Scribd Logo
Upload

Welcome to Scribd!

  • 61 views

    2k-p Fractional Factorial Designs

    Uploaded by

    rasha assaf
    This document discusses fractional factorial designs, which are experimental designs that study the effects of factors using fewer experiments than a full factorial design. A fractional factorial design uses a fraction of the total number of experiments in a full factorial design, such as half the experiments in a 1/2 fraction design or a quarter of the experiments in a 1/4 fraction design. It provides an example of a 27-4 fractional factorial design to study the effects of 7 factors using only 8 experiments instead of the 128 experiments required for a full factorial design. It also shows how to prepare a sign table for a fractional factorial design.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    2k-p Fractional Factorial Designs

    Uploaded by

    rasha assaf
    61 views4 pages
    This document discusses fractional factorial designs, which are experimental designs that study the effects of factors using fewer experiments than a full factorial design. A fractional factorial design uses a fraction of the total number of experiments in a full factorial design, such as half the experiments in a 1/2 fraction design or a quarter of the experiments in a 1/4 fraction design. It provides an example of a 27-4 fractional factorial design to study the effects of 7 factors using only 8 experiments instead of the 128 experiments required for a full factorial design. It also shows how to prepare a sign table for a fractional factorial design.

    Original Description:

    2k-p Fractional Factorial Designs

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses fractional factorial designs, which are experimental designs that study the effects of factors using fewer experiments than a full factorial design. A fractional factorial design uses a fraction of the total number of experiments in a full factorial design, such as half the experiments in a 1/2 fraction design or a quarter of the experiments in a 1/4 fraction design. It provides an example of a 27-4 fractional factorial design to study the effects of 7 factors using only 8 experiments instead of the 128 experiments required for a full factorial design. It also shows how to prepare a sign table for a fractional factorial design.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    61 views4 pages

    2k-p Fractional Factorial Designs

    Uploaded by

    rasha assaf
    This document discusses fractional factorial designs, which are experimental designs that study the effects of factors using fewer experiments than a full factorial design. A fractional factorial design uses a fraction of the total number of experiments in a full factorial design, such as half the experiments in a 1/2 fraction design or a quarter of the experiments in a 1/4 fraction design. It provides an example of a 27-4 fractional factorial design to study the effects of 7 factors using only 8 experiments instead of the 128 experiments required for a full factorial design. It also shows how to prepare a sign table for a fractional factorial design.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 4

    k-p

    2 Fractional Factorial Designs

    -Pros and cons

     Save time and expense as compared to full factorial designs


     Information obtained is less: may not be possible to incorporate interactions
    among all factors.

    Fractional factorial design implications


    k-1
    —2 design  half of the experiments of a full factorial design

    k-2
    —2 design  quarter of the experiments of a full factorial design

    Ex I A B C D E F G
    pt
    • Study the effects of
    7 factors 1 1- - - 1 1 1 - with 8
    experiments
    • 1 1 1 1 Full factorial
    design would
    have required
    7
    2 11 - - - - 1 1
    2 =128
    1 1 1 1 experiments

    3 1- 1 - - 1 - 1
    1 1 1 1

    Model 4 11 1 - 1 - - - equation
    for 27-4 1 1 1 1 design
     q0  qA xA y
    5 1- - 1 1 - - 1
    qB xB  qC xC 
    1 1 1 1
    qDxD  qE xE 
    6 11 - 1 - 1 - -
    qF xF  qG xG 
    1 1 1 1
    Analyzing data with a 7-
    7 1- 1 1 - - 1 -
    1 1 1 1
    8 11 1 1 1 1 1 1
    7-4
    factor 2 experimental design

    expe I A B C D E F G Y
    11
    1 1 -1 -1 -1 1 1 1 -1
    35
    2 1 1 -1 -1 -1 -1 1 1
    8
    3 1 -1 1 -1 -1 1 -1 1
    42
    4 1 1 1 -1 1 -1 -1 -1
    31
    5 1 -1 -1 1 1 -1 -1 1
    51
    6 1 1 -1 1 -1 1 -1 -1
    52
    7 1 -1 1 1 -1 -1 1 -1
    91
    8 1 1 1 1 1 1 1 1
    32 117 65 129 29 1 57 9 Total
    1
    40 14. 8.1 16. 3.6 0.1 7.1 1.1 Total/
    .1 63 25 13 25 25 25 25 8

    As before, effects of factors in last line of table Percent


    variation explained
    A B C D E F G
    37.26 4.47 43.40 6.75 0.0 8.0 0.0
    0 7 3

    k-p
    Preparing a Sign Table for a 2 Design
    Prepare a sign table for a full factorial design with k-p factors
    k-p
    table of 2 rows and columns—

    first column with all 1’s; mark it “I—


    ”

    next k-p columns: mark with chosen k-p factors—


    k-p
    of the 2 -k+p-1 columns remaining, relabel p of them with —
    remaining factors

    Example: prepare a 27-4 table


    3
    —prepare a sign table for a 2 design for first 3 factors

    —relabel rightmost 4 columns with additional factors D, E, F, G

    ABC BC AC AB
    I A B C D E F G
    1 -1 -1 -1 1 1 1 -
    1
    1 1 -1 -1 -1 -1 1 1
    1 -1 1 -1 -1 1 -1 1
    1 1 1 -1 1 -1 -1 -
    1
    1 -1 -1 1 1 -1 -1 1
    1 1 -1 1 -1 1 -1 -
    1
    1 -1 1 1 -1 -1 1 -
    1
    1 1 1 1 1 1 1 1

    -There are k factors of interest each having 2 levels. There are only enough resources to run 1/2 p of the
    full factorial 2k design. Thus, we say we want to run a 1/2 p fraction of a 2k design. This design is
    called a 2 k−p fractional factorial design.

    – Suppose there are 7 factors of interest (A, B, C, D, E, F, G). There are only enough resources for 16
    experimental runs which is 1/8 of a 27 design. Thus, we want to runa 1/8 fraction of a 27 design. This
    design is called a 27−3 fractional factorial design.[1]

    [1]Art Of Computer Systems Performance Analysis Techniques For Experimental Measurements


    Simulation And Modeling, Raj_Jain, 1991

    You might also like