1. SIMPLE LINEAR REGRESSION. For this and the next 3 parts. Thejournal, Fisheries Science (Feb 1995) reported on a study of thevariables that affect endogenous nitrogen excretion (ENE) in carpraised in Japan. Carp were divided into groups of 2 to 15 fish eachaccording to body weight and each group placed in a separate tank.The carp were then fed a protein-free diet three times daily for aperiod of 20 days. One day after terminating the feedingexperiment, the amount of ENE in each tank was measured. The tablebelow gives the mean body weight (in grams) and ENE amount (inmilligrams per 100 grams of body weight per day) for each carpgroup [Source: Watanabe, T. and Ohta, M. "Endogenous NitrogenExcretion and Non-Fecal Energy Loss in Carp and Rainbow Trout,"Fisheries Science, Vol. 61, No. 1, Feb 1995, p. 56]. You should beable to determine which variable is the response variable and whichis the explanatory variable. Which of the following is true? [I]Plot of the residuals shows an upward curvature [II] Plot of theresiduals shows a downward curvature [III] The regression issignificant at the 1% level [IV] Correlation coefficient of the twovariables = -0.68 [V] Standard error of the estimate is 0.0297.

   Tank	Body Weight	ENE
   1	11.7	15.3
   2	25.3	9.3
   3	90.2	6.5
   4	213.0	6.0
   5	10.2	15.7
   6	17.6	10.0
   7	32.6	8.6
   8	81.3	6.4
   9	141.5	5.6
   10	285.7	6.0

   		I and V only
   		II, IV, V
   		I and IV only
   		II and III only
   		None of the above

Part B.

1. SIMPLE LINEAR REGRESSION (above data). Give a 99% predictioninterval for the expected (mean) value of the dependent variablewith X = 0 (note alpha = 0.01).

   		8.3724; 14.4355
   		6.9928; 15.8151
   		-0.0508; -0.0034
   		-0.0615; 0.0073
   		None of the above

Part C.

1. SIMPLE LINEAR REGRESSION (above data). Give a 99% confidenceinterval for the slope (note alpha = 0.01).

   		8.3724; 14.4355
   		6.9928; 15.8151
   		-0.0508; -0.0034
   		-0.0615; 0.0073
   		None of the above

Part D.

1. MULTIPLE REGRESSION (refer to above data). Conduct a multipleregression by introducing a quadratic term to the model. Which ofthe following is true? [I] About 74% of the variation in Yexplained the regression [II] At the 1% level, the regression isstatistically significant [III] At the 5% level, the regression isstatistically significant [IV] Both coefficients are statisticallysignificant at the 5% level [V] At least one of the independentvariables is not significant

   		I, III, V
   		III, IV, V
   		I, II, IV
   		None of the above