California State University, Hayward
Hong Kong MBA Program
MGMT 611O Business Forecasting
Dr. Z. Radovilsky
C O U R S E O U T L I N E
COURSE OBJECTIVES
This course will present a systematic and in-depth study of the modern principles and applications of business forecasting employed in operations, marketing, finance and other business functions. The main purpose is to develop important management skills in identifying appropriate quantitative methods and developing best forecasts to successfully managing business decisions. The emphasis is also made on utilizing modern forecasting techniques and computer software.
COURSE CONTENT
Introduction to Forecasting
Science and art of forecasting. Forecasting categories. Principles and steps in forecasting. Forecasting software. Using Excel and Minitab in forecasting.
Statistical concepts
Statistical concepts applied in forecasting. Quantitative data and variables. Descriptive statistics: measures of central tendency and variations. Mean and standard deviation. Descriptive statistics in Excel and Minitab. Normal distribution and its properties. Statistical inference: interval estimate and hypothesis testing. Correlation coefficient. Utilizing statistical analysis in Excel and Minitab.
Identifying Data Patterns and Choosing Forecasting Method
Historical data patterns: stationary, trend, seasonal, and cyclical. Using autocorrelation coefficients and correlograms to identify data patterns. Developing correlograms in Minitab. Forecast error and forecast accuracy. Measures of forecast accuracy. Utilizing accuracy measures in Excel and Minitab. Choosing the best forecasting technique.
Simple forecasts. Moving Average and Smoothing Techniques
Simple forecasting techniques: why use them? Naive and simple average (mean) forecasts. Moving averages forecast. Simple exponential smoothing. Exponential smoothing adjusted for trend--Holt's method. Exponential smoothing adjusted for trend and seasonality--Winter's method. Utilizing Excel and Minitab to developing moving average and exponential smoothing forecasts.
Time Series Decomposition
Introduction to time series decomposition: multiplicative and additive models. Forecasting with trend and seasonality. Deseasonalized data. Identifying seasonal indexes. Forecasting with cyclical variations. developing time series decomposition in Excel and Minitab.
Simple and Multiple Regression Analysis
Definition of regression analysis and its characteristics. Simple linear regression and its development in Excel and Minitab. Analyzing regression equation: coefficient of determination, regression coefficient and intercept, F-statistic, and standard error of estimate. Identifying forecast estimate with standard error of forecast.
Defining multiple regression analysis. Developing and analyzing multiple linear regression in Excel and Minitab. Multiple regression with binary (dummy) variables. Multicollinearity: how to identify and remove it. Utilizing Minitab in detecting and removing multicollinearity.
Regression with Time Series Data
Autocorrelation (serial correlation) in time series: definition and why it occurs. First order serial correlation. Durbin-Watson statistic to detect autocorrelation. Methods to remove autocorrelation in time series data. Developing regression of time series in Excel and Minitab.
TEXT
|
|
Business Forecasting, by J. E. Hanke, D.W. Wichern, and A.G. Reitsch, Seventh Edition, Prentice Hall, 2001. |
SOFTWARE
|
|
Microsoft Excel 2000 or '97 |
COURSE WEB PAGE
|
|
The course web page will be available on or after July 18. The course web page contains all course materials including PowerPoint lecture materials, Excel files, etc. |
|
|
To access to course web page, go to the instructors web page at http://www.sbe.csuhayward.edu/~zradovil and then click on the link MGMT6110 (Hong Kong). |
|
|
The course web page is password protected. Please, read instruction about your user name and password prior to accessing the page. |
SCHEDULE
| Session | Day | Topic | Chapter |
| 1 | Sunday, July 29 | Introduction to
Forecasting A Review of Basic Statistical Concepts Exploring Data Patterns and Choosing a Forecasting Technique |
Chs. 1, 2, 3 |
| 2 | Monday, July 30 | Moving Averages and Smoothing Methods | Ch. 4
Case study # 1 is assigned (Due on August 5) |
| 3 | Tuesday, July 31 | Moving Averages and Smoothing Methods | Ch. 4 |
| 4 | Thursday, August 2 | Time Series Decomposition | Ch.
5 In-class quiz #1 |
| 5 | Friday, August 3 | Simple Linear Regression | Ch. 6
Case study #2 is assigned (Due on August 8) |
| 6 | Saturday, August 4 | Multiple Regression Analysis | Ch. 7
In-class quiz #2 |
| 7 | Sunday, August 5 | Regression of Time Series
Data
Conclusion of the course |
Ch.8 |
| Saturday, August 18 | Course project is due |
REQUIRED ASSIGNMENTS
|
|
The case studies and their requirements will be presented by the instructor during the class sessions. |
PROJECT
|
|
The course project is due on August 18. The project requirements will be discussed at the fist class session. |
GENERAL INFORMATION
| Telephone | (510) 885-3302 |
| zradovil@csuhayward.edu | |
| Instructor's web page | www.sbe.csuhayward.edu/~zradovil |
| Course web page | Will be available on or after July 18 (go to the instructor's web page to see instructions and the link to the course page) |
GRADING SYSTEM
The final grade in the course will be based on the maximum of 500 points with the following breakdown:
|
|
Two case studies handed in, 75 points maximum each for a total of 150 points. |
|
|
Two in-class quizzes, 50 points maximum each for a total of 100 points. |
|
|
Class attendance and participation, 50 points maximum. |
|
|
Course project for 200 points. |
The final grades will be as following:
|
|
"A"--450 points and up |
|
|
"A-"--435-449 points |
|
|
"B+"--420-434 points |
|
|
"B"--400-419 points |
|
|
"B-"--385-399 points |
|
|
"C+"--370-384 points |
|
|
"C"--350-369 points |
|
|
"C-"--335-349 points |