WILLIAM PATERSON UNIVERSITY OF NEW JERSEY
			 COLLEGE OF SCIENCE AND HEALTH

		    Computer Science Syllabus and Outline

	 Course:       CS270-60, Computer Stat. Techniques
                       Tuesday 7:00 PM - 9:40 PM, Y123B
						    
         Instructor:   Dr. John Najarian, Assoc. Prof. of Computer Science
         Office:       Coach House 205, Tele. (973)-720-2952 
         Office Hours: Tuesday  3:30PM-6:45PM 
                       Wednesday 12:30PM-1:45PM & 6:00PM-6:45PM 
                       And also by appointment.

         Last day for course withdrawal 10/20/99.  Classes: 9/2/99-12/12/99.
         Holidays:  9/6/99 LD, 11/25-28/99 TGD, 
         Final Exam. Period:   Tuesday 12/14/99, 8:00PM-10:40PM.

         Class Rules:
          1. Attendance will be recorded.  Departmental guidelines require
             that: 3 absences (2 for night) --->  departmental warning letter
                   7 absences (4 for night) --->  automatic failure in course
             Only valid excuses (in writing) submitted to the professor will
             allay these consequences.   Attendance and success coincide.
          2. Projects will be collected as scheduled.
          3. All exams will be announced at least one full week in advance.
             If you are absent on the day an exam is announced, you are
             responsible for finding out about it from a fellow student or
             the professor.  No make-up exams will be given except for
             extraordinary circumstances.
          4. Bring the specified textbook to each class session.
          5. Final Grade = Average of 3-5 Quizzes (100%)
             Optional project work will be offered if requested early.
			                                             
       Objective of Course:
       Introduction to fundamental concepts, methodologies, and algorithms 
       of statistics and probability with extensive applications to computer 
       science.  After the lecture phase of each session will be problem 
       solving from the problems in the text.  All axioms/definitions will 
       be reviewed in detail prior to application.  Programming projects 
       will be in C\C++, and Minitabs under Windows NT.  
       Theory, application, and problem-solving constitutes at least 90% 
       of the course; Minitabs pragmatics will be presented at a limited scale.
       C++ programming will be preferred to Minitabs in order to demonstrate
       the computational algorithm design and their foundational statistical 
       principles.  Note: my approach stresses distributions and constructive 
       models as in simulation and AI-oriented design .  

       Tentative Schedule (of Topics):
       Session & Topic (Tentative Schedule; 1 Session=1 Night)   Chapter
--------------------------------------------------------------   -------
1. DESCRIBING DATA WITH GRAPHS.                                  1 MBB
   Variables and Data. Types of Variables. 
   Graphs for Categorical Data. Graphs for Quantitative. 
   Relative Frequency Histograms. Key Concepts. Stem-Leaf.
   About MINITAB--Introduction to MINITAB. Case Study.
   How Is your Blood Pressure?

2. DESCRIBING DATA WITH NUMERICAL MEASURES.                      2 MBB
   Describing a Set of Data with Numerical Measures.
   Measures of Center. Measures of Variability.
   On the Practical Significance of the Standard Deviation.
   A Check on the Calculation of s. Measures of Relative Standing.
   The Box Plot. Key Concepts and Formulas.
   About MINITAB-Numerical Descriptive Measures.
   Case Study: The Boys of Summer.

3. DESCRIBING BIVARIATE DATA.                                    3 MBB
   Bivariate Data. Graphs for Qualitative Variables.
   Scatterplots for Two Quantitative Variables.
   Numerical Measures for Quantitative Bivariate Data. Key Concepts.
   About MINITAB--Describing Bivariate Data.
   Case Study: Do You Think Your Dishes Are Really Clean? .

Quiz # 1   Fundamentals, Basic Statistical Measures, Bivariates.

4. PROBABILITY AND PROBABILITY DISTRIBUTIONS.                    4 MBB
   The Role of Probability inStatistics. Events & Sample Spaces.
   Calculating Probabilities Using Simple Events.
   Useful Counting Rules (Optional).
   Event Composition and Event Relations.
   Conditional Probability and Independence.
   Bayes' Rule (Optional).
   Discrete Random Variables and Their Probability Distributions.
   About MINITAB-Discrete Probability Distributions.
   Case Study: Probability and Decision Making in the Congo.

5. SEVERAL USEFUL DISCRETE DISTRIBUTIONS. Introduction.           5 MBB
   The Binomial Probability Distribution.
   The Poisson Probability Distribution.
   The Hypergeometric Probability Distribution.
   About MINITAB-Binomial and Poisson Probabilities.
   Case Study: A Mystery: Cancers Near a Reactor.
                                                                  
6. THE NORMAL PROBABILITY DISTRIBUTION.                           6 MBB
   Probability Distributions for Continuous Random Variables.
   The Normal Probability Distribution.
   Tabulated Areas of the Normal Probability Distribution.
   Normal Approx. to Binomial Probability Distribution.
   About MINITAB-Normal Probabilities.
   Case Study: The Long and Short of It.

Quiz # 2  RV's, Probabilty, and Distributions

7. SAMPLING DISTRIBUTIONS. Sampling Plans and Experimental Designs.  7 MBB
   Statistics and Sampling Distributions. The Central Limit Theorem.
   The Sampling Distribution of the Sample Mean.
   The Sampling Distribution of the Sample Proportion.
   A Sampling Application: Statistical Process Control (Optional).
   About MINITAB-The Central Limit Theorem at Work.
   Case Study: Sampling the Roulette at Monte Carlo.

8. LARGE-SAMPLE ESTIMATION.                                          8 MBB
   Statistical Inference. Types of Estimators.
   Point Estimation.  Interval Estimation.
   Estimating the Difference Between Two Population Means. 
   Estimating the Difference Between Two Binomial Proportions.
   One-Sided Confidence Bounds. Choosing the Sample Size.
   Case Study: How Reliable is That Poll?

9. LARGE-SAMPLE TESTS OF HYPOTHESES.                                 9 MBB
   Testing Hypotheses About Population Parameters.
   A Statistical Test of Hypothesis.
   A Large-Sample Test about a Population Mean.
   A Large-Sample Test of Hypothesis for the Difference
        in Two Population Means.
   A Large-Sample Test of Hypothesis for a Binomial Proportion.
   A Large-Sample Test of Hypothesis for the Difference in Two Binomial.
   Proportions. Case Study: An Aspirin a Day?

10.INFERENCE FROM SMALL SAMPLES. Introduction. Student's Distribution. 10 MBB
   Small-Sample Inferences Concerning a Population Mean.
   Small-Sample Inferences for the Difference Between Two Population Means:
        Independent Random Samples.
   Small-Sample Inferences for the Difference Between Two Means:
   A Paired Difference Test.
   Inferences Concerning a Population Variance.
   Comparing Two Population Variances.
   Revisiting the Small Sample Assumptions.
   About MINITAB-Small-Sample Testing and Estimation.
   Case Study: How Would You Like a Four-Day Work Week? .

Quiz # 3   Sampling: Distribution, Estimation, Inf Large, Inf Small 

11.THE ANALYSIS OF VARIANCE . The Design of an Experiment.             11 MBB
   What is an Analysis of Variance?
   The Assumptions for an Analysis of Variance.
   The Completely Randomized Design: A One-Way Classification.
   The Analysis of Variance for a Completely Randomized Design.
   Ranking Population Means.
   The Randomized Block Design: A Two-Way Classification.
   The Analysis of Variance for a Randomized Block Design.
   The a x b Factorial Experiment: A Two-Way Classification.
   The Analysis of Variance for an a x b Factorial Experiment.
   Revisiting the Analysis of Variance Assumptions.
   A Brief Summary.
   About MINITAB-Analysis of Variance Procedures.
   Case Study: "A Fine Mess".

12.LINEAR REGRESSION AND CORRELATION. Introduction.                    12 MBB
   A Simple Linear Probabilitistic Model. The Method of Least Squares.
   Analysis of Variance for Linear Regression.
   Testing the Usefulness of the Linear Regression Model.
   Estimation and Prediction Using the Fitted Line.
   Revisiting the Regression Assumptions. Correlation Analysis.
   About MINITAB-Linear Regression Procedures.
   Case Study: Is Your Car "Made in the U.S.A.?"

13.MULTIPLE REGRESSION ANALYSIS. Introduction.                         13 MBB
   The Multiple Regression Model. A Multiple Regression Analysis.
   A Polynomial Regression Model.
   Using Quantitative & Qualitative Predictor Variables in Regression Models.
   Testing Sets of Regression Coefficients. Interpreting Residual Plots.
   Stepwise Regression Analysis. Misinterpreting a Regression Analysis.
   Steps to Follow When Building a Multiple Regression Model.
   About MINITAB-Multiple Regression Procedures.
   Case Study: "Made in the U.S. A.- Another Look".

Quiz # 4   ANOVA, Experiments, Linear Regression, & Nonlinear Regression

14.ANALYSIS OF CATEGORICAL DATA. Description of Experiments.           14 MBB
   Pearson's Chi-Square Statistic.
   Testing Specified Cell Probabilities: The Goodness-of-Fit Test.
   Contingency Tables: A Two-Way Classification.
   Comparing Several Multinomial Populations:
   A Two-Way Classification with Fixed Row or Column Totals.
   Equivalence of Statistical Tests. Other Applications.
   About MINITAB-The Chi-Square Test.
   Case Study: Can a Marketing Approach Improve Library Services?
                                        
15.NONPARAMETRIC STATISTICS. Introduction.                             15 MBB
   The Wilcoxon Rank Sum Test: Independent Random Samples.
   The Sign Test for a Paired Experiment.
   A Comparison of Statistical Tests.
   The Wilcoxon Signed-Rank Test for a Paired Experiment.
   The Kruskal-Wallis H Test for Completely Randomized Designs.
   The Friedman F Test for Randomized Block Designs.
   Rank Correlation Coefficient. Summary. Key Concepts and Formulas.
   Case Study: How's Your Cholesterol Level?

16.Epilogue Lecture:                                                   Notes
   Statistical Applications in Neural Nets, AI Inference,              
   Monte Carlo Simulation, Computer Graphics (eg. sampling,
   pseudo-fractals, textures, ...), Randomized design and
   complexity, and other areas of Computer Science

Quiz # 5   (Final) Categorical Analysis & Nonparametrics Statistics.


       Required Texts:
       
        "Introduction To Probability and Statistics"
        Mendenhall, Beaver & Beaver [1999], Tenth Edition,
        Duxbury Press/ITP, ISBN 0-534-35778-4 (includes super CD & many aux.)  

        Diskettes (provided by the Computer Science Dept.) will be
        distributed.

       Recommended Readings (first being the best): 

	"Probabilty & Statistics for Engineers & Scientists"
	Walpole, Myer, & Myer [1998], Sixth Edition, Prentice-Hall
        
	"Statistics for Engineering and the Sciences, 4/edition" 
	William Mendenhall, Terry Sincich, published January, 1995 by 
	Prentice Hall ESM, ISBN 0-02-380581-1  
	(text has many C.S. applications but little at the level of lecture 32)
	
	"Introduction To Probability and Statistics: Principles and
	Applications for Engineering and the Computing Sciences", Third
	Edition, by Susan J. Milton and Jesse C. Arnold, 0-07-042623-6  
	(Jan 1995), McGraw-Hill 

	"AI and Computer Power: the Impact of Statistics" by D J Hand,
	 1993, Thompson, ISBN: 0-412-45550-1

	"Probability, Statistics and Queueing Theory with Computer Science 
	Applications", (2/e) Arnold O. Allen, Academic Press, 1990
	
	"Miller and Freund's probability and statistics for engineers",
	Irwin Miller, Prentice-Hall, 1994

	"Statistics for Engineering Problem Solving", Stephen Vardeman,  
	1993, Wadsworth

	"Probability and Statistics for Engineers", Richard L. Scheaffer,
	1994, Wadsworth       


	Lighter Reading:
	"How to Lie with Statistics" by Darrell Huff, Penguin Books Ltd. 1991