 96 78 (79, 74)
Max 120 95
43
Student Grade Sheet
44
Statistics 5802 Spring 2008
  • The End
About PowerShow.com