Hello. I'm sending 8 images attached. For most questions the answers are already there. I need help with the questions in blank starting on page 6. Please let me know if it's ok, I'm willing to pay more money to get this done today.

Thank you very much!

STEP 1 MODEL 1 - Build a Multiple Regression Model Sale Price will be our response variable, build model using the original predictor variables Now, let us do Multiple Regression Analysis 1. Perform a Multiple Linear Regression analysis using stepwise method (using the variables from age to location) and all the statistically relevant predictor variables against Y= Sale Price AND perform residual analysis using the leverage plots. a. What is the estimated regression equation? Y-hat=b0+blx1+b2x2+b3x3+b4x4+b5x5 Y=-3609151 + 87.481444(Building Area in Sqfeet) + (-288295.1)(Miles to Freeway) + 39446.195(Ceiling Height in feet) + 1379500.6(Exterior Wall) + 1866440.1(Facilities Score) Summary of Fit RSquare 0.856546 RSquare Adj 0.842482 Root Mean Square Error 569271.9 Mean of Response 4315614 Observations (or Sum Wgts) 57 Analysis of Variance Sum of Source DF Squares Mean Square F Ratio Model 5 9.8685e+13 1.974e+13 60.9032 Error 51 1.6528e+13 3.241e+11 Prob > F C. Total 56 1.1521e+14 <.0001 parameter estimates term estimate std error t ratio prob>/t| Intercept -3609151 1097606 -3.29 0.0018* Building Area in Sqfeet 87.481444 5.233713 16.71 <.0001 miles to freeway ceiling height in feet exterior wall facilities_score b. provide the predictive power of model and standard error estimate. r-square is which means price determined by consisting building area square facilities score.c. does this multiple regression seem useful support your answer where appropriate use a significance level ho="B1=" b2="B3=" not ha="Bi#0" least one bi zero p-value for f-test="0.0001<0.05" we can reject conclude that useful. d. examine each predictor variables individually determine are contributing significantly model. would you recommend keeping ho: bxi="0," xi prediction ha: t-test: sqfeet=""> P-value =0.0001 P-Value=0.0215 P-Value=0.0094 P-Value=0.0001 P-Value= 0.0073 |t| VIF Intercept -3609151 1097606 -3.29 0.0018 Building Area in Sqfeet 87.481444 5.233713 16.71 <.0001 miles to freeway ceiling height in feet exterior wall facilities_score f. evaluate the required conditions linearity and homoscedasticity only based on your leverage plots.residual by row plot residual number there is no bend plot. so it linearity. then almost this as well. g. do you have any suggestions for remedying problems be specific. model can predictive power sq which currelty improved including some additional predictors like age location. per domain knowledge we know that parameters building years location town or near major economic center affects shall included. inclusion of higher order term another aspect h. provide a point estimate an appropriate interval predict price seven potential properties. pridected sales lower95 indiv upper95 teammemberl teammember2 teammember3 teammember4 teammember5 teammember6 teammember7 d.3721 i. examine from business perspective state conclusion. according f-test say useful prediction about price. also high portion determined model. addition satisfices assumption homoscedasticity. multicollinearity problem between variables. every individual variable has lower p-value than contributing significantly therefore conclude situation use all variables because correlation small vif less inflation factor .especially area sqfeet are more important factors when situation.stepz best using transformation interaction etc. original enriched predictor build created existing techniques etc help with relatively justify it. need stepwise method expertise y="Sale" a. what estimated regression equation standard error estimate. y-hat="b0+b1xl+b2x2+b3x3+b4x4+b5x5+b6x6+b7x7+b8x8+b9x9" facilities score squared .323 summary fit rsquare adj root mean square response observations sum wgts analysis variance source df squares f ratio prob> F C. Total 56 1.1521e+14 <.0001 parameter estimates term estimate std error t ratio prob>|t| VIF Intercept -8427923 1839785 -4.58 <.0001 building area in sqfeet miles to freeway ceiling height feet exterior wall facilities_score building_area_squared ceiling_squared location lotsize b. provide the predictive power of model and standard error estimate. r-square is which means price determined by consisting above nine variables are facilities score squared c. does this multiple regression seem useful support your answer where appropriate use a significance level ho="BI=" b2="B3=" b4="$5=16=17-18-89-0" not ha="Bi#0" least one bi zero p-value for f-test="0.0001<0.05" we can reject conclude that useful. d. examine each predictor individually determine contributing significantly model. would you recommend keeping ho: bxi="0," xi prediction ha: t-test:1> P-value =0.0001 P-value =0.0206 P-value =0.0273 P-value =0.0001 P-value =0.0238 P-value =0.0053 P-value =0.0712> a=0.05 I would not recommend keeping this in model 8) Location => P-value =0.0049 P-value =0.006310, therefore, it is high correlation with the others, multicollinearity 2) Miles to Freeway =1.323058410, it is high correlation with the others, multicollinearity 4) Exterior Wall =1.334265 5) Facilities Score 6) Building Area Squared 7) Ceiling Squared 8) Location 9) LotSize Location 4 Parameter Estimates Term Estimate Std Error t Ratio Prob> |t| VIF Intercept -8427923 1839785 -4.58 <.0001 building area in sqfeet miles to freeway ceiling height feet exterior wall facilities_score building_area_squared ceiling_squared location lotsize f. evaluate the required conditions linearity and homoscedasticity only based on your leverage plots. g. provide a point estimate an appropriate interval predict price of seven potential properties. h. examine model from business perspective state conclusion. step best has predicted prices estimates properties sale. this is starting negotiations now you have select property so need create multiple criteria buy recommendation ptice. guide for preparation group project outline use yourjudgment write report not qkla style make sure everyone team read final report. general instructions as writing ofyour project. maximum number pages including supporting documents single page should be executive summary last will usc-ct title with members name name. which describes key results reader company keep it simple avoid too many technical terms. or bid what offered b. introduction beginning body orients problem gives necessary background motivation c. data describe variables may summarized graphs charts etc. explain statistics median observations like outliers relevant variables. link information tables appendix. variablel: sqfeet: sale are strong positive correlation. d. enrichedftransformedflnteraction va riables limit e. analysis models given set questions detail. why first nd conclusion violated almost assumptio assumption ns but bit fanning. r-sq better useful f-test value="0)" p-value="0.0001<" t-test squared facilities lot size rmse performance measure give kpis model. rsquare adj>