Monday, March 3
Read chapter 7.4-7.5
HW #4
Due: Wednesday, March 5,2014
Undergraduates: Problem 6.2, 3, 4, 9, 15
Graduates: Problem 6.2, 3, 4, 5, 9, 15
Exam #1
Friday, March 7, 2014
Chapter 2-7
Closed book/notes - may bring one formula
sheet of your own
1
Statistics 4540/7540 Experimental Design
Name_
Review - Exam 1
Problem #1. (80 pts) A new examination method was evaluated. Five teachers reviewed the new tool and scores
(from 0 to 5) on the 5 items incorporated in the examination method were collected.
Statistics 4540/7540 Experimental Design
Name: _
Review - Exam 2
Directions: This section contains four computational problems worth a total of 100 points. For
each problem, you must present all your work, as well as the final answer, in order to receive
EXPERIMENTAL DESIGNS:
THE RANDOMIZED BLOCK
DESIGN
(Two-way ANOVA)
Randomized Block Design
The RBD utilizes experimental units that are matched
sets, assigning one from each set to each treatment.
The matched sets of experimental units are called
blocks. T
Design & Analysis of Split-Plot
Experiments
Split-Plot Designs vs. Full factorial
With a 23 full factorial design most would choose to run
the 8 treatment combinations in a completely
randomized order. Unfortunately, limitations involving
time, cost, mat
MAKING INFERENCE:
CONFIDENCE INTERVALS AND
TESTS OF HYPOTHESIS
STATISTICAL INFERENCE
Statistical inference means drawing
conclusions about the population
parameters based on sample data. Two
ways of making inference are:
Confidence intervals
Test of hyp
LATIN SQUARE DESIGN
A Latin square is a table filled with N different
symbols in such a way that each symbol occurs
exactly once in each row and exactly once in
each column.
If each entry of a Latin square is written as a triple (r,c,s), where
R is the r
Fixed, random, and
Mixed Models
Each term in a statistical model represents either a fixed effect or a random
effect.
Models in which all effects are fixed are called fixed-effects models.
Similarly, models in which all effects are randomapart from possib
SIMPLE LINEAR
REGRESSION
SIMPLE LINEAR REGRESSION ANALYSIS
The simple linear regression analysis
is the methodology of estimating
using the straight-line relationship,
the simplest of the models relating a
population mean to another variable.
It is always
EXPERIMENTAL
DESIGNS:
Completely
Randomized
Design
(One-way ANOVA)
ANALYSIS OF VARIANCE
A Designed Experiment is one for which the
analyst controls the specification of the treatment
and the method of assigning the experimental
units to each treatment.
El
Binary Logistic Regression
Odds Ratio (OR)
OR is a measure of association indicating magnitude and
direction.
Commonly used in epidemiology
Ranges from zero to infinity
Approximates how much more likely (or unlikely) it is for the
outcome to be presen
POLYNOMIAL REGRESSION
The simplest extension of the straight-line
model is the second-order polynomial, or
PARABOLA, which involves a second term
(quadratic) in addition to X:
The terms in the deterministic component equation
represent:
Y = dependent or r
Wednesday, January 22
Welcome to the class!
1
STAT4540/7540
Lecture 1
Lecture 1
Read chapter 1
Basic concepts (p.1-8)
Example (p.9-16)
Objectives of Today
Syllabus
Overview of experimental design
2
STAT4540/7540
Lecture 1
Instructor:
Dr. Suhwon Lee
Office
Monday, February 24
Read chapter 6
Please do NOT submit HW to Blackboard anymore; submit a
hard copy. Thanks!
HW #3
Due: Friday, February 28,2014
Undergraduates: Problem 5.1-4, 30
Graduates: Problem 5.1-4, 21, 24, 30
HW #4
Due: Wednesday, March 5,2014
Un
Wednesday, February 26
Read chapter 6.6
Please do NOT submit HW to Blackboard anymore; submit a
hard copy. Thanks!
HW #3
Due: Friday, February 28,2014
Undergraduates: Problem 5.1-4, 30
Graduates: Problem 5.1-4, 21, 24, 30
HW #4
Due: Wednesday, March 5,20