WPC &6|?[[mƆh>;OHɤa]%>vUݰR"e\c4Pvn$`E+Ha }öHTdMfv4PoJ]T&X(ǿv u~ A3C)6L?)Lu,`tO+p D?B.IiQ])\l\ _ jxg5mnZU.ejj5糘nGUndҠpԈ3 >5[6`d[o-[`ֿ\ܻkbEȴ -LxÔ+sBӊdLHm@`?6T|hdwmJ4% 7W!TY; B96ؤ o/MuZ7,na>qcѭ.j$w-dɳ f8q"RcHT+8q Ͼ*jw # UWN % 0 (fG^ IwU4Ym| m~f 0 l 0 DNGMIMMNQMS 03cW 1u 0w/ 0 00 0M 0 0O 0* 1E 0N A5U:bVpMNfaaMUJ 0DDfaU N 0D 0D0 1tM 1 1M MMMNE ! 0D.!fr!at!!a!!Mk#fo#hq#a%%(&@*&o&@&pM D54il/ i8 B*f i=< B BC D5, B)*a AS 0D D/"aQ D5e B* CZ D5t B7 B7 D5ML D7PM B  U(*R 72U@@JPo?,, C C0000000000 i[JJU>M A 0K D+ AY 0F A3 D3 B* 0D9 0z}}}} 0PMGGMKMOOOMSMWM[N______a\\CENSUS\PRED-TR2-2-HP8000-3.PRED.DECENNIAL.HQ.CENSUS0(hH  Z6Times New Roman RegularX($t. ʄ8.x3|xU((3$ !      0  (#$  0  (;3$2#  0  .3  0  3#37=CIQYag1.a.i.(1)(a)(i)1)a)(O;$0  2#  a  .3  0` (#(#(b$0  0` (#(#2#   .3  0 ` (#` (#(xir$0  0` (#(#0 ` (#` (#2#(  0  )3  0 (# (#($0  0` (#(#0 ` (#` (#0 (# (#2#(  a  )3  0h(#(#(F$0  0` (#(#0 ` (#` (#0 (# (#0h(#(#2#(   )3  0h(#h(#($0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#2#  0  )3  0(#(#({$0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#2#  a  )3  0p(#(#xAGaeimquy}Bullet ListBullets List ;  $    9    _Ø XXԀNosignificantfactorswerefoundwhenthemodelincludedonlyelectronicmoderespondents.dB  ԍ(31,all  pages,R1)C  d#X'<X ØS#(O$NZ I&mage <=8C HKKKK,  AZ"Arial Regularhttp://www.ascusc.org/jcmc/vol3/issue1/smith.htm L  $    6    _ԀØ XXUAAsfromtheinitialmailoutinthisexperimentweredeliveredtoheadquartersfromthe_NPC_Ԁafterform  processing.WecannotbesurethatwereceivedeveryUAA.(TABLE HTABLE FkIA`2WP TypographicSymbols(3$ !  TABLE H(hH  Z 6Times New Roman Regular6b$Triangle0 (3$ !  (5hCEKQW]cioAutoList1I.I.I.I.I.I.I.I.(uhCEKQW]cioAutoList5IIIIIIIIIIIIIIII(hCEKQW]cioAutoList6IIIIIIIIIIIIIIII   $    5    _ԀØ XXTheanalysisinTable4wasconductedwiththeinclusionofthelatemailreturns.Theconclusionsdid  notchangewiththeadditionofthesecasesdB  ԍ(22,page4,R1)C  Ԛ#X'<X ØU#dØ XX'<,withtheexceptionofthedifferencebetweenthe_ASQ_Ԁincentiveand  nonincentivepanelwithoverallresponserates.Thedifferencebetweenthesepanelsinnotsignificantwhenlate ` mailreturnsareconsidered.dB  ԍ(22,page4,R2)C  d#X'<X Ør#(3$ !  ݘTABLE A   TABLE B  SSNnonresponse SSNsmailoutmailback SQTprenoticeDillman SFC LFC DMAFA.C.E LCA HCA UAA UAAs AQE USPS PMPDSCMOpairwiseHochbergReltnshpA.C.E.undercoveragex ^  $    10    _ԀØ XXTheraceandethnicityvariablesarenotsignificantlydifferentfromzerowhensimultaneouslycompared.dB  ԍ(30,page2,R2)C  d#X'<X ØV#Ԁ  Ø XX'<Moreover,thesefindingsdonotchangewhenstrataorhouseholdsizeisomittedfromthemodel.#X'<X ØH#Ø XX'<dB  ԍ(30,page5,R3)C  Ԛ#X'<X Ø#dTABLE C   KL*OLE*WPC@@>>>>!>>& D(f . - "- "-  "Arial-,f2 ,?Figure 1. Treatment Groups and Sample Sizes in the Experiment    ( "  (       ( "ArialCo- ?2 ,4%(Mailout Sample Sizes in Parentheses)         -   "Arial-  C# E O s O s  O s O E C#    C# E "--B(UUUU-Nd'Bz'M' '' O "--NL'``'L' pp'`p' s "- -NU'WW''W'--- "- $WW'X "-  i  "Arial- 2  Incentive  s G - > s G - > s G - $2 $(1075)   s- '- "- WW'---- $qqWW'Xr "- i - 2  No Incentive  s G - > s G - > s G - ,2 ,(979)   s-'- "-qWqW' O---- $WW'X "- E - 2  Reverse CATI   O E - > O E - > O E - -2 -(2054)   O-'- "-WW' s  "--NU'WW''W'---- $WW'X "- i - 2  Incentive  s  G - > s  G - > s  G - ,2 ,(967)   s -'- "-WW'---- $qqWW'Xr "- iR - 2  No Incentive  s  GR - > s  GR - > s  GR - ,2 ,(999)   s -'- "-qWqW' O---- $GGWW'XH "-  - 8 2 8ASQ O  - > O  - > O  - -2 -(1966)   O-'- "-GWGW' s "--NU'WW''W'---- $WW'X "- i - 2  Incentive  s G - > s G - > s G - $2 $(1068)   s-'- "-WW'---- $qqWW'Xr "- i - 2  No Incentive  s G - > s G - > s G - $2 $(1042)   s-'- "-qWqW' O---- $WW'X "- 5 - &2 &Internet  O 5 - > O 5 - > O 5 - -2 -(2110)   O-'- "-WW' E--- - $yy'z "-! ; - ]$2 ]Initial Nonresponse  E q; - 32 Group Eligible for Experiment     E O; - 2 (6130)   E -; - > E-!'- "-!yy'---"- $yy'z "-# h -1+2 1Mail Respondents 4/26/00 E qh - *.2 *71.5% w/out undeliverables   E Oh - :2 "(12,787 rspdnts, 60 blank returns)      E -h -> E-#'- "-#yy'---$- $bbyy'zc "-%  - 2-2 2Initial Nonresponse Group   E q - ?-2 ?Ineligible for Experiment    E O - 2 (662)   E - - > E-%'- "-%byby' C#---&- $yy'z "-' 9 - B(2 BHouseholds Included in C#  - 2 Initial Mailing C#  - 2  (19,639)   C#  - > C#-''- "-'yy' WPWin 6.0/OLE 1.0 Prefix Information MarkerOrgPlusWOPX.4bࡱ>   !"#$%&'()*+,-./Root Entry@%1h`t(ƽOle 7CompObjZCONTENTS-'F! WP 7 [0] @%1h OrgPlus.4 OrgPlus.4OrgPlusWOPX.49qMo} UOCF i(c) Copyright 1992 Banner Blue Software Incorporated. All rights reserved. The OPX file format is the confidential and proprietary property of Banner Blue. Banner Blue requires prior written consent and advanced royalty payment to use this format. A violation of these rights is against the law and Banner Blue will aggressively pursue prosecution. ) Copyright 1992 Banner Blue Software Incorporated. All rights reserved. The OPX file format is the confidential and proprietary property  \  \@@@@`Name`Title` Comment 1` Comment 2`"r Bl7`@!dDD33 "" $m.,+"N,%%HP LaserJet 5Si MX,HPPCL5MS,LPT1:P\BOC\pq3231IIP odLetterPRIV''''0   @##### # # ` @%Arial `@aaaaaa aa a a a aa` @&`@aa`&`eFigure 1. Treatment Groups and Sample Sizes in the Experiment (Mailout Sample Sizes in Parentheses)@aa aaa ?a?a?`&`@aa`&`@aa`&`@aa`&`@aa` `$#RSTZV@AB@PQ$$S@`Households Included in@aaa``Initial Mailing@aaa`` (19,639)@aaa``@aaa``` @ `AB@PQ$$ST$@`Initial Nonresponse@aaa``Group Eligible for Experiment@aaa``(6130)@aaa``@aaa``PQ$$ST$@`Mail Respondents 4/26/00 @aaa``71.5% w/out undeliverables@aaa``#(12,787 rspdnts, 60 blank returns)@aaa``@aaa``PQ$$ST$@`Initial Nonresponse Group @aaa``Ineligible for Experiment@aaa``(662)@aaa``@aaa``` @VVVVVVVVVV V V V V VVV `AB@PQ$$ ST$@` Reverse CATI@aaa``@aaa``@aaa``(2054)@aaa``PQ$$ ST$@`ASQ@aaa``@aaa``@aaa``(1966)@aaa``PQ$$ ST$@` Internet@aaa``@aaa``@aaa``(2110)@aaa``` @VVVVVVVVVV V V V V VVV `AB @PQ$$ ST$@` Incentive@aaa``@aaa``@aaa``(1075)@aaa``P Q$$ ST$@` No Incentive@aaa``@aaa``@aaa``(979)@aaa``` @VVVVVVVVVV V V V `AB @P Q$$ ST$@` Incentive@aaa``@aaa``@aaa``(967)@aaa``P Q$$ ST$@` No Incentive@aaa``@aaa``@aaa``(999)@aaa``` @VVVVVVVVVV V V V `AB @P Q$$ ST$@` Incentive@aaa``@aaa``@aaa``(1068)@aaa``P Q$$ ST$@` No Incentive@aaa``@aaa``@aaa``(1042)@aaa``` @VVVVVVVVVV V V V ``@`@```` - V V V V ``@`@```` o%OP a``(2500)@aaa``` @VVVVVVVVVV V V V V VVV `A B @PQ$$ST$@` Panel 7A@aaa`` @aaa`` (Incentive)@aaa``(1300)@aaa``PQ$$ST$@` Panel 7B@aaa`` @aaa`` @aaa``(1300)@aaa``` @VVVVVVVVVV V V V `AB @PQ$$ST$@` Panel 8A@aaa`` @aaa`` (Incentive)@aaa``(1300)@aaa``PQ$$ST$@` Panel 8B@aaa`` @aaa`` @aaa``(1300)@aaa``` @VVVVVVVVVV V V V `AB @PQ$$ST$@` Panel 9A@aaa`` @aaa`` (Incentive)@aaa``(1300)@aaa``PQ$$ST$@` Panel 9B@aaa`` @aaa`` @aaa``(1300)@aaa``` @VVVVVVVVVV V V V ``@`@```` v-BOlePartOlePres000&% & D(f . - "- "-  "Arial-,f2 ,?Figure 1. Treatment Groups and Sample Sizes in the Experiment    ( "  (       ( "ArialCo- ?2 ,4%(Mailout Sample Sizes in Parentheses)         -   "Arial-  C# E O s O s  O s O E C#    C# E "--B(UUUU-Nd'Bz'M' '' O "--NL'``'L' pp'`p' s "- -NU'WW''W'--- "- $WW'X "-  i  "Arial- 2  Incentive  s G - > s G - > s G - $2 $(1075)   s- '- "- WW'---- $qqWW'Xr "- i - 2  No Incentive  s G - > s G - > s G - ,2 ,(979)   s-'- "-qWqW' O---- $WW'X "- E - 2  Reverse CATI   O E - > O E - > O E - -2 -(2054)   O-'- "-WW' s  "--NU'WW''W'---- $WW'X "- i - 2  Incentive  s  G - > s  G - > s  G - ,2 ,(967)   s -'- "-WW'---- $qqWW'Xr "- iR - 2  No Incentive  s  GR - > s  GR - > s  GR - ,2 ,(999)   s -'- "-qWqW' O---- $GGWW'XH "-  - 8 2 8ASQ O  - > O  - > O  - -2 -(1966)   O-'- "-GWGW' s "--NU'WW''W'---- $WW'X "- i - 2  Incentive  s G - > s G - > s G - $2 $(1068)   s-'- "-WW'---- $qqWW'Xr "- i - 2  No Incentive  s G - > s G - > s G - $2 $(1042)   s-'- "-qWqW' O---- $WW'X "- 5 - &2 &Internet  O 5 - > O 5 - > O 5 - -2 -(2110)   O-'- "-WW' E--- - $yy'z "-! ; - ]$2 ]Initial Nonresponse  E q; - 32 Group Eligible for Experiment     E O; - 2 (6130)   E -; - > E-!'- "-!yy'---"- $yy'z "-# h -1+2 1Mail Respondents 4/26/00 E qh - *.2 *71.5% w/out undeliverables   E Oh - :2 "(12,787 rspdnts, 60 blank returns)      E -h -> E-#'- "-#yy'---$- $bbyy'zc "-%  - 2-2 2Initial Nonresponse Group   E q - ?-2 ?Ineligible for Experiment    E O - 2 (662)   E - - > E-%'- "-%byby' C#---&- $yy'z "-' 9 - B(2 BHouseholds Included in C#  - 2 Initial Mailing C#  - 2  (19,639)   C#  - > C#-''- "-'yy'  METAFILEPICT%&%  D(f . - "- "-  "Arial-,f2 ,?Figure 1. Treatment Groups and Sample Sizes in the Experiment    ( "  (       ( "ArialCo- ?2 ,4%(Mailout Sample Sizes in Parentheses)         -   "Arial-  C# E O s O s  O s O E C#    C# E "--B(UUUU-Nd'Bz'M' '' O "--NL'``'L' pp'`p' s "- -NU'WW''W'--- "- $WW'X "-  i  "Arial- 2  Incentive  s G - > s G - > s G - $2 $(1075)   s- '- "- WW'---- $qqWW'Xr "- i - 2  No Incentive  s G - > s G - > s G - ,2 ,(979)   s-'- "-qWqW' O---- $WW'X "- E - 2  Reverse CATI   O E - > O E - > O E - -2 -(2054)   O-'- "-WW' s  "--NU'WW''W'---- $WW'X "- i - 2  Incentive  s  G - > s  G - > s  G - ,2 ,(967)   s -'- "-WW'---- $qqWW'Xr "- iR - 2  No Incentive  s  GR - > s  GR - > s  GR - ,2 ,(999)   s -'- "-qWqW' O---- $GGWW'XH "-  - 8 2 8ASQ O  - > O  - > O  - -2 -(1966)   O-'- "-GWGW' s "--NU'WW''W'---- $WW'X "- i - 2  Incentive  s G - > s G - > s G - $2 $(1068)   s-'- "-WW'---- $qqWW'Xr "- i - 2  No Incentive  s G - > s G - > s G - $2 $(1042)   s-'- "-qWqW' O---- $WW'X "- 5 - &2 &Internet  O 5 - > O 5 - > O 5 - -2 -(2110)   O-'- "-WW' E--- - $yy'z "-! ; - ]$2 ]Initial Nonresponse  E q; - 32 Group Eligible for Experiment     E O; - 2 (6130)   E -; - > E-!'- "-!yy'---"- $yy'z "-# h -1+2 1Mail Respondents 4/26/00 E qh - *.2 *71.5% w/out undeliverables   E Oh - :2 "(12,787 rspdnts, 60 blank returns)      E -h -> E-#'- "-#yy'---$- $bbyy'zc "-%  - 2-2 2Initial Nonresponse Group   E q - ?-2 ?Ineligible for Experiment    E O - 2 (662)   E - - > E-%'- "-%byby' C#---&- $yy'z "-' 9 - B(2 BHouseholds Included in C#  - 2 Initial Mailing C#  - 2  (19,639)   C#  - > C#-''- "-'yy' QQQQ)!dxdxLevel 1Level 2Level 3Level 4Level 5 b  $    7    _Ø XXԀTheoverallresponserateincludespaperformsreceivedaftertheelectronicmodeswereshutdownand  thereforecannotbedirectlycomparedtothemodespecificresponserate.Sincemailcheckindatesaredependent t uponmaildeliveryspeedaswellascheckindelaysduetobacklogs,itisnotpossibletocontrolthedateofthe 8 returntoidenticallymatchthedatefortheelectronicreturns.#X'<X ØS#Viii( c &p Pd ddii1)     $    2    _ԀØ XXԀQuestionnairesareconsideredblankiftheycontainlessthan2completeditemsamonghouseholdcount,  tenure,andallpersonitemsundercensusproceduresgivenin_DSSD_ԀCENSUS2000MEMORANDUMSERIES:  #K3fromHoganto_Miskura_Ԁand_Longini_#X'<X ØT#Ø XX'<.dB  ԍ(7,page2,R1)C  dDuetointenselaborinvolvedinreplicatingtheblankformalgorithm ,a ` simpler techniqueisusedforallCensus2000experiments.Formsareblankwhenthenumberofcompleteditems $t forthehousehold,person1andperson2islessthantwo.#X'<X Ø# d dXXXX)!dxdx&0 d dZM -, dc(3$ !  V)!dxdxTABLE E^^^^)!dxdx&p d Pd   $    3    _ԀØ XXTherewasonlyoneSpanishinterviewtakenduringthisexperiment.dB  ԍ(8,page1,R1)C  dThiscallcamethroughtheOperator  AssistancenumberfromarespondentintheInternetwithincentivegroup,andthereforewillnotbecountedasa  respondentinthemoderesponseratesinordertoeliminateanyconfoundingeffectsfromtheallowanceofSpanish ` speakinghouseholdsin_CATI_.#X'<X ØU#ddbcbc)!dxdx3+0 d d d3+0 d d dUUUU)!dxdxVVVVV)!dxdx x  $    4    _Ԁ_ASQ_ԀØ XXassignedcasesthattransferredto_CATI_Ԁbeforeprovidinganyinformationhaveonly_CATI_Ԁrecords  onthedatafile(18cases)andaretreatedas_CATI_Ԁresponses.dB  ԍ(9,page1,R1)C  dCasesthatcompletedatleastsomeportionofthe  questionnairein_ASQ_Ԁbeforetransferringto_CATI_Ԁhaveboth_ASQ_Ԁand_CATI_Ԁrecords(5cases).dB  ԍ(10,allpages,R1)C  d#X'<X Øy#Ø XX'<ԀInordertoisolate ` theeffectofthetreatmentmode,therecordcorrespondingtotheassignedmodeforthepanelisretainedwhen $t duplicaterecordsarepresent,regardlessofwhetherthatrecordisconsideredblankbycensusdefinition.Several 8 caseshaveduplicate_ASQ_Ԁresponses.Whendiscrepanciesbetweentherecordsexist,themostcompleterecordis  retained.#X'<X ØU#  d%2A`HelvLevel 1Level 2Level 3Level 4Level 5Level 1Level 2Level 3Level 4Level 5i)(G Z(Times New Roman pH:\MURAWSKI\LATESTMO\1CPOSTAG.TIFWPC   !!!"""###$$$%%%&&&'''((()))***+++,,,---...///000111222333444555666777888999:::;;;<<<===>>>???@@@AAABBBCCCDDDEEEFFFGGGHHHIIIJJJKKKLLLMMMNNNOOOPPPQQQRRRSSSTTTUUUVVVWWWXXXYYYZZZ[[[\\\]]]^^^___```aaabbbcccdddeeefffggghhhiiijjjkkklllmmmnnnooopppqqqrrrssstttuuuvvvwwwxxxyyyzzz{{{|||}}}~~~o}sϏO/??oL߯O? ?O??O???̅{3OD_/_3߬.7_/o.ߓ3o/_2;)ߜ?A?>2_?_O/+.? ?5_/o+_?1oo//_7) O:+?AO=?0/=?$o-+?._ O??4+0?/"4?)$_8+o@o=??O/;?'?.+?. ?3_,/?/$3?O*&_6+@=?OO. /? ?: O_/?.?*?. 2_ _o/ ,.o Oo? o0&_2O*/&6+@<O- O_?8_  _ .O*?.o1_? ,??- O 0&_1*O'5*? ?<￟? ߿_. ?7/ ??0Ͽ? ߂0o __2/ _-߿/ ?Ͽ. 2 ￿O 1￟? ߿_.Ͽ? OO 6 ς?_ <￟? ߿_ ??0??6/ ?2 o3 /3/O0 0o4? _ 3 ??2  7? ?> o? ?? ?O/__5/ /2 3 3?0 /0o/4? ? ?3 ?O2 / _7? ?> ? ?_ _0O5O _?2 3 20 ?/?4 _ 2 _2 / 6 > > O /4 _?2 3 ?3?/?0 ??/_o4 ? _2 3  _6 = O>  /?/3 ?2 ￏO?3? 2_1 ??/o4  2 3  5 ??=_>  .?3/ 2 Q? ?21 ?./4 _ 2 3 ? 5 Z>  ?.2 ?/2 Q????2?߿1 o.o￯4  2 ?3  _5 Z> ??.oM o$3 Qo??2?M .?Q  O2?4  /5 Z/?? =???.?N [ Q??1?N .?Q /?2??4 ? 5 Y O=????.?M \ QO??1?N .Q ??2??4 O 5 Y_ <????.?L \ Q/ ??1/N . Q ??2??4  4 X__ <????.?L/ o] Q? ??1 M . P ?O2??4  4 X <????.?/K ] Q?? o??1 M . oP ?2??4  4 X?// ;????.O J O^ Q? ??2 M .O 2??4 o 5 W O;????. ?J/ ^ Q? ??2 L .? oO  2??4 ? 5 Wo :????. H ^ Q?/ ??2_ K . N O3??4 /?5 W__ :????/ G ?_ Q? ??2 J . M _3??4  o5 V :????/ Fo _ Q? /??3 I /? L /4??4  5 V? 9????/ _D/ _ Q? ??3 H / K o4??4 _6 U _9????0 C ` Q? ??4/ OF 0O ?I o5??4 _6 U 8????1/ o@ ?` Q?o ???4 E 0 H /6??4  6 UO _ 8????1 ? _` Q? ??5?C 1F //6??4 _7 T  8????2= ` Q? ??6__A 2?D /7??4 O7 TO  7????3?; ` Q?O O??7_? 3oB __8??4 _ 8 So  _7????49O ` 8? ??8o> 4A ߿/:??4 _ _9 :  6????5/8? a!8?  ??9?< 5/?_;??4 / ?:!:? O 6????6_?6? a!8? ? o ??:/: 6?_=_=??4 ? O:!9  /6????85? a!8?  ??;o9 8<????4 ? o<!9_ 5????9_3? a!8?   ??=/O7 9??:o<??4=!9o _5????;/2? a!8? /  ???6 ;9:??4o>!9 4????=?0? a ߃9?  ??@_5 <_7 O/8??4o@ σ9/O 4????>/? a Q?  / ??B?_3 >O/6 o O6??4B P /4????@O.? a Q?  ??D/2 @?/5 _ 5??4?B P_ 3????B/- a Q?  ??F_2 B/4 ? 4??4  A O_o _3????D /, ` Q?o ???G_1 C_4  3??4 o @ O 2????Eo o, ` Q? ??I/ 0 E? 3 / 2??4  ?@ O/? 2????G + ` Q? ??K ?0 G 3 / O2??4  ? N ?2????H/ _+ O` Q?O O??L / H 2  1??4 ? > No 1????I_ +` Q? ??M O/ I/ 2  1??4  ?> N(o1????J/ +O _ Q? ??N . J 1 O 0??4 o = M)1????K O+ _ Q?? o??O . K 1  _0??4  < M?*0????L + O_ Q? ??P? o. L_ ?1 /0??4  O< L+?0????M + ^ Q? ??P ?. L 1  /??4 ? ; Lo,/??OM +_ ^ Q?/ ??Q./MO 1  /O4  : L?? o/_oM + /^ Q? ??Qo .?M 1  /4 _ O: K /o?N , ] Q? /??Q .OOM 1  /?4  9 KO? .??N, ?] Q? ??Q .o?O 1  /?4  8 Jo ?./ ON?, \ Q? ??Q.?O 1  / O4 / O8 J - OO?- \ Q?o ???Q?.OO1  05  7 J/o ./OOO. [ Q??Q_/N?1 / 0OO5 _ 6 I .OO_._?/ Z Po/?1o/Oo.ooo1  0_5  O6 I ? -OO.0/ X 1?O?1?O///??o1  /1O4  5 )_! ?- O/O/_0 /W _?1??1?/0/?2  2/O5 / 4 O?(?" -/O_/_?2 /#1 1??11_?/?2 O 2_5  /4 '# ?-_O?0?_3_ / ?1 1? ?12 o02  _4O?6 _ 3 '?o# -O? 0?o?4/ 1 1 ?1O3_ 0o3o  4 6  2o ?&$O O- ? o1?_5/ o1 o1 ?0_?413? O 6? o7  1? ?&?/% -? O _1?7/ 1 /1/ ?0?_5 oO24?  _ ?7 _7 / O1? %& _- _  ?2 O _9/ ߏ/-Ͽo ? O-_? ?0 ? 7 ?/2 ? ? 1߿ Ͽ_ /8 ?4￟/ o ?(ϯ_ ?/ "/_߿/ o+ ?  ? 3 o_ _;_/oￏ_ -?,?,o ?0 /? 9_ ?ߏ2 O 2(/: ? 5?o_(-"O o+ ?  OO/ 4?? >?/-/,?,_ ?0/_o? ; /_O 3Oo? 3'o= OO/ 6?O(-"? ?, O_/  /5!@O$/-?,? ?0!O=?4!/3%?/7/?'-" /-/ o6oC? 0-?,__?0@o65#?Co7 '-O"/o _9ϏO_G__2-,??1o?C_o9?6/_F_9'-?!o0__/?ϟo?/Lo/?5﮿,ϐ?6O/_HOO?_/O9ߝN_/;'߭!ߒ3_/ϟO?/?_G߿??/?ORo????_Ƈ;o???_OϏ????oHϯo???OϟO?/?_lϟO?/?_AJPO?[?_o/Oo?P/[_O Po[??/   $.O]  TO)F 0ooo/?_No%?c o  O&/-] _ TO+G O/?/L??$c  &/.] OU*OG .?Jo$c /'o._oWO,I0Ooϯ/H$c O(.O/`/_YO-I?0/ _G$Od ?(.a_o o?Z?-J0??O F%d ?(o /Z-??JO0o/ /)??O [oo.oJ/0O_?)? /\?O/o??-J/0_O?o(O] /o-I_0o__O ?/o _?߃?/o//__?/o? ߏ?/ _?o?? /o/?oO?? ?ߏ?O?O o_ o?? ߂o?__O?_ _o//?/O//o?ߏ?__/Oo? O?o _?_/O _?o___/O/_o o /??_ ?  ?_/  ?? ??__    OO_O__?/ _ O  o? ? ?_?/ ? ??? ??? _?O_ O /_o_? O? _ o _ // o  /  O?_/ oO   ?/ ??/  / ? ???? oo/ oo/ o_? __/?/ _ߟ/_? ?_?oO   O_/ o/ o o/o/  o _ OOo?? //_ _?߯_/o _/o __? _ ? _o /  ?oO  o / o_ ?/? ? /o ? ? ?o_ //? __ _//? _oO /o_? /? /oo/??  ? ?O/ _ /  oO ? O/  O o/ _  _/ o  _/? o//_? _ o??oo_? _ / Oo/_? /?O? ? /_O //? ?/ O o /?     _ ? _ ?OO_o   ?// ?_o_ /o_   ?/߿/?/_  / O??/? O  / /o _ o_O/ O//  ?? O_   !_/ / _ Oo/o   _O ?/ ? _O _ o/ ??// O _/ O?/_   o    /_?? O߿? /_ _ o/ ?_? O o" O ? ?/_? /? O/ o O/  /?   //O/  // O? __ o /  ?ooO _  ??#/O _ ? /o  _ /? ?_ O_   ?O_Oo_ ?  / _ ? O ?_O/?  /?O /O  #  ??? /? ?   _o   oo O OoO_? /O? O_O/ _/ o _o ?_ _ # / ?o O?o?O _  ?/OOo_ ?/??  _ _?o?/??__  ??_? ?? ? Oo _O? ?/  // / #o O  ?o   O?O_O//  _  //__ ? OO_o/_/_  ?? /_?_/o _ oo  ?/ O$   ?O? _o ? ?/  /?  /  _// _/ o/ oo  _ ooo/  ?/ _  _  ?$   o O  ?_ OO   _? OO _?ߏ _/ O_ o _ _/o ?? _ _oO  _? /? ? /O o$? O/ ?/ O_O  o_??   o  o OO?o _?_/o  ?o?? / /? O  /o /o   o  O ?$? ? O__??/O  ?/O? _"_  ?O   _  /O   ??_ _ ?// o /o o ???o? ?    _ # o _?oo o O/O%/ ?  _  ?? _ ?_O O_??oO/  /  ?? o?O o /  ? o$  /o?O?_  /+/   /?  _ _ /? _O/o/?/  O  o ?? ? _ _ _/O?$o  _?oo_? ?O ?+_ O    O  _/? oO   _ o o _ //  /__O?o$/  / ?Oo_?//  ?+ O _   _ O  _o/O?? ?/?  _ //__o   _  ?_$? ? O O///_ ? o_  /O    _  /OOoO??//o??_ O_ / /? o/ / /  ??  o ?#_  o /__O ?_ O?/  o/   _ O  ? O  ?/_?/ ? oo_??o  ?  /?O O/  _?? o /  // ?O$ / o?/ ? ?/ __o O O/  o  /? o o O   O  o / _? ?/   O /O _ ??  ? _ ? ?O/O/$? _O/ o O O ?_/  _?? /  _ /  o O?? ?/ OO/?o? oo? o ?o _ O/    _oo/_$ / ? ߿  ?_/? OOOߏ/ O ? _ oO  ? oOO_?ߟ?o ?/?O/oO// _O / ?_ _ ??????O?   /!o O_ߟ/O  oO/oO? _o/??? o/Ϗo / _ oO? /o?o????/o??__oo ? ?OO/      ? ?  _!O / ? ?O ?_  o _  ?  /  o /?_ _??/_   ?  /?? / _   _ o_?/ Oo  ? oo O? _?  o ? /?/ ? O  ? ? //? o  O  ?  o  _   //_ ?O/?߄  O?/!ߊOO/oτ?o ?OO?_  _? o?/_ ߄  OO?o?oO _?O  //o ?? 4߿%_V _@aD\߿m߿`Ͽ*Ͽ)Ͽ@\bi\Ooj_\_Poj?\?Q /jo[oQ_? j[Qoko[oQ??l/[/Sn?Z?S_ /noZX߯oq???o?????/??_O??/?__????????_??o????o?/???/???????_/???o??__???????/OO?o??_????/o??o???/??O_????_????//??_???????__?/??OO??????OO??_o__??_o_????O???o߿/??__????/?????/_??/??O????_????o??/?__???O/????????o????o_????_????/O??o??o_????/??/????o??????߿???__O/??oϿ/O??????/???_O/oO??/????O????/?/_???_????/???_/???_o_????/?o???__??o????oo???/?/???/?????????/O???????/_O?OO?????o????_???O/???o????/O???O??o????O??o??_???????O????o_?/??O????????????o??O_?/??/OO??o_o/???o?_Oo??/??OO?O???????o??o?/O?????O/OO??o????O/o/OO??_?/OO_OO__?o/?oOoooo_O?OO/?O??O/??o/O_?O/O_/_????/?/O/O??/O__?/??_??O_/?_O??__/???o_O?_?oO??o?/?O_ooo?OO?o?_/oo?_??O?o???/?O_?///??_oO?_?_/O?__?O_/ߏ/Ͽo?????????????????O_????/??߿Ͽ_/?￟/o?ϯ_????????????????//_߿/o??o___/oￏ_??o?/?_?ߏO/??o_Oo?OO/??????//?_?/_o?/_OOo?oOO/?O??O_//O???O?///?//oo??__?o?oOo_ϏO___??o?_o?/__?o__/ϟo?/o/?￿Ͽ?O/_OO_/O߿_/￿߿￿߿_/ϟO?/?_߿??/?Oo????_o???_Ϗ????oϯo???OϟO?/?_ϟO?/?_O??????????_o/Oo?????/_Oo??/OOooo/?_o?oO/_OO?/??/OO?o/ooOOoϯ/OO//_O?/_O?_oo????O?o/??Oo//??Oooo/O_??/?O/o??/_O?oO/o_o__O????/o_????????/o//__?/o?ߏ?/_????o?????/o/?oO?????ߏ?O???Oo_o??o????__O???__o//?/O//o?ߏ?__/Oo????O?o_????_/O_???o___/O/_oo/??_??_/????__OO_O__?/_Oo???_?/???????_?O_O/_o_?O?_o_//o/O?_/oO?/??//?????oo/oo/o_?__/?/_ߟ/_??_?oOO_/o/oo/o/o_OOo??//__?߯_/o_/o__?_?_o/?oOo/o_?/??/o???o_//?___//?_oO/o_?/?/oo/????O/_/oO?O/Oo/__/o_/?o//_?_o??oo_?_/Oo/_?/?O??/_O//??/Oo/?_?_?OO_o?//?_o_/o_?/߿/?/_/O??/?O//o_o_O/O//??O__//_Oo/o_O?/?_O_o/??//O_/O?/_o/_??O߿?/__o/?_?OoO??/_?/?O/oO//?//O///O?__o/?ooO_??/O_?/o_/??_O_?O_Oo_?/_?O?_O/?/?O/O???/??_oooOOoO_?/O?O_O/_/o_o?__/?oO?o?O_?/OOo_?/??__?o?/??__??_????Oo_O??////oO?oO?O_O//_//__?OO_o/_/_??/_?_/o_oo?/O?O?_o??//?/_//_/o/oo_ooo/?/__?oO?_OO_?OO_?ߏ_/O_o__/o??__oO_?/??/Oo?O/?/O_Oo_??ooOO?o_?_/o?o??//?O/o/ooO???O__??/O?/O?__?O_/O??__?//o/oo???o??_o_?oooO/O/?_??_?_OO_??oO//??o?Oo/?o/o?O?_///?__/?_O/o/?/Oo???___/O?o_?oo_??O?_OO_/?oO_oo_///__O?o//?Oo_?//?O__O_o/O???/?_//__o_?_??OO///_?o_/O_/OOoO??//o??_O_//?o///??o?_o/__O?_O?/o/_O?O?/_?/?oo_??o?/?OO/_??o///?O/o?/??/__oOO/o/?ooOOo/_??/O/O_???_??O/O/?_O/oOO?_/_??/_/oO???/OO/?o?oo?o?o_O/_oo/_/?߿?_/?OOOߏ/O?_oO?oOO_?ߟ?o?/?O/oO//_O/?__????????O?/oO_ߟ/OoO/oO?_o/???o/Ϗo/_oO???/o???o????/o????__oo??OO/??_O/??O?_o_?/o/?__??/_?/??/__o_?/Oo?ooO?_?o?/?/?O??//?oO?o_//_?O/?O?/OO/o?????o?OO????__?o?/_OO?????o?oO_?O//o??߿__߿߿ϿϿϿo__o??/oo_?ooo?????//??_/o߯oo@DH:\MURAWSKI\LATESTMO\1CPOSTAG.TIFH:\Murawski\Latest Models\1cpostag.tifT4b̤"ͤͤnJ' ']&I{s u&d dViiiKCC$ \  `&Times New RomanNZ&OLE 2.0 Box <=8C HKKKK( $ Figure  1  'dxdLevel 1Level 2Level 3Level 4Level 5Level 1Level 2Level 3Level 4Level 5ZM << deUU(n$ (  1  ) NZ&OLE 2.0 Box <=8C HKKKKVVVV'dxd&P d d($$  0  (;2r$ !  yXX  0  .((3/Q$ !   d  y  $    1    _ԀØ XX662_nonrespondent_Ԁcasesnotincludedinthenonresponseuniverseareineligibleforfollowupusing  censusdefinitionsgivenin_DSSD_ԀCENSUS2000PROCEDURESANDOPERATIONSMEMORANDUM#BB4R  and_DSSD_ԀCENSUS2000PROCEDURESANDOPERATIONSMEMORANDUM#D6.dB  ԍ(4,pages1and2,R1)(5,allpages,R1)(6,allpages,R1)C  d#X'<X ØT# !  _     `     h      p  XXCensus2000Testing,  0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#0p(#(#Experimentation,&p(#p(# 0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#0p(#(#andEvaluationProgram`p(#p(# #X'<X ј#   `     h     AV<) xdEI xA J     `     h      p  XX'<July10,2001#X'<X ѣ# Y     `     h    `     h      p   X'<XXX'<xEvXX'<AssessingtheImpactofDifferential /  IncentivesandAlternativeData O  CollectionModes#xEvvxE#xEvvxEԀonCensusResponse#X'<XvxE#@2K?XX'< o  #X'<X?@2K#RrQXX'<#RrQQRr# 0RrQQRr#0X'<XQ0Rr># 0 X0X'< FINALREPORT #0X'<X0 #  'w #X'<XX0X'<#0X'<XXX'<#X'<XX0X'<|#?+ ` hp x X?nX'<XXX'<ThisresearchpaperreportstheresultsofresearchandanalysisundertakenbytheU.S.Census M Bureau.Itispartofabroadprogram,theCensus2000Testing,Experimentation,andEvaluation 9 (_TXE_)Program,designedtoassessCensus2000andtoinform2010Censusplanning.Findings %u fromtheCensus2000_TXE_ԀProgramreportsareintegratedintotopicreportsthatprovidecontext a andbackgroundforbroaderinterpretationofresults. M #X'<XXnX'<#   `    0X'<XXX'<0 X0X'<0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#0p(#(#Jennifer_Guarino_!_p(#p(# AV<) xdMEH"xA I"     0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#0p(#(#Planning,Research,andX"p(#p(# 0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#0p(#(#EvaluationDivision#0X'<X0  #0 X0X'<#p(#p(# # 0  #0  #0X'<X0  #0 X0X'<q!o=-)`~0(/ `(*E(//e(-qO # 0 Y##X'<X ћ# *(#*(#(#(#  (#(#*(#*(# @  @`  @  @  @h  @  @  z,'% 8'<XXdXXd8   TABLEOFCONTENTS   |   EXECUTIVESUMMARY......................................................................................................iv t 1..0  BACKGROUND...........................................................................................................18 (#(# 2.0  METHODOLOGY.......................................................................................................5 L (#(# 3.0  LIMITATIONS...........................................................................................................11 (#(# 4.0  RESULTS....................................................................................................................12 (#(# 5.0  RECOMMENDATIONS............................................................................................20H(#(# REFERENCES........................................................................................................................21  \  h+&* _ԇ   EXECUTIVESUMMARY   h      p     chXX'< #X'<Xch#ThisreportdocumentstheanalyticalfindingsfromtheNonresponsecomponentoftheResponse  ModeandIncentiveExperiment.Thepurposeofthisanalysisistoassesstheeffectsofa  promisedincentiveandalternativeresponsemodeoptionsonresponsetothecensusamonga  sampleofhouseholdswhofailedtoreturntheircensusformsbyApril26th,2000.Notethatitis t  nottheintentionofthisanalysistotestincentivesorresponsemodeoptionsasnonresponse `  conversiontechniquesforthecensus.Instead,thisexperimentisdesignedtotesttheeffectof L  thesefactorsonresponseamongagrouprepresentingthosewhoaretraditionallydifficultto 8  enumerate. $ t  Resultsinthispapershowthat: L   (Ax3"3"  3D2A3  0    Thecallincomputerassistedtelephoneinterviewmodegainedthehighestamountof $  response(7.8percent)comparedtoaspeechrecognitionsystem(4.8percent)andthe   Internet(3.7percent),althoughthecomparisonisconfoundedbythefactthatInternet   accessmaybeespeciallyproblematicforthistargetpopulation.3Dq݌(#(# Ќ  "3"  3z2A3  0    Speechrecognitionsystemrespondentsaresignificantlyyoungerandresideinhouseholds p with,onaverage,fewerpeoplethanbothmailand_CATI_Ԁrespondents._CATI_Ԁrespondents \ aredisproportionatelymoreBlackwithmorehouseholdsresidinginlowcoverageareas H comparedtoInternetrespondents.3z݌4(#(# Ќ  "3"  32A3  0    Thecallingcardincentiveincreasedresponsetothealternativemodesby1.9percent  \ acrossallresponsemodes. h     3݌H(#(# Ќ  "3"  33 2A3  0    Person1inhouseholdsreceivingtheincentivetendstobeyoungerthanPerson1in   householdsnotreceivingtheincentive,wheretheoddsofreceivingtheincentivedecrease   by7.2% foreach5yearincreaseintheageofPerson1.33 ` ݌(#(# Ќ  "3"  3!2A3  0    Contrarytopastsurveyresearch,theincreaseinresponseduetotheincentiveisnot   statisticallydifferentinareaswithhighconcentrationsoftheBlackandHispanic l! populationsandrenters(1.9percent)fromotherareas(2.0percent).3!,"݌X" (#(# Ќ  "3"  3#2A3  0    Whentotalresponsetotheexperimentalsecondmailingisconsidered,nosignificant 0$" incentiveeffectremains.Thatis,whenmailresponsesareincludedasrespondents,the %l # incentivegroup(13.8percent)isnomorelikelytorespondthanthenonincentivegroup &X!$ (13.2percent).3##݌&D"%(#(# Ќ  "3"  3%2A3  0    Giventhesefindings,itappearsthattheincentivemerelyredirectsresponsesthatwould ($' haveotherwisebeenobtainedbymailtoalternativemodes.3%&݌)%((#(# Ќ       `     h      p    +&* "3"  3'2A3  0    Irrespectiveoftheexperimentaltreatments,itisworthwhiletonotethataround13  percentparticipationwasobtainedfromcasesthatdidnotinitiallyreturnthe  questionnaireorreturnedthequestionnairelate.Replacementquestionnaireswerenot  includedinthesecondmailing,implyingthatrespondentswhoreturnedamailform, t around6to9percent,usedtheiroriginalquestionnairemailedinMarch2000.3''݌`(#(# Ќ  Thesefindingsleadtothefollowingrecommendations: 8  "3"  3*2A3  0    ݀Asecondmailingcontainingarequestforcensusparticipationmayinitselfbeamethod  ` forincreasingparticipationinthecensusandreducingcostassociatedwithpersonalvisit  L  followupinterviews.3**݌ 8 (#(# Ќ  "3 "  3g,2A3  0    Inordertodeterminethefeasibilityofusingalternativeresponsemodes,furthertestingis   neededintheyearstocomeasInternetaccesscontinuestospreadacrosstheUnited   Statespopulation.3g,,݌ (#(# Ќ  "3 "  3 .2A3  0    Theincentivedoesnotappeartobeeffectiveinrecruitingthosewhootherwisewouldnot p participate.However,theincentivemaybeeffectiveinredirectingresponsetoan \ alternativeresponsemodeinplaceofcostlypersonalvisitinterviews.3 .8.݌H(#(# Ќ     `     h          `    @   Thispageintentionallyblank   `  A@HP  1.0  BACKGROUND (#(# 0X'<XXX'<TheCensusBureauundertakesaprogramofexperimentationduringdecennialcensusesto  measuretheeffectivenessofnewtechniques,methodologies,and/ortechnologiesinthespecial t environmentthatadecennialcensusgenerates.Resultsfromexperimentsform ` recommendationsforsubsequenttestingandultimatelyhelpdesignthenextdecennialcensus. L  TheexperimentdiscussedinthispaperisonecomponentoftheResponseModeandIncentive 8  Experiment(_RMIE_),designedtotesttheeffectofanincentiveandalternativeresponsemode $ t optionsoncensusresponse.ThescopeofthispaperistheanalysisoftheNonresponse  ` component,wheretheeffectofresponsemodesandanincentiveoncensusresponseistested  L  amonghouseholdswhodidnotinitiallymailbackpaperformsafterthestandardCensus2000  8  mailing.Notethatthesametreatmentsarealsotestedinafirstcontactwithasampleof $  households.Analysisofthelattercomponentcanbefoundinareportfrom_Westat_Ԁentitled    ResponseModeandIncentiveExperimentforCensus2000:ResultsforResponseRates.For   furtherdetailsonthedesignandimplementationoftheexperiment#X'<XX0X'<|1#,pleaseseethe_RMIE_   ProgramMasterPlan(_Malakhoff_ԀandSanders,2000).   1.1Motivation \    `     h   Since1960,mostU.S.decennialcensusdatahavebeencollectedviathereturnofapaper 4 questionnaireforhouseholdsrespondingtothemailbackrequest(Cohen,White,andRust,1999),  p andviafacetofaceinterviewsforhouseholdsthatdidnotmailbackcensusforms.Under  \ standardCensus2000procedures,allhouseholdsthatdidnotreturnacensusformbyApril18th, H 2000werevisitedorcalledbyacensusenumerator whocollectedinformationthroughaPaper 4 andPencilInterview(_PAPI_).Sixattemptsweremadebyphoneand/orvisitsbeforeproxydata   weresought.   NonresponseFollowup(_NRFU_)procedures,suchastheonejustdescribed,areextremelycostly.  Forthe1990census,Dillmanetal.(1994)estimatethatnonresponsefollowup(withfacetoface  interviews)co_sted_Ԁasmuchas$17millionforeach1percentdecreaseinthemailbackresponse l rate.Inordertocontrolcosts,theCensusBureauhasaninterestinfindingacostefficient X  techniqueforcollectingdatathatsimultaneouslyencouragescooperation.X'<XXX'< D! 1.2PastResearch #l! #X'<XXX'<=#X'<XXX'<Grovesetal.(1992)exploreheuristicsaswellassurveydesignfeaturessuchasmodeofcontact#X'<XXX'#X'<XXX'< $D # thatinfluencethedecisiontoparticipateinasurvey. Heuristicsrefertoprocessesthatare %0!$ shortcutmeanstomakingadecision.Forexample,socialnorms,suchasthenormof &"% reciprocation,mayinfluencebehaviorinthesurveycontext.#X'<XXX'<?#X'<XXX'<Thisnorm,whichformsthe '#& theoreticalbasisfortheuseofincentivesinsurveys,purportsthatpeoplewhoreceivefavors (#' fromanotherwillreciprocatebyfurnishingafavorforthatperson.Surveyresearchersoften )$( attempttocontrolfeaturesofthesurveyinordertoevokeheuristicsthatmayincrease |*%) participation.#X'<XXX'<@#X'<XXX'< h+&* ЇTwosuchmethodswithwhichresearchershaveexperimentedasmeansofincreasingsurvey  participationare#X'<XXX'<`B#X'<XXX'<Ԁalternativeresponsemodesandincentives.#X'<XXX'<5C#ԀWithrespecttoresponsemode,past  researchsuggeststhatdatacollectionmodecaninfluencesurveyparticipation(Grovesand  Kahn,1979;De_Leeuw_,1993). t  Theexperimentbeingexaminedinthispaperinvestigatestheeffectonparticipationofan L  invitationtorespondthroughanalternativemode(phoneorInternet),whichisquitedifferent 8  fromthedesignofmosttelephonemodecomparisonswhereasamplecaseiscontacteddirectly $ t throughthemodeofinterest.X'<XXX'<Inastudysimilartothecurrentdesign,Dillmanetal.(1994)  ` investigatetheeffectofaninvitationtorespondtoacensustestviathetelephoneinsteadof  L  returningapaperformonresponse.Whiletheadditionofthetelephoneoptiondidnotincrease  8  initialmailbackcompletionrates,theauthorsfindthatablanketfollowupmailingsignificantly $  improvedoverallcompletionrates(withincreasesof0.2%bymail,2.6%bytelephone),when   thefollowuplettercontainedaninvitationtorespondbythetelephonebutdidnotcontaina   replacementquestionnaire.#X'<XXX'<F# Inanotherstudyofmodeeffectsonparticipation,Claytonetal.   (1992)findthataspeechrecognitionsystemwasabletoretainthesameresponserate asreverse   ComputerAssistedTelephoneInterviewing(_CATI_)and_Touchtone_ԀDataEntry(_TDE_)ina p longitudinalpanelsurveyofbusinesses,whenbusinessesthathadpreviouslyreportedby_TDE_ \ and_CATI_Ԁsystemswereswitchedtothespeechrecognitionsystem.Notethatthisfinding H pertainstoabusinesssurveywherethesamefactualinformationisgatheredmonthlyfrom 4 companies,andthereforemaynotgeneralizetoonetimesurveysofhouseholdsorpersons.  p TheuseoftheInternetasapotentialresponsemodeforgeneralpopulationsisjustbeginningto H bestudied.MostsurveyresearchonInternetdatacollectionfocusesonthepotentialforcoverage 4 biasduetodisproportionatelylowerInternetaccessratesamonglowsocioeconomicstatus(_SES_)   groupscomparedtohigh_SES_Ԁgroups(Dillman,_Tortora_,andBowker,1998;Smith,1997;Sweet   andRussell,1996).ModestudiesamongpopulationswithInternetcoveragesuggestthatweb  surveysobtainlowerresponsethanpapersurveys(_Kwak_ԀandRadler,2000);however,embedding  aweboptionintoapapersurveycanincreasetotalresponse(_Elig_,Quigley,andHoover,2000).  X'<XXX'<Inadditiontoalternativeresponsemodes,incentivesareanothermethodtestedasameansof X  increasingresponse.Numerousempiricalstudieslendsupportfortheconclusionthatincentives D! increaseresponserates(Singer,Van_Hoewyk_,_Gebler_,_Raghunathan_,andMcGonagle,1999; 0"  AbreuandWinters,1999;#X'<XXX'30 '" ̐@1075 ̐@ H172 0 ( (16.4) G= )"  <@28<@G28 g]10 *"  <@28 <@ @628@g628 h^20 +" @628 @ n@247n@h247 f\20 ," n@247 n@  @3@f3 @600 -"  @3 @ @  8 - Noincentive ?5 L . @979@?979 G=2L /" @979 @ G171 L 0 (18.0) G=8 1"  ;@27;@G27 g]1L 2"  ;@27 ;@ @579@g579 h^2L 3" @579 @ @i@202@i@h202 f\2L 4" @i@202 @i@  ?1?f1 @60L 5"  ?1 ? @ASQ &6" &Incentive ?5 7 8@9678@?967 G=28" 8@967 8@ G186 9 (19.8) G=:"  <@28<@G28 g]1;"  <@28 <@ @547@g547 h^2<" @547 @ i@206i@h206 f\2=" i@206 i@  @4@f4 @60>"  @4 @ @  > Noincentive ?5 $t? 8@9998@?999 G=2$t@" 8@999 8@ G170 $tA (17.5) G=`B"  ;@27;@G27 g]1$tC"  ;@27 ;@ @593@g593 h^2$tD" @593 @  j@209 j@h209 [Q2$tE"  j@209  j@ # [0 5+%$tF" #  5Internet &G" &Incentive @6 H @1068@@1068 H>3I" @1068 @ H168 J (16.2) G=|K"  @@33@@G33 g]1L"  @@33 @@ (@645(@g645 h^2M" (@645 (@ k@222k@h222 f\2N" k@222 k@  @3@f3 @60O"  @3 @ @  O Noincentive @6 LP H@1042H@@1042 H>3LQ" H@1042 H@ H162 LR (16.0) G=8S"  >@30>@G30 g]1LT"  >@30 >@ @631@g631 h^2LU" @631 @ `k@219`k@h219 [Q2LV" `k@219 `k@ # [05+)LW" #   5Notethatcertaincasesinthenonresponseuniversewerefoundtohavereturnedtheircensus @X formsaftertheApril26cutoff.SinceexperimentalpackagesweremailedonMay2,2000,any ,Y casereturningacensusformbymailpriortoMay4willbeexcludedfromtheanalysissince Z thesecasesarenottruenonrespondents.Atotalof173outofthe6130initialnonresponding  [ households,including11casesthatprovidedbothalatemailreturnandanelectronicreturn,are !\ eliminatedunderthiscriteria= #  5      ׀(seeTable1). "] Duetosecurityconcerns,censuswebadministratorsinsistedthattheInternetdatacollectionsite d$_ forthisexperimentremainactivefornolongerthanonemonth.Therefore,thecensusInternet P% ` sitewastakendownonJune3atmidnighteasterntime.dB  ԍ(20,page1,R1)C  dTheASQandCATIcapabilitieswere <&!a shutdownonJune9.dB  ԍ(21,page1,R1)C  d ('x"b ЀModeresponseratespresentedthroughoutthisreportreflectresponsesobtainedviaelectronic  modesbeforeJune4.   2.4Measurements t Responseratesareameasureofrespondentbehaviorwithregardtothereturnofthe L  questionnaire.Undeliverableforminformation,usedtodistinguishcasesthatreceivedthe 8  experimentalpackage,wasgatheredthroughamanualcheckinofreturnedexperimental $ t packages$ #  6      .Therearetworesponserates:  ` 0  1.Modespecificresponserate:Themodespecificresponserateisdefinedasthe  8  numberofnonblankquestionnairesreturnedbythemodeassignedtothetreatmentgroup $  dividedbythenumberofexperimentalformsmailedoutlessundeliverableforms.The   numeratorcontainsonlythoserespondinghouseholdsthatprovidedtheirdataviathe   moderequestedfortheirpanel. (#(# 0  2.Overallresponserate:Theoverallresponserateisdefinedasthenumberofnon p blankquestionnairesreturnedbyanymodeO@ #  7      ׀(mail,CATI,ASQ,Internet)forthetreatment \ groupdividedbythenumberofexperimentalformsmailedoutlessundeliverableforms.H(#(# Eachratewillbepresentedforthevariousexperimentaltreatmentswithafocusonthemode  p specificresponserateinordertoassesstheeffectoftheincentiveinredirectingresponsetoa  \ newmode,aswellastheefficiencyofthedatacollectiontechnologies.Themodespecificrate H measurestherateatwhichhouseholdsperformedtheprescribedbehaviorinordertoreceivethe 4 incentive,whenhouseholdsareeligiblefortheincentive.Thisrateallowspurecomparisonsof   theefficiencyofthedatacollectionsystems,sincemodeswitches(CATIrolloversorOperator   AssistancecallsthatresultedinCATIinterviews)arenotcountedasrespondents.  Overallresponseratesreflecttotalresponsetothesecondmailing,includingmailreturnswhich  werereceivedupuntilJune14,2000.Comparisonsofoverallresponseratesbetweenthe l incentiveandnoincentivegroupwillrevealwhethertheincentiveincreasedtotalresponsetothe X  secondmailingcomparedtonoincentive. D! 2.5Analysis #l! Theanalysisoftheexperimentaltreatmentsisconductedbymeasuringthepairwisedifferences $D # intheresponseratesamongthetreatmentgroupsandbymodelingthemodespecificresponse  rateusinglogisticregression.Forpairwisecomparisonsinvolvingmorethantwolevelsofa  treatment,theBonferronimultiplecomparisonprocedureiscarriedoutsothatstatementsabout  theentirefamilyofpairwisecomparisonsaremadewhilemaintaininga90percentsimultaneous t confidencelevel.Interpretationofthelogisticregressionresultsusesparameterestimatesof ` significantexperimentaltreatmentstoassessthemagnitudeoftheimpactofthetreatmentona L  householdsoddsofrespondingtothecensusinthepresenceofothertreatments.Additionally, 8  testsofdifferentialincentiveeffectsamongotherexperimentaltreatmentsandpopulationswill $ t taketheformofinteractiontermsinlogisticregressionmodels.Allanalysesareconductedso  ` thatstatementsaboutthesignificanceoftreatmenteffectscanbemadewitha90percent  L  confidencelevel(theCensusBureaustandard).  8  Notethatitemnonresponseanalysiswasoriginallyplannedasapartofthisexperiment.Dueto   extremelylowitemnonresponse,analysesofthisnaturewerenotsupportedbythedata.   3 X,[XX32.6VarianceEstimation   Inordertotakeintoaccountthestratifiedsampledesign,WesVarPCversion3isusedto \ computestandarderrorsforallestimatesandmodels.Ajackknifereplicationmethodologyusing H randomgroupswasusedtoestimatestandarderrors.Sincethereisnoclusteringinthesample 4 andonlytwostratatowhichthesampleisallocated,100elementreplicateswereformedwithin  p eachstratumbyconsecutivelynumberinghouseholdsfrom1to100,afterthehouseholdswere  \ sortedinthesameorderinwhichthesamplewasselected.Duetosmallersamplesizes,25 H replicateswereformedwithineachstratatomodeltheoddsofrespondentsreceivingthe 4 incentiveondemographicsofthenonresponseconversionhouseholds.   X'<XXX'<Qualityassuranceprocedureswereappliedtothedesign,implementation,analysis,and  preparationofthisreport.Theproceduresencompassedmethodology,specificationofproject  proceduresandsoftware,computersystemdesignandreview,developmentofclericaland  computerprocedures,anddataanalysisandreportwriting.Adescriptionoftheproceduresused l isprovidedinthe#X'<XXX'<4#,XXXX'<>#X'<XX,XG#X'<XXX'<Census2000EvaluationProgramQualityAssuranceProcess.  #X'<XXX'<# X   3.0  LIMITATIONS 0" (#(# 3.1PopulationCoverage $X" Thesamplingframeinthisexperimentincludesonlymailout/mailbackareaswithcitystyle %0!$ addresses,withtheexclusionofAccuracyandCoverageEvaluation(A.C.E.)initiallisting &"% samplesandcongressionaladdresses.Moreover,addressesinmailoutareasaddedthrough '#& coverageimprovementprogramsbetweentheprintingofaddresslabelsinJuly1999andthe (#' initialmailoutinMarch2000arenotincludedinthesamplingframewhichmayresultinaslight )$( undercoverageofthetargetpopulation. |*%)  h+&* X'<XXX'<Furthermore,nonEnglishspeakinghouseholds(withtheexceptionofSpanishspeaking  householdsinCATI)aredisproportionatelyunderrepresentedinthisexperimentsincethe  experimentalquestionnairesandformsareonlyavailableinEnglish.#X'<XXX'<#X'<XXX'<  #X'<XXX'"V 6 ' \?" ' ,V \@" , 6,! \A"V 6 ,V \B" , 6,! \C"V 6 3V  \D" 3ASQ 9/!E"V 94.8% F (1555) Ai0!xG" A1.2% OV@2H"[i O5.2% I (1140) Ai0!xJ"V A.7% OV@2K"]i O3.9% L (415) Ai0!xM"V A 2.5% * SV@2N"_i SInternet 9/!HO"iV 93.7% HP (1717) 4*!4Q"i 4 8V)Qi 84.5% HR (1276) 4*!4S"Vi 4 8V)Si 81.4% HT (441) 4*!4U"Vi 4+!U i +Ø XX'<*statisticallysignificantwhenthefamilywiseerrorrateiscontrolledusingBonferroniat=.1forallcomparisons#X'<X Ø# PU Ø XX'<**Notethatthenumbersisthedifferencecolumnmaybeslightlydifferentfromthecomputationsusingtherates V presentedduetoroundingerror.#X'<X Ø# W Inaccordancewiththehypothesis,CATIelicitsconsistentlyhigherresponsethantheInternet, 8!Y regardlessofwhichpopulationisstudied.Thedisagreementwiththehypothesisisrelatedtothe $"tZ factthattheASQdidnotperformaswellasexpected.CATIobtainshigherresponsethanASQ, #`[ andASQdoesnotgainhigherresponsethantheInternetaregressiـ(withtheexceptioninlowcoverage #L\ areas,seebelow).Thereissomeevidencetosuggestthatthesefindingsmaybedueto $8 ] difficultiesinusingtheASQ.FeedbackfromcensusASQtestersrevealedthatthesystemwas %$!^ somewhatdifficulttouse.dB  ԍ(26,allpages,R1)C  dThelevelofresponsedoesnotdifferbetweenCATIandASQwhen &"_ callsandrolloverstoCATIarepermittedfromhouseholdsassignedtoASQ,suggestingthat '"` usabilityissuesratherthanmodepreferenceareresponsiblefortheASQandCATIdifference.dB  ԍ(18,page13,R5)C  d (#a Lookingattheeffectofresponsemodealternativesinlowcoverageareas,theresultsagreewith p*%c theexpectationthatCATIandASQgainequallevelsofresponseandthatthatlevelishigher \+&d thanthatoftheInternet.ThesignificantdifferencesbetweenCATIorASQresponseandthe  InternetmaysuggestthatInternetaccessisespeciallylowamongthissubpopulationwhichis  expectedtoresembledemographicallythepopulationwithoutInternetaccess(Newburger,1997).  Inordertodetermineifthealternativemodesattractdifferentrespondents,demographic ` characteristicsofallrespondentswerecomparedbymodesinTable3.Thereissomeevidence L  frompastresearchindicatingthatolderpersonsarelesslikelytorespondoverthetelephone 8  (GrovesandCouper,1998).Notethat,intheabsenceofinformationregardingwhocompleted $ t thequestionnaireinthehousehold,Person1characteristicsareusedtodescribetherespondent.  ` Admittedly,pastresearchindicatesthatPerson1isnottherespondentroughly30%ofthetime  L  (DeMaioandBates,1990).However,nodifferentialeffectsregardingthisassumptionare  8  expectedacrossresponsemodes. $  *EVG~d d9dd 9dd edd edd edd edd edd eRV\(#(#,Q dd ,dd ,dd ,dd ,dd +  $   $Table3.DemographicComparisonsofNonresponseConversion $t  HouseholdsbyActualResponseModeUseddB  ԍ(27,pages3and4,R1)C  d >4)< "  i >Factor RVA289 i RResponseModeUsed >4)8"  V > (i T (Mail =i,!h"i =CATI =i,!h"i =ASQ =i,!h"i =Internet 2(&h"  i 2MeanageofPerson1 I?8  I@50.1 I@I50.1 j`38"  I@50.1  I@ YF@44.7YF@j44.7 j`38" YF@44.7 YF@ B@37.7B@j37.7 j`38" B@37.7 B@ @D@40.5@D@j40.5 ?538" @D@40.5 @D@ ?PercentPerson1Black 'h '12.8% 'h" '16.7% 'h" '10.6% 'h" '5.1% h" PercentPerson1Hispanic '8 '7.8% '8 " '8.3% '8!" '3.6% '8"" '5.1% !8#" !PercentRenteroccupied h$ Households 9/!T% 938.9% 9/!h&" 942.0% 9/!h'" 943.2% 9/!h(" 942.4% 0&!h)" 0PercentHouseholdsinLCA 9/!$* 917.0% 9/!$+" 919.7% 9/!$," 917.8% 9/!$-" 98.5% 7i&!$." 7MeanHouseholdSize biQ!T/i @2.70@b2.70 irBT0" @2.70 @i ףp= @2.73ףp= @2.73 irBT1" ףp= @2.73 ףp= @i RQ@2.04RQ@2.04 irBT2" RQ@2.04 RQ@i p= ף@2.58p= ף@2.58RHFT3" p= ף@2.58  p= ף@i RCrossmodedifferencesforeachfactorarecomparedwhilecontrollingthefamilywiseerrorrate \ 4 at=.1usingtheBonferroniMCP.TheresultsrevealthatASQrespondentsaresignificantly H!5 youngerandresideinhouseholdswith,onaverage,fewerpeoplethanbothmailandCATI 4"6 respondents.dB  ԍ(28,pages1and2,R1)C  dCATIrespondentsaredisproportionatelymoreBlackwithmorehouseholds  #p7 residinginlowcoverageareascomparedtoInternetrespondents.dB  ԍ(28,pages1and2,R2)C  Ԛd  $\8 GiventhatInternetaccessisloweramonglowsocioeconomicgroups,itisnotsurprisingtofind %4!: thatInternetrespondentstendtobelessBlackandmorelikelytoresideinhighcoverageareas & "; thanCATIrespondents.ThedifferencebetweenASQandCATIaresomewhatunexpected, ' #< especiallywithrespecttohouseholdsize.Itispossiblethatrespondentswithlargehouseholds (#= whousedtheASQrealizedveryquicklythatthesystemwassomewhattimeconsuming,and )$> quicklydisconnectedfromthecomputerwhereasCATIrespondentshadahardertime *%? disconnectingduetotheinteractionwiththeinterviewer.Moreover,thedifferenceinage l+&@ betweenCATIandASQrespondentsmaybeduetomorefamiliaritywithnewertechnologieson  thepartofyoungerpersonscomparedtoolderrespondents.Thesesuggestionsaremerely  anecdotalandtherearenodatatosupportordisconfirmthesesuggestions.  4.2Whatistheeffectoftheincentiveonresponse? ` Pastresearchprovidesoverwhelmingevidencethatincentivesincreaseresponsecomparedtono 8  incentives,especiallyamongpopulationsthatarepoorwithahighconcentrationofnonwhites $ t (Kulka,1994;Singer,forthcoming)andintheabsenceofothermotivatingfactors  ` (Singer,forthcoming).Givenpastfindings,itisexpectedthattheincentivewillincrease  L  response,withalargereffectinlowcoverageareascomparedtohighcoverageareas.Similarly,  8  theincentiveeffectwillbegreaterintheASQmodeduetotheabsenceofaninterviewer $  comparedtoCATI,andinCATIcomparedtotheInternetduetoInternetaccessibilitybarriers   maskingtheincentiveeffect.Moreover,itisexpectedthatincentiverespondentswillbeyounger   andmoreraciallyandethnicallydiversethannonincentiverespondents.   Inordertoassesstheeffectoftheincentivewithinandacrossresponsemodes,responseratesin p Table4werecomputedforeachexperimentaltreatmentalongwithpairwisedifferencesbetween \ theincentiveandnonincentivegroupswithinandacrosseachresponsemode. H  Table4.ModeSpecificandOverallResponseRates,SampleSizes,andPairwise  p DifferencesbetweenIncentiveandNoIncentiveGroupswithinandacrossResponseModes   \ *V)d dQ dd Q dd dd dd dd EVG(#(#,9dd ,dd ,dd ,dd ,edd ,dd ,edd +  (LL (Mode <2#`"} < ModeSpecific ` ResponseRate  L dB  ԍ(18,pages5and6,R6)C  d 7X$8" 7 Difference  ` dB  ԍ(18,page6,R9)C  d KA2L" 66X K OverallResponseRate  ` ЀdB  ԍ(18,pages5and6,R8)C  Ԛd 7X$L" 7 Difference  ` dB  ԍ(18,page6,R10)C  d B82L " 66tX B ! T  !Incentive '!" 'Noincentive +!"" + ! T" !Incentive '#" 'Noincentive +!$" +  T$ CATI  8% 8.8% 8& (875) '$t'" '6.7% 8( (781) 0X$t)" 02.1% 6,!8*"X 614.4% 8+ (875) '$t," '14.5% 8- (781) 0X$t." 0Є.1% -#!8/"X -ASQ   0 6.4%  1 (753) '!2" '3.4%  3 (802) 0X!4" 0 3.0% * 6,! 5"X 615.2%  6 (753) '!7" '11.9%  8 (802) 0X!9" 0 3.3% * 4X#! :"X 4Internet 4X##`;X 43.9% #`< (867) =X,!#L="X =3.4% #`> (850) ?XX,!#L?"X ?.5% =X,!#`@"XX =11.9% #`A (867) =X,!#LB"X =13.2% #`C (850) ?XX,!#LD"X ?Є1.3% -#!#`E"XX -TotaldB  ԍ(18,page13,R7)C  d  |% F 6.4% '|% G" '4.5% 0X|% H" 0 1.9% * 6,!|% I"X 613.8% '|% J" '13.2% 0X|% K" 0.6%1'%|% L"  X 1Ø XX'<*indicatesstatisticalsignificancewhen=.1.#X'<X Ø3#  &!L  Resultsinthetableabovelendsupportforthehypothesisthattheincentiveincreasesmode t(#N specificresponsecomparedtonoincentive.Discussionoftheoverallresponseratecomparisons `)$O islocatedinsection4.4.  L*%P  Table5presentslogisticregressioncoefficientswhenthemodespecificresponserateis $,t'R regressedontheexperimentaltreatmentsaswellassomecontrolvariables.Logisticregression  analysisallowsanassessmentoftheeffectofthetreatmentsonresponseinthepresenceofother  treatmentsorcontrolvariables.Forexample,theSimpleModelinvestigatestheeffectofthe  incentiveonresponsewhilecontrollingforstrata(asaproxyforsocioeconomicstatus)underthe t assumptionthattheeffectisconsistentwithineachresponsemode.Thepurposeofthemodels ` withtheinteractiontermsistodetermineiftheincentiveeffectdiffersamongstrataandresponse L  modes.TheIncentiveStrataInteractionModelhelpsdeterminewhethertheeffectofthe 8  incentiveonresponsediffersbasedonthestratumtowhichitisadministered.Lastly,the $ t IncentiveModeInteractionModelrelaxestheassumptionsoftheSimpleModeltotestwhether  ` theincentive(versusnoincentive)increasesresponsedisproportionatelyamongtheresponse  L  modes.  8  *(V*~dd9dd 9dd dd dd edd edd edd eV)(#(#,` dd ,dd ,4dd ,Sdd +  $$ $  $Table5.LogisticRegressionCoefficientsPredictingtheLogOddsof 8  RespondingtotheCensusthroughtheAssignedMode :0)P "  i :PredictorVariables 6,!L i 6 SimpleModel  L  dB  ԍ(29,pages1and2,R1)C  d 6,!8"i 6 IncentiveStrata L  InteractionModel  8 dB  ԍ(29,pages2and3,R2)C  Ԛd 6,!$"i 6 IncentiveMode L  InteractionModel  8 dB  ԍ(29,pages3and4,R3)C  Ԛd ;1&$"  i ;Mode: 'T ' 'T" ' 'T" ' T" ЀInternet=1 '$ ' .302 * I?$" ~jt?.012~jt?I.012 j`3$" ~jt?.012 ~jt? 9v?.0139v?j.013 ?53$" 9v?.013 9v? ?ЀCATI=1 'X ' .496 * 'X " ' .717 * 'X!" ' .717 * X"" ЀASQ=1 ',# 'Є ',$" 'Є ',%" 'Є ',&" 'Incentive: '\' ' '\(" ' '\)" ' ,"\*" ,ЀIncentive=1 ',+ ' .374 * ',," ' .888 * ',-" ' .679 * #,."  # CensusArea(strata): 'i/ ' 'i0" ' 'i1" ' i2" ЀHighCoverageArea=1 '93 ' .567 * '94" ' .725 * '95" ' .568 * 96"  Interactions: 'm!7 ' 'm!8" ' 'm!9" ' m!:" ЀCATI*Incentive '"=; ' J@"=<" \(\׿-.365\(\׿JЄ.365 lb4"==" \(\׿-.365 \(\׿ K׿-.364K׿lЄ.364 @64"=>" K׿-.364 K׿ @ЀInternet*Incentive 'm$? ' 'm$@" ' .534 * 'm$A" ' .537 * !m$B" !ЀIncentive*Strata 9/!%A!C 9 \R!%A!D" x&1п-.253x&1п\Є.253 [QC%A!E" x&1п-.253 x&1п [ 0V#!%A!F" 0Intercept ]VP!q'"GV !rh -3.616!rh ]Є3.616 VsDq'"H" !rh -3.616 !rh V Fx-3.934FxЄ3.934 VsDq'"I" Fx-3.934 FxV Cl-3.803ClЄ3.803 SVFDq'"J" Cl-3.803 ClV SЄ2LogLikelihood ^VQ!(A$KV = ףp@2026.36= ףp@^2026.36 VuE(A$L" = ףp@2026.36 = ףp@V (\@2023.34(\@2023.34 VuE(A$M" (\@2023.34 (\@V (\@2023.89(\@2023.89 TJE(A$N" (\@2023.89 (\@V TDegreesofFreedom XN!q*%Oi  @4@X4 vl?q*%P"  @4 @i  @7@v7 vl?q*%Q"  @7 @i  @6@v6OECq*%R"  @6  @i OØ XX'<*indicatesstatisticalsignificancewhen=.1#X'<X Ø}N# +&R ЇBeforetestingtheincentiverelatedhypotheses,Inotesomeconsistencieswithregardtocensus  andstratificationexpectationsaswellasearlierresults.First,thesignificanceofthestratum  termintheSimpleModelinTable5confirmsexpectationsthatcensusresponseislowerinlow  coverageareasthanhighcoverageareas.Withregardtoincentiveandresponsemodefindings, t testsofparameterestimatesintheSimpleModelconfirmthatCATIobtainshigherresponsethan ` theInternetandASQwhilecontrollingfortheincentivetreatment,andthattheincentiveeffect L  holdswhilesimultaneouslycontrollingforresponsemodeandstratum. 8  4.2.1IncentiveStrataInteraction  ` TheIncentiveStrataModelinTable5isformedtodetermineiftheincentiveismoreeffectivein  8  increasingresponseinlowcoverageareas(highBlackandHispanicandrenterconcentration) $  comparedtohighcoverageareas.Asignificancetestofthisinteraction(Incentive*Strata=   .253)indicatesthattheeffectoftheincentiveonresponseisnotsignificantlydifferentbetween   highandlowcoverageareas,whilestatisticallycontrollingforresponsemode.Thisfinding   contradictstheinitialhypothesisandpastliteratureofamorepronouncedincentiveeffectamong   lowerSESpopulationscomparedtootherpopulations(Kulka,1994;Singer,forthcoming)and p thereforemeritsfurtherinvestigation.Table6belowshowstheeffectoftheincentiveonmode \ specificresponsewithinandacrossmodesforeachstratumpopulation. H @* Table6.ResponseRates,SampleSizes,andResponseRateDifferencesbetweenIncentive  p andNoIncentiveGroupswithinandacrossResponseModesinHighandLowCoverage  \ Areas  H *.V/dd` dd ` dd 4dd 4Sdd S(V*(#(#,9dd ,dd ,dd ,edd ,dd ,dd ,edd +  (44 (Mode EX2#4  EHighCoverageAreas FX3$HX FLowCoverageAreas =3$HX = % d % ModeSpecific  ResponseRate   dB  ԍ(18,pages9and11,R11)C  d 7X$ 7 Difference   dB  ԍ(18,pages11and12,R12)C  Ԛd KA2  66X K ModeSpecific ! ResponseRate  " dB  ԍ(18,pages9and11,R13)C  Ԛd 7X$# 7 Difference  $ dB  ԍ(18,pages11and12,R14)C  Ԛd B82% 66X B !  % !Incentive ' p&" 'Noincentive +! p'" + !  ' !Incentive ' p(" 'Noincentive +! p)" +   ) CATI   * 9.9%  + (628) '!," '7.3%  - (579) 0X!." 02.6% 6,! /"X 66.1%  0 (247) '!1" '5.0%  2 (202) 0X!3" 01.1% -#! 4"X -ASQ   #\5 6.8%  #\6 (547) '#H7" '3.7%  #\8 (593) 0X#H9" 0 3.1% * 6,! #\:"X 65.3%  #\; (206) '#H<" '2.4%  #\= (209) 0X#H>" 02.9% 4X#! #\?"X 4Internet 4X#x% @X 44.5% x% A (645) =X,!d&!B"X =4.4% x% C (631) ?XX,!d&!D"X ?.1% =X,!x% E"XX =2.3% x% F (222) =X,!d&!G"X =.5% x% H (219) ?XX,!d&!I"X ? 1.8% * -#!x% J"XX -TotalB  d(18,pages15and16,R15)dC   '4#K 7.0% ''4#L" '5.1% 0X'4#M" 0 1.9% * 6,!'4#N"X 64.6% ''4#O" '2.6% 0X'4#P" 0 2.0% *1'%'4#Q"  X 1Ø XX'<*indicatesstatisticalsignificancewhen=.1.#X'<X Ø$e# )T$Q Inaccordancewiththelogisticresults,bothstratashowanoverallincentiveeffectofroughlythe *&S samemagnitude(1.9%forHCAversus2.0%forLCA)contrarytoexpectationsbasedonpast +&T research(Kulka,1994;Singer,forthcoming). Thereareatleasttwopossiblereasonsforthis  discrepancy.First,stratum,whileagoodindicatorofcensusresponse,isbasedon1990tract  leveldataandmaynotbeasuitableproxyvariableforSES.Limiteddataonnonrespondents  makeitimpossibletotestthistheory.Secondly,legalityandsponsorshipdifferencesbetween t theU.S.decennialcensusandsurveysmayexplainthisdiscrepancy.Certainpeople,suchas ` illegalimmigrantsandfugitives,maydeliberatelyavoidthecensus.Iflowcoverageareas L  containahigherconcentrationofthesepeoplethanhighcoverageareas,itispossiblethatthese 8  resultsreflectthatfactthattheincentivedoesnotincreaseresponsefromthosewhoare $ t intentionallyavoidingthecensus.  ` 4.2.2IncentiveModeInteraction  8  Untilthispoint,theincentiveeffecthasbeendiscussedwithoutregardtoresponsemode.The   IncentiveModeModelinTable5isformedtoallowcomparisonsoftheincentiveeffectsacross   thethreemodes.RecallthatlargereffectswereexpectedinASQcomparedtoCATIduetothe   absenceofaninterviewerasamotivator.Significancetestsoftheinteractionparametersinthe   IncentiveModeInteractionModelsuggestthattheincreaseinmodespecificresponseduetothe p incentiveisnotsignificantlydifferentbetweenASQandCATI(CATI*Incentive=.364).The \ effectoftheincentiveintheInternetmodeissignificantlylowerthanASQ,butisnot H significantlydifferentfromtheeffectinCATIasdeterminedbyatestforadifferenceinthe 4 interactionparameters(p=.556).dB  ԍ(29,page4,R4)C  ԚdThelackofadifferentialincentiveeffectbetweentheself  p administeredandCATImodesmaybeduetothefactthatthecalltoparticipateisrespondent  \ initiatedineachmodeandtherefore,theintervieweronlyactsasamotivatorinCATIoncethe H respondenthasdecidedtocooperate. 4 4.3IncentiveEffectonResponseDistribution   Finally,logisticregressioncoefficientsinTable7allowanassessmentoftheeffectofthe  incentiveonthedemographicdistributionofmail,CATI,ASQ,andInternetrespondents.  Specifically,thisregressionmodelincludesallrespondents,regardlessoftheirexperimental l panelassignment,inanattempttodeterminewhichfactorsareassociatedwithhouseholdsthat X  performedtheprescribedbehaviortoreceivetheincentive. D!   )$( *?VB~Fdd9dd 9dd dd edd edd dd edd e.V/(#(#,/ dd ,dd +  $ $Table7.LogisticRegressionCoefficientsPredictingtheLog d  OddsofReceivingtheIncentiveAmongRespondents :0),|"  i :Factor @i/!(i @ Model  ( dB  ԍ(30,pages1and2,R1)C  Ԛd 2(&"  i 2AgeofPerson1 * D  * .015 * -#!D " -Person1Black=1 LB  d;O?.239d;O?L.239 NDB  " d;O?.239 d;O? NPerson1Hispanic=1 MCH   Q-.030QMЄ.030 RHCH  " Q-.030 Q RRenteroccupiedHousehold=1 [Q!  Mb?.188Mb? [.188 QGB " Mb?.188 Mb?  QHighCoverageArea=1 \R!H  x&-.067x& \Є.067 RHCH " x&-.067 x&  RFemale=1 [Q!   X9v?.031X9v? [.031 QGB " X9v?.031 X9v?  QHouseholdSize \R!H  K-.091K \Є.091 [VVJCH" K-.091 K  [Intercept cVVR!VV jt-.043jtcЄ.043 WMH" jt-.043  jtVV WЄ2LogLikelihood ]S!Z  Ɇ@729.20Ɇ@ ]729.20 ZiIDZ" Ɇ@729.20 Ɇ@  ZDegreesofFreedom _iN!*i  @7@_7OEC*"  @7 @i O  Ø XX'<*indicatesstatisticalsignificancewhen=.1#X'<X Ø|# F ThemodelsuggeststhatPerson1inhouseholdsreceivingtheincentivetendstobeyoungerthan  Person1inhouseholdsnotreceivingtheincentive,wheretheoddsofreceivingtheincentive  decreaseby7.2% foreach5yearincreaseintheageofPerson1.Thisfindingmaysuggestthat ~ theincentiveismoreattractivetoyoungerpersons.Conversely,sincetheincentivewasonly j activatedforthosewhotriedanewresponsemode,perhapsyoungerpeoplearemorelikelyto V usenewtechnology.Itisimpossibletocontrolfortheeffectsofmodeinthisstudygiventhatan B  alternativemoderesponsewasrequiredinorderforahouseholdtoreceivetheincentive.Anage . ~! comparisonofmailandelectronicmoderespondentsrevealsthatmailrespondentsareon !j" averageolder(50.4)thanelectronicmoderespondents(42.1),suggestingthattheproposed "V# incentiveeffectonyoungerpeoplemaybeduetomorewillingnesstotryanewmode #  9      .dB  ԍ(30,pages $ t 6and7,R4)C  d "B$ Otherwise,whilecontrollingforage,sex,andhouseholdssizethereisnoevidencetosuggest #.% thatincentivesdisproportionatelyrecruitnonwhitesorrentersFT #  10      . $ &  4.4OverallFindings &!( ЇItisinterestingtonotethattheincreaseinmodespecificresponseduetotheincentiveis  significantwhenthethreeresponsemodesarecombined,yettheeffectoftheincentiveis  diminishedwhenoverallresponsetothesecondmailingisconsideredinTable4,exceptfor  ASQ.Thisfindingsuggeststhattheincentivemerelycausesresponsetoberedirectedto t alternativemodesratherthanencourageresponsetothecensus. Itisunclearastowhythis ` findingisnotreplicatedintheASQmode.EmpiricaltestsoftheASQsystemledto L  observationsthatthesystemisgenerallydifficulttouseandtimeconsuming.dB  ԍ(26,allpages,R1)C  dPerhapsthosewho 8  wereofferedtheASQphonenumberthrewawaytheirpaperquestionnairesinhopesofusingthe $ t telephonetocompletetheform.Uponcallingthesystemanddeterminingthatresponsetoa  ` machineratherthanaliveinterviewerwasrequired,perhapsrespondentswhodidnotreceivethe  L  incentivewerenotmotivatedtoworkthroughthesystemdifficulties.Thissuggestionismerely  8  speculativeandthereisnodatatosupportordisconfirmthistheory. $  FromaNonresponseFollowupperspective,itisquitenotablethataround13%participation(see   Table4)wasobtainedfromcasesthatdidnotinitiallyreturnthequestionnaire,especiallysince   replacementquestionnaireswerenotincludedinthesecondmailing.Sinceapproximately4to6   percentofpeoplerespondedusinganalternativemode(seeTable4),around6to9percent p returnedthequestionnairethatwasincludedintheinitialMarchmailing.Thisfindingsuggests \ thatasecondmailingcontainingarequestforcensusparticipationmayinitselfbeamethodfor H increasingparticipationinthecensusaswellasloweringtheamountofcostlypersonal 4 interviews.Pastcensustestsindicatethatfollowuplettersbothwithandwithoutreplacement  p questionnairescanbeeffectiveatincreasingresponse(seeDillmanet.al.(1994),Memorandum  \ fromLesliethroughKilliontoThompson(1997)). H  5.  0  RECOMMENDATIONS  (#(# ExaminationoftheresponsemodealternativesrevealsthatCATIobtainsthehighestlevelof  responsecomparedtoASQandtheInternet.Itshouldnotbeinferredfromthispaperthatthe  peoplepreferCATIovertheInternetfordatacollection.Internetaccessibilitylimitationsamong  thepopulationinthisexperimentconfoundtheresponseratecomparisonsamongthemodes.As l InternetaccesscontinuestospantheUnitedStatespopulation,experimentstestingthefeasibility X  ofthismethodforcensusdatacollectionshouldcontinuetobetested. D! Consistentwithpastfindings,theuseofanincentiveinthisexperimentincreasesresponsetothe #l! alternativemodes;however,theeffectsdisappearwhentotalresponsetothesecondmailingis $X" examined.Therefore,theincentiveinthisexperimentissuccessfulintransferringresponsethat $D # wouldhaveotherwisebeenobtainedbymailtoadifferentmode,butnotinrecruitinghouseholds %0!$ withnointentionofresponding. &"% Incontrasttopastincentiveliterature,thereisnoevidenceofincreasedincentiveeffectswithin (#' areasoflowcensuscoverage(withhighproportionsofnonwhitesandrenterunits)comparedto )$( highcoverageareas,whichmaybeduetothefactthatcoverageareaisnotagoodproxyforSES. |*%) Moreover,thereisnoevidencethatincentivesaremorepowerfulatincreasingresponseinthe h+&* A@ A  A  absenceofaninterviewerasamotivator.ItispossiblethatASQdifficultiesaswellasInternet  accessibilityissuesconfoundtheincentiveeffectwithineachmode.Moreover,theinterviewer  wasonlyamotivatingsourceinkeepingtherespondentfromdiscontinuingtheinterview,since  theinitialcontactwasrespondentinitiated.Perhapsincentiveswouldprovetobemosteffective t intheselfadministeredmodesifthecasesassignedtotheCATImodewerecontacteddirectlyby ` theinterviewerasinatraditionalsurveysetting. L  Comparisonsofrespondentdemographicsrevealthattheincentiveseemstoattractyounger $ t respondents;however,thisfindingisconfoundedwiththeinfluenceofthealternativeresponse  ` modeoptions.Thereissomeevidencetosuggestthatyoungerpersonsmaybeinfluencedbythe  L  chancetouseanewmode.  8  Takentogether,theresultsprovidesomeguidanceforfuturedecennialcensuses.Duetothe   extremelylowresponseratesinthisstudy,itisclearthatincentivesandresponsemodeoptions   arenoteffectivetoolsforincreasingresponseamongtypicalcensusnonrespondents.The   incentive,whilesomewhateffectiveindirectingresponsetoaparticularmode,hasnooverall   effectontotalresponsetothecensus.Moreover,theresponsemodecomparisonsinthisstudy p areconfoundedduetoInternetaccesslimitationsaswellasASQsystemtechnologylimitations. \ Therefore,therecommendationisforfurthertestingintheyearsbeforethe2010census.As H Internetaccessspreadsandtechnologyadvances,thismodemayquicklybecomeatimeefficient 4 wayofrespondingtothecensus.  p Asidefromanyeffectoftheexperimentaltreatments,itmaybeworthwhiletoinvestigatethe H effectofsendingasecondcensusrequesttohouseholdsfailingtoanswerthefirstrequestsince 4 13%participationwasgainedfromtheuseofasecondmailingonly(seeTable4).Although   thereisnoevidencethatthistechniquecouldpotentiallyreplacethepersonal/telephone   interviews,itmaysuccessfullylowerthenumberofcasesthatneedtobefollowedupusingthe  expensiveapproaches.  Acknowledgments:TheauthorwouldtothankLarryMalakhoff,DeniseSanders,Randall l Neugebauer,DebbieBolton,andDennisStoudtfortheirinitiationandimplementationofthis X  experiment.Thisanalysiswouldnothavebeenpossiblewithouttheirhardwork,support,and D! persistenceinthisexperiment.SpecialthankstoLarry,whowasinvolvedinallstagesofthe 0"  implementationoftheexperimentandcontactswiththecontractor.Theauthorswouldalsolike #l! toextendathankyoutoDavidCantorandhisstaffatWestat,whodevelopedandmanagedthe $X" datacollectionforCATIandASQ.AdditionalthankstoJimCopeandCharlesKahnfortheir $D # assistancewiththedatadelivery.Lastly,specialthankstoBobGroves,JoanHill,andHenry %0!$ Woltmanfortheiranalyticalandeditorialadvice. &"%   X'<XXX'<#X'<XXX'<ˢ#   REFERENCES: (#' Abreu,D.A.,andWinters,F.(1999) UsingMonetaryIncentivestoReduceAttritioninthe |*%) ЀSurveyofIncomeandProgramParticipation,ProceedingsoftheSurveyResearchMethods h+&* ЀSectionoftheAmericanStatisticalAssociation.  @* D      L    !         "   Baumgartner,R.andRathbun,P.(1996) PrepaidMonetaryIncentivesandMailSurvey ` ЀResponseRates,ProceedingsoftheGovernmentStatisticsSectionoftheAmericanStatistical L  ЀAssociation,206209. 8  Berry,H.,andKanouse,D.E.(1987) PhysicanResponsetoaMailedSurvey,PublicOpinion  ` ЀQuarterly,54,102114.  L  Cecco,Kevin(1994) CharacteristicsofRespondingandNonrespondingHouseholdsfromthe $  Ѐ1990DecennialCensus,CensusBureauMemorandumfromThompsontoJones,March29,   Ѐ1994.   Church,AllanH.(1993) EstimatingtheEffectofIncentivesonMailSurveyResponseRates:   ЀAMetaAnalysis,PublicOpinionQuarterly,57,6279."XXXX'< p #X'<XX"X#Clayton,R.L.,andWinter,D.L.(1992) SpeechDataEntry:ResultsofaTestofVoice B ЀRecognitionforSurveyDataCollection,JournalofOfficialStatistics,8:377388. .~ Cohen,M.L.,White,A.A.,andRust,K.F.,eds.(1999)MeasuringaChangingNation:Modern V ЀMethodsforthe2000Census,NationalAcademyPress,Washington. B DeLeeuw,E.D.(1993) ModeEffectsinSurveyResearch:AComparisonofMail,Telephone  ЀandFacetoFaceSurveys,BMS,41,315.  DeMaio,T.J.,andBates,N.A.(1990) WhoFillsOuttheCensusForm?,Proceedingsofthe  ЀSurveyResearchMethodsSectionoftheAmericanStatisticalAssociation. z Dillman,D.A.,Tortora,R.D.,andBowker,D.(1998) PrinciplesforConstructingWeb R  ЀSurveys,SESRCTechnicalReport9850,Pullman,Washington. >! Ѐhttp://survey.sesrc.wsu.edu/dillman/papers.htm *"z  Dillman,D.,West,K.,andClark,J.(1994) InfluenceofanInvitationtoAnswerbyTelephone $R" ЀonResponsetoCensusQuestionnaires,PublicOpinionQuarterly,58,557568. $> # Dillman,D.A.(1996) TokenFinancialIncentivesandtheReductionofNonResponseErrorin &"% ЀMailSurveys,ProceedingsoftheGovernmentStatisticsSectionoftheAmericanStatistical '#& ЀAssociation. (#' Edmonston,B.,andSchultze,C.(1995)ModernizingtheU.S.Census,PanelonCensus v*%) ЀRequirementsintheYear2000andBeyond,CommitteeonNationalStatistics,National b+&* ЀResearchCouncil,Washington,DC,NationalAcademyPress.  Elig,T.W.,Quigley,B.,andHoover,E.C.(2000) ResponseRateEffectsofMakingPaperor  ЀWebthePrimaryMode,PaperPresentedattheConferencefortheAmericanAssociationfor t ЀPublicOpinionResearch,2000. ` Groves,R.M.,Cialdini,R.B.,andCouper,M.P.(1992) UnderstandingtheDecisionto 8  ЀParticipateinaSurvey,PublicOpinionQuarterly,56:475495. $ t Groves,R.M.andCouper,M.P.(1998)NonresponseinHouseholdInterviewSurveys,New  L  ЀYork:JohnWiley&Sons.  8  Groves,R.M.andKahn,R.L.(1979)SurveyResearchbyTelephone,NewYork:Academic   ЀPress.   Groves,R.,Singer,E.,Corning,A.,Bowers,A.(1999) ALaboratoryApproachtoMeasuring   ЀtheEffectsonSurveyParticipationofInterviewLength,Incentives,DifferentialIncentives, p ЀandRefusalConversion,JournalofOfficialStatistics,15,2,251268. \ Heberlein,T.A.,andBaumgartner,R.(1978) FactorsAffectingResponseRatestoMailed 4 ЀQuestionnaires:AQuantitativeAnalysisofthePublishedLiterature,AmericanSociological  p ЀReview,43,4,447462.  \ Hopkins,K.D.,Hopkins,B.R.,andSchon,I.(1988) MailSurveysofProfessionalPopulations: 4 ЀTheEffectsofMonetaryGratuitiesonReturnRates,JournalofExperimentalEducation,56,   Ѐ173175.   Irving,Larry(1999) FallingThroughtheNet:DefiningtheDigitalDivide,Departmentof  ЀCommerce:NationalTelecommunicationsandInformationAdministration.  James,J.M.,andBolstein,R.(1990) TheEffectofMonetaryIncentivesandFollowup X  ЀMailingsontheResponseRateandResponseQualityinMailSurveys,PublicOpinion D! ЀQuarterly,54,346361. 0"  Kulka,R.A.(1994)TheUseofIncentivestoSurvey HardtoReachRespondents:ABrief $X" ЀReviewofEmpiricalResearchandCurrentPractice,Paperpreparedfortheseminaron New $D # ЀDirectionsinStatisticalMethodologySponsoredbyCouncilofProfessionalAssociationson %0!$ ЀFederalStatistics(COPAFS),Bethesda,MD,May2526,1994. &"% Kwak,N.,andRadler,B.(2000) AComparisonbetweenMailandWebSurveys:Response (#' ЀPattern,RespondentProfile,DataQuality,andConstructAssociation,Draftpapersubmitted )$( ЀtoPublicOpinionQuarterly,June6th,2000. |*%)  h+&* Lengacher,J.E.,Sullivan,C.M.,Couper,M.P.,andGroves,R.M.(1995) OnceReluctant,  ЀAlwaysReluctant?EffectsofDifferentialIncentivesonLaterSurveyParticipationina  ЀLongitudinalStudy,ProceedingsoftheSurveyResearchMethodsSectionoftheAmerican  ЀStatisticalAssociation,10291034. t Leslie,Teresa. U.S.2000CensusTest!AdditionalResultsfromtheMailResponseAnalysis, L  ЀMemorandumtoJohnH.ThompsonthroughRuthAnnKillion,April3,1997 8  Malakhoff,LawrenceandSanders,Denise(2000)ProgramMasterPlanfortheResponseMode  ` ЀandIncentiveExperiment,May2,2000.  L  Newburger,E.C.(1997) ComputerUseintheUnitedStates,CurrentPopulationReports, $  ЀP20522,U.S.CensusBureau.   Shettle,C.,andMooney,G.(1999) MonetaryIncentivesinU.S.GovernmentSurveys,   ЀJournalofOfficialStatistics,15,2,231250."XXXX'<   #X'<XX"X<#SingerE.,VanHoewyk,J.,Gebler,N.,Raghunathan,T.,andMcGonagle,K.(1999) TheEffect V ЀofIncentivesinInterviewermediatedSurveys,JournalofOfficialStatistics,15,2,217230."XXXX'< B #X'<XX"Xl#Singer,E.,Groves,R.,Corning,A.(1999) DifferentialIncentives:BeliefsaboutPractices, d ЀPerceptionsofEquity,andEffectsonSurveyParticipation,PublicOpinionQuarterly,63: P Ѐ251260. < Singer,E.(forthcoming) TheUseofIncentivestoReduceNonresponseinHouseholdSurveys,  ЀChapterforthcominginbookentitledSurveyNonresponse.  Smith,C.B.(1997) CastingtheNet:SurveyinganInternetPopulation,JournalofComputer  ЀMediatedCommunications,3,1.4#  O  5  http://www.ascusc.org/jcmc/vol3/issue1/smith.htm6@ OT  7  t Sweet,E.andRussell,C.(1996) ADiscussionofDataCollectionviatheInternet, L  ЀProceedingsoftheSurveyResearchMethodsSectionoftheAmericanStatisticalAssociation, 8! Ѐ774779.    $"t  Willimack,D.K.,Schuman,H.,andLepkowski,J.M.(1995) EffectsofaPrepaidNon #L" ЀmonetaryIncentiveofResponseRatesandResponseQualityinaFacetoFactSurvey,Public $8 # ЀOpinionQuarterly,59,7892.     %$!$ Word,D.L.(1997) WhoResponds/WhoDoesnt?AnalyzingVariationinMailResponse '"& ЀRatesDuringthe1990Census,CensusBureauMemorandum,fromWordfortheRecord, (#' ЀMarch10,1997. )$(  \+&* HP H 7 H         -1