DSc 4240/8240 Midterm Exam

 

General Issues

 

  1. What is the role of models in supporting organizational decision-making? Draw your ideas from the following Overview of Decision Sciences, Why Model?, and MB-DSS : Modeling Uncertainty and Complexity.

 

·         What are models? (short definition) 

·         Why is modeling necessary and can be of value? (list points) 

·         Where are they relevant? (a picture of an organization structure with functions outlined) 

·         What are some modeling techniques?  (a short note on optimization, forecasting, decision analysis, etc.)  

·         How are models developed? (stages of modeling)

·         How are the models utilized? (what if, goal-seeking, simulation, scenario analysis, auditing, etc.)

 

 

  1. Describe the role of model management and analytical modeling in Enterprise Applications of Information Technology. Draw your ideas from the following: Putting it all together: Decision Sciences in Context, and Model Management.

 

·         Describe in two short paragraphs (or lists) what model management and enterprise DSS mean to you.

·         Develop a framework integrating key concepts of IT, organizational functions, and analytical modeling support. 

 

 

  1. Describe the process of model development, implementation (DSS design) , and use of models (sensitivity, goal-seeking, simulation, etc) . Use The Modeling Process and MB-DSS : Modeling Uncertainty and Complexity..

 

·         Using the model for estimating demand as an example, describe the use of time-series analysis and regression analysis to develop forecasting models.

·         Describe the process of implementing these forecasting models in a spreadsheet model (DSS). Clearly outline the different components (database, model base, and the interface.

·         How can such a model be used to perform various analyses. Define and provide examples of sensitivity analysis, scenario analysis, and goal-seeking analysis.

 

Specific Issues

 

·         Designing and implementing models in DSS (chapter 2 examples).

·         Modeling trends and comparing trends using measures of error (MAPE).

·         Using Data-tables for sensitivity and two-way scenario analyses.

·         Using goal-seek to determine breakeven points.

 

·         Use of moving averages for estimating seasonal indices.

·         Time-series decomposition for estimating seasonality and trends.

 

·         Developing and evaluating regression models.

·         Developing regression models using backward elimination, forward selection, and stepwise.

 

·         Performing residual analysis to separate exogenous (time-series) effects form endogenous (causal) effects.

·         Implementing complex models for forecasting in DSS. (external inputs, decision inputs and outcomes).