### Design and Analysis of Experiments-II (STAT-6207)

Introduction:

Design of experiments, referred to as DOE, is a systematic approach to understanding how process and product parameters affect response variables such as process ability, physical properties, or product performance. It is a tool similar to any other tool, device, or procedure that makes the job easier. Unlike quality, mechanical, or process tools, DOE is a mathematical tool used to define the importance of specific processing and/or product variables, and how to control them to optimize the system performance while maximizing properties. DOE uses statistical methodology to analyze data and predict product property performance under all possible conditions within the limits selected for the experimental design. In addition to understanding how a particular variable affects product performance, interactions between different process and product variables are identified.

Pre-requisite: STAT-6204

Course Objectives:

The aim of this course is to deliver the applicable knowledge about Statistics and Experimental Design, which can apply in different fields of study and to develop a skills on the data collection from a designed experiment, description measures of data, interpretation of results, and decision making. It deals with the model estimation of parameters of Factorial Experiments, 2^k, 3^k series and mixed levels factorial experiments and its applications in different fields. This covers Confounding and its types, Fractional replication, Quasi-Latin squares, Split-plot, Split Split plot, split block and Incomplete Block Designs. Models and applications of first and second order response surface designs are part of the contents.

Learning outcomes:

An essential part of the course consists of discussions of different methods used in the design of experiments and of how these methods are connected to statistical models. After completing the course students will be able to design simple experiments his/her self and have a general insight into how data analysis is done in connection to designed experiments.

Recommended Books:

1. Clarke, G. M. Kempson, R. E. Introduction to the Design & Analysis of Experiments, Edward Annold (1997).
2. Montgomery, D. C. Design and Analysis of Experiments, John Wiley, New York (1997).
3. Hinkelmann K, Kempthorne O. Design and analysis of experiments, New York, Wiley (1994).
4. Hinkelmann K, Kempthorne O. Advanced Experimental Design, Wiley-Interscience (2005).

Course Plan:

Week

## Books

1.

Experimental design (an introduction), Main Steps in designing an Experiment.

Design and Analysis of Experiments by Montgomery (1-21)

2.

Factorial Experiment

Design and Analysis of Experiments by Montgomery (162-201)

3.

Two-Level Factorial Experiments

Design and Analysis of Experiments by Montgomery (207-229)

4

Un-replicated Factorial Experiments

Design and Analysis of Experiments by Montgomery (229-252)

5.

Major Concept of Blocking and Confounding

Design and Analysis of Experiments by Montgomery(273-279)

6.

Complete and Partial Confounding in 2^k Factorial Experiment.

Design and Analysis of Experiments by Montgomery (279-287)

7.

Fractional Factorial Experiment and its Types

Design and Analysis of Experiments by Montgomery (289-349)

8.

Complete and Partial Confounding in 3^k Factorial Experiment.

Design and Analysis of Experiments by Montgomery (360-373)

9.

Quasi Latin Square Design

Design and Analysis of Experiments by Montgomery

10.

Incomplete Block Design, Balanced Incomplete Block Design (B.I.B.D)

Advanced Experimental Design by Hinkelmann & Kempthorne (71-118)

11.

Partially Balanced Incomplete Block Design (P.B.I.B.D)

Advanced Experimental Design by Hinkelmann & Kempthorne (119-188)

12.

Split-Plot Design

Design and Analysis of Experiments by Montgomery (557-567)

13.

Split-Split-Plot Design

Design and Analysis of Experiments by Montgomery (567-570)

14.

Strip-Split-Plot Design

Design and Analysis of Experiments by Montgomery (570-572)

15.

Lattice Designs

Advanced Experimental Design by Hinkelmann & Kempthorne (649-683)

16.

Response Surface Methodology.

Design and Analysis of Experiments by Montgomery (417-480)

Assessment criteria:

Mid Exam:          30

Final exam:         50

Sessional (Assignment, Presentation, Participation, Attendance, Quizes):             20
Time Table:

MSc 2nd:        Monday(09:00-10:00)      Tuesday(10:00-11:00)     Wednesday(11:00-12:00)       Friday(11:00-12:00)