Download Solutions Manual for Applied Regression Analysis and Other Multivariable Methods | STAT 3115 and more Assignments Statistics in PDF only on Docsity! Instructor's Solutions Manual for Applied Regression Analysis and Other Multivariable Methods Chapter 5 f The line does not differ from the line plotted in (e). The evidence suggests that there is no significant linear relationship. Determining a well fitting line is difficult given the dispersion of the data. 3.5 > 2.5 - 2 , 1.5 1 375 13e 13f 400 425 450 WGT (X) (grams) 475 14. a j90 = 19.882 $=-0.109 #0:$=0 HA:fi*0 r=-0.76 P = 0.458 Since the P-value is > 0.05, we fail to reject HO and conclude there is not a significant linear relationship between wavelength and year. b The 95% CI for Pi equals: /?, ±^_2A975 • SEp= -0.109 ± (2.101)(0.144) = (-0.41,0.19). c See graph (below). 540 530 520 o w 510 - 500 - 490 1870 1880 1890 1900 1910 1920 1930 1940 YEAR (X) 5-16 Instructor's Solutions Manual for Applied Regression Analysis and Other Multivariable Methods Chapter 5 15. a See graph (below). As Xincreases the dispersion of Y increases. b J3G= -2.546 /?,= 0.032 Y = -2.546 + 0.032X c See graph. This graph implies a better linear relationship between X and Y. d J3Q= -6.532 $=1.430 Y = -6.532 + 1.43QAT e The natural log transformation provides the best representation. The natural log plot illustrates the linear relationship better and the dispersion of the data is more similar at each level of toluene exposure. The first plot indicates that there may be a violation of homoscedasticity for the untransformed data. 100 200 300 400 500 600 700 800 900 1000 PPM_TOLU (X) LN_PPMTL (X) 16. a See graph for plot. As house size increases (X) house price (Y) increases. b J30 = -17.365 $=5.582 c Y =-17.365 + 5.582X. See graph for estimated line. The line fits the data well. 200 -, „ 150 - (ft o 8 X 100> LU O OL a. 50 10 15 20 25 HOUSE SIZE (X) (100s of sq. ft.) 30 35 5-17