Page 22 - Regression Guideline
P. 22
Frequently"Asked"QuesJons"
" People&new&to®ression&modeling"o^en"have"quesJons"about"the"technique"and"concerns" about"their"ability"to"use"and"interpret"the"more"complex"but"more"accurate"mulJvariable" models."However,"once"a"level"of"familiarity"is"developed"and"“math"anxiety”"is"overcome," mulJvariable"regression"models"become"an"indispensible"tool"for"developing"sales" appraisals."Some"of"the"most"frequently"asked"quesJons"people"have"as"they"begin"to"learn" and"use"mulJvariable"models"in"the"context"of"sales"appraisal"are:"
"
Why&can’t&I&just&use&the&results&from&a&group&of&simple&bivariate®ressions&and&combine& those&results&to&predict&a&sale&price?&Why&do&I&need&a&complicated&mulDvariable&model?&
" Although"this"approach"is"appealing"because"of"its"simplicity,"it"will"not"produce"as"accurate" a"result"as"a"mulJvariable"regression"analysis"for"a"number"of"reasons."First,"the"selecJon"of" which"variables"to"use"bivariate"regressions"for"might"leave"out"potenJally"important" factors."Second,"bivariate"regression"does"not"control"for"the"associaJons"among"the" predictor"variables"themselves."For"instance,"the"number"of"bedrooms"and"square"footage" might"both"have"a"very"strong"associaJon"with"sale"price"when"considered"independently"in" separate"bivariate"models."When"considered"simultaneously"in"a"mulJvariable"model," however,"the"associaJon"of"number"of"bedrooms"with"sale"price"might"not"be"as"substanJal" relaJve"to"the"associaJon"with"square"footage."MulJvariable"models"will"automaJcally" adjust"for"the"interdependency"of"these"two"(or"more)"predictors"while"bivariate"models"will" not."As"a"consequence,"if"you"used"two"bivariate"models"to"develop"your"esJmate,"you" would"overesJmate"the"sale"price"because"you"would"be"giving"too"much"weight"to"the" number"of"bedrooms"within"the"context"of"the"property’s"square"footage."The"degree"of" error"introduced"by"adding"together"the"results"of"bivariate"models"increases"as"you" consider"more"and"more"predictors."In"the"end,"it"is"much"easier"to"use"a"mulJvariable" model"to"make"the"correct"adjustments"and"esJmate"a"price"without"you"having"to"do"all"of" the"tedious"mental"and"mathemaJcal"work"of"combining"separate"esJmates.""
&
"
21"
