1 / 12

FACTORIAL EXPERIMENTS

FACTORIAL EXPERIMENTS. THIS APPROACH HAS SIGNIFICANT ADVANTAGES AND DISADVANTAGES. BASIC APPROACH. Access to the system or simulation k control-able independent variables (Factors) Each has an on/off, hi/low, present/absent CAUTION: These are not conditions or cases, they are decision-able.

avak
Download Presentation

FACTORIAL EXPERIMENTS

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. FACTORIAL EXPERIMENTS THIS APPROACH HAS SIGNIFICANT ADVANTAGES AND DISADVANTAGES

  2. BASIC APPROACH • Access to the system or simulation • k control-able independent variables (Factors) • Each has an on/off, hi/low, present/absent • CAUTION: These are not conditions or cases, they are decision-able

  3. THE GOAL • We seek unbiased estimates of the marginal EFFECT of the “HI” setting for each Factor • Isolated • In conjunction with other Factors • Independence of effect is NOT assumed • We’re going to collect data according to the design, then produce all the answers at the end

  4. 3-FACTOR 2K EXPERIMENT average of responses for treatment 1

  5. ESTIMATING AN EFFECT • eA is the effect of varying factor A • eA is the average of treatments that vary only in the setting of A • 1&2, 3&4, 5&6, 7&8 • the Variance of eA requires all of the variances, covariances, 3-factor variances • NONE of which we assume to be 0 (negligible)

  6. SINGLE-FACTOR ESTIMATION • Note the connection between the terms in the expression and the signs (+/-) on the table

  7. TWO-FACTOR ESTIMATION • eAB is half the distance between... • marginal effect of A when B is a “+” • (1/2)*[(R1-R2) + (R5-R6)] • marginal effect of A when B is a “-” • (1/2)*[(R3-R4) + (R7-R8)]

  8. ...more TWO-FACTOR ESTIMATION • the signs are the vector product of columns A and B! • eAB = eBA • Higher-order combinations are built the same way • averages and mid-points • vector products

  9. DISCUSSION • eA is the AVERAGE of the effect of A • over the equally-weighted mixture of the hi’s and low’s of the other factors • Is eA significant? • Is eA an unbiased estimate of the Truth? • Could you do a cost/benefit analysis with this sort of analysis?

  10. ONE CURE • Let Rij be the jth observation of response to the ith treatment • Treat the eAj as a sample, build a confidence interval, do univariate analysis • Not available to traditional experimental statisticians

  11. FRACTIONAL FACTORIAL • 3 factors require 8 treatments!!? • 5 factors would require 32! • supports up to 5-way effect measurement • high-order effects can often be assumed negligible • 2k-p factorial design • “confounds” effects of order k-p+1, k-p+2, ...,k

  12. 24-1 design D’s column is the same as AxBxC eABC is confounded with eD more than two settings: Latin Squares more control on confounding: Blocked Experiment DESIGN TABLE

More Related