Instructor: Anthony Yeboah; Ph.D. Economics
24-A C.H. Moore Agricultural Research Facility
Phone:(336)334-7070
Fax: (336) 334-7658
e-mail:yeboaha@ncat.edu
Required Text: Snedecor and Cochran: Statistical Methods.
Recommended Text: Harnett and Murphy: Statistical Analysis for Business and Economics.
Course Objectives:
This course deals with techniques for collecting, analyzing, and drawing conclusions from data. It is useful to students who are preparing for a career in one of the sciences and to persons working in any branch of knowledge in which much quantitative research is carried out. Such research is largely concerned with gathering and summarizing observations or measurements made by planned experiments, by questionnaire surveys, by the records of a sample of cases of a particular kind, or by combing past published work on some problem. From these summaries, the investigator draws conclusions hoped to have broad validity.
Course Outline
I. ANALYSIS OF VARIANCE
1.1 One-Way Classification
1.2 The Variance Ration, F.
1.3 Linear Models
1.4 Comparison Among Class Means (Contrasts)
1.5 Samples of Unequal Sizes.
II. SIMPLE REGRESSION AND CORRELATION ANALYSIS
2.1 The regression models
2.2 The method of Least Squares
2.3 Assumptions and Estimator Properties
2.4 Measures of Goodness of Fit
2.5 Test on the Significance of the Sample Regression Line
2.6 Constructing a Forecast Interval
2.7 The F-Test (analysis of variance of regression)
2.8 Correlation Coefficient and its Estimation
2.9 Relationship between Correlation and Regression
III. MULTIPLE REGRESSION AND CORRELATION ANALYSIS
3.1 The Multiple Regression Models
3.2 Assumptions under Model
3.3 Multiple Least Squares Estimation
3.4 Analysis of Variance Tests
3.5 Tests on Parameters
3.6 Linear Functions of Parameters
3.7 Goodness-of-Fit Measures
3.8 The General Linear Models (the use of dummy variables in Anova)
IV. ANALYSIS OF VARIANCE: SINGLE CLASSIFICATION WITH SUB-SAMPLING (NESTED MODELS)
4.1 Random Models
4.2 Mixed Models
V. CROSS CLASSIFICATION LINEAR MODELS (one observation per cell)
5.1 Randomized Block Model
5.2 Analysis of Variance
5.3 Regression Analysis of a Cross Classification Model
5.4 Unequal Sample Sizes
5.5 Missing Data
5.6 Efficiency of Design
VI. CROSS CLASSIFICATION MODELS (more than one observation per cell or FACTORIAL ARRANGEMENT OF TREATMENTS)
6.1 2 x 2 Cross Classification
6.2 3 x 3 Cross Classification
6.3 Regression Analysis of 2 x 3 Factorial Design
VII. ANALYSIS OF COVARIANCE
VIII. MISCELLANEOUS TOPICS
8.1 Binomial Tests and Estimation
8.2 Normal Approximation to the Binomial Use of Chi-Square Distribution in Discrete Tests.