(Course Syllabus)
Email:
alok@gsu.edu
Office: 829 CBA
Office
Hrs.: By appointment
Website:
http://aloks.com
COURSE
DESCRIPTION
This course deals with the basics of
converting corporate data into actionable information for managerial decision
making. Statistical data analysis techniques in the context of Business
Intelligence are covered with applications in various functional areas of
business. Specific techniques include data visualization, descriptive
statistics, estimation, hypothesis testing modeling relationships, basic
forecasting techniques, and optimization techniques for decision support. The
contextual topics focus on the implementation of six sigma methodologies for
corporate performance management.
DETAILED
COURSE DESCRIPTION
Upon completion of the course, the
student will be able to build Decision Support Systems (DSS) – apply mathematical, graphical and
spreadsheet modeling techniques to business situations to aid decision-making.
Students will go through the process of describing and visualizing data,
estimating unknown parameters, evaluating trends for forecasting and estimating
relationships between process inputs and outcomes. Students will also get an
overview of using models for business intelligence and decision support and
will be able to evaluate various scenarios to optimize business decisions.
Overall, the course will provide the student with an analytical foundation for
dealing with business situations.
This course will provide the student
with several opportunities to apply concepts and techniques to "real-world
like" cases. The approach is applications oriented and students are
encouraged to apply concepts to real world cases. Students are also encouraged to apply the
concepts to their work-related datasets for a more meaningful learning
experience. The content of this course is “interdisciplinary” covering
applications from marketing, finance, operations and strategy. A key focus of
this course is the Six Sigma methodology for process improvement.
Collaborative learning is strongly
encouraged in this course. Students are encouraged to work in groups on
application-oriented projects. It is expected that each person in the group
will make equal contributions to group effort. The course will allow the
student to acquire all aspects of knowledge associated with the content of this
course. These aspects are : Know-what, Know-how and Know-why.
Know-what is associated with the understanding of concepts and techniques.
Know-how is the understanding related to the application of
concepts/techniques. Know-why is an understanding of the relevance and
appropriateness of the application to real-world situations.
TEXT
BOOK:
Data
Analysis and Decision Making with Microsoft® Excel (with CD-ROM, InfoTrac®, and Decision Tools and Statistic Tools Suite),
3rd Edition, 2006
Albright/Winston/Zappe, ISBN-10: 0-324-40082-9
GRADING:
1. Four
Projects 40%
2. Midterm 30%
3. Comprehensive Final Project / Exam 20%
4. Participation and Contributions 10%
POLICIES
AND PROCEDURES:
·
I expect you to
publish (turn-in) your reports on time to receive proper credit/grade. You will demonstrate continuous improvement
in the quality of both content and presentation as we progress through the
semester.
·
Due to the
online nature of this course, I recommend that you think seriously about taking
it this semester. If you are uncomfortable with web publishing, using Microsoft
Office (Word, Excel, etc.) and email you may want to delay taking this class
until the next semester. To get a tuition refund you will have to drop this
class during the first week.
·
I expect
everyone to contribute equally to group assignments. I encourage
collaborative learning. Your assignments should be in a report format (Word, etc)
or should be posted on the web. I will assign exercises from the text and each
question should address know-what, know-how, know-why, and care-why aspects. At
the beginning of each class period, I will select a few groups to make a brief presentation
of the previous week's work. Class participation and discussion is strongly
encouraged.
·
Although I will
try to maintain the class schedule, I may need to make adjustments.
·
All
assignments and projects should be
done using a software package (like Excel) and the reports written
professionally in a word processing package (like Word), converted to html
format and posted on the web.
·
I prefer
communication via email (alok@gsu.edu ) . You can also call me at any reasonable hour. I usually
forward my calls to my home/cell phone.
Course Schedule:
This
is a general plan for the course. Deviations may be necessary. Detailed
schedule is posted on the course's web site.
(see Course Schedule )
|
1 |
Managerial Decision Making Data
Analysis in a Business Modeling
and Models Graphical
Models Algebraic
Models Spreadsheet
Models |
|
2 |
Exploratory
Data Analysis: Graphs and Tables Basic
Concepts Frequency
Tables and Histograms Analyzing
Relationships with Scatterplots Time
Series Graphs Exploring
Data with Pivot Tables |
|
3 |
Exploratory Data Analysis: Summary Measures Measures
of Central Location Quartiles
and Percentiles Minimum,
Maximum, and Range Measures
of Variability: Variance and Standard Deviation Obtaining
Summary Measures with StatTools Measures
of Association: Covariance and Correlation Describing
Data Sets with Boxplots |
|
4 |
Statistical Estimation / Confidence Intervals Sampling
Distribution of the Sample Mean The
Central Limit Theorem The
t Distribution Confidence
Interval for a Mean Confidence
Interval for a Total Confidence
Interval for a Proportion |
|
5 |
Hypothesis
Testing Types
of Errors Significance
Level and Rejection Region Significance
from p-values Hypothesis
Tests and Confidence Intervals Practical
Versus Statistical Significance Hypothesis
Tests for a Population Mean |
|
6 |
Hypothesis Testing: Analysis of Variance Tests
for Normality Chi-Square
Test for One-Way
ANOVA Two-Way
ANOVA |
|
7 |
Midterm |
|
8 |
Regression
Analysis: Estimating Relationships Scatterplots: Graphing Relationships Linear
Versus Nonlinear Relationships Correlations:
Indicators of Linear Relationships Simple
Linear Regression Least
Squares Estimation Standard
Error of Estimate R-Square:
The Coefficient of Determination |
|
9 |
Multiple Regression Interpretation of Regression Coefficients Interpretation
of Standard Error of Estimate and R-Square Inferences
About the Regression Coefficients Multicollinearity Include/Exclude
Decisions |
|
10 |
Modeling for Decision Support Demand
Models Marketing
Models Manufacturing
Models Financial
Models |
|
11 |
Decision Support Systems Model Implementation and Use Sensitivity Analyses Goal Seeking Scenario Analyses |
|
12 |
Optimization Modeling Linear
Programming Graphical
Solution Using
Solver Product
Mix Models Multi-Period
Applications |
|
13 |
Business Intelligence Data
Warehousing and Marts Corporate
Dashboards Corporate
Performance Management |
|
14 |
Project Presentations |
|
15 |
|
COURSE
OBJECTIVES
Global Objectives: Upon completion of the course, the student will be
able to build Decision Support Systems (DSS) – apply mathematical, graphical and
spreadsheet modeling techniques to business situations to aid decision-making.
Students will go through the process of describing and visualizing data,
estimating unknown parameters, evaluating trends for forecasting and estimating
relationships between process inputs and outcomes. Students will also be
developing and implementing models for business intelligence and decision
support and be able to evaluate various scenarios to
optimize business decisions. Overall, the course will provide the student with
an analytical foundation for dealing with business situations.
Exploratory Data Analysis
1.
Distinguish
between cross sectional and time ordered data and between univariate
and multivariate data.
2.
Construct and
interpret a histogram.
3.
Explain the role
of histograms in univariate data analysis.
4.
Construct and
interpret a line graph.
5.
Explain the role
of line graphs in univariate data analysis
6.
Assess if time
ordered data are stationary.
7.
Determine if a
data set is reasonably normally distributed
8.
Compute the
sample mean and sample standard deviation to summarize a symmetric data set.
9.
Determine when
there are outliers for symmetric data.
10. Explain why outlier detection is an important
managerial activity.
11. Explain the role of scatter diagrams in bivariate data analysis
12. Construct and interpret scatter diagrams.
13. Explain in plain English the meaning of the term,
“best fitting line.”
14. Interpret scatter diagrams that contain linear or
nonlinear relationships or clusters.
Statistical
Estimation and Hypothesis Testing
Multiple Regression Analysis
1.
Explain how a
regression model, or equation, helps managers predict, explain, and control.
2.
Explain in
non-technical language the sample regression coefficients and what a best
fitting model means.
3.
Explain the role
of (or need for) the analysis of variance in answering the question, "Is
a regression model worth using at all?"
4.
Explain in plain
English the decomposition of sum of squares, mean squares, variance ratio and
p-value.
5.
Use Excel's (StatPro’s) multiple regression analysis to conduct an ANOVA
and follow-up t Stat analysis to develop a model that minimizes the standard
error of the estimate.
6.
Explain the role
of the standard error of the estimate in predicting values of the dependent
variable and why we want to reduce it.
Optimization:
Business Intelligence:
1. Describe the Business framework for managing organizations. Use an appropriate framework to integrate various areas.
GENERAL
TEACHING PHILOSOPHY:
This
is more about "facilitation of learning," even though I
am calling this my teaching philosophy. I have outlined the general nature of
my approach to create opportunities for you to acquire and develop skills that
will prove to be valuable in your life. In an era of continuous improvement,
interdisciplinary integration, and short lifecycle of skills (life-long
learning), my motivation is to help you build confidence and prepare you for
"Just-In-Time" training. The world is rapidly adopting the
"open-systems" model for knowledge creation, dissemination, and use -
which is making it necessary for me to try the approaches described below. Please
provide me your input as I try to make a transition into developing a web-based
environment for your learning.
Collaborative
Learning: I strongly advocate
team-oriented learning in my class. I recommend that you work in groups (of
three) and contribute equally to all group efforts. I believe that the best strategy for this
course is to create a structure of topics, provide several opportunities to
bring related topics into perspective, and create an environment that
facilitates implementation of concepts into meaningful applications. The
motivation is to accomplish synergy through sharing of information and
skills. You will make your projects
available to everyone by publishing them to your websites. Please visit and
contribute to the discussions on the bulletin/message board.
"Learning
by Doing" Model for Pedagogy: This model (constuctivism)
calls for facilitation of learning versus the traditional approach of
instructor-imparted teaching (objectivism). I will provide you with several
opportunities to apply concepts and techniques to "real-world like"
cases. This kind of integration/synthesis of knowledge from diverse sources is
necessary to be able to create meaningful IT solutions/applications. An
important part of this approach is "reverse engineering" to learn
systems/model development. I will provide examples of solutions to cases and we
will reverse engineer these solutions to gain a better understanding of the
modeling process.
Student-Centered
Learning: This approach encourages you to develop your own context
for learning. Meaning and relevancy of concepts can be highly enhanced if you
think of an application scenario in your profession and be able
to use ideas covered in the course to enhance existing methods. I recommend
that you demonstrate the application of the techniques covered in this course
to “real-world” situations. Select projects from your work environment or from
an area of your interest. Your projects should reflect applications that
demonstrate improvement over conventional methods and cover technology skills
that are considered current.
Covering all aspects of Knowledge Acquisition: I will
try to create opportunities for you to acquire all aspects of knowledge
associated with the content of this course. These
aspects are : Know-what, Know-how, Know-why, and
Care-why. Know-what is associated with the understanding of concepts
and techniques. Know-how is the understanding related to the application of
concepts/techniques. Know-why is an understanding of the relevance and appropriateness
of the application to real-world situations. Care-why is something you need to
think about (this aspect of knowledge acquisition is more about you than the
content of any course). All of your
projects should cover each of these aspects of knowledge.
Welcome
to your MBA program at