|
-
STA 2216 — Statistical Methods
Professor András Farkas
Contact Information
Office: Room 221
Office Thursday 12:00-13:00 PM
Phone: 413‑3025 (to leave a message at the Dean's Office)
Email: farkas.andras@kgk.uni-obuda.hu
Term: Spring 2012
Prerequisite: Elementary Statistics for Social Sciences ST 2215
Day of classes: Thursday 8:30-12:00 AM
Classroom: 220
Number of credits: 4 credits
Number of classroom hours: 60
Required Texts and Readings
D.R.Anderson-D.J.Sweeney-T.A.Williams(1999): Statistics for Business and Economics=. Textbook. Seventh Edition. West Publishing Company, St Paul [referenced as Chapters]. This textbook is recommended for less prepared students only.
A.Farkas (2011): 'Statistical Methods'. Handout. (Course Material in Statistical Methods. Most parts are from R.C.Pfaffenberger‑J.H.Patterson (1987): Statistical Methods for Business and Economics=. Third Edition, Irwin, Homewood)
Handout must be brought along by the students to the classroom hours; furthermore, students must be prepared for each of the classroom hours. The use of the Handout is permitted on the examinations, i.e., on the Mid-term test and on the Final test
Required Software Package
SPSS 8.0 for Windows (Statistical Package for Social Sciences)
[this software package is available on the PCs in the Computer Laboratory]
Internet access to this software to download: http://taxi.bmf.hu/~ivancs/spss8.zip
Objective
The objective of this course is to provide students with an understanding of the concepts, the theory and the practice of statistical methodologies and to prepare students to conduct and critically evaluate statistical studies based on both large and small data sets of univariate and/or multivariate statistical analysis with a healthy scepticism. Emphasis is on underlying assumptions, limitations, adequate interpretations and practical applications of modern statistical methods. Drawing heavily from the methodologies of business administration and economics disciplines, the course focuses on the analytical tools that can be used for problem solving and showing the probabilistic way of thinking in decision making for a variety of applied fields in macroeconomics, microeconomics, industrial and international marketing, accounting, consumer's behaviour and quality planning & control. In addition, the course provides the students with the required knowledge and self‑contained application skills needed for their further professional career.
Content and Prerequisites
In recent years the probabilistic approach has become an essential and widely used scientific methodology, and it has been integrated into modern business, economic and engineering technologies. Therefore, this course presents the world-wide used basic statistical methods and some advanced multivariate methods. Furthermore, the course discusses a number of case studies and examples emerging in the international real‑world practice. In summary, the course stresses those fundamental aspects of statistics that have a broad applicability. Although, a limited number of a sophisticated material is also addressed, the class requires only the basic knowledge in probability theory, descriptive statistics, sampling, sampling distributions, statistical estimation, hypothesis testing as prerequisites and an elementary knowledge in algebra and calculus.
Teaching Method
The course is a combination of lecturing, problem solving, tutorial and discussion sections. To achieve the required progress in the material, students must use the Handout during the classroom hours, which contains a selected collection of the basic notions, theorems, definitions, formulas, illustrative graphs, case studies selected examples and stands for making notes as well. In the handout, however, there is only a limited amount of detailed description of the statistical theory covered during the classroom hours. Therefore, students must follow the material from the textbook on a regular basis. Also, students must demonstrate a satisfactory working knowledge in the use of the SPSS software package. To promote this goal, some 2 classroom hour classes (5-6 occasions) will be scheduled to the computer lab. A necessary condition to pass the exams is to perform the numerical calculations by using this computer software when making the homework assignments.
Homework Assignments
Each student will be given 2 comprehensive homework assignments. Dates of submission will be announced during the classroom hours. No late submission will be accepted without any reasonable explanation. Each assignment will be graded on a scale from 0 to 10 points.
Examinations
Examinations (mid-term and final) will be closed book but open handout type tests. The mid-term test will cover Sessions 1and take about 80 minutes. The final-test will cover Sessions 9and take about 90 minutes. These examinations will be problem solving type tests, with exercises, numerical examples and multiple choice type questions. No make‑up examinations are permitted, therefore both the attendance and a good preparation of the students are of utmost importance.
In all other questions associated with the academic process the policies and the rules of the Code of Academic Integrity and Honesty of the McDaniel College, Budapest should be considered. Plagiarism results in either a failure of the course or in a more serious case the withdrawal from the program.
Course Requirements
-
1. Attendance, active and informed participation in the classroom‑hours.
-
2. Two homework assignments of a length of maximum 4 pages each including a demonstrated use of the SPSS statistical software package (Printout must be attached). Submissions are due at the beginning of the class succeeding the week of the deadline.
-
3. Individual problem solving exercises (examples) and case study analyses assigned from the textbook during the whole term.
-
4. Preparation for the subsequent class discussion of the material.
-
5. Midterm test' covering the material up to about the first half of the course.
-
6. Final examination' covering the material of the second half of the course.
Evaluation and Grading Policy
-
Class participation: 10%
-
Homework assignment #1: 10%
-
Homework assignment #2: 10%
-
Midterm test: 30%
-
Final examination: 40%
-
Total: 100%
Topics and Reading Assignments—Dates
-
Week 1 A Summary in Elementary Probability and Statistics
(February 2)
Data and Statistics, Descriptive Statistics, Set Theory, Elementary Probability Calculus, Basic Probability Distributions.
Readings: Recall the respective knowledge from Chs. 1-6
-
Week 2 A Summary in Elementary Statistics (continued) and Intro to SPSS
(February 9)
Sampling and Sampling Distributions, Statistical Inference Making: Statistical Estimation and Hypothesis Testing, Chi‑Square Tests for Goodness-of-Fit and for Independence.
Introduction to the use of the SPSS (Computer Lab Session)
Readings: Recall the respective knowledge from Chs. 6-12, SPSS Tutorial
-
Week 3 Analysis of Variance
(February 16)
One‑Factor Completely Randomized Design: Underlying Assumptions, Model Building, Among (Between) Treatment Estimate of the Variance, Within Treatment Estimate (Error) of the Variance, Expectations of the Estimators, F‑statistic, One-Way Analysis of Variance (ANOVA) Table. Interpretation of the p-values. The Principle of Multiple Comparisons.
Examples and Case Study Analyses.
Readings: Ch. 13.1,2,5
-
Week 4 Multiple-Factor (Two-factor) Analysis of Variance
(February 23)
Experimental Design: Factorial Experiments, Two‑factor Completely Randomized Design, Assumptions, Model Building, Interaction Effects, Multiple-Factor Analysis of Variance Table.
Examples and Case Study Analyses.
Computer Lab Session.
Readings: Ch. 13.4,7 SPSS Tutorial
-
Week 5 Simple Linear Regression/Correlation
(March 1)
Simple Linear Regression and Correlation: Underlying Assumptions, Model Building, Fitting of the Regression Line (Curve), Gauss‑Markov Theorem, Parameter Estimation, Least-Squares Criterion, Normal Equations, Residuals and their Properties, Estimator of the Conditional Probability Distribution Variance, The Standard Error of the Estimator: Measure of the Absolute Fit, Coefficient of Determination. Measure of the Linear Association (Strength of a Linear Relationship); Bivariate Normal Distribution: Pearson's Product Moment Correlation Coefficient.
Examples and Case Study Analysis.
Readings: Ch. 14.1-4,8
-
Week 6 Inferences in Simple Linear Regression/Correlation
(March 8)
Inferences Concerning the Population Y-intercept, the Population Slope, the Mean of the Conditional Probability Distribution Variance, Estimation and Prediction of the Mean, Inferences Concerning the Population Correlation Coefficient.
Examples and Exercises.
Readings: Ch. 14.5-8
-
Week 7 Hungarian Public Holiday No classes
(March 15)
-
Week 8 MIDEXAMINATION
(March 22) 8:30-10:00 AM Tutorial for the Mid-term test
10:30-12:00 AM Mid-term test
-
Week 9 Model Building in Simple Linear Regression
(March 29)
Steps of Model Building in Simple Linear Regression. A Summary and Interpretation of the Terms used in Simple Linear Regression and Correlation.
Case Study Analysis.
Computer Lab Session.
Readings: Handout, and from the Textbook, respectively and SPSS Tutorial
-
Week 10 Spring break (Easter Holiday) –No classes
(April 5)
-
Week 11 Multiple Linear Regression/Correlation
(April 12)
Multiple Linear Regression; Introduction to the Case of more than one Independent (Predictor) Variables, Assumptions, Model Building, Parameter Estimation, Hypothesis Testing in Multiple Linear Regression: Two-Tailed t-tests, Testing the Significance of the Model: Joint F-test, Model Validation: Residual Plots, Durbin-Watson test for First-Order Auto-correlation, NSCORES test for Normality, Tests for Equal Variances. Multiple Linear Regression and Correlation: Detection and Correction for Multi-collinearity, Formal and Informal Methods, Variance Inflation Factor, Coefficient of Multiple Correlation, Coefficient of Multiple Determination, Coefficient of Partial Correlation, Coefficient of Partial Determination.
Examples and Exercises.
Readings: Ch. 15.1-4 and Ch.16.5 Ch. 15.5-6,8 and Handout
-
Week 12 Model Building in Multiple Linear Regression
(April 19)
Steps of Model Building in Multiple Linear Regression. Variable Selection Procedures: Enter, Forward, Stepwise and Backward Regression.
Examples and Exercises.
Case Study Analysis.
Computer Lab Session.
Readings: Ch. 16.1-4,6 SPSS Tutorial
-
Week 13 Time Series Analysis
(April 26)
Components and Models of a Time Series, Multiplicative, Additive, and Mixed Models of Time Series, Patterns of Secular Trend, Classical Decomposition: Measuring the Trend Component, Measuring the Seasonal Component, Measuring the Cyclical Component, Measuring the Irregular Component (Noise) of a Time Series.
Examples. Exercises.
Readings: Ch. 18.1,3-4 and Handout
-
Week 14 Forecasting methods
(May 3)
Time Horizons in Forecasting: Classification of Forecasting Models and Techniques with Respect to Their Properties and Data Patterns, Models for Stationary Processes: the Simple Moving Average Model, the Single Exponential Smoothing, Selection of a Proper Forecasting Model: Forecasting Errors, Mean Absolute Deviation, Mean Square Error, Tracking Signal, Impulse Response and Noise Dampening Abilities. Qualitative Approaching to Forecasting: Delphi, Scenario Writing, Intuitive Approaches.
Examples.
Computer Lab Session.
Readings: Ch. 18.2, 5-6 and Handout, SPSS Tutorial
-
Week 15 Statistical Decision Making-Term Summary
(May 10)
8:30-10:00 AM Statistical Decision Theory and Analysis
Structuring a Statistical Decision Problem: Payoff Tables and Regret Tables, Opportunity Loss, Decision Trees, Decision Making under Uncertainty: Optimizing Decision Criteria, Decision Making under Risk: Expected Monetary Value (EMV), Expected Value of Perfect Information (EVPI), Expected Profit under Certainty (EPPP). Fundamentals of Measurement Theory. Scaling Methods; Thurstone-Guilford Paired Comparison Method. The Analytic Hierarchy Process.
Examples. Problem Solving Session.
Readings: Handout
Sample examples (problem solving session).
Readings: Handout
-
Week 16 FINAL EXAMINATION (May 17) 10:30AM Tutorial for the Final-exam
8:30-10:00 AM Final Test
-
|
|
|
