NTHU STAT 5510 - Experimental Design and Analysis

Feb ~ Jun 2019

Instructor

Institute of Statistics, National Tsing Hua University
(鄭少為, 清華大學/統計所)

## Course outline

The course will be given on the basis of 3 hours a week (Thursday, 2:20~5:20 PM) in 綜合三館 room 840. The materials for teaching will be regularly posted on the course website (http://www.stat.nthu.edu.tw/~swcheng/Teaching/stat5510/).

Data in statistical studies are often collected by conducting either experiments or surveys. Statistical experimental design is the branch of statistics that deals with the design and analysis of experiments. The methods of experimental design are widely used in the fields of agriculture, medicine, biology, marketing research, and industry. In this course, the topics to be covered include:

• basic principles and introduction to regression analysis

• experiments with a single factor, analysis of variance

• experiments with more than one factor, blocking, Latin squares, analysis of variance and covariance, random effects models, other analysis techniques

• factorial experiments at two levels, comparison with “one-factor-at-a-time” plans, analysis of location and dispersion, choice of optimal blocking schemes

• fractional factorial experiments at two levels, maximum resolution and minimum aberration for choosing optimal 2n-k designs, choice of optimal blocking schemes

• robust parameter designs

• three-level designs

• orthogonal arrays and analysis of experiments with complex aliasing

## Textbooks

Wu, C.F.J. and Hamada, M. (2009), Experiments: Planning, Analysis, and Parameter Design Optimization. 2nd Edition. John Wiley & Sons.

References
:
1. Dean, A.M., Voss, D., and Draguljic, D. (2017), Design and Analysis of Experiments, 2nd Edition, Springer.

2. Lawson, J. (2015), Design and Analysis of Experiments with R, Chapman & Hall/CRC.

3. Faraway, J. J. (2015), Linear Models with R, 2nd Edition, Chapman & Hall/CRC.

4. Cheng, C.-S. (2014), Theory of Factorial Design: Single- and Multi-Stratum Experiments, Chapman & Hall/CRC.

## Assignment

There will be assignments for each topics. You are free to discuss the assignment questions with your classmates, but you must write up your answers individually. You CANNOT turn answers in as a group or simply reproduce a classmate's write up. All homework must be handed in before the end of class on the day it is due.

## Contact method and office hours

My office is in 綜合三館 room 818 (phone extension: 33162). My office hour is scheduled on Thursday, 1:00~2:00 PM. Questions by e-mail are also welcome: my e-mail address swcheng@stat.nthu.edu.tw.

The information of teaching assistants is as follows:

 name email address office hour location office hour time 黃昭惠 b01601033@ntu.edu.tw 綜合三館, room 840 Tuesday, 11:10 AM ~ 12:00 PM

Your grade will be determined by homework (30 %), a midterm (30 %), and a final exam (40 %).

## Prerequisites

Basic linear model knowledge (STAT 5410).