MBAC6080 Decision Modeling Midterm Exam Review Professor Stephen Lawrence
Dec 22, 2015
MBAC6080 Decision Modeling
Midterm Exam ReviewMBAC6080 Decision Modeling
Midterm Exam Review
Professor Stephen Lawrence
AgendaPrepare for Midterm ExamDescribe midtermReview highlights of material to dateAnswer questions
Course OutlineIntroduction to OMProductivity
Linear programming
QualitySPC tools
TimelinessQueueing Theory
Flexibility & SCMInventory Theory
InnovationProject Management
Environmental OpsOperations StrategyWrap-up
Midterm Details & AdministrationClosed book75 minutes in lengthCalculators OKNo Computers1-page cheat sheetFair Game for Exam
Lectures & readingsHomework assignmentsCases
7 topics, 7 partsMultiple choiceTrue/False – ExplainProblemsProblem fragments
Focus on interpretation
Defining OperationsDefining Operations
Professor Stephen Lawrence
TransformationProcesses
TransformationProcesses
GoodsGoods
ServicesServices
LaborLabor
KnowledgeKnowledge
CapitalCapital
MaterialsMaterials
What is Operations?
Transformation Definition
INPUTS OUTPUTS
Who are “operations” managers?
Manufacturing and Services Continuum of Characteristics
Mining (coal)
Automobiles
Fast Food
Banking
Consulting
ServiceOrientation
Manufacturing Orientation
Example:
Bicycle Manufacturing
Labor Used per unit produced
Capital Used(equipment) per unit produced
Huffy
Serotta
Schwinn ’80sLots of automationLots of labor / unit
Automated equipmentLittle labor per unit
Little automationLots of skilled laborModerate Automation
Moderate LaborTrek
Example:
Bicycle Manufacturing
Labor Used per unit produced
Capital Used(equipment) per unit produced
Desirable
Desirable
Undesirable!
Desirable
EfficientFrontier
Labor Used per unit produced
Capital Used(equipment) per unit produced
What is Operations?
Economic Definition
Added Value Model
adapted from Porter, Competitive Advantage, Free Press, 1985
Information SystemsInformation Systems
People and OrganizationPeople and Organization
FinanceFinance
AccountingAccounting
MarketingMarketing OperationsOperations
Profit!Profit!
CostCost
Added Value for CustomerAdded Value for Customer
Added Value Model
adapted from Porter, Competitive Advantage, Free Press, 1985
Suppliers Customers
Competitors
The Firm
BusinessEnvironment
Value Chain
Operations is the fundamental means by
which firms…
What is Operations?
Added-Value Definition
Add Value!
What is Operations?
How do Firms Add Value?Greater Productivity
Lower costs and expensesLower prices for the customer
Higher QualityBetter performanceGreater durability, reliability, aesthetics, ...
Better TimelinessFaster response and turnaroundOn-time delivery, meet promises
Greater FlexibilityGreater varietyCustomization for customer needs / desires
Useful InnovationFeatures, technologyBetter performanceNew capabilitiesOften unrecognized
The Value Equation
price
ePerformancValue
price
InnovationyFlexibilitTimelinessQualityValue
P
IFTQValue
Competing with Competing with ProductivityProductivityLeeds School of BusinessLeeds School of BusinessUniversity of ColoradoUniversity of ColoradoBoulder, CO 80309-0419Boulder, CO 80309-0419
Professor Stephen Lawrence
The Value Equation
price
yFlexibilitTimelinessQualityValue
How are productivity
and price related?
Inputs
OutputstyProductivi
Productivity Defined
Inputs: labor, materials, capital, …
Outputs: goods, services
Single Factor ProductivityMeasures increase in productivity in relation to a single factor of productionLabor, materials, capital, …Productivity = Output / Single InputExample:
Output LaborPeriod 1 1000 units 100 hrsPeriod 2 1100 105
Productivity10.0 units / hour10.6 units / hour
Total Factor ProductivityMeasures increased in productivity from all relevant factors of productionProductivity (TFP)
= all outputs / all factor inputsExample: product sales + internal services
TFP Index = ----------------------------------------------------------------------------- labor + material + services + depreciation + investment
4.94% IncreaseTFP Index
2002 20031.073 1.126
TFP LimitationsIssues affecting TFP measurement
inflation, currency exchange gains (losses)depreciation, inventory valuationproduct mix changes, choice of base period, output measures ...
Theoretically interesting, practically difficult
Why Productivity is Important
Agriculture Services
Mfg
Knowledge
0102030405060708090
100
1800
1820
1840
1860
1880
1900
1920
1940
1960
1980
2000
Per
cent
of
the
labo
r fo
rce
Year
Allocative vs. Technical Efficiency Capital Used(equipment) per unit produced
AY
B
Labor Used per unit
C
EfficientFrontier
EfficientFrontier
CostLine
1 / c
ost o
f c a
pita
l
1 / cost of labor
Allocative inefficiency
Technical inefficiency
O
Inefficiency = BC÷OB
How Much Inefficiency Exists?
Tech efficiency based on gross output 63-95%
Tech efficiency based on value-added 28-50%
Mean levels of technical inefficiency for 365 U.S. industries:
Caves and Barton, Efficiency in U.S. Manufacturing Industries, MIT 1990.
Management FindingsOligopoly is detrimental to technical efficiencyImport competition is favorable to technical efficiencyEnterprise diversification is hostile to an industry’s technical efficiencyTechnical efficiency is negatively related to the presence of trade unions in industries that operate large plantsCapital vintage distributions have an important impact on technical efficiency -- importance of optimizing capital modernization and replacement decisions
Caves and Barton, Efficiency in U.S. Manufacturing Industries, MIT 1990.
Evolving Economic TheoryPosits a new factor of production: knowledge
Knowledge increases return on capital investmentKnowledge doesn’t just happen, it is paid for by foregoing current consumptionVirtuous cycle in which investment spurs knowledge and knowledge spurs investment
Four factors of productionCapital, unskilled labor, human capital (training), ideas (patents)
The Economist, Jan 4, 1992, pgs15-18
Introduction to Linear Programming
Professor Stephen LawrenceLeeds School of Business
University of Colorado
Boulder, CO 80309-0419
An LP Example
Product Mix LP. A potter produces two products, a pitcher and a bowl. It takes about 1 hour to produce a bowl and requires 4 pounds of clay. A pitcher takes about 2 hours and consumes 3 pounds of clay. The profit on a bowl is $40 and $50 on a pitcher. She works 40 hours weekly, has 120 pounds of clay available each week, and wants more profits.
Graphical LP SolutionsWorks well for 2 decision variables“Possible” for 3 decision variablesImpossible for 4+ variables
Other solution approaches necessary
Good to illustrate concepts, aid in conceptual understandingAn automated tool…
LP Standard Form
Max Z = c1x1 + c2x2 + … + cnxn
Subject to (s.t.)
a11x1 + a12x2 + … + a1nxn b1 a21x1 + a22x2 + … + a2nxn b2
…am1x1 + am2x2 + … + amnxn bm
x1 0, x2 0, …, xn 0
Assumptions of LPLinear objective function, constraints
ProportionalityAdditivity
DivisibilityContinuous decision variables
CertaintyDeterministic parameters
LP ConceptsDecision variablesObjective functionConstraintsFeasible solutionsFeasible region (convex polytope)Corner point solutionsOptimal solution“Constrained optimization”
Linear Programming ApplicationsProduct MixDietInvestmentCash flowEmployee SchedulingProductionMarketing
Competing with Competing with QualityQualityLeeds School of BusinessLeeds School of BusinessUniversity of ColoradoUniversity of ColoradoBoulder, CO 80309-0419Boulder, CO 80309-0419
Professor Stephen Lawrence
The Value Equation
price
yFlexibilitTimelinessQualityValue
Quality
Why Quality is CriticalQuality: Quality is the single most important thing you can work on to improve the effectiveness of your company. It's as simple as that. Things just cascade when you get control of your quality. John Young, CEO Hewlett Packard
Micro-economic interpretation:
Quantity
Price Demand Supply
Quality affects both!
Eight Dimensions of Quality
1. Performancethe primary operating characteristics of the product or service.
2. Featuresthe characteristics that supplement the basic functioning of the product or
service.
3. Reliabilityprobability of the product or service failing within a specified period of time.
4. Conformancethe degree to which a product or service meets acknowledged standards
Quality is not uni-dimensional, but has a numberof important dimensions:
David Garvin, “Competing on the Eight Dimensions of Quality,” Harvard Business Review, Nov-Dec 1987
Eight Dimensions of Quality
5. Durabilitya measure of product life (both technical and economic).
6. Serviceabilitythe speed, courtesy, competence, and ease of repair or recovery.
7. Aestheticshow a product or service looks, feels, sounds, tastes, or smells.
8. Perceived Qualityvarious tangible and intangible aspects of the product from which quality is
inferred.
Quality is not uni-dimensional, but has a numberof important dimensions:
David Garvin, “Competing on the Eight Dimensions of Quality,” Harvard Business Review, Nov-Dec 1987
Quality Costs
Prevention costs: process/product design, training, vendor relations;Appraisal costs: quality audits, statistical quality control;Correction costs (internal failure): yield losses, rework charges;Recovery costs (external failure): returns, repairs, lost business.
Costs associated with quality:Costs associated with quality:
Quality Costs
Quality costs escalate as value is added to product or service:
Supplier Inspection
Incoming Inspection
Fabrication Inspection
Subproduct Test
Final Product Test
Field Service
0.003
0.03
0.30
$3
$30
$300
Cost of finding and correcting a defective component
Quality MastersW. Edwards Deming
The basic cause of sickness in American industry and resulting unemployment is failure of top management to manage.Began consulting with Japanese in 1950Japanese Deming Prize
Joseph M. Juran“Fitness of Use”Runs the Juran InstituteLarge impact on Japanese quality
Phillip B. CrosbyStarted as an industrial inspectorRuns the Crosby Quality College“Zero Defects”
Total Quality ManagementTotal Quality Management
TQMTQM
Commitmentto Quality
Commitmentto Quality
TotalInvolvement
TotalInvolvement
Scientific Toolsand TechniquesScientific Toolsand Techniques
ContinuousImprovementContinuous
Improvement
Malcolm Baldridge Award
Stimulate companies to attain excellenceRecognize outstanding companiesDisseminate information and experienceEstablish guidelines for quality assessmentGather “how to” information from winners
U.S. Quality Award (patterned after Deming award)
International standards for business quality and control
ISO 9000
Management responsibilityQuality systemContract reviewDesign controlDocument ControlPurcasingTraceability
Process controlInspection / testingReject controlHandlingQuality recordsInternal auditsTraining Statistical techniques
Six Sigma“Invented” by MotoralaChampioned by GE and Jack WelchGoal of parts-per-million process defectsFour steps
1. Measure – new metrics; measure all processes2. Analyze – determine performance objectives3. Improve – wholesale changes, focus on results4. Control – monitor processes to maintain control
66
Does Quality Matter?
Quality and total quality costnegatively correlated.
Quality and productivitypositively correlated.
Quality and profitabilitypositively associated.
Garvin, Managing Quality, The Free Press, 1988
Statistical ProcessStatistical ProcessControl (SPC)Control (SPC)Leeds School of BusinessLeeds School of BusinessUniversity of ColoradoUniversity of ColoradoBoulder, CO 80309-0419Boulder, CO 80309-0419
Professor Stephen Lawrence
Process Control Tools
Process tools assess conditions in existing processes to detect problems that require intervention in order to regain lost control.
Run ChartsRun Charts
Check sheetsCheck sheets Pareto analysisPareto analysis
Cause & effect diagramsCause & effect diagrams ScatterplotsScatterplots
HistogramsHistograms Control chartsControl charts
Check SheetsCheck sheets explore what and where
an event of interest is occurring.
Attribute Check Sheet
27 15 19 20 28
Order Types 7am-9am 9am-11am 11am-1pm 1pm-3pm 3pm-5-pm
Emergency
Nonemergency
Rework
Safety Stock
Prototype Order
Other
Run Charts
time
mea
sure
men
t
Look for patterns and trends…
PARETO ANALYSISA method for identifying and separating
the vital few from the trivial many. P
erce
nta
ge o
f O
ccu
rren
ces
Factor
AB
CD
E F G IH J
CAUSE & EFFECT DIAGRAMS
Employees
Proceduresand Methods
TrainingSpeed Maintenance
Equipment
Condition
ClassificationError
Inspection
BADCPU
Pins notAssigned
DefectivePins
ReceivedDefective
Damagedin storage
CPU Chip
HISTOGRAMSA statistical tool used to show the extent and type of variance within the system.
Fre
qu
ency
of
Occ
urr
ence
s
Outcome
SCATTERPLOTSV
aria
ble
A
Variable B
x x x x x x xx x x x x xx x x x x x xx x xx x x x x xx x x x x x xx x x x xx xxx x x x x xx xx x x x x xx x x x xxx xx x x x x xxx x x xx x x xx xx x x x x x xx x x xxx xx xx xxx x x xx xxx x x x x x x xx x x x x x x xx x x xx x x xx x x x
Larger values of variable A appear to be associated with larger values of variable B.
Process Control
Causes of Variation
Natural Causes Assignable Causes
What prevents perfection?
Exogenous to processNot randomControllablePreventableExamples
tool wear“Monday” effectpoor maintenance
Inherent to processInherent to process RandomRandom Cannot be controlledCannot be controlled Cannot be preventedCannot be prevented ExamplesExamples
– weatherweather
– accuracy of measurementsaccuracy of measurements
– capability of machinecapability of machine
Process variation...
Specification vs. Variation
Product specificationdesired range of product attributepart of product designlength, weight, thickness, color, ...nominal specificationupper and lower specification limits
Process variabilityinherent variation in processeslimits what can actually be achieveddefines and limits process capability
Process may not be capable of meeting specification!
Process CapabilityMeasure of capability of process to meet (fall within) specification limitsTake “width” of process variation as 6If 6 < (USL - LSL), then at least 99.7% of output of process will fall within specification limits
LSL USLSpec
6
3
99.7%
Process Capability Ratio
Define Process Capability Ratio Cp as
CpUSL LSL
6If Cp > 1.0, process is... capable
If Cp < 1.0, process is... not capable
Process Capability Index Cpk
3
,3
minUSLLSL
C pk
If Cpk > 1.0, process is... Centered & capable
If Cpk < 1.0, process is... Not centered &/or not capable
Mean
Std dev
Process Control Charts
Establish capability of process under normal conditionsUse normal process as benchmark to statistically identify abnormal process behaviorCorrect process when signs of abnormal performance first begin to appearControl the process rather than inspect the product!
Statistical technique for tracking a process anddetermining if it is going “out to control”
Upper Control Limit
Lower Control Limit
6
3
Target Spec
Process Control Charts
Upper Spec Limit
Lower Spec Limit
UCL
Target
LCL
Samples
Time
In control Out of control !
Natural variation
Look forspecial
cause !
Back incontrol!
Process Control Charts
Types of Control Charts
1. Attribute control chartsmonitors frequency (proportion) of defectives p - charts
2. Defects control chartsmonitors number (count) of defects per unit c – charts
3. Variable control chartsmonitors continuous variables x-bar and R charts
Using p-chartsFind long-run proportion defective (p-bar) when the process is in control.Select a standard sample size nDetermine control limits
p
p
pLCL
pUCL
3
3
n
ppp
)1(
Using c-chartsFind long-run proportion defective (c-bar) when the process is in control.Determine control limits
c
c
cLCL
cUCL
3
3
cc
3. Control Charts for Variablesx-bar and R chartsMonitor the condition or state of continuously variable processesUse to control continuous variables
Length, weight, hardness, acidity, electrical resistanceExamples
Weight of a box of corn flakes (food processing)Departmental budget variances (accountingLength of wait for service (retailing)Thickness of paper leaving a paper-making machine
Range (R) ChartChoose sample size nDetermine average in-control sample ranges R-bar where R=max-min
Construct R-chart with limits:
nRR / RDUCLRDLCL 43
Mean (x-bar) ChartChoose sample size n (same as for R-charts)Determine average in-control sample means x-double-bar where x-bar = sample mean
Construct x-bar-chart with limits:
kxx / RAxUCLRAxLCL 22
x & R Chart Parametersn d(2) d(3) A(2) D(3) D(4)2 1.128 0.853 1.881 0.000 3.2693 1.693 0.888 1.023 0.000 2.5744 2.059 0.880 0.729 0.000 2.2825 2.326 0.864 0.577 0.000 2.1146 2.534 0.848 0.483 0.000 2.0047 2.704 0.833 0.419 0.076 1.9248 2.847 0.820 0.373 0.136 1.8649 2.970 0.808 0.337 0.184 1.81610 3.078 0.797 0.308 0.223 1.77711 3.173 0.787 0.285 0.256 1.74412 3.258 0.778 0.266 0.284 1.71616 3.532 0.750 0.212 0.363 1.63717 3.588 0.744 0.203 0.378 1.62218 3.640 0.739 0.194 0.391 1.60919 3.689 0.734 0.187 0.403 1.59720 3.735 0.729 0.180 0.414 1.58621 3.778 0.724 0.173 0.425 1.57522 3.819 0.720 0.167 0.434 1.56623 3.858 0.716 0.162 0.443 1.55724 3.895 0.712 0.157 0.452 1.54825 3.931 0.708 0.153 0.460 1.540
Control Chart Error Trade-offsSetting control limits too tight (e.g., ± 2) means that normal variation will often be mistaken as an out-of-control condition (Type I error).Setting control limits too loose (e.g., ± 4) means that an out-of-control condition will be mistaken as normal variation (Type II error).Using control limits works well to balance Type I and Type II errors in many circumstances.
Competing with TimeGraduate School of Business University of ColoradoBoulder, CO 80309-0419
Competing with TimeGraduate School of Business University of ColoradoBoulder, CO 80309-0419
Professor Stephen Lawrence
The Value Equation
price
InnovationFlexTimeQualityValue
Timeliness
Comparative Lead Times
Engineer to Order
Make to Order
Assemble to Order
Make to Stock
Customer LeadtimeInternal Leadtime
Just-In-Time & Lean ConceptsJIT
produce only what is needed only when it is needed!Goal of Just-In-Time Systems: SIMPLIFY!
Reduce inventories;Reduce setup times;Reduce information flows;Fewer, more reliable suppliers;Design products for manufacturability
Reduce WASTE of all types!
Ch 15 - 3
Basic Elements of Lean Ops & JIT
Flexible resourcesCellular layoutsPull production systemKanban controlSmall-lot production
Quick setupsUniform productionQuality at the sourceTotal productive maint.Supplier networks
© 2000 by Prentice-Hall Inc, Russell/Taylor Operations Management 3/e
Ch 15 - 5
Flexible Resources
Multifunctional workers
General purpose machines
Study operators & improve operations
© 2000 by Prentice-Hall Inc, Russell/Taylor Operations Management 3/e
Ch 15 - 7
Cellular Layouts
Group dissimilar machines into a manufacturing cell to produce family of partsWork flows in one direction through cellCycle time adjusted by changing worker paths
© 2000 by Prentice-Hall Inc, Russell/Taylor Operations Management 3/e
Ch 15 - 10
Kanban Production Control
Kanban card indicates standard quantity of productionDerived from two-bin inventory systemKanban maintains discipline of pull productionProduction kanban authorizes productionWithdrawal kanban authorizes movement of goods
© 2000 by Prentice-Hall Inc, Russell/Taylor Operations Management 3/e
Ch 15 - 21
Small-Lot Production
Requires less space & capital investmentMoves processes closer togetherMakes quality problems easier to detectMakes processes more dependent on each other
© 2000 by Prentice-Hall Inc, Russell/Taylor Operations Management 3/e
Ch 15 - 25
Reducing Setup Time
Preset desired settingsUse quick fastenersUse locator pinsPrevent misalignmentsEliminate toolsMake movements easier
© 2000 by Prentice-Hall Inc, Russell/Taylor Operations Management 3/e
Ch 15 - 26
Uniform Production
Results from smoothing production requirementsKanban systems can handle +/- 10% demand changesSmooths demand across planning horizonMixed-model assembly steadies component production
© 2000 by Prentice-Hall Inc, Russell/Taylor Operations Management 3/e
Ch 15 - 28
Quality At The Source
Jidoka is authority to stop production lineAndon lights signal quality problemsUndercapacity scheduling allows for planning, problem solving & maintenanceVisual control makes problems visiblePoka-yoke prevents defects
© 2000 by Prentice-Hall Inc, Russell/Taylor Operations Management 3/e
Ch 15 - 29
KaizenContinuous improvementRequires total employment involvementEssence of JIT is willingness of workers to
spot quality problemshalt production when necessarygenerate ideas for improvementanalyze problemsperform different functions
© 2000 by Prentice-Hall Inc, Russell/Taylor Operations Management 3/e
Ch 15 - 32
Visual Control
Library shelfWork station
Visual kanbansTool board
Machine controls
BetterGood Best
30-50
Howto
sensor
© 2000 by Prentice-Hall Inc, Russell/Taylor Operations Management 3/e
Ch 15 - 34
Benefits Of Lean Ops & JIT
1. Reduced inventory 2. Improved quality 3. Lower costs 4. Reduced space
requirements 5. Shorter lead time 6. Increased productivity
7. Greater flexibility8. Better relations with
suppliers9. Simplified scheduling
and control activities10. Increased capacity11. Better use of human
resources12. More product variety
© 2000 by Prentice-Hall Inc, Russell/Taylor Operations Management 3/e
Benefits of Fast ThroughputThroughput time reduction encourages
Improved qualityReduced inventoriesProcess rationalizationAttention to and reduction of bottlenecksDiminished chaos and confusionOverhead eliminationFaster response to the marketImproved capital appropriations
Queueing Theory
Professor Stephen LawrenceLeeds School of Business
University of ColoradoBoulder, CO 80309-0419
Service
Queuing Analysis
Arrival
Rate ( Average Number
in Queue (Lq )
Avg Time in System (W )
Avg Number in System (L )
Average Wait
in Queue (Wq )
Rate (Departure
Principal Queue ParametersArrival ProcessDeparture ProcessNumber of ServersQueue Discipline
Queue NomenclatureX / Y / k (Kendall notation)X = distribution of arrivals (iid)Y = distribution of service time (iid)
M = exponential (memoryless)Em = Erlang (parameter m)G = generalD = deterministic
k = number of servers
Exponential Distribution
m
etf
mt /
)(
Exponential Density
Mean = mStd Dev = m
f(t)1/m
tm
M/M/1 Queues
M/M/1 Assumptions
Arrival rate of Poisson distribution
Service rate of Exponential distribution
Single serverFirst-come-first-served (FCFS) Unlimited queue lengths allowed“Infinite” number of customers
M/M/1 Operating Characteristics
Utilization (fraction of time server is busy)
Average waiting times
Average number waiting
1W WWq
L LLq
Managerial Implications
Low utilization levels provide better service levelsgreater flexibilitylower waiting costs (e.g., lost business)
High utilization levels provide better equipment and employee utilizationfewer idle periodslower production/service costs
Must trade off benefits of high utilization levels with benefits of flexibility and service
Cost Trade-offs
= 0.0
Cost CombinedCosts
Cost ofWaiting
Cost ofService
Sweet Spot –Min Combined
Costs
G/G/k Queues
G/G/k AssumptionsGeneral interarrival time distribution with mean and std. dev. = sa
General service time distribution with mean and std. dev. = sp
Multiple servers (k)First-come-first-served (FCFS)“Infinite” calling populationUnlimited queue lengths allowed
General DistributionsTwo parameters
Mean (m)Std. dev. (s)
ExamplesNormalWeibullLogNormalGamma
f(t)
tm
s
Coefficient of Variationcv = s/m
G/G/k Operating Characteristics
Average waiting times (approximate)
Average number in queue and in system
m
sc
k
ccW
kpa
q
)1(2
1)1(222
WL qq WL
1
qWW
Alternative G/G/k Formulation
pk
cc
k
ccW
kpa
kpa
q)1(2)1(2
1)1(2221)1(222
pk
ccW
kpa
q
)1(2
1)1(222
VarianceTerm
CongestionTerm
Service TimeTerm
G/G/k Variance AnalyzedWaiting times increase with the square of the coefficient of variance
No variance, no wait!
Wq
c
Other Queueing Behavior
Server
Queue(waiting line)Customer
Arrivals
CustomerDepartures
Customer balks(never enters queue)
Customer reneges(abandons queue)
Wait too long?Line too long?
Waiting Line Psychology
1. Waits with unoccupied time seem longer2. Pre-process waits are longer than process3. Anxiety makes waits seem longer4. Uncertainty makes waits seem longer5. Unexplained waits seem longer6. Unfair waits seem longer than fair waits7. Valuable service waits seem shorter8. Solo waits seem longer than group waits
Maister, The Psychology of Waiting Lines, teaching note, HBS 9-684-064.
Good Luck!