Hw4_09fall sol

# Hw4_09fall sol - Question1 .10(1 and thetypeoffilm....

This preview shows pages 1–6. Sign up to view the full content.

Question 1 We first fit the model given in Section 3.10: (1) This model assumes the relationship of and is a linear relationship that does not depend on the type of film. The MINITAB output is shown below. Regression Analysis: y versus x, tau2, tau3 The regression equation is y = 158 + 62.5 x - 83.7 tau2 + 70.4 tau3 Predictor Coef SE Coef T P Constant 158.3 179.8 0.88 0.383 x 62.50 17.06 3.66 0.001 tau2 -83.67 86.10 -0.97 0.336 tau3 70.36 67.78 1.04 0.305 S = 164.650 R-Sq = 68.1% R-Sq(adj) = 66.0% PRESS = 1428711 R-Sq(pred) = 62.70% Analysis of Variance Source DF SS MS F P Regression 3 2610082 870027 32.09 0.000 Residual Error 45 1219940 27110 Total 48 3830022 Source DF Seq SS x 1 2553357 tau2 1 27513 tau3 1 29212 Unusual Observations Obs x y Fit SE Fit Residual St Resid 39 10.8 1282.0 903.6 44.6 378.4 2.39R 40 10.1 1233.8 859.9 51.1 373.9 2.39R 41 12.7 1660.0 1022.4 41.9 637.6 4.00R R denotes an observation with a large standardized residual.

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

View Full Document
Residual Percent 500 250 0 -250 -500 99 90 50 10 1 Fitted Value Residual 1200 1000 800 600 400 600 400 200 0 -200 Residual Frequency 600 400 200 0 -200 24 18 12 6 0 Normal Probability Plot of the Residuals Residuals Versus the Fitted Values Histogram of the Residuals Residual Plots for y (Common Slope Model) A model with three separate intercept and slope terms is given by (2) where , , . Fitting the model with MINITAB gives the results shown below. Regression Analysis: y versus d1, d2, d3, d1x, d2x, d3x The regression equation is y = 191 d1 - 751 d2 + 587 d3 + 59.3 d1x + 189 d2x + 32.5 d3x Predictor Coef SE Coef T P Noconstant d1 191.0 234.9 0.81 0.421 d2 -751.0 323.3 -2.32 0.025 d3 587.5 307.9 1.91 0.063 d1x 59.29 22.65 2.62 0.012 d2x 188.91 49.20 3.84 0.000 d3x 32.51 25.54 1.27 0.210
S = 154.664 PRESS = 1287347 Analysis of Variance Source DF SS MS F P Regression 6 29414933 4902489 204.95 0.000 Residual Error 43 1028601 23921 Total 49 30443534 Source DF Seq SS d1x 1 8370407 d2x 1 4652848 d3x 1 16159726 d1 1 15817 d2 1 129071 d3 1 87063 Obs d1 y Fit SE Fit Residual St Resid 2 1.00 610.0 564.5 98.1 45.5 0.38 X 39 0.00 1282.0 938.6 47.9 343.4 2.34R 40 0.00 1233.8 915.8 60.6 318.0 2.23R 41 0.00 1660.0 1000.3 42.0 659.7 4.43R R denotes an observation with a large standardized residual. X denotes an observation whose X value gives it large influence. Residual Percent 800 400 0 -400 99 90 50 10 1 Fitted Value Residual 1000 800 600 400 200 600 400 200 0 -200 Residual Frequency 600 400 200 0 -200 20 15 10 5 0 Normal Probability Plot of the Residuals Residuals Versus the Fitted Values Histogram of the Residuals Residual Plots for y (Model with Different Slopes)

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

View Full Document
The residual plots above indicate that there are three large outliers: observations 39, 40, and 41. After removal of outliers, we obtain the results shown below. Regression Analysis: y versus d1x, d2x, d3x, d1, d2, d3 The regression equation is y = 59.3 d1x + 189 d2x + 55.9 d3x + 191 d1 - 751 d2 + 209 d3 Predictor Coef SE Coef T P Noconstant d1x 59.29 11.17 5.31 0.000 d2x 188.91 24.27 7.78 0.000 d3x 55.95 13.72 4.08 0.000 d1 191.0 115.8 1.65 0.107 d2 -751.0 159.5 -4.71 0.000 d3 208.8 167.7 1.25 0.220 S = 76.2782 PRESS = 333176 Analysis of Variance Source DF SS MS F P Regression 6 24289413 4048236 695.77 0.000 Residual Error 40 232734 5818 Total 46 24522148 Source DF Seq SS d1x 1 8370407 d2x 1 4652848 d3x 1 11112242 d1 1 15817 d2 1 129071 d3 1 9028 Obs d1x y Fit SE Fit Residual St Resid 1 7.7 791.7 647.5 35.0 144.2 2.13R 2 6.3 610.0 564.5 48.4 45.5 0.77 X 20 0.0 400.0 552.4 19.7 -152.4 -2.07R 38 0.0 950.0 751.5 39.1 198.5 3.03R R denotes an observation with a large standardized residual. X denotes an observation whose X value gives it large influence.
Residual Percent 200 100 0 -100 -200 99 90 50 10 1 Fitted Value Residual 1000 800 600 400 200 200 100 0 -100 -200 Residual Frequency 200 150 100 50 0 -50 -100 -150 12 9 6 3 0 Normal Probability Plot of the Residuals Residuals Versus the Fitted Values Histogram of the Residuals Residual Plots for y (Model

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 ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern