{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

q5_anova_soln

# q5_anova_soln - 16.881 Robust System Design Solution to...

This preview shows pages 1–2. Sign up to view the full content.

16.881 – Robust System Design Solution to Quiz #5 Analysis of Variance 1) In Taguchi methods, the F value for a factor effect is defined as a) The probability that the we reject the hypothesis that the factor effect equals zero. b) The sum of squares due to a factor divided by the error variance. c) The mean square due to a factor divided by the error variance. d) The sum of squares due to a factor divided by the DOF for the factor. C is the correct answer. It is very simply the definition of the F value in Taguchi methods. Note that in traditional one-way ANOVA, the F test statistic is defined differently dfB F SSB dfW SSW Where SSB is the sum of squares within treatments and SSW is the sum of squares within treatments. A is incorrect. To compute a probability from an F test statistic, you need to integrate the F distribution over the critical region. This can be done in Mathcad with the pF function or in excel with the FDIST function. F statistics are not normally used to compute probabilities in robust design. B is incorrect. The sum of squares due to a factor divided by the DOF of the factor is the mean square due to a factor. This is the key difference. You should note the similarity in form between the F as defined in one way ANOVA and the Taguchi use of ANOVA.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}