Академический Документы
Профессиональный Документы
Культура Документы
SolutionstoOddNumberedEndofChapterExercises
Chapter2
ReviewofProbability
2.1.
(a) ProbabilitydistributionfunctionforY
Outcome(numberofheads)
Probability
Y0
0.25
Y1
0.50
Y2
0.25
(b) CumulativeprobabilitydistributionfunctionforY
Outcome(numberofheads)
Probability
Y0
0
0Y1
0.25
1Y2
0.75
d
(c) Y = E (Y ) (0 0.25) (1 0.50) (2 0.25) 1.00 . F Fq, .
Y2
1.0
2
2
UsingKeyConcept2.3: var(Y ) E (Y ) [ E (Y )] ,
and
(ui | X i )
sothat
W2 var (3 6 X ) 62 X2 36 0 21
7 56,
2
2
2
8 4084
3528
corr (W , V ) WV
04425
WV
756 84084
2011PearsonEducation,Inc.PublishingasAddisonWesley
2.5.
LetXdenotetemperatureinFandYdenotetemperatureinC.RecallthatY0whenX32and
Y100whenX212;thisimplies Y (100/180) ( X 32) or Y 17.78 (5/9) X. UsingKey
Concept2.3,X70oFimpliesthat Y 17.78 (5/9) 70 21.11C, andX7oFimplies
Y (5/9) 7 3.89C.
2.7.
2
2
2
Usingobviousnotation, C M F ; thus C M F and C M F 2cov( M , F ). This
implies
2
2
2
2
2
2
(c) C M F 2cov( M , F ), sothat C 12 18 2 172.80 813.60, and
C 813.60 28.524 thousanddollarsperyear.
(d) FirstyouneedtolookupthecurrentEuro/dollarexchangerateintheWallStreetJournal,the
FederalReservewebpage,orotherfinancialdataoutlet.Supposethatthisexchangerateise
(saye0.80Eurosperdollar);each1dollaristhereforewitheEuros.Themeanistherefore
eC(inunitsofthousandsofEurosperyear),andthestandarddeviationiseC(inunits
ofthousandsofEurosperyear).Thecorrelationisunitfree,andisunchanged.
ValueofY
1
5
8
ProbabilitydistributionofY
ValueofX
14
0.02
0.17
0.02
0.21
22
0.05
0.15
0.03
0.23
30
0.10
0.05
0.15
0.30
40
0.03
0.02
0.10
0.15
65
0.01
0.01
0.09
0.11
Probability
Distributionof
X
0.21
0.40
0.39
1.00
(a) Theprobabilitydistributionisgiveninthetableabove.
E (Y ) 14 0.21 22 0.23 30 0.30 40 0.15 65 0.11 30.15
E (Y 2 ) 142 0.21 222 0.23 302 0.30 402 0.15 652 0.11 1127.23
var(Y ) E (Y 2 ) [ E (Y )]2 218.21
Y 14.77
2011PearsonEducation,Inc.PublishingasAddisonWesley
(b) TheconditionalprobabilityofY|X8isgiveninthetablebelow
ValueofY
14
22
30
40
65
0.02/0.39
0.03/0.39
0.15/0.39
0.10/0.39
0.09/0.39
Y X 8 15.54
(c) E ( XY ) (1 14 0.02) (1 22 : 0.05) L (8 65 0.09) 171.7
cov( X , Y ) E ( XY ) E ( X ) E (Y ) 171.7 5.33 30.15 11.0
corr( X , Y ) cov( X , Y )/( X Y ) 11.0 / (2.60 14.77) 0.286
2.11.
(a) 0.90
(b) 0.05
(c) 0.05
2
Y /10 ~ F10, .
(d) When Y ~ 10 , then
2
(e) Y Z , where Z ~ N (0,1), thus Pr (Y 1) Pr (1 Z 1) 0.32.
2.13.
2
2
2
2
(a) E (Y ) Var (Y ) Y 1 0 1; E (W ) Var (W ) W 100 0 100.
(b)YandWaresymmetricaround0,thusskewnessisequalto0;becausetheirmeaniszero,this
meansthatthethirdmomentiszero.
4
4
4
(c) Thekurtosisofthenormalis3,so 3 E (Y Y ) / Y ;solvingyields E(Y ) 3; asimilar
calculationyieldstheresultsforW.
X 0, sothat S W :
(d) First,conditionon
E ( S | X 0) 0; E ( S 2 | X 0) 100, E ( S 3 |X 0) 0, E ( S 4 | X 0) 3 1002.
Similarly,
2
3
4
E ( S | X 1) 0; E ( S | X 1) 1, E ( S | X 1) 0, E ( S | X 1) 3.
2011PearsonEducation,Inc.PublishingasAddisonWesley
Fromthelawofiteratedexpectations
E ( S ) E ( S | X 0) Pr (X 0) E ( S | X 1) Pr( X 1) 0
E ( S 2 ) E ( S 2 | X 0) Pr (X 0) E ( S 2 | X 1) Pr( X 1) 100 0.01 1 0.99 1.99
E (S 3 ) E (S 3 | X 0) Pr (X 0) E ( S 3 | X 1) Pr( X 1) 0
E ( S 4 ) E ( S 4 | X 0) Pr (X 0) E ( S 4 | X 1) Pr( X 1)
3
3
(e) S E ( S ) 0, thus E ( S S ) E ( S ) 0 frompart(d).Thusskewness0.Similarly,
4/n
4/n
4/n
Pr (9.6 Y 10.4) Pr
10.4 10
9.6 10
Z
4/n
4/n
Pr
2.15.
(a)
whereZ~N(0,1).Thus,
(i) n20;
10.4 10
9.6 10
Z
Pr (0.89 Z 0.89) 0.63
4/n
4/n
Pr
(ii) n100;
(iii)
10.4 10
9.6 10
Z
Pr( 2.00 Z 2.00) 0.954
4/n
4/n
Pr
n 1000;
10.4 10
9.6 10
Z
Pr(6.32 Z 6.32) 1.000
4/n
4/n
Pr
4/n
Pr (10 c Y 10 c) Pr
Pr
(b)
Y 10
4/n
4/n
c
c
Z
.
4/n
4/n
c
Asngetlarge 4 / n getslarge,andtheprobabilityconvergesto1.
(c) Thisfollowsfrom(b)andthedefinitionofconvergenceinprobabilitygiveninKeyConcept2.6.
2.17.
2
Y=0.4and Y 0.4 0.6 0.24
Y 0.4
0.6124
Pr
0.27
0.24/n
0.24/n
0.24/n
Pr
2011PearsonEducation,Inc.PublishingasAddisonWesley
Y 0.4
1.22 0.11
Pr
0.24/n
0.24/n
0.24/n
Pr
(ii) P( Y 0.37)
0.41
(b) WeknowPr(1.96Z1.96)0.95,thuswewantntosatisfy
0.39 0.40
1.96.
24 / n
and
Solvingtheseinequalitiesyieldsn9220.
0.41 0.40
1.96
24 / n
Pr (Y y j ) Pr ( X xi , Y y j )
i 1
l
2.19.
Pr (Y y j | X xi )Pr ( X xi )
(a)
i 1
j 1
i 1
E (Y ) y j Pr (Y yj ) yj Pr (Y yj |X xi ) Pr ( X xi )
j 1
l
yj Pr (Y yj |X xi ) Pr ( X xi )
i 1 j 1
E (Y | X xi )Pr ( X xi )
(b)
i 1
Pr (X xi , Y y j ) Pr (X xi )Pr (Y yj )
so
XY E[( X X )(Y Y )]
l
( xi X )( y j Y ) Pr ( X xi , Y y j )
i 1 j 1
l
( xi X )( y j Y ) Pr ( X xi ) Pr (Y y j )
i 1 j 1
k
(
x
)
Pr
(
X
x
)
i
X
i ( y j Y ) Pr (Y y j
i 1
j 1
E ( X X ) E (Y Y ) 0 0 0,
corr(X , Y )
XY
0
0
XY XY
E ( X )3 E[( X ) 2 ( X )] E[ X 3 2 X 2 X 2 X 2 2 X 2 3 ]
E ( X 3 ) 3E ( X 2 ) 3 E ( X ) 2 3 E ( X 3 ) 3E ( X 2 ) E ( X )
3E ( X )[ E ( X )]2 [ E ( X )]3
2.21.
(a)
E ( X 3 ) 3E ( X 2 ) E ( X ) 2 E ( X ) 3
2011PearsonEducation,Inc.PublishingasAddisonWesley
E ( X ) 4 E[( X 3 3 X 2 3 X 2 3 )( X )]
E[ X 4 3 X 3 3 X 2 2 X 3 X 3 3 X 2 2 3 X 3 4 ]
E ( X 4 ) 4 E ( X 3 ) E ( X ) 6 E ( X 2 ) E ( X ) 2 4 E ( X ) E ( X )3 E ( X ) 4
(b)
2011PearsonEducation,Inc.PublishingasAddisonWesley
2.23.
XandZaretwoindependentlydistributedstandardnormalrandomvariables,so
X Z 0, X2 Z2 1, XZ 0.
(a) Becauseoftheindependencebetween X and Z , Pr ( Z z| X x) Pr ( Z z ), and
E ( Z |X ) E ( Z ) 0. Thus E (Y | X ) E ( X 2 Z | X ) E ( X 2| X ) E ( Z |X ) X 2 0 X 2
2
2
2
2
2
(b) E ( X ) X X 1, and Y E ( X Z ) E ( X ) Z 1 0 1
3
3
(c) E ( XY ) E ( X ZX ) E ( X ) E ( ZX ). Usingthefactthattheoddmomentsofastandard
normalrandomvariableareallzero,wehave E ( X ) 0. Usingtheindependencebetween
3
X and Z , wehave E ( ZX ) Z X 0. Thus E ( XY ) E ( X ) E ( ZX ) 0.
3
0
corr (X , Y ) XY
0
XY XY
(d)
2.25.
i 1
i 1
(a)
n
(x
i 1
yi ) ( x1 y1 x2 y2 L xn yn )
( x1 x2 L xn ) ( y1 y2 L yn )
(b)
n
(c)
i 1
i 1
a ) na
i 1
n
i 1
2.27
a (a a a L
(a bx
(d)
xi yi
i 1
i 1
i 1
i 1
i 1
2011PearsonEducation,Inc.PublishingasAddisonWesley
(b) E(WZ)E[E(WZ|Z)]E[ZE(W)|Z]E[Z0]0
(c) Usingthehint:VWh(Z),sothatE(V2)E(W2)E[h(Z)2]2E[Wh(Z)].Usingan
argumentlikethatin(b),E[Wh(Z)]0.Thus,E(V2)E(W2)E[h(Z)2],andtheresult
followsbyrecognizingthatE[h(Z)2]0becauseh(z)20foranyvalueofz.
Chapter3
ReviewofStatistics
3.1.
Thecentrallimittheoremsuggeststhatwhenthesamplesize( n )islarge,thedistributionofthe
2
Y2 Y .
N Y , Y2
n Givenapopulation Y 100,
sampleaverage( Y )isapproximately
with
Y2 430, wehave
(a) n 100,
Y2
Y2 43
043,
n 100
and
Y 100
Pr (Y 101) Pr
(b) n 64,
Y2
043
101 100
(1.525) 09364
043
Y2 43
06719,
n 64
and
101 100 Y 100 103 100
06719
06719
06719
(36599) (12200) 09999 08888 01111
Pr(101 Y 103) Pr
(c) n 165,
Y2
Y2 43
02606,
n 165
and
Y 100 98 100
02606
02606
1 ( 39178) (39178) 10000 (rounded to four decimal places)
Pr (Y 98) 1 Pr (Y 98) 1 Pr
3.3.
2011PearsonEducation,Inc.PublishingasAddisonWesley
215
05375.
400
(a)
(b)Theestimatedvarianceof p is
2
standarderrorisSE ( p ) (var( p )) 00249.
(c) Thecomputedtstatisticis
t act
p p0
SE( p )
05375 05
1506
00249
(a) (i)
Thesizeisgivenby Pr(| p 0.5| .02), wheretheprobabilityiscomputedassuming
that p 0.5.
Pr(|p 0.5| 0.02) 1 Pr( 0.02 p 0.5 .02)
0.02
1 Pr
0.5 0.5/1055
p 0.5
0.5 0.5/1055
0.5 0.5/1055
0.02
p 0.5
1 Pr 1.30
1.30
0.5 0.5/1055
0.19
wherethefinalequalityusingthecentrallimittheoremapproximation.
(ii) Thepowerisgivenby Pr(| p 0.5| 0.02), wheretheprobabilityiscomputedassuming
thatp0.53.
2011PearsonEducation,Inc.PublishingasAddisonWesley
0.53 0.47/1055
0.53 0.47/1055
0.53 0.47/1055
1 Pr
0.05
0.53 0.47/1055
1 Pr
p 0.53
0.53 0.47/1055
0.01
0.53 0.47/1055
p 0.53
1 Pr 3.25
0.65
.53 0.47/1055
0.74
wherethefinalequalityusingthecentrallimittheoremapproximation.
0.54 0.50
2.61, and Pr(|t | 2.61) 0.01,
(0.54 0.46) / 1055
(b) (i)
sothatthenullisrejectedatthe
5%level.
(ii) Pr(t 2.61) .004, sothatthenullisrejectedatthe5%level.
(iii) 0.54 1.96 (0.54 0.46) / 1055 0.54 0.03, or 0.51 to 0.57.
(iv) 0.54 2.58 (0.54 0.46) / 1055 0.54 0.04, or 0.50 to 0.58.
(v) 0.54 0.67 (0.54 0.46) / 1055 0.54 0.01, or 0.53 to 0.55.
(c) (i) Theprobabilityis0.95isanysinglesurvey,thereare20independentsurveys,sothe
20
probabilityif 0.95 0.36
(ii) 95%ofthe20confidenceintervalsor19.
1.96 SE( p ) .01 or 1.96 p(1 p) / n .01.
(d) Therelevantequationis
Thusnmustbe
2
1.96 p(1 p )
n
,
0.012
chosensothat
sothattheanswerdependsonthevalueofp.Notethatthe
largestvaluethatp(1p)cantakeonis0.25(thatis,p0.5makesp(1p)aslargeas
1.962 0.25
n
9604,
0.012
possible).Thusif
thenthemarginoferrorislessthan0.01forall
valuesofp.
3.7.
Thenullhypothesisisthatthesurveyisarandomdrawfromapopulationwithp=0.11.Thet
p 0.11
t
,
SE( p ) where SE( p ) p (1 p )/n. (AnalternativeformulaforSE( p )is
statisticis
statisticis2.71,whichhasapvalueofthatislessthan0.01.Thusthenullhypothesis p 0.11
(thesurveyisunbiased)canberejectedatthe1%level.
3.9.
Y
200
20
n
100
hours.The
2011PearsonEducation,Inc.PublishingasAddisonWesley
| 2000
20
20
1 Pr
Thepowerofatestistheprobabilityofcorrectlyrejectinganullhypothesiswhenitisinvalid.We
calculatefirsttheprobabilityofthemanagererroneouslyacceptingthenullhypothesiswhenitis
invalid:
Y 2150 2100 2150
| 2150
20
20
act
2000
1645 Y act 2000 1645 20 20329
20
Themanagershouldbelievetheinventorsclaimifthesamplemeanlifeofthenewproductis
greaterthan2032.9hoursifshewantsthesizeofthetesttobe5%.
3.11.
1 1
3
1
3
E (Y%
) E (Y1 ) E (Y2 ) L E (Yn 1 ) E (Yn )
n 2
2
2
2
1 1 n
3 n
Y Y Y
n 2 2
2 2
1 1
9
1
9
var(Y%
) 2 var(Y1 ) var(Y2 ) L var(Yn 1 ) var(Yn )
n 4
4
4
4
1 1 n 2 9 n 2
Y Y
n2 4 2
4 2
2
1 25 Y
n
2011PearsonEducation,Inc.PublishingasAddisonWesley
3.13
s12 s22
19.42 17.92
18281.
n1 n2
238
182
Thehypothesistestsforhigheraverage
scoresinsmallerclassesis
H 0 1 2 0
vs H1 1 2 0
Thetstatisticis
t act
Thepvaluefortheonesidedtestis:
Fromthetextbookequation(2.46),weknowthatE( Y )Yandfrom(2.47)weknowthat
Y2
var( Y ) n .Inthisproblem,becauseYaandYbareBernoullirandomvariables, p a Ya , p b
2011PearsonEducation,Inc.PublishingasAddisonWesley
5801
4249
95%CIis(.859.374)1.96
or0.4850.017.
3.17.
(a) The95%confidenceintervalis
SE(Ym , 2008 Ym , 1992 )
2
m ,2008
nm ,2008
2
m ,1992
nm ,1992
11.782 10.17 2
0.37;
1838
1594
where
the95%confidence
intervalis(24.9823.27)0.73or1.710.73.
(b) The95%confidenceintervalis
SE(Yw, 2008 Yw, 1992 )
2
w,2008
nw,2008
2
w ,1992
nw,1992
9.662 7.782
0.31;
1871 1368
where
the95%confidenceinterval
(Y
Y
) (Yw, 2004 Yw, 1992 ) 1.96 SE[(Ym, 2008 Ym,1992 )
(c) The95%confidenceintervalis m , 2004 m, 1992
(Yw, 2008 Yw, 1992 )],
SE[(Ym , 2008 Ym , 1992 ) (Yw, 2008 Yw, 1992 )]
where
sm2 ,2008
sm2 ,1992
sw2 ,2008
sw2 ,1992
3.19.
(a) No.
1
1 n
E (Y ) E Yi 2
n
n i 1
2
E (Y
i 1
1
n2
Thus
E (Y Y )
i 1 j i
2
Y
1
Y2
n
getsarbitrarilycloseto Y withprobabilityapproaching1asngetslarge.(Asitturnsout,
thisisanexampleofthecontinuousmappingtheoremdiscussedinChapter17.)
2
3.21.
Setnmnwn,anduseequation(3.19)writethesquaredSEof Ym Yw as
2011PearsonEducation,Inc.PublishingasAddisonWesley
1
1
in1 (Ymi Ym ) 2
in1 (Ywi Yw )2
(n 1)
(n 1)
2
[ SE (Ym Yw )]
n
n
Similarly,usingequation(3.23)
1 n
1
i 1 (Ymi Ym ) 2
in1 (Ywi Yw ) 2
2( n 1)
( n 1)
Chapter4
LinearRegressionwithOneRegressor
4.1.
(a) Thepredictedaveragetestscoreis
2011PearsonEducation,Inc.PublishingasAddisonWesley
TestScore
5204 582 22 39236
(b) Thepredictedchangeintheclassroomaveragetestscoreis
TestScore (582 19) (582 23) 2328
(d) Usetheformulaforthestandarderroroftheregression(SER)inEquation(4.19)togetthe
sumofsquaredresiduals:
Usetheformulafor R inEquation(4.16)togetthetotalsumofsquares:
TSS
SSR
12961
13044
2
1 R 1 0082
TSS
2
13044
1318.
s sY2 115.
99
Thesamplevarianceis sY n1
Thus,standarddeviationis Y
4.3.
(a) Thecoefficient9.6showsthemarginaleffectofAgeonAWE;thatis,AWEisexpectedto
increaseby$9.6foreachadditionalyearofage.696.7istheinterceptoftheregressionline.It
determinestheoverallleveloftheline.
(b) SERisinthesameunitsasthedependentvariable(Y,orAWEinthisexample).ThusSERis
measuredindollarsperweek.
(c) R2isunitfree.
(d) (i) 696.7 9.6 25 $936.7;
(ii) 696.7 9.6 45 $1,128.7
(e) No.Theoldestworkerinthesampleis65yearsold.99yearsisfaroutsidetherangeofthe
sampledata.
(f) No.Thedistributionofearningispositivelyskewedandhaskurtosislargerthanthenormal.
2011PearsonEducation,Inc.PublishingasAddisonWesley
4.5.
4.7.
(a) uirepresentsfactorsotherthantimethatinfluencethestudentsperformanceontheexam
includingamountoftimestudying,aptitudeforthematerial,andsoforth.Somestudentswill
havestudiedmorethanaverage,otherless;somestudentswillhavehigherthanaverage
aptitudeforthesubject,otherslower,andsoforth.
(b) BecauseofrandomassignmentuiisindependentofXi.Sinceuirepresentsdeviationsfrom
averageE(ui)0.BecauseuandXareindependentE(ui|Xi)E(ui)0.
(c) (2)issatisfiedifthisyearsclassistypicalofotherclasses,thatis,studentsinthisyears
classcanbeviewedasrandomdrawsfromthepopulationofstudentsthatenrollintheclass.
(3)issatisfiedbecause0Yi100andXicantakeononlytwovalues(90and120).
(d) (i) 49 0.24 90 70.6; 49 0.24 120 77.8; 49 0.24 150 85.0
(ii) 0.24 10 2.4.
Theexpectationof 0 isobtainedbytakingexpectationsofbothsidesofEquation(4.8):
1 n
E ( 0 ) E (Y 1 X ) E 0 1 X ui 1 X
n i 1
n
1
0 E ( 1 1 ) X E (ui )
n i 1
0
wherethethirdequalityintheaboveequationhasusedthefactsthatE(ui)0andE[( 1 1) X ]
4.9.
(a) With 1 0, 0 Y , and Yi 0 Y . ThusESS0andR20.
n
i 1
(Xi X ) 0
2
and 1 isundefined(seeequation(4.7)).
(a) Theleastsquaresobjectivefunctionis i 1
n
4.11.
(Yi b1 X i ) 2.
Differentiatingwithrespecttob1
(Yi b1 X i ) 2
i 1
yields
b1
2 i 1 X i (Yi b1 X i ).
n
Settingthiszero,andsolvingfortheleast
1
squaresestimatoryields
X Y
i 1
n
i i
X
i 1
2
i
2011PearsonEducation,Inc.PublishingasAddisonWesley
1
(b) Followingthesamestepsin(a)yields
4.13.
X (Y 4)
i 1
X i2
i 1
TheanswerfollowsthederivationsinAppendix4.3inLargeSampleNormalDistributionofthe
OLSEstimator.Inparticular,theexpressionforiisnowi(XiX)ui,sothatvar(i)
3var[(XiX)ui],andtheterm2carrythroughtherestofthecalculations.
Chapter5
RegressionwithaSingleRegressor:Hypothesis
TestsandConfidenceIntervals
5.1
1 0 582
26335
SE( 1) 221
Thepvalueforthetest H 0 1 0 vs. H1 1 0 is
t act
1 (5.6) 022
0.10
SE ( 1)
221
The99%confidenceintervalis1.5{3.942.580.31)or4.71lbsWeightGain7.11lbs.
2011PearsonEducation,Inc.PublishingasAddisonWesley
5.5
(a) Theestimatedgainfrombeinginasmallclassis13.9points.Thisisequalto
approximately1/5ofthestandarddeviationintestscores,amoderateincrease.
13.9
5.56,
2.5
(b) Thetstatisticis
whichhasapvalueof0.00.Thusthenullhypothesisis
rejectedatthe5%(and1%)level.
t act
(c) 13.92.582.513.96.45.
5.7.
3.2
2.13
(a) Thetstatisticis 1.5
withapvalueof0.03;sincethepvalueislessthan0.05,the
nullhypothesisisrejectedatthe5%level.
(b) 3.21.961.53.22.94
(c) Yes.IfYandXareindependent,then 1 0; butthisnullhypothesiswasrejectedatthe
5%levelinpart(a).
(d) 1 wouldberejectedatthe5%levelin5%ofthesamples;95%oftheconfidenceintervals
wouldcontainthevalue 1 0.
5.9.
(a)
1
n
(Y1 Y2 L Yn )
X
sothatitislinearfunctionofY1,Y2,,Yn.
(b) E(Yi|X1,,Xn)Xi,thus
1
n (Y1 Y2 L Yn )
E ( |X 1 , K , X n ) E
| ( X 1 , K , X n )
X
1
( X1 L X n )
n
.
X
5.11.
2
m
2
w
s
s
.
nm nw
SE (Ym )
sm
nm
and
SE ( 1 ) 7.65.
5.13.
5.15.
(a) Yes,thisfollowsfromtheassumptionsinKC4.3.
(b) Yes,thisfollowsfromtheassumptionsinKC4.3andconditionalhomoskedasticity
(c) Theywouldbeunchangedforthereasonsspecifiedintheanswerstothosequestions.
(d) (a)isunchanged;(b)isnolongertrueastheerrorsarenotconditionallyhomosckesdastic.
isconsistentlyestimatedas
and
is
2011PearsonEducation,Inc.PublishingasAddisonWesley
2011PearsonEducation,Inc.PublishingasAddisonWesley
Chapter6
LinearRegressionwith
MultipleRegressors
6.1.
Byequation(6.15)inthetext,weknow
R2 1
n 1
(1 R 2 ).
n k 1
Thus,thatvaluesof R are0.175,0.189,and0.193forcolumns(1)(3).
6.3.
6.5.
(a) Onaverage,aworkerearns$0.29/hourmoreforeachyearheages.
(b) Sallysearningspredictionis 440 548 1 262 1 029 29 1567 dollarsperhour.
Betsysearningspredictionis 440 548 1 262 1 029 34 1712 dollarsperhour.
Thedifferenceis1.45
(a) $23,400(recallthatPriceismeasuredin$1000s).
(b) InthiscaseBDR1andHsize100.Theresultingexpectedchangeinpriceis23.4
0.15610039.0thousanddollarsor$39,000.
(c) Thelossis$48,800.
(d) Fromthetext
R 2 1 n n k11 (1 R 2 ),
so
R 2 1 n n k 11 (1 R 2 ),
thus,R20.727.
6.7.
(a) Theproposedresearchinassessingthepresenceofgenderbiasinsettingwagesistoo
limited.Theremightbesomepotentiallyimportantdeterminantsofsalaries:typeofengineer,
amountofworkexperienceoftheemployee,andeducationlevel.Thegenderwiththelower
wagescouldreflectthetypeofengineeramongthegender,theamountofworkexperienceof
theemployee,ortheeducationleveloftheemployee.Theresearchplancouldbeimproved
withthecollectionofadditionaldataasindicatedandanappropriatestatisticaltechniquefor
analyzingthedatawouldbeamultipleregressioninwhichthedependentvariableiswages
andtheindependentvariableswouldincludeadummyvariableforgender,dummyvariables
fortypeofengineer,workexperience(timeunits),andeducationlevel(highestgradelevel
completed).Thepotentialimportanceofthesuggestedomittedvariablesmakesadifference
inmeanstestinappropriateforassessingthepresenceofgenderbiasinsettingwages.
(b) Thedescriptionsuggeststhattheresearchgoesalongwaytowardscontrollingforpotential
omittedvariablebias.Yet,therestillmaybeproblems.Omittedfromtheanalysisare
characteristicsassociatedwithbehaviorthatledtoincarceration(excessivedrugoralcohol
use,gangactivity,andsoforth),thatmightbecorrelatedwithfutureearnings.Ideally,dataon
thesevariablesshouldbeincludedintheanalysisasadditionalcontrolvariables.
6.9.
Foromittedvariablebiastooccur,twoconditionsmustbetrue:X1(theincludedregressor)is
correlatedwiththeomittedvariable,andtheomittedvariableisadeterminantofthedependent
variable.SinceX1andX2areuncorrelated,theestimatorof1doesnotsufferfromomitted
variablebias.
6.11.
(a)
(Y b X
i
1i
b2 X 2i )2
(Yi b1 X 1i b2 X 2i ) 2
2 X 1i (Yi b1 X 1i b2 X 2 i )
b1
(Yi b1 X 1i b2 X 2 i )2
2 X 2i (Yi b1 X 1i b2 X 2 i )
b2
(b)
1i
(Yi 1 X 1i 1 X 2 i ) 0
X 1iYi 2 X 1i X 2i
1
X 12i
or
andtheresultfollowsimmediately.
(d) Followinganalysisasin(c)
X 2iYi 1 X 1i X 2i
2
X 22i
andsubstitutingthisintotheexpressionfor 1 in(c)yields
X Y
X 1i X 2 i
X 1iY 2 i i X1
X 1i X 2 i
2
2i
1
.
X 12i
Solvingfor 1 yields:
X 22i X 1iYi X 1i X 2 i X 2iYi
1
X 12i X 22i ( X 1i X 2 i ) 2
(e) Theleastsquaresobjectivefunctionis
withrespecttob0is
(Yi b0 b1 X 1i b2 X 2 i ) 2
andthepartialderivative
(Yi b0 b1 X 1i b2 X 2 i ) 2
2 (Yi b0 b1 X 1i b2 X 2i ).
b0
Settingthistozeroandsolvingfor 0 yields: 0 Y 1 X 1 2 X 2 .
2011PearsonEducation,Inc.PublishingasAddisonWesley
Noticethattheestimatorfor1isidenticaltotheOLSestimatorfromtheregressionofYonto
( X X 1 )( X 2 i X 2 ) 0
X1,omittingX2.Saiddifferently,when 1i
,theestimatedcoefficient
onX1intheOLSregressionofYontobothX1andX2isthesameasestimatedcoefficientin
theOLSregressionofYontoX1.
Chapter7
HypothesisTestsandConfidence
IntervalsinMultipleRegression
7.1and7.2
Regressor
(1)
(2)
(3)
College(X1)
5.46**
(0.21)
5.48**
(0.21)
5.44**
(0.21)
Female(X2)
2.64**
(0.20)
2.62**
(0.20)
2.62**
(0.20)
0.29**
(0.04)
0.29**
(0.04)
Age(X3)
Ntheast(X4)
0.69*
(0.30)
Midwest(X5)
0.60*
(0.28)
South(X6)
0.27
(0.26)
Intercept
12.69**
(0.14)
4.40**
(1.05)
3.75**
(1.06)
(a) Thetstatisticis5.46/0.2126.0,whichexceeds1.96inabsolutevalue.Thus,thecoefficient
isstatisticallysignificantatthe5%level.The95%confidenceintervalis5.461.960.21.
(b) tstatisticis2.64/0.2013.2,and13.21.96,sothecoefficientisstatisticallysignificant
atthe5%level.The95%confidenceintervalis2.641.960.20.
7.3.
(a) Yes,ageisanimportantdeterminantofearnings.Usingattest,thetstatisticis
0.29 / 0.04 7.25, withapvalueof4.21013,implyingthatthecoefficientonageis
statisticallysignificantatthe1%level.The95%confidenceintervalis0.291.960.04.
(b) Age[0.291.960.04]5[0.291.960.04]1.451.960.20$1.06to$1.84
t
7.5.
college,1998 college,1992
SE( college,1998 college, 1992 )
Thetstatisticforthedifferenceinthecollegecoefficientsis
.Because
college,1998
college,1992
and
arecomputedfromindependentsamples,theyareindependent,which
2011PearsonEducation,Inc.PublishingasAddisonWesley
meansthat
t act
Thus,
.Thisimpliesthat
=
1
5.48 5.29
0.6552.
0.212 0.20 2
Thus,
Thereisnosignificantchangesincethecalculatedtstatistic
islessthan1.96,the5%criticalvalue.
7.7.
(a) Estimate
Yi 0 X 1i 2 ( X 1i X 2i ) ui
andtestwhether0.
(b) Estimate
Yi 0 X 1i 2 ( X 2 i aX 1i ) ui
andtestwhether0.
(c) Estimate
Yi X 1i 0 X 1i 2 ( X 2i X1i ) ui
andtestwhether0.
7.11.
(a) Treatment(assignmenttosmallclasses)wasnotrandomlyassignedinthepopulation(the
continuingandnewlyenrolledstudents)becauseofthedifferenceintheproportionoftreated
continuingandnewlyenrolledstudents.Thus,thetreatmentindicatorX1iscorrelatedwithX2.
Ifnewlyenrolledstudentsperformsystematicallydifferentlyonstandardizedteststhan
continuingstudents(perhapsbecauseofadjustmenttoanewschool),thenthisbecomespart
oftheerrortermuin(a).ThisleadstocorrelationbetweenX1andu,sothatE(u|Xl)0.
(b)Becausetreatmentwasrandomlyassignedconditionalonenrollmentstatus(continuingor
newlyenrolled),E(u|X1,X2)willnotdependonX1.Thismeansthattheassumptionof
conditionalmeanindependenceissatisfied,and 1 isunbiasedandconsistent.However,
becauseX2wasnotrandomlyassigned(newlyenrolledstudentsmay,onaverage,have
attributesotherthanbeingnewlyenrolledthataffecttestscores),E(u|X1,X2)maydependof
X2,sothat 2 maybebiasedandinconsistent.
2011PearsonEducation,Inc.PublishingasAddisonWesley
Chapter8
NonlinearRegressionFunctions
8.1.
100
(a) Thepercentageincreaseinsalesis
is100[ln(198)ln(196)]1.0152%.
198 196
1.0204%.
196
Theapproximation
100
205 196
4.5918%
196
andthe
(b) WhenSales2010205,thepercentageincreaseis
approximationis100[ln(205)ln(196)]4.4895%.WhenSales2010250,thepercentage
250 196
100
27.551%
196
increaseis
andtheapproximationis100[ln(250)ln(196)]
100
500 196
155.1%
196
andthe
24.335%.WhenSales2010500,thepercentageincreaseis
approximationis100[ln(500)ln(196)]93.649%.
(c) Theapproximationworkswellwhenthechangeissmall.Thequalityoftheapproximation
deterioratesasthepercentagechangeincreases.
8.3.
(a) Theregressionfunctionsforhypotheticalvaluesoftheregressioncoefficientsthatare
consistentwiththeeducatorsstatementare: 1 0 and 2 0. When TestScore isplotted
against STR theregressionwillshowthreehorizontalsegments.Thefirstsegmentwillbefor
valuesof STR 20; thenextsegmentfor 20 STR 25; thefinalsegmentfor STR 25. The
firstsegmentwillbehigherthanthesecond,andthesecondsegmentwillbehigherthanthe
third.
(b) Ithappensbecauseofperfectmulticollinearity.Withallthreeclasssizebinaryvariables
includedintheregression,itisimpossibletocomputetheOLSestimatesbecausetheintercept
isaperfectlinearfunctionofthethreeclasssizeregressors.
8.5.
(a) (1)
Thedemandforolderjournalsislesselasticthanforyoungerjournalsbecausethe
interactiontermbetweenthelogofjournalageandpricepercitationispositive.(2)There
isalinearrelationshipbetweenlogpriceandlogofquantityfollowsbecausetheestimated
coefficientsonlogpricesquaredandlogpricecubedarebothinsignificant.(3)Thedemand
isgreaterforjournalswithmorecharactersfollowsfromthepositiveandstatistically
significantcoefficientestimateonthelogofcharacters.
(ii) Asdescribedinequation(8.8)andthefootnoteonpage261,thestandarderrorcanbefound
bydividing0.28,theabsolutevalueoftheestimate,bythesquarerootofthe
Fstatistictestingln(Pricepercitation)ln(80)ln(Age)ln(Pricepercitation)0.
(c)
Characters
ln(Characters ) ln(a)
a
foranyconstanta.Thus,estimatedparameteron
ln
Characterswillnotchangeandtheconstant(intercept)willchange.
8.7.
(ii) Femaleiscorrelatedwiththetwonewincludedvariablesandatleastoneofthevariablesis
importantforexplainingln(Earnings).Thustheregressioninpart(a)sufferedfromomitted
variablebias.
(c) ForgettingabouttheeffectorReturn,whoseeffectsseemssmallandstatisticallyinsignificant,
theomittedvariablebiasformula(seeequation(6.1))suggeststhatFemaleisnegatively
correlatedwithln(MarketValue).
8.9.
Notethat
Y 0 1 X 2 X 2
0 ( 1 21 2 ) X 2 ( X 2 21X ).
2
Defineanewindependentvariable Z X 21X , andestimate
Y 0 X 2 Z ui
Theconfidenceintervalis
8.11.
196 SE .
dE (Y | X )
1
dX
Linearmodel:E(Y|X)01X,sothat
andtheelasticityis
1 X
X
1
E (Y | X ) 0 1 X
dE (Y | X ) 1 0 1 ln( X )
E (Y | X )
ce
1
dX
X
X
Thus
,andtheelasticityis1.
Chapter9
AssessingStudiesBasedon
MultipleRegression
9.1.
Asexplainedinthetext,potentialthreatstoexternalvalidityarisefromdifferencesbetweenthe
populationandsettingstudiedandthepopulationandsettingofinterest.Thestatisticalresults
basedonNewYorkinthe1970sarelikelytoapplytoBostoninthe1970sbutnottoLosAngeles
inthe1970s.In1970,NewYorkandBostonhadlargeandwidelyusedpublictransportation
systems.AttitudesaboutsmokingwereroughlythesameinNewYorkandBostoninthe1970s.In
contrast,LosAngeleshadaconsiderablysmallerpublictransportationsystemin1970.Most
residentsofLosAngelesreliedontheircarstocommutetowork,school,andsoforth.Theresults
fromNewYorkinthe1970sareunlikelytoapplytoNewYorkin2010.Attitudestowards
smokingchangedsignificantlyfrom1970to2010.
9.3.
Thekeyisthattheselectedsamplecontainsonlyemployedwomen.Considertwowomen,Beth
andJulie.Bethhasnochildren;Juliehasonechild.BethandJulieareotherwiseidentical.Both
canearn$25,000peryearinthelabormarket.Eachmustcomparethe$25,000benefittothecosts
ofworking.ForBeth,thecostofworkingisforgoneleisure.ForJulie,itisforgoneleisureandthe
costs(pecuniaryandother)ofchildcare.IfBethisjustonthemarginbetweenworkinginthe
labormarketornot,thenJulie,whohasahigheropportunitycost,willdecidenottoworkinthe
labormarket.Instead,Juliewillworkinhomeproduction,caringforchildren,andsoforth.
Thus,onaverage,womenwithchildrenwhodecidetoworkarewomenwhoearnhigherwagesin
thelabormarket.
9.5.
1 0 0 1 1u 1v
.
1 1
1 1
0 0
uv
.
1 1 1 1
(a)
and
E (Q)
(b)
1 0 0 1
0
, E ( P) 0
1 1
1 1
1
2 2
2 2
var(Q)
( 1 u 1 v ), var( P )
1 1
1
2
2
( u v ),
1
1
(c)
and
1
2
2
cov( P, Q)
( 1 u 1 V )
1 1
2 1 v2
p cov(Q, P )
1
1 u2
,
2
var(
P
)
u
v
(d) (i)
cov( P, Q )
p
0
E (Q ) E ( P )
var( P)
( )
1 1 u 2 1 2 1 0,
u v
(ii)
usingthefactthat10(supplycurvesslopeup)and10
(demandcurvesslopedown).
p
9.7.
(a) True.CorrelationbetweenregressorsanderrortermsmeansthattheOLSestimatoris
inconsistent.
(b) True.
9.9.
Bothregressionssufferfromomittedvariablebiassothattheywillnotprovidereliableestimates
ofthecausaleffectofincomeontestscores.However,thenonlinearregressionin(8.18)fitsthe
datawell,sothatitcouldbeusedforforecasting.
9.11.
Again,therearereasonsforconcern.Hereareafew.
Internalconsistency:Totheextentthatpriceisaffectedbydemand,theremaybesimultaneous
equationbias.
Externalconsistency:TheinternetandintroductionofEjournalsmayinduceimportantchangesin
themarketforacademicjournalssothattheresultsfor2000maynotberelevantfortodaysmarket.
1 i 1
300
9.13.
%
( X%
i X )(Yi Y )
(a)
300
i 1
%2
( X%
i X)
.BecausealloftheXisareused(althoughsomeareusedfor
thewrongvaluesofYj), X% X ,and i 1
Usingtheseexpressions:
n
1 1 in1
0.8 n
i 1
( X i X )2
( X i X )2
n
i 0.8 n 1
( X i X )2
.Also, Yi Y 1 ( X i X ) ui u .
( X%
i X )( X i X )
n
i 1
( X i X )2
n
i 1
( X%i X )(ui u )
n
i 1
( X i X )2
1 0.8 n
1 n
1 n %
( X i X )2
( X%
i 1 ( X i X )(ui u )
i X )( X i X )
i 1
i 0.8 n 1
n
n
n
1
1
1 n
1 n
1 n
2
2
(
X
X
)
(
X
X
)
( X i X )2
i
i
i 1
i 1
n
n
n i 1
wheren300,andthelastequalityusesanorderingoftheobservationssothatthefirst
240observations(0.8n)correspondtothecorrectlymeasuredobservations( X i Xi).
Asisdoneelsewhereinthebook,weinterpretn300asalargesample,soweusethe
approximationofntendingtoinfinity.Thesolutionprovidedherethusshowsthatthese
expressionsareapproximatelytruefornlargeandholdinthelimitthatntendstoinfinity.
Eachoftheaveragesintheexpressionfor 1 havethefollowingprobabilitylimits:
p
1 n
2
(
X
X
)
X2
i
i 1
n
,
p
1 0.8 n
2
(
X
X
)
0.8 X2
i
n i 1
,
p
1 n %
(
X
X
)(
u
u
)
i
i
n i 1
,and
p
1 n
% X )( X X ) 0
(
X
i
i
n i 0.8n 1
,
wherethelastresultfollowsbecause X i XiforthescrambledobservationsandXjis
p
(c) Yes,theestimatorbasedonthefirst240observationsisbetterthantheadjustedestimator
frompart(b).Equation(4.21)inKeyConcept4.4(page129)impliesthattheestimatorbased
onthefirst240observationshasavariancethatis
1 var ( X i X )ui
var( 1 (240obs ))
2
240
var( X i )
Frompart(a),theOLSestimatorbasedonalloftheobservationshastwosourcesofsampling
300
( X% X )(u u )
i
i 1
error.Thefirstis
300
i 1
( X i X )2
whichistheusualsourcethatcomesfromthe
( X% X )( X X )
300
i 241
i 1 ( X i X )2 ,whichisthesourcethatcomes
omittedfactors(u).Thesecondis
fromscramblingthedata.Thesetwotermsareuncorrelatedinlargesamples,andtheir
respectivelargesamplevariancesare:
var
300
( X%
1 var ( X i X )ui
i X )(ui u )
300
2
2
i 1 ( X i X ) 300 var( X i )
300
i 1
and
var 1
( X%i X )( X i X )
12 0.2
300
2
300
i 1 ( X i X )
300
i 241
Thus
1 (300obs)
1 1 var ( X i X )ui
2 0.2
1
2
0.8
0.64 300
300
var( X i )
var
whichislargerthanthevarianceoftheestimatorthatonlyusesthefirst240observations.
Thus
1 (300obs)
1 1 var ( X i X )ui
2 0.2
1
2
0.8
0.64 300
300
var( X i )
var
whichislargerthanthevarianceoftheestimatorthatonlyusesthefirst240observations.
Chapter10
RegressionwithPanelData
10.1.
(b)
(c)
(d)
(e)
(a) Witha$1increaseinthebeertax,theexpectednumberoflivesthatwouldbesavedis
0.45per10,000people.SinceNewJerseyhasapopulationof8.1million,theexpected
numberoflivessavedis0.45810364.5.The95%confidenceintervalis(0.451.96
0.22)810[15.228,713.77].
WhenNewJerseylowersitsdrinkingagefrom21to18,theexpectedfatalityrateincreasesby
0.028deathsper10,000.The95%confidenceintervalforthechangeindeathrateis0.028
1.960.066[0.1014,0.1574].Withapopulationof8.1million,thenumberoffatalities
willincreaseby0.02881022.68witha95%confidenceinterval[0.1014,0.1574]810
[82.134,127.49].
WhenrealincomepercapitainNewJerseyincreasesby1%,theexpectedfatalityrate
increasesby1.81deathsper10,000.The90%confidenceintervalforthechangeindeathrate
is1.811.640.47[1.04,2.58].Withapopulationof8.1million,thenumberoffatalities
willincreaseby1.818101466.1witha90%confidenceinterval[1.04,2.58]810
[840,2092].
Thelowpvalue(orhighFstatistic)associatedwiththeFtestontheassumptionthattime
effectsarezerosuggeststhatthetimeeffectsshouldbeincludedintheregression.
Defineabinaryvariablewestwhichequals1forthewesternstatesand0fortheotherstates.
Includetheinteractiontermbetweenthebinaryvariablewestandtheunemploymentrate,
west(unemploymentrate),intheregressionequationcorrespondingtocolumn(4).Suppose
thecoefficientassociatedwithunemploymentrateisandthecoefficientassociatedwith
west(unemploymentrate)is.Thencapturestheeffectoftheunemploymentrateinthe
easternstates,andcapturestheeffectoftheunemploymentrateinthewesternstates.
Thedifferenceintheeffectoftheunemploymentrateinthewesternandeasternstatesis .
10.3.
Thefivepotentialthreatstotheinternalvalidityofaregressionstudyare:omittedvariables,
misspecificationofthefunctionalform,imprecisemeasurementoftheindependentvariables,
sampleselection,andsimultaneouscausality.Youshouldthinkaboutthesethreatsonebyone.
Arethereimportantomittedvariablesthataffecttrafficfatalitiesandthatmaybecorrelatedwith
theothervariablesincludedintheregression?Themostobviouscandidatesarethesafetyofroads,
weather,andsoforth.Thesevariablesareessentiallyconstantoverthesampleperiod,sotheir
effectiscapturedbythestatefixedeffects.Youmaythinkofsomethingthatwemissed.Since
mostofthevariablesarebinaryvariables,thelargestfunctionalformchoiceinvolvestheBeerTax
variable.Alinearspecificationisusedinthetext,whichseemsgenerallyconsistentwiththedata
inFigure8.2.Tocheckthereliabilityofthelinearspecification,itwouldbeusefultoconsidera
logspecificationoraquadratic.Measurementerrordoesnotappeartoaproblem,asvariableslike
trafficfatalitiesandtaxesareaccuratelymeasured.Similarly,sampleselectionisanotaproblem
becausedatawereusedfromallofthestates.Simultaneouscausalitycouldbeapotentialproblem.
Thatis,stateswithhighfatalityratesmightdecidetoincreasetaxestoreduceconsumption.Expert
knowledgeisrequiredtodetermineifthisisaproblem.
10.5.
LetD2i1ifi2and0otherwise;D3i1ifi3and0otherwiseDni1ifinand0
otherwise.LetB2t1ift2and0otherwise;B3t1ift3and0otherwiseBTt1iftT
and0otherwise.Let011;i i 1andt t 1.
10.7.
(a) Averagesnowfalldoesnotvaryovertime,andthuswillbeperfectlycollinearwiththe
statefixedeffect.
(b) Snowitdoesvarywithtime,andsothismethodcanbeusedalongwithstatefixedeffects.
u2
.
1 T Y
(a) i T t 1 it whichhasvariance T BecauseTisnotgrowing,thevarianceisnot
gettingsmall. i isnotconsistent.
10.9.
(b) Theaveragein(a)iscomputedoverTobservations.InthiscaseTissmall(T4),sothe
normalapproximationfromtheCLTisnotlikelytobeverygood.
10.11 Usingthehint,equation(10.22)canbewrittenas
1DM
n
i 1
1
1
X i 2 X i1 Yi 2 Yi1 X i 2 X i1 Yi 2 Yi1
4
4
n 1
1
2
2
i 1 4 X i 2 X i1 4 X i 2 X i1
X X Y Y
X X
n
i2
i 1
i1
i2
i 1
i1
i2
BA
1
i1
RegressionwithaBinary
DependentVariable
Chapter11
11.1.
(a) ThetstatisticforthecoefficientonExperienceis0.031/0.0093.44,whichissignificant
atthe1%level.
(b) zMatthew 0.712 0.031 10 1.022; (1.022) 0.847
z
0.712 0.031 0 0.712; (0.712) 0.762
(c) Christopher
(d) z Jed 0.712 0.031 80 3.192; (3.192) 0.999, thisisunlikelytobeaccuratebecausethe
sampledidnotincludeanyonewithmorethat40yearsofdrivingexperience.
11.3.
(a) ThetstatisticforthecoefficientonExperienceist0.006/0.0023,whichissignificant
athe1%level.
ProbMatther0.7740.006100.836
ProbChristopher0.7740.00600.774
(b)
Theprobabilitiesaresimilarexceptwhenexperienceinlarge(40years).Inthiscasethe
LPMmodelproducesnonsensicalresults(probabilitiesgreaterthan1.0).
11.5.
(a) (0.8060.041100.17410.015110)0.814
(b) (0.8060.04120.17400.01502)0.813
(c) Thetstatontheinteractiontermis0.015/0.0190.79,whichisnotsignificantatthe10%
level.
11.7.
(a) ForablackapplicanthavingaP/Iratioof0.35,theprobabilitythattheapplicationwillbe
1
F ( 4.13 5.37 0.35 1.27)
27.28%.
1 e0.9805
deniedis
(b) WiththeP/Iratioreducedto0.30,theprobabilityofbeingdeniedis
1
F (4.13 5.37 0.30 1.27)
22.29%
1 e1.249
.Thedifferenceindenialprobabilities
comparedto(a)is4.99percentagepointslower.
(c) ForawhiteapplicanthavingaP/Iratioof0.35,theprobabilitythattheapplicationwillbe
1
F (4.13 5.37 0.35)
9.53%.
1 e2.2505
deniedis
IftheP/Iratioisreducedto0.30,the
1
7.45%.
1 e2.519
Thedifferencein
probabilityofbeingdeniedis
denialprobabilitiesis2.08percentagepointslower.
(d) Fromtheresultsinparts(a)(c),wecanseethatthemarginaleffectoftheP/Iratioonthe
probabilityofmortgagedenialdependsonrace.Inthelogitregressionfunctionalform,
themarginaleffectdependsonthelevelofprobabilitywhichinturndependsontherace
oftheapplicant.Thecoefficientonblackisstatisticallysignificantatthe1%level.Thelogit
andprobitresultsaresimilar.
11.9.
(a) Thecoefficientonblackis0.084,indicatinganestimateddenialprobabilitythatis
8.4percentagepointshigherfortheblackapplicant.
(b) The95%confidenceintervalis0.0841.960.023[3.89%,12.91%].
(c) Theanswerin(a)willbebiasedifthereareomittedvariableswhichareracerelatedandhave
impactsonmortgagedenial.Suchvariableswouldhavetoberelatedwithraceandalsobe
relatedwiththeprobabilityofdefaultonthemortgage(whichinturnwouldleadtodenialof
themortgageapplication).Standardmeasuresofdefaultprobability(pastcredithistoryand
employmentvariables)areincludedintheregressionsshowninTable9.2,sotheseomitted
variablesareunlikelytobiastheanswerin(a).Othervariablessuchaseducation,marital
status,andoccupationmayalsoberelatedtheprobabilityofdefault,andthesevariablesare
omittedfromtheregressionincolumn.Addingthesevariables(seecolumns(4)(6))have
littleeffectontheestimatedeffectofblackontheprobabilityofmortgagedenial.
11.11.
(a) Thisisacensoredortruncatedregressionmodel(notethedependentvariablemightbe
zero).
(b) Thisisanorderedresponsemodel.
(c) Thisisthediscretechoice(ormultiplechoice)model.
(d) Thisisamodelwithcountdata.
Chapter12
InstrumentalVariablesRegression
12.1.
12.3.
cigarettes
ln( Pi ,cigarettes
) ln( Pi ,1985
),
1995
(a) Thechangeintheregressor,
froma$0.50perpackincreasein
theretailpriceisln(8.00)ln(7.50)0.0645.Theexpectedpercentagechangeincigarette
demandis0.940.0645100%.07%.The95%confidenceintervalis(0.941.96
0.21)0.0645100%[8.72%,3.41%].
(b) Witha2%reductioninincome,theexpectedpercentagechangeincigarettedemandis
0.53(0.02)100%1.06%.
(c) Theregressionincolumn(1)willnotprovideareliableanswertothequestionin(b)when
recessionslastlessthan1year.Theregressionincolumn(1)studiesthelongrunpriceand
incomeelasticity.Cigarettesareaddictive.Theresponseofdemandtoanincomedecrease
willbesmallerintheshortrunthaninthelongrun.
(d) Theinstrumentalvariablewouldbetooweak(irrelevant)iftheFstatisticincolumn(1)was
3.6insteadof33.6,andwecannotrelyonthestandardmethodsforstatisticalinference.Thus
theregressionwouldnotprovideareliableanswertothequestionposedin(a).
2 1 n (Y 0TSLS 1TSLS X i )2
2
(a) Theestimator a n 2 i 1 i
isnotconsistent.Writethisas a
1
TSLS TSLS
TSLS
in1 (ui 1TSLS ( X i X i )) 2 ,
n2
where ui Yi 0 1 X i . Replacing 1 with1,
2 1 n (u 1 ( X i X i )) 2 1n in1 ui2
assuggestedinthequestion,writethisas a n i 1 i
1
in1[ 12 ( X i X i )2 2ui 1 ( X i X i )].
n
Thefirsttermontherighthandsideoftheequation
convergesto u , butthesecondtermconvergestosomethingthatisnonzero.Thus a is
notconsistent.
(b) Theestimator
b2
(a),wecanwrite
12.5.
1
n 2
u ,
2
b
1
n
n
2
i 1 i
isconsistent.Usingthesamenotationasin
andthisestimatorconvergesinprobabilityto u .
(a) Underthenullhypothesisofinstrumentexogeneity,theJstatisticisdistributedasa 1
randomvariable,witha1%criticalvalueof6.63.Thusthestatisticissignificant,andinstrument
exogeneityE(ui|Z1i,Z2i)0isrejected.
2
12.9.
(a) Thereareotherfactorsthatcouldaffectboththechoicetoserveinthemilitaryandannual
earnings.Oneexamplecouldbeeducation,althoughthiscouldbeincludedintheregression
asacontrolvariable.Anothervariableisabilitywhichisdifficulttomeasure,andthus
difficulttocontrolforintheregression.
(b) Thedraftwasdeterminedbyanationallotterysothechoiceofservinginthemilitarywas
random.Becauseitwasrandomlyselected,thelotterynumberisuncorrelatedwithindividual
characteristicsthatmayaffectearningandhencetheinstrumentisexogenous.Becauseit
affectedtheprobabilityofservinginthemilitary,thelotterynumberisrelevant.
Chapter13
ExperimentsandQuasiExperiments
13.1.
Forstudentsinkindergarten,theestimatedsmallclasstreatmenteffectrelativetobeingina
regularclassisanincreaseof13.90pointsonthetestwithastandarderror2.45.The95%
confidenceintervalis13.901.962.45[9.098,18.702].
Forstudentsingrade1,theestimatedsmallclasstreatmenteffectrelativetobeinginaregular
classisanincreaseof29.78pointsonthetestwithastandarderror2.83.The95%confidence
intervalis29.781.962.83[24.233,35.327].
Forstudentsingrade2,theestimatedsmallclasstreatmenteffectrelativetobeinginaregular
classisanincreaseof19.39pointsonthetestwithastandarderror2.71.The95%confidence
intervalis19.391.962.71[14.078,24.702].
Forstudentsingrade3,theestimatedsmallclasstreatmenteffectrelativetobeinginaregular
classisanincreaseof15.59pointsonthetestwithastandarderror2.40.The95%confidence
intervalis15.591.962.40[10.886,20.294].
13.3.
X
X Control
(a) Theestimatedaveragetreatmenteffectis TreatmentGroup
1241120140
points.
(b) Therewouldbenonrandomassignmentifmen(orwomen)haddifferentprobabilitiesofbeing
assignedtothetreatmentandcontrolgroups.LetpMendenotetheprobabilitythatamaleis
assignedtothetreatmentgroup.RandomassignmentmeanspMen0.5.Testingthisnull
p Men 0.5
0.55 0.50
tMen
1.00,
1
1
p Men (1 p Men )
0.55(1 0.55)
n Men
100
hypothesisresultsinatstatisticof
sothatthenullofrandomassignmentcannotberejectedatthe10%level.Asimilarresultis
foundforwomen.
13.5.
(a) Thisisanexampleofattrition,whichposesathreattointernalvalidity.Afterthemale
athletesleavetheexperiment,theremainingsubjectsarerepresentativeofapopulationthat
excludesmaleathletes.Iftheaveragecausaleffectforthispopulationisthesameasthe
averagecausaleffectforthepopulationthatincludesthemaleathletes,thentheattritiondoes
notaffecttheinternalvalidityoftheexperiment.Ontheotherhand,iftheaveragecausal
effectformaleathletesdiffersfromtherestofpopulation,internalvalidityhasbeen
compromised.
(b) Thisisanexampleofpartialcompliancewhichisathreattointernalvalidity.Thelocalarea
networkisafailuretofollowtreatmentprotocol,andthisleadstobiasintheOLSestimatorof
theaveragecausaleffect.
(c) Thisposesnothreattointernalvalidity.Asstated,thestudyisfocusedontheeffectofdorm
roomInternetconnections.Thetreatmentismakingtheconnectionsavailableintheroom;the
treatmentisnottheuseoftheInternet.Thus,theartmajorsreceivedthetreatment(although
theychosenottousetheInternet).
(d) Asinpart(b)thisisanexampleofpartialcompliance.Failuretofollowtreatmentprotocol
leadstobiasintheOLSestimator.
13.7.
Fromthepopulationregression
Yit i 1 X it 2 ( Dt Wi ) 0 Dt vit ,
wehave
BydefiningYiYi2Yi1,XiXi2Xi1(abinarytreatmentvariable)anduivi2vi1,andusing
D10andD21,wecanrewritethisequationas
Yi 0 1 X i 2Wi ui ,
whichisEquation(13.5)inthecaseofasingleWregressor.
13.9.
Thecovariancebetween 1i X i andXiis
BecauseXiisrandomlyassigned,Xiisdistributedindependentlyof1i.Theindependencemeans
E ( 1i X i ) E ( 1i ) E ( X i ) and E ( 1i X i2 ) E ( 1i ) E ( X i2 ).
So
cov( 1i X i , X i ) E ( 1i ) X2
E ( 1i ).
X2
X2
13.11. FollowingthenotationusedinChapter13,let1idenotethecoefficientonstatesalestaxinthe
firststageIVregression,andlet1idenotecigarettedemandelasticity.(Inbothcases,suppose
thatincomehasbeencontrolledforintheanalysis.)From(13.11)
p
E ( 1i 1i )
cov( 1i , 1i )
cov( 1i , 1i )
TSLS
E ( 1i )
Average Treatment Effect
,
E ( 1i )
E ( 1i )
E ( 1i )
wherethefirstequalityusestheusespropertiesofcovariances(equation(2.34)),andthesecond
equalityusesthedefinitionoftheaveragetreatmenteffect.Evidently,thelocalaveragetreatment
effectwilldeviatefromtheaveragetreatmenteffectwhen cov( 1i , 1i ) 0.Asdiscussedin
Section13.6,thiscovarianceiszerowhen1ior1iareconstant.Thisseemslikely.But,forthe
sakeofargument,supposethattheyarenotconstant;thatis,supposethedemandelasticitydiffers
fromstatetostate(1iisnotconstant)asdoestheeffectofsalestaxesoncigaretteprices( 1iisnot
constant).Are1iand1irelated?Microeconomicssuggeststhattheymightbe.Recallfromyour
microeconomicsclassthattheloweristhedemandelasticity,thelargerfractionofasalestaxis
passedalongtoconsumersintermsofhigherprices.Thissuggeststhat 1iand1iarepositively
related,sothat cov( 1i , 1i ) 0. BecauseE( )0,thissuggeststhatthelocalaveragetreatment
1i
effectisgreaterthantheaveragetreatmenteffectwhen 1ivariesfromstatetostate.
Chapter14
IntroductiontoTimeSeriesRegression
andForecasting
14.1.
(a) SincetheprobabilitydistributionofYtisthesameastheprobabilitydistributionofYt1
(thisisthedefinitionofstationarity),themeans(andallothermoments)arethesame.
(b) E(Yt)01E(Yt1)E(ut),butE(ut)0andE(Yt)E(Yt1).ThusE(Yt)01E(Yt),and
solvingforE(Yt)yieldstheresult.
14.3.
(a) Totestforastochastictrend(unitroot)inln(IP),theADFstatisticisthetstatistictesting
thehypothesisthatthecoefficientonln(IPt1)iszeroversusthealternativehypothesisthatthe
0.018
t
2.5714.
0.007
coefficientonln(IPt1)islessthanzero.Thecalculatedtstatisticis
FromTable14.4,the10%criticalvaluewithatimetrendis3.12.Because2.57143.12,
thetestdoesnotrejectthenullhypothesisthatln(IP)hasaunitautoregressiverootatthe10%
significancelevel.Thatis,thetestdoesnotrejectthenullhypothesisthatln(IP)containsa
stochastictrend,againstthealternativethatitisstationary.
(b) TheADFtestsupportsthespecificationusedinExercise14.2.Theuseoffirstdifferencesin
Exercise14.2eliminatesrandomwalktrendinln(IP).
E[(W c )2 ] E{[W W ) ( W c )]2 }
E[(W W ) 2 ] 2 E (W W )( W c) ( W c) 2
14.5.
W ( W c) .
(a)
(b) Usingtheresultinpart(a),theconditionalmeansquarederror
2
withtheconditionalvariance
t2|t 1 E[(Yt Yt |t 1 )2 ].
Thisequationisminimizedwhenthe
f Y .
secondtermequalszero,orwhen t 1 t |t 1 (Analternativeistousethehint,andnoticethat
theresultfollowsimmediatelyfromexercise2.27.)
(c) ApplyingEquation(2.27),weknowtheerrorutisuncorrelatedwithut1ifE(ut |ut1)0.
FromEquation(14.14)fortheAR(p)process,wehave
ut 1 Yt 1 0 1Yt 2 2Yt 3 L pYt p 1 f (Yt 1 , Yt 2 ,..., Yt p 1 ),
Thusutandut1areuncorrelated.Asimilarargumentshowsthatutandutjareuncorrelated
forallj1.Thusutisseriallyuncorrelated.
14.7.
(a) FromExercise(14.1)E(Yt)2.50.7E(Yt1)E(ut),butE(Yt)E(Yt1)(stationarity)and
E(ut)0,sothatE(Yt)2.5/(10.7).Also,becauseYt2.50.7Yt1ut,var(Yt)
0.72var(Yt1)var(ut)20.7cov(Yt1,ut).Butcov(Yt1,ut)0andvar(Yt)var(Yt1)
(stationarity),sothatvar(Yt)9/(10.72)17.647.
(b) The1stautocovarianceis
The2ndautocovarianceis
cov(Yt , Yt 2 ) cov[(1 0.7)2.5 0.72 Yt 2 ut 0.7ut 1 , Yt 2 ]
0.72 var(Yt 2 ) cov(ut 0.7ut 1 , Yt 2 )
0.72 Y2
0.72 17.647 8.6471.
(c) The1stautocorrelationis
corr (Yt , Yt 1 )
cov(Yt , Yt 1 )
var(Yt ) var(Yt 1 )
0.7 Y2
0.7.
Y2
The2ndautocorrelationis
corr (Yt , Yt 2 )
cov(Yt , Yt 2 )
var(Yt ) var(Yt 2 )
0.7 2 Y2
0.49.
Y2
YT 1/T
2.50.7YT2.50.7102.374.11.
(a) E(Yt)0E(et)b1E(et1)bqE(etq)0[becauseE(et)0forallvaluesoft].
14.9.
e2 (1 b12 L bq2 )
wherethefinalequalityfollowsfromvar(et) e foralltandcov(et,ei)0forit.
2
(c) Yt0etb1et1b2et2bqetqandYtj0etjb1et1jb2et2j
q q b b cov(et k , et j m ),
bqetqjandcov(Yt,Ytj) k 0 m 0 k m
whereb01.Noticethat
cov(etk,etjm)0foralltermsinthesum.
(d)
and
forj1.
14.11. WritethemodelasYtYt101(Yt1Yt2)ut.Rearrangingyields
Yt0(11)Yt11Yt2ut.
Chapter15
EstimationofDynamicCausalEffects
15.1.
(a) Seethetablebelow.iisthedynamicmultiplier.Withthe25%oilpricejump,the
predictedeffectonoutputgrowthfortheithquarteris25ipercentagepoints.
Periodahead
(i)
Dynamic
multiplier
( i)
Predictedeffecton
outputgrowth(25 i)
95%confidence
interval25[ i1.96SE
( i)]
0.055
1.375
[4.021,1.271]
0.026
0.031
0.65
0.775
[3.443,2.143]
[3.127,1.577]
0.109
0.128
0.008
2.725
3.2
0.2
[4.783,0.667]
[5.797,0.603]
0.025
0.625
[1.025,1.425]
[1.727,2.977]
0.019
0.067
0.475
1.675
[2.386,1.436]
[0.015,0.149]
2
3
4
5
6
7
8
(b) The95%confidenceintervalforthepredictedeffectonoutputgrowthfortheithquarterfrom
the25%oilpricejumpis25[i1.96SE(i)]percentagepoints.Theconfidenceintervalis
reportedinthetablein(a).
(c) ThepredictedcumulativechangeinGDPgrowthovereightquartersis
25(0.0550.0260.0310.1090.1280.0080.0250.019)8.375%.
(d) The1%criticalvaluefortheFtestis2.407.SincetheHACFstatistic3.49islargerthanthe
criticalvalue,werejectthenullhypothesisthatallthecoefficientsarezeroatthe1%level.
15.3.
ThedynamiccausaleffectsareforexperimentA.Theregressioninexercise15.1doesnotcontrol
forinterestrates,sothatinterestratesareassumedtoevolveintheirnormalpatterngivenchanges
inoilprices.
15.5.
Substituting
X t X t X t 1
X t X t 1 X t 2
L L
X t X t 1 L X t p 1 X t p
intoEquation(15.4),wehave
Yt 0 1 X t 2 X t 1 3 X t 2 L r 1 X t r ut
0 1 ( X t X t 1 L X t r 1 X t r )
2 ( X t 1 L X t r 1 X t r )
L r ( X t r 1 X t r ) r 1 X t r ut
0 1 X t ( 1 2 ) X t 1 ( 1 2 3 ) X t 2
L ( 1 2 L r ) X t r 1
( 1 2 L r r 1 ) X t r ut .
ComparingtheaboveequationtoEquation(15.7),wesee 00,11,212,
3123,,andr112rr1.
15.7.
i
%
Write ut i 0 1 ut i
15.9.
(a) Thisfollowsfromthematerialaroundequation(3.2).
t , andtheGLSestimatorof
(b) QuasidifferencingtheequationyieldsYt1Yt1(11)0 u%
1
T (Y Y )
(11)0isthemeanofYt1Yt1 T 1 t 2 t 1 t 1 .Dividingby(11)yieldstheGLS
estimatorof0.
(c) Thisisarearrangementoftheresultin(b).
1 T Y 1 (Y Y1 ) TT1 T11 Tt 21 Yt ,
0GLS T1 (YT Y1 ) T1 T11 Tt 21 Yt
(d) Write 0 T t 1 t T T
sothat 0
1
.
1
1
2
1 T 1 (YT Y1 )
andthevarianceisseentobeproportionalto T
Chapter16
AdditionalTopicsinTime
SeriesRegression
16.1.
Y E (Yt )
0
,
1 1
(a) Thehperiodaheadforecastof
is
1 1 L 1h 1 0 1hYt
1 1h
0 1hYt
1 1
Y 1h (Yt Y ).
(b) Substitutingtheresultfrompart(a)intoXtgives
X t iYt i |t i [ Y 1i (Yt Y )]
i 0
i 0
i 0
i 0
Y i (Yt Y ) ( 1 )i
16.3.
Y Y
Y
t
.
1 1 1
2
2
utfollowstheARCHprocesswithmeanE(ut)0andvariance t 1.0 0.5ut 1.
2
2
(b) When ut 1 0.2, t 1.0 0.5 0.2 1.02. Thestandarddeviationofutist1.01.Thus
3 ut
3
1.01 t 1.01
(2.9703) (2.9703) 0.9985 0.0015 0.9970.
Pr ( 3 ut 3) Pr
2
2
Whenut12.0, t 1.0 0.5 2.0 3.0. Thestandarddeviationofutist1.732.Thus
u
3
3
t
1.732 t 1.732
(1.732) (1.732) 0.9584 0.0416 0.9168.
Pr ( 3 ut 3) Pr
16.5.
Because Yt Yt Yt 1 Yt 1 Yt 1 Yt ,
T
t 1
t 1
t 1
t 1
t 1
Notethat
Y
t 1
T
T
Yt 21 (Yt ) 2 .
t 1
t 1
Tt 1 Yt 2 Tt 1 Yt 21 Tt 11 Yt 2 YT2 Y02 Tt 11 Yt 2 Y 2 Y 2 Y 2
T
0
T becauseY 0.Thus:
0
1 T
1 1 2 T
YT (Yt )2
t 1
t
T t 1
T 2
t 1
1 YT
1 T
(Yt ) 2 .
2 T
T t 1
Y Xt
t 1 t
16.7.
T
t 1
X t2
Y Y
Y
T
t 1 t
T
t 1
t 1
t 1
1 T
t 1Yt Yt 1
T
.
1 T
2
Y
t 1
T t 1
Followingthehint,thenumeratoristhesame
expressionas(16.21)(shiftedforwardintime1period),sothat
1
denominatoris T
directly.
16.9.
Tt 1 (Yt 1 ) 2 T1 Tt 1 ut21 u2
1
T
d
Tt 1 Yt Yt 1
u2
2
( 12 1).
The
(a) Fromthelawofiteratedexpectations
bythelawoflargenumbers.Theresultfollows
E (ut2 ) E t2
E 0 1ut21
0 1 E ut21
0 1 E ut2
2
wherethelastlineusesstationarityofu.Solvingfor E (ut ) givestherequiredresult.
(b) Asin(a)
E (ut2 ) E t2
sothat
E (ut2 )
0
1 tp1 i .
2
(c) Thisfollowsfrom(b)andtherestrictionthat E (ut ) >0.
(d) Asin(a)
E (ut2 ) E t2
0 1 E ut21 1 E t21
0 (1 1 ) E ut21
0 (1 1 ) E ut2
0
1 1 1
(e) Thisfollowsfrom(d)andtherestrictionthat
E ut2 0.
Chapter17
TheTheoryofLinearRegression
withOneRegressor
17.1.
(a) Supposetherearenobservations.Letb1beanarbitraryestimatorof1.Giventhe
estimatorb1,thesumofsquarederrorsforthegivenregressionmodelis
n
(Y b X ) .
i 1
2(Y b X )( X ) 0.
i 1
Solvingforb1fromthefirstorderconditionleadstotherestrictedleastsquaresestimator
XY
1RLS i n1 i 2 i .
i 1 X i
n
1RLS isunbiased.Wecanrepresenttherestrictedleastsquaresestimator
(b) Weshowfirstthat
1RLS intermsoftheregressorsanderrors:
n X Y n X ( X ui )
n X u
1RLS i n1 i 2 i i 1 i n 1 2i
1 i n1 i 2 i .
i 1 X i
i 1 X i
i 1 X i
Thus
in1 X i ui
in1 X i E (ui | X 1,K , X n )
1
n
2
in1 X i2
i 1 X i
E ( 1RLS ) 1 E
1 ,
wherethesecondequalityfollowsbyusingthelawofiteratedexpectations,andthethird
equalityfollowsfrom
in1 X i E (ui | X 1 ,K , X n )
0
in1 X i2
RLS
Underassumptions13ofKeyConcept17.1, 1 isasymptoticallynormallydistributed.
RLS
Thelargesamplenormalapproximationtothelimitingdistributionof 1 followsfrom
considering
1
n X u
n X u
1RLS 1 i n1 i 2 i n1 i n1 i 2 i .
i 1 X i
n i 1 X i
ConsiderfirstthenumeratorwhichisthesampleaverageofviXiui.Byassumption1ofKey
Concept17.1,v hasmeanzero: E ( X i ui ) E[ X i E (ui | X i )] 0. Byassumption2,v isi.i.d.By
i
assumption3,var(vi)isfinite.Let
theorem,thesampleaverage
v / v
v
1
n
X i ui , then /n.
n
i 1
2
v
v
n
i 1
2
v
Usingthecentrallimit
N (0, 1)
or
1 n
d
X i ui
N (0, v2 ).
n i 1
2
Forthedenominator, X i isi.i.d.withfinitesecondvariance(becauseXhasafinitefourth
moment),sothatbythelawoflargenumbers
1 n 2 p
X i E ( X 2 ).
n i 1
CombiningtheresultsonthenumeratorandthedenominatorandapplyingSlutskystheorem
leadto
n ( 1RLS u )
1
n
1
n
in1 X i ui
n
i 1
2
i
var( X i ui )
d
N 0,
.
E( X 2 )
RLS
(c) 1 isalinearestimator:
n X Y
n
1RLS i n1 i 2 i i 1 aiYi ,
i 1 X i
where ai
Xi
.
in1 X i2
Theweightai(i1,,n)dependsonX1,,XnbutnotonY1,,Yn.
Thus
Xu
1RLS 1 i n1 i 2 i .
i 1 X i
n
1RLS isconditionallyunbiasedbecause
n X u
E ( 1RLS | X 1 ,K , X n E 1 i n1 i 2 i | X 1 ,K , X n
i 1 X i
n
Xu
1 E i n1 i 2 i |X 1 ,K , X n 1 .
i 1 X i
Thefinalequalityusedthefactthat
in1 X i ui
in1 X i E (ui | X 1 ,K , X n )
|
X
,
K
,
X
0
1
n
n
2
in1 X i2
i 1 X i
becausetheobservationsarei.i.d.andE(ui |Xi)0.
RLS
(d) Theconditionalvarianceof 1 , givenX1,,Xn,is
n X u
var( 1RLS | X1,K , X n ) var 1 i n1 i 2 i | X1 ,K , X n
i 1 Xi
n
2
X var(u | X ,K , X n )
i 1 i n i 2 12
( i 1 Xi )
in1 X i2 u2
( in1 Xi2 )2
2
u
n
2
i 1
i
(e) TheconditionalvarianceoftheOLSestimator 1 is
var( 1 |X1 ,K , X n )
u2
.
in1 ( X i X )2
Since
n
i 1
i 1
i 1
i 1
i 1
( X i X )2 X i2 2 X X i nX 2 X i2 nX 2 X i2 ,
RLS
theOLSestimatorhasalargerconditionalvariance: var( 1 |X 1 ,K , X n ) var( 1 |X 1 ,K , X n ).
RLS
Therestrictedleastsquaresestimator 1 ismoreefficient.
RLS
(f) Underassumption5ofKeyConcept17.1,conditionalonX1,,Xn, 1 isnormally
distributedsinceitisaweightedaverageofnormallydistributedvariablesui:
Xu
1RLS 1 i n1 i 2 i .
i 1 X i
n
RLS
Usingtheconditionalmeanandconditionalvarianceof 1 derivedinparts(c)and(d)
RLS
respectively,thesamplingdistributionof 1 ,conditionalonX ,,X ,is
1
1RLS ~ N 1 , n u 2 .
i 1 X i
(g) Theestimator
in1 Yi
in1 ( 1 X i ui )
in1 ui
%
1
1
in1 X i
in1 X i
in1 X i
Theconditionalvarianceis
in1 ui
var( %
|
X
,
K
,
X
)
var
| X 1 ,K , X n
1
1
n
1
n
i 1 X i
n
var(ui | X 1 ,K , X n )
i 1
( in1 X i ) 2
n u2
.
( in1 X i ) 2
%
RLS
Thedifferenceintheconditionalvarianceof 1 and 1 is
RLS | X ,K , X )
var( %
1 | X 1 ,K , X n ) var( 1
1
n
n u2
2
n u 2.
2
( X i )
i 1 X i
n
i 1
%
RLS
Inordertoprove var( 1| X 1 ,K , X n ) var( 1 | X 1 ,K , X n ), weneedtoshow
n
1
n
2
( X i )
i 1 X i2
n
i 1
orequivalently
i 1
X i .
i 1
n X i2
ThisinequalitycomesdirectlybyapplyingtheCauchySchwartzinequality
( ai bi )
i 1
i 1
i 1
i 1
i 1
i 1
ai2 bi2
whichimplies
X i 1 Xi
i 1 i 1
n
12 X i2 n X i2 .
n
2
n
2
%
RLS
Thatis ni 1 X i ( x 1 X i ) , or var( 1| X 1 ,K , X n ) var( 1 | X 1 ,K , X n ).
%
Note:because 1 islinearandconditionallyunbiased,theresult
RLS | X ,K , X )
var( %
1 | X 1 ,K , X n ) var( 1
1
n followsdirectlyfromtheGaussMarkovtheorem.
17.3.
(a) UsingEquation(17.19),wehave
1
n ( X X )ui
n ( 1 1 ) n n1 in1 i
i 1 ( X i X )2
n
1
n
in1[( Xi X ) ( X X )]ui
n
2
1
n i 1 ( X i X )
1
n
in1 ( X i X )ui
1
n
in1 ( X i X )2
1
n
1
n
in1 vi
in1 ( X i X )2
(X X )
1
n
in1 ui
in1 ( X i X )2
( X X )
1
n
1
n
1
n
in1 ui
in1 ( X i X )2
bydefiningvi(XiX)ui.
2
(b) Therandomvariablesu1,,unarei.i.d.withmeanu0andvariance 0 u . Bythe
centrallimittheorem,
n (u u )
1
n
in1 ui
N (0, 1).
X X 2 , or X X 0.
Thelawoflargenumbersimplies
Bytheconsistencyofsample
2
1 n
(
X
X
)
variance, n i 1 i
convergesinprobabilitytopopulationvariance,var(Xi),whichis
finiteandnonzero.TheresultthenfollowsfromSlutskystheorem.
p
(c) Therandomvariablevi(XiX)uihasfinitevariance:
var(vi ) var[( X i X ) i ]
E[( X i X ) 2 ui2 ]
E[( X i X ) 4 ]E[(ui ) 4 ] .
TheinequalityfollowsbyapplyingtheCauchySchwartzinequality,andthesecondinequality
followsbecauseofthefinitefourthmomentsfor(Xi,ui).Thefinitevariancealongwiththefact
thatvihasmeanzero(byassumption1ofKeyConcept15.1)andviisi.i.d.(byassumption2)
impliesthatthesampleaverage v satisfiestherequirementsofthecentrallimittheorem.Thus,
1
n
in1 vi
satisfiesthecentrallimittheorem.
(d) Applyingthecentrallimittheorem,wehave
1
n
in1 vi
N (0, 1).
Becausethesamplevarianceisaconsistentestimatorofthepopulationvariance,wehave
1
n
in1 ( X i X ) 2 p
1.
var( X i )
UsingSlutskystheorem,
in1 vt
v
d
N (0,1),
n
2
1
(
X
X
)
i 1
t
n
X2
1
n
orequivalently
1
n
in1 vi
var(vi )
d
N 0,
.
(Xi X )
[var( X i )]2
1
n
n
i 1
Thus
n ( 1 1 )
1
n
1
n
in1 vi
in1 ( X i X )2
( X X )
1
n
1
n
in1 ui
in1 ( X i X )2
var(vi )
d
N 0,
[var( X i )]2
sincethesecondtermfor n ( 1 1 ) convergesinprobabilitytozeroasshowninpart(b).
17.5.
17.7.
(a) Thejointprobabilitydistributionfunctionofui,uj,Xi,Xjisf(ui,uj,Xi,Xj).Theconditional
probabilitydistributionfunctionofuiandXigivenujandXjisf(ui,Xi |uj,Xj).Sinceui,Xi,i
1,,narei.i.d.,f(ui,Xi |uj,Xj)f(ui,Xi).Bydefinitionoftheconditionalprobability
distributionfunction,wehave
f (ui , u j , X i , X j ) f (ui , X i | u j , X j ) f (u j , X j )
f (ui , X i ) f (u j , X j ).
(b) TheconditionalprobabilitydistributionfunctionofuiandujgivenXiandXjequals
f (ui , u j | X i , X j )
f (ui , u j , X i , X j )
f (Xi , X j )
f (ui , X i ) f (u j , X j )
f (Xi ) f (X j )
f (ui | X i ) f (u j | X j ).
Thefirstandthirdequalitiesusedthedefinitionoftheconditionalprobabilitydistribution
function.Thesecondequalityusedtheconclusionthefrompart(a)andtheindependence
betweenXiandXj.Substituting
f (ui , u j | Xi , X j ) f (ui | X i ) f (u j | X j )
intothedefinitionoftheconditionalexpectation,wehave
f (ui , X i , Q)
f ( X i , Q)
f (ui | X i , Q)
f (ui , X i ) f (Q )
f ( X i ) f (Q)
f (ui , X i )
f (Xi )
f (ui | X i )
wherethefirstequalityusesthedefinitionoftheconditionaldensity,thesecondusesthefact
that(ui,Xi)andQareindependent,andthefinalequalityusesthedefinitionoftheconditional
density.Theresultthenfollowsdirectly.
(d) Anargumentlikethatusedin(c)implies
f (ui u j | X i , K X n ) f (ui u j | X i , X j )
andtheresultthenfollowsfrompart(b).
17.9.
Weneedtoprove
1 n
p
[( X i X )2 ui2 ( X i X )2 ui2 ] 0.
n i 1
Usingtheidentity X X ( X X ),
1 n
1 n
1 n
[( X i X ) 2 ui2 ( X i X ) 2 ui2 ] ( X X ) 2 ui2 2( X X ) ( X i X )ui2
n i 1
n i 1
n i 1
n
1
( X i X ) 2 (ui2 ui2 ).
n i 1
Thedefinitionof ui implies
Substitutingthisintotheexpressionfor n
yieldsaseriesofterms
b X u
eachofwhichcanbewrittenasanbnwhere an 0 and n
whererandsare
integers.Forexample, an ( X X ), an ( 1 1 ) andsoforth.Theresultthenfollowsfrom
1
Slutksystheoremif n
in1 X ir uis d
1
n
n
i 1
r s
i i
r s
wheredisafiniteconstant.Let wi X i ui andnotethatwi
isi.i.d.Thelawoflargenumberscanthenbeusedforthedesiredresultif E ( wi ) . Thereare
twocasesthatneedtobeaddressed.Inthefirst,bothrandsarenonzero.Inthiscasewrite
2
1
2
(1 XY
)
2
Y
x
x X
1
X
exp
2 XY
2
2(1 XY ) X
X
y Y
y Y
Y
Y
2
1 x X
.
2 X
Simplifyingyieldsthedesiredexpression.
(b) TheresultfollowsbynotingthatfY|X=x(y)isanormaldensity(seeequation(17.36))withT|
Y2|X
2
and
.
X
(c) LetbXY/ X andaYbX.
2
17.13
(a) Theanswerisprovidedbyequation(13.10)andthediscussionfollowingtheequation.
TheresultwasalsoshowninExercise13.10,andtheapproachusedintheexerciseis
discussedinpart(b).
(b) WritetheregressionmodelasYi01Xivi,where0E(0i),1E(1i),andviui
(0i0)(1i1)Xi.Noticethat
E(vi|Xi)E(ui|Xi)E(0i0|Xi)XiE(1i1|Xi)0
because0iand1iareindependentofXi.BecauseE(vi|Xi)=0,theOLSregressionofYionXi
willprovideconsistentestimatesof0E(0i)and1E(1i).Recallthattheweightedleast
squaresestimatoristheOLSestimatorofYi/ionto1/iandXi/i,where
Writethisregressionas
i 0 1 X i2
Yi / i 0 (1 / i ) 1 ( X i / i ) vi / i .
Thisregressionhastworegressors,1/iandXi/i.Becausetheseregressorsdependonlyon
Xi,E(vi|Xi)0impliesthatE(vi/i|(1/i),Xi/i)0.Thus,weightedleastsquaresprovidesa
consistentestimatorof0E(0i)and1E(1i).
Chapter18
TheTheoryofMultipleRegression
18.1.
(a) Theregressioninthematrixformis
YX U
with
1 Income1
1 Income 2
X
M
M
1 Income n
TestScore1
TestScore 2
Y
,
TestScore n
U1
U
U 2 ,
M
U n
Income12
Income 22
M
Income 2n
0
1 .
2
TheheteroskedasticityrobustFstatistictestingthenullhypothesisis
F ( R r) R R
( R r)/q
Withq1.Underthenullhypothesis,
d
F
Fq ,
WerejectthenullhypothesisifthecalculatedFstatisticislargerthanthecriticalvalueofthe
Fq ,
distributionatagivensignificancelevel.
Var (Q) E[(Q Q ) 2 ]
E[(Q Q )(Q Q )]
E[(cW c W )(cW c W )]
cE[(W W ) ( W W )]c
18.3.
c var( W ) c c w c
(a)
wherethesecondequalityusesthefactthatQisascalarandthethirdequalityusesthefact
thatQc w.
finite,sovar(Q) c wc isalsofinite.Thus,0<var(Q)<.
18.5.
PXX(XX)1X,MXInPX.
(a)PXisidempotentbecause
PXPXX(XX)1XX(XX)1X X(XX)1XPX.
MXisidempotentbecause
M X M X (I n PX ) (I n PX ) I n PX PX PX PX
I n 2PX PX I n PX M X
PXMX0nxnbecause
PX M X PX (I n PX ) PX PX PX PX PX 0n n
1
(b) Because ( X X) X Y, wehave
X X (XX )1 X Y P Y
Y
X
whichisEquation(18.27).Theresidualvectoris
YY
Y P Y (I P ) Y M Y.
U
X
n
X
X
WeknowthatMXXisorthogonaltothecolumnsofX:
MXX(InPX)XXPXXXX(XX)1XXXX0
sotheresidualvectorcanbefurtherwrittenas
M Y M ( X U ) M X M U M U
U
X
X
X
X
X
whichisEquation(18.28).
18.7.
(a) Wewritetheregressionmodel,Yi1Xi2Wiui,inthematrixformas
YXWU
with
Y1
Y
Y 2 ,
M
Yn
X
1
X
X 2 ,
M
X
n
W1
W
W 2 ,
M
Wn
1 ,
u1
u2
,
M
un
2 .
TheOLSestimatoris
1
1
X X XW X Y
W X WW
WY
2
1
X X X W X U
1
W X W W W U
2
X X
WX
1
2
1
n
1
n
1
2
in1 X i2
n
1
n i 1 Wi X i
1
n
1
n
1
n
X W
W W
1
n
1
n
1
n
X U
W U
in1 X iWi
n
2
1
n i 1 Wi
in1 X i ui
1 n
W u
n i 1 i i
1
n
Bythelawoflargenumbers n
p
p
in1 X i2
E ( X 2 ); 1n ni 1 Wi 2
E (W 2 );
p
in1 X iWi
n
p
1
E ( XW ) 0 (becauseXandWareindependentwithmeansofzero); n i 1 X i ui E ( Xu ) 0
p
in1 X i ui
E ( Xu ) 0
(becauseXanduareindependentwithmeansofzero); n
Thus
1
1 p 1
0
E( X 2 )
0
2
0
E (W )
E (Wu )
2
2
1
.
2 EE ((WWu2 ))
E (Wu )
p
2
2
2
E (W 2 )
(b) Fromtheanswerto(a)
ifE(Wu)isnonzero.
(c) ConsiderthepopulationlinearregressionuiontoWi:
uiWiai
whereE(Wu)/E(W2).Inthispopulationregression,byconstruction,E(aW)0.Usingthisequationfor
uirewritetheequationtobeestimatedas
Yi X i 1 Wi 2 ui
X i 1 Wi ( 2 ) ai
X i 1 Wi ai
where 2 . Acalculationlikethatusedinpart(a)canbeusedtoshowthat
n ( 1 1 )
n ( 2 )
in1 X i2
1
in1 Wi X i
n
1
n
E( X 2 )
1
n
in1 X iWi
1
in1 Wi 2
n
0
E (W )
2
S1
S 2
in1 X i ai
1 in1 Wu ai
n
1
n
a2
d
n ( 1 1 )
N 0,
E ( X 2 )
NowconsidertheregressionthatomitsW,whichcanbewrittenas:
Yi X i 1 d i
wherediWiai.Calculationslikethoseusedaboveimplythat
d2
d
n 1r 1
N 0,
.
E ( X 2 )
2
2
2
2
r
Since d a E (W ), theasymptoticvarianceof 1 isneversmallerthantheasymptotic
varianceof 1 .
( XM W X)1 XM W Y
( XM W X) 1 XM W ( X W U )
18.9.
(a)
( XM W X) 1 XM W U.
ThelastequalityhasusedtheorthogonalityMWW0.Thus
( XM W X)1 XM W U (n 1 XM W X)1 (n 1 XM W U ).
(b) UsingMWInPWandPWW(WW)1Wwecanget
n 1XM W X n1X(I n PW )X
n 1XX n 1XPW X
n 1XX ( n 1XW)( n 1W W ) 1 ( n 1WX).
1
n X X .
n 1XX 1n in1 X i Xi .
Firstconsider
The(j,l)elementofthismatrixis n i 1 ji li By
Assumption(ii),Xiisi.i.d.,soXjiXliisi.i.d.ByAssumption(iii)eachelementofXihasfour
moments,sobytheCauchySchwarzinequalityXjiXlihastwomoments:
n i 1
Thisistrueforalltheelementsofn1XX,so
n 1XX
1 n
Xi Xi p E (Xi Xi ) XX. .
n i 1
ApplyingthesamereasoningandusingAssumption(ii)that(Xi,Wi,Yi)arei.i.d.and
Assumption(iii)that(Xi,Wi,ui)havefourmoments,wehave
1 n
p
Wi Wi E ( Wi Wi ) WW ,
n i 1
1 n
p
n 1 XW Xi Wi E ( Xi Wi ) XW ,
n i 1
n 1WW
and
n 1 WX
1 n
p
Wi Xi E ( Wi Xi ) WX .
n i 1
XX XW -1WW WX
whichisfiniteandinvertible.
(c) Theconditionalexpectation
E (u1| X, W )
E (u2 | X, W )
E (U|X, W )
E (un | X, W)
W1 W
1
W
W2
2
M M
Wn W
n
E (u1| X1 , W 1 )
E (u2 | X 2 , W2)
E (un | X n , W n )
W .
ThesecondequalityusedAssumption(ii)that ( X i , Wi , Yi ) arei.i.d.,andthethirdequality
appliedtheconditionalmeanindependenceassumption(i).
(d) Inthelimit
p
n 1 XM W U
E ( XM W U|X, W) XM W E (U|X, W) XM W W 0 k1 1
because M W W 0.
1
1
Thisimplies
p
.
18.11.
(a) UsingthehintC[Q1Q2]
Ir
0
0
0
Q1 '
Q '
2
,whereQQI.TheresultfollowswithAQ1.
(b) WAVN(A0,AInA)andtheresultfollowsimmediately.
(c) VCVVAAV(AV)(AV)WWandtheresultfollowsfrom(b).
18.13.
(a) ThisfollowsfromthedefinitionoftheLagrangian.
(b) Thefirstorderconditionsare
%
(*)X(YX )R 0
and
%
(**)R r0
Solving(*)yields
%
(***) (XX)1R .
But(YX )X0,sothelasttermvanishes,andtheresultfollows.
su2 SSR
Unrestricted
18.15.
/(nkUnrestricted1),andtheresultfollowsimmediately.
(a) Thisfollowsfromexercise(18.6).
% % %
(b) Yi Xi u i ,sothat
%' X
%
X
i
i
i 1
1 n
%' X
%
X
i
i
i 1
1 n
%' X
%
X
i
i
i 1
1 n
1 n
%' X
%
X
i
i
i 1
X%' u%
i 1
X ' M ' Mu
i 1
X ' M 'u
i 1
X%' u
i 1
X% 1n in1 (T 1 Tt 1 ( X it X i ) 2 ),
Q
2
(f) i arei.i.d.,andtheresultfollowsfromthelawoflargenumbers.
1/ 2 %
1/ 2
% %
%' u% 2 T 1 ( )2 ( X
%' X
%)2 2T 1/ 2 ( ) X
% %
i2 T 1/2 X
i
i
i
i
i
i i ' Xi
1
%' X
%) 2 2T 1/ 2 ( ) 1 n X
% %
in1 i2 in1 i2 T 1 ( )2 1n in1 ( X
i
i
i 1 i i ' X i
n
n
and
1
n
p
p
1
%
% %
in1 i X%
i ' X i E (i X i ' X i ).
p
Both(a)and(b)followfromthelawoflargenumbers;both
(a)and(b)areaveragesofi.i.d.randomvariables.Completingtheproofrequiresverifying
% %2
% %