Chapter 4: Modeling and Analysis Flashcards
Certainty
A condition under which it is assumed that future values are known for sure and only one result is associated with an action.
Complexity
A measure of how difficult a problem is in terms of its formulation for optimization, its required optimization effort, or its stochastic nature.
Decision analysis
Methods for determining the solution to a problem, typically when it is inappropriate to use interval algorithms
Decision table
Conveniently organized data in a tabular manner to prepare it for analysis.
Decision tree
A graphical presentation of a sequence of interrelated decisions (nodes and roots) to be made under assumed risk.
Decision variable
A variable in a model that can be changed and manipulated by the decision maker. Decision variables correspond to the decisions to be made.
Dynamic modals
Models whose input data are changed over time e.g. 5-year profit projection.
Environmental scanning and analysis
The monitoring, scanning, and interpretation of collected information.
Forecasting
Predicting the future.
Goal seeking
Asking a computer what values certain variables must have in order to attain desired goals.
Heuristic programming
The use of heuristics in problem solving.
Heuristics
Informal, judgmental knowledge of an application area that constitutes the rules of good judgment in the field. Heuristics also encompasses the knowledge of how to solve problems efficiently and effectively, how to plan steps in solving a complex problem, how to performance and so forth.
Influence diagram
A graphical representation of a modal – a model of a model.
Intermediate result variable
A variable that contains the values of intermediate outcomes in mathematical models.
Linear programming
A mathematical model for the optimal solution of resource allocation problems. All relationship among the variables are linear.
Mathematical (quantitative) model
A system of symbols and expressions representing a real situation
Mathematical programing
An optimization technique for the allocation of resources subject to constraints.
Model base management system
(MBMS) Software for establishing, updating, combining, and so on (e.g. managing) a DSS modal base.
Multidimensional analysis
A modeling method the involves data analysis in several dimensions.
Multiple goals
Refers to a decision in which alternatives are evaluated with several, sometimes conflicting, goals.
Object orientated model base
management system
(OOMBMS) An MBMS constructed in an object orientated environment.
Optimal solution
A best possible solution to a modeled problem.
Parameter
(uncontrollable variable) A factor that affects the result of a decision but is not under the control of the decision maker, they can be internal or external.
Quantitative software package
A preprogrammed (sometimes call a ready-made) model or optimization system. These packages sometimes serve as building blocks for other quantitative models.
Relational model base management system
(RMBMS) A relational approach (as in relational databases) to the design and development of a model base management system.
Result (outcome) variable
A variable that analyzes the result of a decision, usually one of the goals pf a decision-making problem.
Risk
A probabilistic or stochastic decision situation.
Risk analysis
A decision-making method that analyzes the risk associated with different alternatives. Also, known as calculated risk.
Sensitivity analysis
A study of the effect of a change in one or more input variables on a proposed situation.
Simulation
An imitation of reality.
Static models
Models that describe a single interval of a situation.
Uncertainty
In expert systems, a value that cannot be determined during consultation. Many expert systems can accommodate uncertainty; that is, they allow the user to indicate whether he or she does not know the answer.
Visual interactive simulation
(VIS) A simulation approach used in the decision-making process that shows graphical animation in which systems and processes are presented dynamically to the decision maker. It enables visualization of the results of different potential actions.
What-if analysis
A process that involves asking a computer what the effect of changing some input data or parameters would be.
What is the difference between a static and a dynamic model
Static models are a single event whereas dynamic models change over time
o Static models assume that data won’t change
o Dynamic models are important because they can model patterns over a given stretch of time
o Dynamic models can get increasingly more complex to the point that they cannot be solved
Certainty, Uncertainty, and Risk
o Certainty assumes that complete knowledge of the problem is available to the decision maker
o Uncertainty considers situations in which many different outcomes are possible
o Risk is where the decision maker must consider the probability of many different outcome i.e. risk analysis
MSS modeling with spreadsheets
There are many different ways of showing and manipulating data
The key takeaway from this section is that spreadsheets are a very popular way of modeling and analyzing data for the following reasons
o They incorporate many different functions into one tool
o Easy and familiar to most end-users
o They can be seamlessly integrated into other systems such as databases
o The user can easily construct static and dynamic models
Decision analysis with decision trees and tables
Decision tables are a fairly simple model that can easily be solved for certain and uncertain situations. They can also allow for probabilities to be added to account for risk
Decision trees are an alternative to decision tables and can be used in a similar way. They do however show the relationships of the problem as roots and nodes
The structure of mathematical models for decision support
Mathematical models are made up of these basic components o Result variable o Parameter o Intermediate result variable o And decision variables
Mathematical programming optimization
This chapter describes mathematical programming as a way of allocating resources among competing activities to optimize a goal (p. 153) one of the most common ways of doing so is through linear programming
LP models consist of decision variables, and objective function, and constraints
Lingo is a popular tool for quickly solving LP models
LP typically assumes non-negative values for result variables
Multiple goals, Sensitivity analysis, what-if analysis, goal seeking
Multiple goals – This is where one attempts to solve several different and possibly conflicting problems to achieve simultaneous goals. Goal programming and A point system are some ways that one can solve these issues.
Sensitivity analysis – This is where looks at the impact of changing parameters or input data has on the solution. This can be used for revising models, adding details, getting a better idea of external variables, and altering a system to make it more or less sensitive.
The two types of sensitivity analysis are:
o Automatic
o Trial and error
What-if analysis – This is a fairly self-explanatory analysis with the idea being what will happen if we change ______. The blank being an input value, parameter, or assumption.
Goal seeking – this approach can be described as working a problem backward. One example that is common among retailers is how many products need to be sold to achieve annual revenue growth of _____%
Problem solving search methods
The book discusses several ways of problem-solving searching, they include:
o Algorithms – uses a step-by-step process (analytical)
o Blind searching – non-guided approaches to finding a possible solution
o Heuristic searching – finds rules to guide the searching
Simulation
In this section, the authors state that simulation is a way of experimenting using a computer based model.
Some initial key takeaways from this section include:
o The idea of simulation is descriptive vs. normative – meaning that a simulation describes the system under different circumstances rather than attempting to find an optimal solution
o Some advantages are:
The theory is straightforward
The model is built from the perspective of the manager
It can include real complexities of the problem
It is the only DSS modeling method that can handle relatively unstructured problems
o Some disadvantages are:
An optimal solution cannot be guaranteed
The construction of the model can be slow and expensive
The software can require special skills because of the complexity of the formal solution method
The methodology of simulation is depicted in the graphic below
Simulation types – see pg. 169 for more details o Probabilistic simulation o Time in/dependent simulations o Object orientated simulations o Visual simulations
