Academic Integrity: tutoring, explanations, and feedback — we don’t complete graded work or submit on a student’s behalf.

11.34. Box and Liu (1999) describe an experiment flying paper helicopters where

ID: 3321042 • Letter: 1

Question

11.34. Box and Liu (1999) describe an experiment flying

paper helicopters where the objective is to maximize flight

time. They used the central composite design shown in Table

P11.11. Each run involved a single helicopter made to the following

specifications: x1 $ wing area (in2), !1 $ 11.80 and

%1 $ 13.00; x2 $ wing-length to width ratio, !1 $ 2.25 and

%1 $ 2.78; x3 $ base width (in), !1 $ 1.00 and %1 $ 1.50;

and x4 $ base length (in), !1 $ 1.50 and %1 $ 2.50. Each

helicopter was flown four times and the average flight time

and the standard deviation of flight time was recorded.

(a) Fit a second-order model to the average flight time

response.

(b) Fit a second-order model to the standard deviation of

flight time response.

(c) Analyze the residuals for both models from parts (a)

and (b). Are transformations on the response(s) necessary?

If so, fit the appropriate models.

(d) What design would you recommend to maximize the

flight time?

(e) What design would you recommend to maximize the

flight time while simultaneously minimizing the standard

deviation of flight time?

11.34. Box and Liu (1999) describe an experiment flying

paper helicopters where the objective is to maximize flight

time. They used the central composite design shown in Table

P11.11. Each run involved a single helicopter made to the following

specifications: x1 $ wing area (in2), !1 $ 11.80 and

%1 $ 13.00; x2 $ wing-length to width ratio, !1 $ 2.25 and

%1 $ 2.78; x3 $ base width (in), !1 $ 1.00 and %1 $ 1.50;

and x4 $ base length (in), !1 $ 1.50 and %1 $ 2.50. Each

helicopter was flown four times and the average flight time

and the standard deviation of flight time was recorded.

(a) Fit a second-order model to the average flight time

response.

(b) Fit a second-order model to the standard deviation of

flight time response.

(c) Analyze the residuals for both models from parts (a)

and (b). Are transformations on the response(s) necessary?

If so, fit the appropriate models.

(d) What design would you recommend to maximize the

flight time?

(e) What design would you recommend to maximize the

flight time while simultaneously minimizing the standard

deviation of flight time?

Explanation / Answer

(a)

Design Expert Output

Response 1                        Avg Fit Time

ANOVA for response surface reduced quadartic model

Analysis of variance table [Partial sum of squares - Type III]

P-value

Prob >F

Std. dev 0.040           R squared    0.9060

mean   3.66                Adj R-squared 0.8486

c.v% 1.09                    Pred R squared 0.7581

press 0.074                   Adeq predision   19.913

Source Sum of squares df Mean square F value

P-value

Prob >F

Model 0.28 11 0.025 15.78 <0.0001 significance A-wing area 1.67E005 1 1.667E005 0.010 0.9198 B length width 0.062 1 0.062 38.83 <0.0001 Cbase width 1.500E004 1 1.500E004 0.094 0.7628 Dbase width 0.089 1 0.089 55.61 <0.0001 AB 0.013 1 0.013 8.28 0.0100 AC 0.023 1 0.023 14.09 0.0015 AD 0.031 1 0.031 19.17 0.0004 BC 0.034 1 0.034 21.43 0.0002 CD 7.225E003 1 7.22E003 4.52 0.0475 A2 7.511E003 1 7.51E003 4.70 0.0438 C2 0.013 1 0.013 8.04 0.0110 Residual 0.029 18 1.597E003 LACK OF FIT 0.020 13 1.513E003 0.83 0.6382 PURE ERROR 9.083E003 5 COR TOTAL 0.31 29