WPC+ S{ڰz:kEn>omeϰX+NS7Ӡ,e}tD H+EP YM'cʪ[A\@B¶cc'-ݟƷ _z)1K-I:yAuZ۬W68)^1|R0Q jsQ[S+ utˆc[Ze@0(AQ,^ S6*w-hf^oJgVHuWX4^=B(&/%~W6s&UʺیTV5D)ў,&^_(zgbP% L@ 2+sqgKK|Lyt9muZ:"gv)j3{ҫ,r2*=S~|ڻv tD0$ wY yLJ) @-4H b#UN %  0(^ 7wC4G[j mlRNUNUN% B-s 1u 72U*GU@q 0tc D- 0wA 0 0B 0 0 0s 0N 1=Efa 0U>f 0U aU fi k a f a f a f a 0D f!a! D51! D5f!! 0! 0" 0M# 0$ 0$ 0f% 0 & 0& 0I' 0( 0( 0) 0'* 0* 0c+ 0+ 0, 0- 0- 0. 0 B*C> D5m> B*> C> B7> B7?T?j??? D5? B? B? D1@L@L@ D5b@ B*@ D5@ D5@ D5+A B`A}AAdC"zCCCCC"CD,D,D,D,D,D,D,D,D,D,D,D i8BDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBDBD B5zD DEDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDD@JDDDo>E>E>E>E?*\\CENSUS\PRED-TR2-2-HP5Si-1.PRED.DECENNIAL.HQ.CENSUS,,,,0(9 Z6Times New Roman RegularX($ϊg. 7.+003|xU Brudvig JensubpopulationpairwiseDillmannonresponse SSNsGuarinoDeMaio LCA HCAoversamplingNonmatchesnonmatchWesVarPC SQTNeugebauer RDD subpopulationsKulkaMathiowetzCoupermailback SSN LRA LRAs HCAs LCAsWesVar psuWoltmanMachowskiTorturaMiskura T.J.CASIC K.L.Thurn D.R.mailout PSUs G.W. J.A. J.M. H.F.Numident (hH  Z6Times New Roman Regular(hH  Z 6Times New Roman Regular)Hairline d3#37=CIQYag1.a.i.(1)(a)(i)1)a)i)%2A`Arial(9 Z(Times New Roman (;3$2#  0  .3  0  )!dxdx(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(#(#({$0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#2#  a  )3  0p(#(#xAGaeimquy}Bullet ListBullets List TABLE A6L` 4Body Text?%2A`Arial?  S#\  `&Times New RomanS  \  `&Times New Roman*+ (_2623  ..TABLE C e TABLE CTABLE DTABLE ETABLE E6b$Triangle0 TABLE EVVVV)!dxdxtutu)!dxdx   *D+D (_25   ," <DL,23  ..," <DL,   *5+5 (_24  ) <DL)23  ..) <DL)  *2+2 (_23 ` &<<DL&23  ..&<<DL& ` */+/ (_22  #DL#23  ..#DL#  *,+, (_21   DL 23  .. DL  *)+) (_20 h DDL23  ..DDL h *&+& (_19  L23  ..L  *#+# (_18   L23  .. L  *>> (_17  2( 4 <DL223  Ԁ2( 4 <DL2  *DD (_16   ," <DL,23  Ԁ," <DL,   *55 (_15  ) <DL)23  Ԁ) <DL)  *22 (_14 ` &<<DL&23  Ԁ&<<DL& ` *// (_13  #DL#23  Ԁ#DL#  *,, (_12   DL 23  Ԁ DL  *)) (_11 h DDL23  ԀDDL h *&& (_10  L23  ԀL  (## &_9   L23  Ԁ L  (>> &_8  2( 4 <DL223  2( 4 <DL2  (DD &_7   ," <DL,23  ," <DL,   (55 &_6  ) <DL)23  ) <DL)  (22 &_5 ` &<<DL&23  &<<DL& ` (// &_4  #DL#23  #DL#  (,, &_3   DL 23   DL  ()) &_2 h DDL23  DDL h (&& &_1  L23  L  &## $_   L23   L  :Xl 8Body Text 3XXX?%2A`Arial?S#\  `&Times New RomanS,*DateTABLE C8! ,toc 1toc 1             dXXXX)!dxdx&0 d dZabcd($0 ^\] I&mage <=8C HKKKK(3$ !  ( $ Figure  1  Level 1Level 2Level 3Level 4Level 5  ddd($0 0 (@$0  0` (#(#0 ` (#` (# ` (2$0 0 0 0 (<$0 0 0 0 0 (5hCEKQW]cioAutoList11.1.1.1.1.1.1.1.<PPD!:QuickFormat1XXX Ȑ cb  XXX Ȑ cb         Q k$    2    _` XXCaseswithareportedSSNthatislessthanninedigitsorismissingarecountedasmissingvalues.Item  nonresponseratesforSSNarepresentedinaseparatereport.#XX `S#   ((3$ !      0  (#$  0      e k$    1    _` XXArelatedpaper, TheEffectofAdministrativeRecordUseNotificationonSSNReports,focuses  specificallyonresponseratestotheSSNitematthepersonlevel(Stapleton,2002).#XX `S#pppp)!dxdx&p d Pdrrrr)!dxdx&p Pd dd3+0 d d d3+0 d d d     e       {{{{)!dxdx dP Pd||)! dxdx   )!dxdx&P d d____)!dxdx||||)!dxdx)!dxdx d     k$    3    _` XXSource:AdministrativeRecordsStaff. StatisticalAdministrativeRecordsSystem,1999!SocialSecurity  NumberVerificationProgrammingSpecification,U.S.CensusBureau;Planning,Research,andEvaluation t Division.October12,2000. 8 #XX `S#                              V___( c 1Large Dashed d9Hairline!dxdxH:\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?????//??_/o߯o@DH:\MURAWSKI\LATESTMO\1CPOSTAG.TIFH:\Murawski\Latest Models\1cpostag.tifT4b̤"ͤͤnJ' ']&I{s u& !  _ [AXX0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#0p(#(#Census2000Testing,p(#p(# 0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#0p(#(#Experimentation,:p(#p(# 0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#0p(#(#andEvaluationProgram$tp(#p(#   AV) xdVE]xA ^ 0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#0p(#(#January13,2003mp(#p(# #XX [A+#         `     h      p   xvXXAnalysisoftheSocialSecurityNumber C  ValidationComponent c  oftheSocialSecurityNumber,Privacy   Attitudes,andNotificationExperiment#XXvx#      `  [AXX [A [A#XX [A# [AXX FINALREPORT # # [A [A## [A [A##XX# [A*#ThisresearchpaperreportstheresultsofresearchandanalysisundertakenbytheU.S.Census G  Bureau.Itispartofabroadprogram,theCensus2000Testing,Experimentation,andEvaluation 3! (_TXE_)Program,designedtoassessCensus2000andtoinform2010Censusplanning.Findings "o fromtheCensus2000_TXE_ԀProgramreportsareintegratedintotopicreportsthatprovidecontext  #[ andbackgroundforbroaderinterpretationofresults.#XXX#X# #G    `     h      p      x     `     h      p    [AXX0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#0p(#(#Linda_Brudvig_& "p(#p(# AV) xdME'xA 'E#     0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#0p(#(#Planning,Research,and(T# p(#p(# 0  0` (#(#0 ` (#` (#0 (# (#0h(#(#0h(#h(#0(#(#0p(#(#EvaluationDivision#XX [AM #>)$!p(#p(#   XXXX  X X  q[=-)`~0I,/ `(*EI,//+-q   (#(#    (#(#  (#(#  (#(#,'$(#(# #    ##XX  #  8XXdd8 #XXXX# X#XCONTENTS    Y   U        B  C  @*$(#X$##XX# #EXECUTIVESUMMARY""I(#.H H iv & 1.  BACKGROUND""J(#. 1    1.1  Overview""J(#. 1     1.2  Pastresearch""J(#. 2     1.3  Hypotheses""J(#.f f #XXX#X##XXXX4 r  2.  METHODS""J(#. 5 J     2.1  Paneldesign""J(#. 5 6    2.2  Sampledesign""J(#.Z Z 6 "r    2.3  _SSN_Ԁverificationprocedures""J(#.+7 ^  0  2.4  Analyticprocedures""J(#.##XXX#X##XXXX7J (#(# 0  2.5  Varianceestimation""J(#.  #76 (#(# 0  2.6  Applyingqualityassuranceprocedures""J(#.5#XXX#X##XXXX7"(#(# #XXX#X##XXXX3.  LIMITS""J(#.8  4.  RESULTS""J(#.p p 8    4.1  Arethe_SSNs_Ԁprovidedaccurate""J(#..8 n   4.2  Aretheredifferencesin_SSN_Ԁverificationratesbetween_HCA_Ԁand_LCA_`"`"I(#.S10 Z 0  4.3  Aretheredifferencesinthevalid_SSN_Ԁratesbetweenthetwostrategiesforobtaining0@:"(#(#0@:"0@:" F _SSN_Ԁandthetwodifferentlywordednotificationsofadministrativerecordsuse`"`"I(#.Z102(#(# 0  4.4  Howdothe_SSN_ԀvalidationratesfortheCensus2000SPANcomparetothe1992n(#(# Ѐ0  _SQT_Ԁ_SSN_Ԁvalidationrates`"`"I(#.(($12 Z(#(#   #XXX#X0##XXXX5.  RECOMMENDATIONS`"`"I(#. 12 2   Acknowledgments`"`"I(#. 13   #XXX#Xe##XXXXReferences`"`"I(#.$$13 ! U1(        U         e(5h83! !Appendix:Abbreviated_SSN_ԀVerificationProcedures`"`"I(#.JJ;15 j#! #XXX#XG##XXXXU(        %U        U(        #XXX#Xt#  (V#&   XXLISTOFTABLES     #XX # Table1.Numberof_SSN_Ԁresponsesbypanel""J(#.46 & XXXXTable2._SSN_Ԁverificationratesbypanel.""J(#.49  Table3.Verificationratesforvalidandinvalid_SSNs_Ԁbypanel`"`"I(#.bbJ10   Table4._SSN_Ԁverificationratesby_mailout_/_mailback_Ԁareasinallexperimentalpanels.`"`"I(#.^^`10 ^  Table5.Valid_SSN_ԀratesforPerson1bypanel`"`"I(#.911 6  Table6.Multiplecomparisonsofvalid_SSN_ԀratesforPerson1bypanel`"`"I(#.66Q11 ^  Table7.Valid_SSN_ԀratesforPersons26bypanel`"`"I(#.>11 6  Table8.Comparisonof1992_SQT_ԀandCensus2000Panel1validandinvalid_SSN_Ԁrates`"`"I(#. ^#XXXX #12 XXԈ   OaVdOOa[OaEXECUTIVESUMMARY#XX ;%# @h  @  @     Thepossibilityofusingadministrativerecordsfromotherfederalgovernmentagenciesto  supplementcensusdatahasbeeninvestigatedforsometimeattheCensusBureau.Theuseof  administrativerecordscouldpotentiallyincreasecompletenessofmeasurementbyreducing  respondentburdenwithshorterquestionnairesandimprovedataqualitybyeliminating r  memory/respondenterrors.XXXXTheSocialSecuritynumberhasbecomeawidelyusedpersonal ^  identifierforidentifyingprogramparticipantsand,forthisreason,#XXXX1(#XXXXtheCensusBureauconducted J  researchaboutitscollectionanduse#XXXX )#.ThepurposeoftheSocialSecuritynumber,Privacy 6  Attitudes,andNotificationExperimentistoassesstheeffectsofSocialSecuritynumberrequests " r  anddifferentnotificationsofadministrativerecorduseoncensusresponsebehavior. ^  XXXXThisstudyisoneofthreeanalyticalcomponentsoftheSocialSecuritynumber,Privacy 6  Attitudes,andNotificationExperiment.ItexaminestheaccuracyofrespondentsreportedSocial "  SecuritynumbersbycomparingthemtotheCensus_Numident_ԀFile#XXXX*#Ԁandassessingoverall   accuracy,differencesbetweenhighcoverageandlowcoverageareas,anddifferencesbetween   SocialSecuritynumberrequeststrategiesandadministrativerecordsusenotificationstrategies.  Theresultsarefurthercomparedtotheresultsofthe1992SimplifiedQuestionnaireTest.  Theanalysisoftheexperimentaldata(SocialSecuritynumbervalidationrates)wasconductedby Z usingasimpletestforstatisticalsignificanceandbymeasuringthe_pairwise_Ԁdifferencesinthe F validationratesamongthepanels.The_pairwise_Ԁanalysiswasdesignedsothatstatementsabout 2 thesignificanceoftreatmenteffects(i.e.,differencesinvalidationrates)canbemadeaboutall n testssimultaneouslywhilemaintaininga90percentconfidencelevel.  Z Thispapershowsthat,ifreported,SocialSecuritynumbersareaccurate.Thereisasmallbut 2 statisticallysignificantdifferencebetweenhighandlowresponseareas.Thereisnoevidencethat  requestingSocialSecuritynumberforPerson1only,allpersonsinhousehold,orinclusionof   generalorspecificnotificationofadministrativerecordsuseaffectsthequalityofthereported  B  ԍSocialC  Securitynumber.Morespecifically:  ! ! (Ax8e"3"  332A3  0    TherespondentprovidedSocialSecuritynumbersareaccurate.Theoverallvalidationrate j! (basedonmatchingSocialSecuritynumber,name,gender,andyearofbirthtotheCensus V"  _Numident_ԀFile)is94.77percent.B  C  B  Ȑd(21,page1,R44)ȐdC  33C3݌B#!(#(# Ќ  "3"  3052A3  0    ValidSocialSecuritynumberratesarehighforbothhighresponseareas(95.15percent)and %j # lowresponseareas(92.80percent).B  Ȑd(22,page2,R45)ȐdC  ԀThedifferenceissmall(2.35percent)andstatistically &V!$ significantȐdB  ԍ(23,pages1,2,R46)ȐdC  .305]5݌&B"%(#(# Ќ  @*B  C  Ԉ"3"  3f72A3  0    TherateofvalidSocialSecuritynumbersforPerson1ineachpanelishigh,rangingfrom ($' 96.01to96.93percent.B  Ȑd(24,page2,R47)C  ȐdB  C  dTB  C  dheresultsofthe_pairwise_Ԁcomparisonsshownostatistical )%( significancewhenthepanelrequestingSocialSecuritynumberforPerson1onlyis *%) comparedtothepanelrequestingSocialSecuritynumberforallhouseholdmembers. +&* Oa    _ Further,thedistinctionbetweengeneralandspecificnotificationofadministrativerecords  usehasnomeasurableinfluenceonvalidresponses.B  C  ȐdB  ԍ(25,page3,R48)C  B  C  Ȑd3f77݌(#(# Ќ  "3"  3;2A3  0    SocialSecuritynumbervalidationratesgenerallyshowasteadydeclineineachpanelfrom t Person2throughPerson6.B  Ȑd(24,pages37,R49)ȐdC  3;;݌`(#(# Ќ  "3"  3=2A3  0    The1992SimplifiedQuestionnaireTestsupportedthehighvalidationratesshowninthis 8  studywhenconsideringcomparablepaneldesignandmatchingvariables.Overallvalidation $ t rateswere91.00percentddȐdB  ԍ(10,page5,R43)ȐdC  and94.83B  Ȑd(21,page1,R50)ȐdC  percentrespectively.3=C=݌ `(#(# Ќ    Overall,theresponsesthatwereceivetorequestsforSocialSecuritynumberareaccurate.  8  However,toassesstheusefulnessofsuchrequestswithintheuniqueenvironmentofadecennial $  census,wemustalsoconsiderthereductioninmailresponsewhenSocialSecuritynumberis   requested,increasedSocialSecuritynumberitemnonresponse,theextenttowhichhavingavalid   SocialSecuritynumberallowsustolinktootherfiles,andtheextenttowhichweareableto   obtaincorrectinformationfromsuchalink.Tothisend,werecommendthefollowingresearch:   ! ! (Axx"3"  3B2A3  0    LookatthecumulativenonresponsetorequestsforSocialSecuritynumber (unit \ nonresponse,SocialSecuritynumberitemnonresponse,andSocialSecuritynumberinvalid L rates)toobtainanindicatoroftheextenttowhichmatchingtoadministrativerecordscould 8 takeplace.3BB݌$t(#(# Ќ  "3"  3D2A3  0    Conductanalysisofthecharacteristicsofhouseholds thatprovideanddonotprovidethe L SocialSecuritynumber,theaccuracyofhouseholdsreconstructedfromadministrative < records,andtheeffectofhavingandnothavingtheSocialSecuritynumberinhousehold ( reconstruction.InconjunctionwiththeaccuracyoftheSocialSecuritynumber,thisanalysis  wouldbeanindicatorofthequalityofdatawemightexpect.3DD݌(#(# Ќ  "3"  3qG2A3  0    UsethecumulativenonresponsetoSocialSecuritynumberandtheresultsofother  researchtoconductacostbenefitanalysistodeterminetheextenttowhichwecould x useadministrativerecordsdatatocompletehouseholdenumeration (assuming d  decennialcensuspopulationandhousingunituniverseswithindecennialcensustime T! constraints).3qGG݌@" (#(# Ќ  "3"  3I2A3  0    ConductfocusgroupsorresearchsimilartotheSurveyofPrivacyAttitudeslaterin $h" thedecade. XXXXThisSurveyofPrivacyAttitudesexaminedpatternsofattitudechangeinthe %X # publicsprivacyconcernsbetween1996,1999,and2000.#XXXXJ#Giventheprofoundimpactof %H!$ September11,2001,wemayexpectchangingviewsonprivacyattitudes.3IJ݌&4"%(#(# Ќ  "3"  3]L2A3  0    ContinuetoworkcloselywiththePrivacyOfficeandprivacyadvocatestostay ( $' informedoftrendsintheprivacyandconfidentialityarena. 3]LL݌)$((#(# Ќ  @* +&* )OOa XX    1.0 @ BACKGROUND #XX "N#  NNЫXX1.1Overview#XXЫN#  XXXXTheCensusBureauundertakesaprogramofexperimentationduringdecennialcensusesto  measuretheeffectivenessofnewtechniques,methodologies,andtechnologiesinthespecial   environmentthatadecennialcensusgenerates,suchasmasstemporaryhiring,promotionand t  outreachincoordinationwithlocalgovernments,thenationalpaidadvertisingcampaign,andthe `  nationwidedistributionofpublicuseforms.Resultsfromexperimentsformrecommendations L  forsubsequenttestingandultimatelyhelpdesignthenextdecennialcensus(Neugebauer,1999).B  Ȑd(12,page1,R1)ȐdC   8   Decennialcensusesbeginningin2010mayrelyonexpandeduseofadministrativerecords `  informationobtainedfromotherFederalagencies#XXXX(O#XXXX(Neugebauer,1999)B  Ȑd(12,page1,R2)ȐdC  #XXXXR#XXXX.Theuseofadministrative L  recordscouldpotentiallyincreasecompletenessofmeasurementbyreducingrespondentburden 8  withshorterquestionnairesandimprovedataqualitybyeliminatingmemory/respondenterrors $  (Guarino,Hill,andWoltman,2001)B  Ȑd(8,pageiv,R3)ȐdC  .TheSocialSecuritynumber(SSN)hasbecomeawidely  usedpersonalidentifierforidentifyingprogramparticipants#XXXXdS#XXXX.Forexample,citizensarerequired  touseSSNasthetaxpayeridentificationnumber.Likewise,manyotherfederal,state,andlocal  governmentagenciescollectanduseSSNtoadministertheirprograms.SincetheSSNissucha  widelyusedpersonalidentifier,theCensusBureauconductedresearchdealingwithitscollection p anduse(LeslieandTreat,1994).B  Ȑd(10,page H 1,R4)C  Ȑd \ TheSocialSecurityNumber,PrivacyAttitudes,andNotification(SPAN)experimentconsistsof 4 threemajorcomponentstoachievetheresearchobjectives.Thefirstcomponentusesalist  p assistedrandomdigitdial(RDD)telephonesurveytocollectdataonthepublicsprivacy  \ concerns;itisreferredtoastheStudyofPrivacyAttitudesin2000(SPA2000).#XXXXU#XXXXThesecond H componentanalyzestheeffectsofdifferentnotifications,twostrategiesforobtainingSSN 4 information,andnotificationcombinedwiththeSSNrequestonresponsebehaviorandiscalled   theSSNnotificationcomponent.Thethirdanalyticalcomponentinvolvesthevalidationof   SSNscollectedfromfourexperimentalpanelsthatrequestit.Itexamineswhatpercentageof  SSNsobtainedintheexperimentarevalidbypanel#XXXXY#XXXX(Neugebauer,1999)B  Ȑd(12,pages1,2,R5)ȐdC  .#XXXX[#ԀThisreportisthethird   component.ItcontainsafullanalysisoftheSSNvalidation.n l#  1      ׀ !     ThegoaloftheSSNvalidationcomponentistoexaminethevalidationratesoftheSSNs X#! collectedfromthefourpanelsthatrequestit.Itisthefirstempiricalresearchtomeasurethe D$" effectsofanSSNrequestorpublicnotificationofadministrativerecorduseonthevalidityofthe 0% # SSNsprovidedbyrespondentsinadecennialcensusenvironment.Thisreportexamines &l!$ verifyingtheSSNscollectedfromthefourpanelsthatrequestitagainsttheCensusNumerical 'X"% Identification(Numident)file.ItdefinesandexamineswhatpercentageofSSNsobtainedinthe 'D#& experimentarevalid(directandindirectmatches)andinvalidbypanelXXXX(Neugebauer,1999)B  Ȑd(12, *&) page23,R6)ȐdC  .#XXXX]`#Ԁ (0$' Notethatplannedanalysisofthecharacteristicsofhouseholdsthatprovideanddonotprovide )%( theSSN,theaccuracyofhouseholdsreconstructedfromadministrativerecords,andtheeffectof *&) V    havingandnothavingtheSSNinhouseholdreconstructionwasnotundertakenbecauseof  decennialresourceconsiderations.   ЫXX1.2Pastresearch#XXЫb# @* t ЫXX1.2.1WillingnesstoprovideSSNsandaccuracyofSSNs#XXЫ}c# ^  Paststudiesintheprivacyandconfidentialityrealmshowthatpeoplewhoaremostconcerned J  withprivacyparticipatelessinsurveysandcensusesthanthosewhoarenotconcerned(Kulka, 6  Holt,Carter,andDowd,1991B  Ȑd(9,page33,R7)ȐdC  ;Singer,Mathiowetz,andCouper,1993B  Ȑd(15,page J  479,R8)ȐdC  ;GatesandBolton,1998ȐdB  ԍ(7,page6,R9)ȐdC  ). " r  Tostudythisphenomenon,qualitativeandquantitativeanalyseshavebeenconductedtoassess ^  publicopinionandresponsebehaviortoSSNrequestsoncensusforms(Guarinoetal.,2001)B  Ȑd(8,page2,R10)ȐdC  . J  Responsebehaviorsincludemailresponserates,dataqualityassuggestedbyformcompleteness, 6  SSNitemresponse,andthevalidityofreportedSSNs. "  Qualitativeresearchsuchasthe1992focusgroupsindicatedextremenegativereactiontoan   SSNrequest;howeveramailout/mailbacktest[the1992SimplifiedQuestionnaireTest(SQT)]  showedthattherewasasmall,butsignificant,actualdecrease(3.4percent)inmailresponse  rates.ItalsoindicatedthataskingforSSNseemedtolowertheresponseintheLowResponse n Area(LRA)stratummorethantheHighResponseAreastratum.Additionally,itshowedthat Z respondentsdoagoodjobreportingaccurateSSNswhentheychoosetoreportanSSNandthat F SSNsforPerson1wereprovidedmoreaccuratelythanPerson6(LeslieandTreat,1994)B  Ȑd(10, F pages46,R11)ȐdC  B  C  .These 2 findingswereunexpectedandseeminglycontradictedtheanticipatedextenttowhichrespondents n wouldresistprovidinganaccurateidentifierwithdatalinkingimplications(Guarinoetal.,2001)B  Ȑd(8,page2,R12)ȐdC  .  Z Dillman,Sinclair,andClark(1993)B  Ȑd(6,page289,R13)ȐdC  ԀalsofoundthataskingSSNlowerssurveycompletionrates. 2 Thesedropscouldbeduetotherespondentsobjectionstoprovidingpersonallyidentifying  information,ortothedifficultyinobtainingthisinformationforsomehouseholdmembers.   Forfurtherinvestigation,aquestionaskingrespondentswillingnesstoprovidetheirSSNson  censusformswasincludedinaseriesofsurveysaimedatmeasuringprivacyattitudesofU.S. ~  residentsovertime.Singer(Singer,VanHoewyk,Tourangeau,Steiger,Montgomery,and j! Montgomery,2001)reportsthatthepercentageofrespondentswillingtoprovidetheirSSNona V"  censusformdeclinedfrom68percentin1996to55percentin1999and56percentin2000.The B#! dropinwillingnesswassignificantbetween1996and1999,buttherewasnofurthersignificant .$~" changebetween1999and2000.B  Ȑd(16,page54,R14)ȐdC   %j # ЫXXwW1.2.2Accessdifficulty#XXЫ*q# &B"% Bates(1992)analyzedresponsetoSSNbypersonnumberonthequestionnaire.Theresults (.$' indicatethatthereportingofSSNbecomesmoredifficultbeyondpersonnumbertwo.B  Ȑd(3,page3,  R15)ȐdC  ԀXXXXThereis )%( someevidencethatfailuretoprovideSSNisnotalwaysduetounwillingness.Nonresponsemay *&) sometimesbearesultofthelackofavailability,orinaccessibilityoftheinformationtothe +&*  OawW  we w  respondent.#XXXXr#XXXXPreviousresearchindicatesthatthefirstpersononthecensusform(Person1)is  usuallytherespondentfortheentirehousehold(DeMaioandBates,1990).B  Ȑd(5, 8  page585,R16)C  ȐdRelationshipto  Person1maybeanindicatorofitemresponsetoSSNandreflectiveoftherespondentsinability  toprovideSSNforhouseholdmembers. t Bates(1992)B  ԍ(3,page3,R17)C  ԀcitesfocusgroupevidencethatprovidingSSNsforchildrenmightbemoredifficult L  becauseSSNsarenotroutinelyusedbeforeacertainage.Shefoundthatitemnonresponsetothe 8  SSNitemincreasedaspersonnumberincreased.ԀwPresumably,thisreflectsthedifficultyin $ t providingSSNforchildrenorunrelatedhouseholdmembers(ashouseholdmembersareoften  ` listedinorderbyageorbyrelationshiptotherespondent).AreportbyDillman,Sinclair,and  L  Clark(1993)B  ԍ(6,page300,R18)C  ԀnotedthatitemnonresponsetoSSNforchildrenunderage17was25percent,  8  substantiallyhigherthanforotherquestions.Dillman,Reynolds,andRockwood(1991)report $  thatafocusgroupinvestigationrevealedthateventhoughsomepeoplehadnoobjectionto   providingSSNs,findingthisinformation,especiallyforchildrenandunrelatedhousehold   members,mightbedifficult.B  Ȑd(6,page292,R19)ȐdC     ЫXX6OagOa1.2.3SSNRequestandNotificationofAdministrativeRecordUse#XXЫ9{# p #XXXXqt#X XXX#XX XX|#XXXXBeforeCensus2000,noempiricalresearchmeasuredandassessedresponsebehavior(suchas V mailresponse,questionnaireitemnonresponse,nonresponsetotheSSNitem,andthevalidityof B theSSNsthatwerereceivedfromrespondents)#XXXX[|#XXXXtoaparticulartypeofSSNrequest(SSN .~ requestedforallhouseholdmembersversusonlyforthepersoncompletingtheform)and j notificationofadministrativerecorduse(generalnotificationthattheCensusBureaumayuse V statisticaldatafromotherfederalagenciesversusmorespecificnotificationwhereagenciesare B named)inadecennialcensusenvironment.However,someresearchwasconductedduringmid . cycletests.BatesstudieditemnonresponsetoSSNinthe1992SimplifiedQuestionnaireTest  (SQT).ShefoundthataskingSSNsignificantlyloweredunitԀ~responseratesoverallandforthe  1990LRAgroups.MailcompletionratesfortheSSNformwere6.2percentagepointslowerfor  householdsfromLRAs.However,theitemnonresponseratefromresidentsof1990LRAswas  notsignificantlydifferentthanrespondentsfromotherareas.B  ԍ(3,page4,R20)C  Ԁ z #XXXX}#Pastresearchonnotificationofadministrativerecorduseisqualitativeinnatureandtherefore R! doesnotindicatetheeffectofnotificationoncensusresponseoraccuracyoftheSSNsthatare >"  reported.However,Singer(1978)B  ԍ(14,page150,R21)C  Ԁinvestigatedtheeffectsinfacetofaceinterviewsofmore *#z! (versusless)informationaboutsensitivesubjectmatterinsurveyintroductions.Shefoundno $f" effectofvaryinginformationaboutcontentonresponserates.Otherfindingsrevealthatfocus %R # groupparticipantsaregenerallyunsureaboutwhateffectnotificationwillhaveoncensus %>!$ response(Guarinoetal.,2001)B  Ȑd(8,page3,R22)ȐdC  .Somebelievethatnotificationofadministrativerecordusewill &*"% havenoeffectonresponse,whileothersbelievethatnotificationwilldecreaseresponse.With '#& regardtothetypeofnotification,focusgroupadministratorsnotethatmanyoftheparticipants ($' didnotunderstandthetaskofratingwhichnotificationwasmostpersuasiveinincreasing )$( participation,andinsteadratedthenotificationspecimensbywhichuseofrecordstheyfeltwas *%) mostjustifiable(AguirreInternational,1995)B  Ȑd(1,pagevi,R23)ȐdC  .  v+&*  b,'+ [  e   Interestingly,currentresearchduringCensus2000(Guarinoetal.,2001)B  ԍ(8,pagesiv,v,R24)C  Ԁshowsthat:SSN  requestslightlydecreasesresponseandthereisnodifferentialeffectofSSNrequestbetweenlow  coverageareas(LCA)andhighcoverageareas(HCA);SSNrequestincreasesreturnof  incompleteforms;generalnotificationofadministrativerecorduseslightlydecreasesresponse t whiletheinclusionofspecificnotificationdoesnot;andspecific/generalnotificationincreases ` responsetothePerson1SSN. L  Additionally,Stapleton(2002)indicatesthat,forPerson1,thetypeofSSNrequestdoesnot $ t affectresponsetotheSSNitem.However,forPerson1andPersons26,includingnotification  ` ofadministrativerecorduse(regardlessoftype)doessignificantlyincreasetheoddsofa  L  respondentprovidingtheirSSNB  Ȑd(17,page3,R25)ȐdC  .  8  ЫXX1.2.4Summary#XXЫ#   Insummary,areviewofpreviousandcurrentresearchindicatesthat:askingSSNdecreases   surveyresponserates;increasesincompleteforms;resultsinhighSSNitemnonresponse;and   thereisnodifferentialeffectofSSNrequestbetweenHCAsandLCAs.Thereissomeevidence  thatthereisnodifferenceonresponseratesandSSNitemresponserateswhenrespondentswere p providedmoreinformationaboutasensitivesubject(notificationofSSNuse).Otherresearch \ indicatesthatrespondentshavedifficultyprovidingthisinformationforchildrenandunrelated H householdmembers.Lastly,previousresearchshowsthatwhenrespondentsdoprovideanSSN, 4 itisaccurate.  p  1.3Hypotheses  H Relyinguponpriorresearch,threehypothesesweredevelopedconcerningthevalidationratesof $ reportedSSNsoverall,bycoveragearea,andbypersonnumber.Intheabsenceofpast  quantitativestudiesregardingtheeffectsofnotificationuponthevalidityofSSNresponses,two  hypothesesweredevelopedbasedonexpectationsfromprivacyresearch.  1.0  TheSSNvalidationratewillbehighwhenSSNisreported.p (#(# 2.0  Therewillbelittledifferenceinvalidationratesbetweenlowcoverageareasandhigh H"  coverageareas.4#!(#(# 3.0  SSNvalidationrateswillsteadilydecreasebyPersonnumber.Thatis,Person2willhave  %\ # higherSSNvalidationratesthanPerson3andsoonthroughPerson6.%H!$(#(# 4.0  NotificationofadministrativerecordusewillcausesmallbutsignificantdropsinSSN ' #& validationrates,withspecificnotification(includingagencynames)havingastrongereffect ( $' thangeneralnotification.)$((#(# 5.0  RequestingSSNintheabsenceofgeneralorspecificnotificationwillyieldhighervalidation +&* ratesforPerson1whenSSNisrequestedonlyforPerson1ascomparedtoallhousehold l,'+ members.X-(,(#(# Oa     TheSSNvalidationcomponentwillprovideabetterunderstandingofthepotentialramifications  ofrequestingSSNonbehaviorregardingaccuracyofSSNsina(limited)decennialcensus  environment.9 X,[X(#9      XX2.METHODS#XX 4#  ` (ЫXX 2.1Paneldesign #XXЫ# `  TheexperimentaltreatmentsfortheSPANexperimentareimplementedwithintenpanels.The J  SSNvalidationcomponentinvolvesthefourpanelswhereSSNisrequested.Households 6   selectedforthisexperimentwererandomlyassignedtoeachpanel(Guarinoetal.,2001)B  Ȑd(8,page  4,R26)ȐdC  .Two "r  shortformpanelshaveformsmodifiedwithanSSNrequesteitherforallhouseholdmembersor ^  foronlythepersoncompletingtheform(i.e., PersonOne).Notification,beyondthestatement J  informingrespondentsthatprovidingSSNisvoluntary,isnotapartofthesepanels.Twoshort 6  formpanelscombinethenotificationaspectandSSNrequestforallhouseholdmembers. "  0   (#(# Specifically,thefourexperimentalgroupsare:          "  N &%XX0  #XX%&6#Panel1:All(householdmembers)SSNRequest0D(#(#0D(#D(#0(#(#0L(#(#0L(#L(#0!(#(#!(#!(# 0  Panel2:One(Person1)SSNRequest0(#(#0D(#(#0D(#D(#n(#(# 0  Panel3:AllSSNRequest,GeneralNotificationZ(#(# 0  Panel4:AllSSNRequest,SpecificNotification&%XXF(#(# #XX%&j#Eachpanelreceivesthefullcomplementofcensusmailoutmaterialsinthesamesequenceand n timingastheofficialCensus2000schedule.Experimentallettersandformsaretheofficial  Z censusformsreceivedbythesampledhouseholds(Guarinoetal.,2001)B  Ȑd(8,page4,R27)ȐdC  . F 0   (#(# Asnoted,thetwonotificationsarereferredtoas generaland specific.Thenotificationis  writteninthelettersaccompanyingthequestionnairesanddescribeshowandwhytheCensus   BureaumayuseadministrativerecordsdatafromotherFederalagencies.Thegeneral  notificationmentionstheCensusBureauspossibleuseofstatisticaldatafromotherFederal   agencies,whilethespecificnotificationgoesfurthertonametheFederalagencies.Thegeneral ~! notificationis: j"  0  ` XXToimprovethequalityofcensusstatistics,theCensusBureausometimesusesrecordsfromothergovernment B$" agencies.Usingotheragenciesrecordshelpsmakethecensusmorecomplete.Bymakingbetteruseof %V # governmentrecordsthatalreadyexist,theCensusBureaumaybeabletoaskyoufewerquestionsinthecensus.%!$(#(# #XX `ޣ#Thespecificnotificationwordingis: R'"& ` XX0  Toimprovethequalityofcensusstatistics,theCensusBureausometimesusesrecordsfromothergovernment *)z$( agencies,suchastheSocialSecurityAdministration,theInternalRevenueService,oragenciesprovidingpublic )>%) housingassistance.Usingotheragenciesrecordshelpsmakethecensusmorecomplete.Bymakingbetteruse *&* ofgovernmentrecordsthatalreadyexist,theCensusBureaumaybeabletoaskyoufewerquestionsinthe v+&+ census.:,',(#(# dO     #XX `#BecauseprovidingtheSSNisvoluntary,thecoverletterforallfourpanelswiththeSSNrequest  containedanadditionalstatement:  ` XX0  Toimprovethequalityofcensusstatistics,theCensusBureausometimesusesrecordsfromothergovernment t agencies.Forthatpurpose,weareaskingforyoursocialsecuritynumber;however,providingyoursocial 8 securitynumberisvoluntary.L(#(# #XX `d# ЫXX2.2Sampledesign#XXЫ#            "  N ThesampleofhouseholdswastakenfromtheJuly1999versionoftheDecennialMaster    AddressFile(DMAF)mailout/mailbackuniverseofover92millionaddresses.Thisuniverse    excludessamplesfortheAccuracyandCoverageEvaluation(A.C.E.)Listing,thecontamination n  evaluation,congressionaladdresses,list/enumerateareas,andupdate/leaveareas. Z  Thesamplewasequallyallocatedtotwostratathatreflectexpecteddifferenceinthepopulation 2  compositionbyrace,tenure,andanticipatedCensus2000mailreturnrates(takenfromprevious n  censusexperience).Thesestrataarebasedon1990censustractlevelraceandtenuredataand  Z referredtoaslowandhighcoverageareas(LCAandHCA,respectively).TheLCAstratumwas F expectedtocontainahighproportionofAfricanAmericanandHispanicpopulationsandrenter 2 occupiedhousingunits.Whenselectionofthesamplehouseholdswasconducted,nearly81  percentofthetotalDMAFuniverseconsistedofhouseholdswithintheHCAstratum.   OversamplingoftheLCAoccurredtoequallyallocatethesampleacrossthetwostrata.  Approximately52,000householdswereselectedandrandomlyassignedtoeachexperimental ~ panel.Themailoutsamplesizeforeachofthetenpanelsconsistedofalittleover5,200 j addresses,equallyallocatedtotheHCAandLCAstrata(i.e.,around2,600addressesper V stratum).Specificdetailsaboutaddressomissionssuchasundeliverablesandduplicatesand B replacementscanbefoundinGuarinoetal.,2001B  Ȑd(8,page5,R28)ȐdC  . .~ y[~OajOaThetotalnumberofhouseholdsselectedinthisexperiment(i.e.,Panels1through4)was20,998. V Forthispaper,weexaminetheaccuracyoftheSSNsthatwerereportedi l#  2      ׀forallpersonsinthese B housingunitsthatreturnedtheirquestionnairesbymail.Therewereatotalof21,745reported  . SSNsasshownbypanelinTable1. !          "  N  z  [        D      L   Table1.NumberofSSNresponsesbypanel B  Ȑd(19,page4,R29)ȐdC   #" * V!ddd Xdd Xdd X(#(#,dd ,dd ,dd ,dd ,dd +  0VV$#$ 0` XXAllPanels =VV,!v&!&"VV =Panel1 %!( (AllSSNs) =VV,!v&!)"VV =Panel2 %!+ (OneSSN) =VV,!v&!,"VV =Panel3 $B - (AllSSNs,general %!. notification) =VV,!v&!/"VV =Panel4 $B 0 (AllSSNs,specific %!1 notification) eVT&v&!2"  VV @<@21745@<@e#XX `#` XX21,745#XX `V# VpC'#3" @<@21745 @<@V ̸@6348̸@` XX6,348#XX `# ^VMB'#4" ̸@6348 ̸@V ^` XX2,713* _VN!'#5"V ߸@6367߸@_6,367 VoB'#6" ߸@6367 ߸@V @6317@6,317RHF'#7" @6317  @V R#XX `Ļ#` XX*InPanel2,SSNwasrequestedforPerson1only;inPanels1,3,and4,SSNwasrequestedforPersons16. ($7 Oa     #XX `G#FiguresinthispaperwillbeweightedtoaccountforoversamplingoftheLCAstratum.The  inverseofthesamplingintervalforeachstratumwithanexperimentalgroupistheweightfor  eachcasecontainedinthepanelandstratum(Guarinoetal.,2001)B  Ȑd(8,page6,R30)ȐdC  .   ЫXX2.3SSNverificationprocedures#XXЫ¿#  `   TheuneditedpersonrecordswithSSNentriesonthequestionnairesfromhousingunitswithin J  themailout/mailbackexperimentalsamplePanels1,2,3,and4werematchedtotheCensus 6  NumidentfiletodeterminethevalidityoftheSSNthatwasprovided.TheCensusNumidentfile " r isprovidedbytheSocialSecurityAdministration(SSA)andisreformattedforCensususe.It  ^  includesthefollowinginformation,ifavailable:SSN,first,middle,andlastname,yearofbirth,  J  gender,alternateorpreviousnames,andrace(AdministrativeRecordsResearchStaff,2000). 6  SeetheAppendixforanabbreviatedversionoftheverificationproceduresB  Ȑd(1,page2,R31)ȐdC  . "  ` XX#XX `# ЫXX2.4Analyticprocedures#XXЫ#    Theanalysisoftheexperimentalquestionnairedataisconductedbymeasuringthepairwise l differencesinSSNvalidationratesamongthepanels.Theanalysisisdesignedsothatstatements X aboutthesignificanceoftreatmenteffects(i.e.differencesinSSNvalidationrates)canbemade D aboutalltestssimultaneouslywhilemaintaininga90percentconfidencelevel(theCensus 0 BureauStandard).Foramorecompletediscussiononpairwiseanalysis,refertotheSSN l notificationcomponent(Guarinoetal.,2001).B  Ȑd(8,page10,R32)ȐdC   X  ЫXX2.5Varianceestimation#XXЫ#  0 XXXXSincetheanalysisisdoneatthepersonlevel,aclusteringeffectatthehouseholdlevelmustbe  consideredbecauseeachhouseholdhasonerespondentforallhouseholdmembers.Thisisdone  withinWesVar,treatingthesurveyasaonestagesampledesign,andtreatingeachhouseholdas  aprimaryselectionunit(PSU).SincethiscreateswelloverthemaximumnumberofPSUsthat  WesVarcanhandle,clustersweregroupedrandomlyinto256"pseudo"clusters.Totakeinto z accountthestratifiedsampledesigninthedataanalysis,WesVarwasusedtocomputestandard f  errorsforallestimatesusingastratifiedjackknifeapproach.Thisreplicationoptionissuitable R! forstratifieddesignswithtwoormorePSUsperstratum#XXXXs#Ԁ(Stapleton,2002).B  Ȑd(17,page3,R33)ȐdC   >"   ЫXXmOavOaxOaOaOa2.6Applyingqualityassuranceprocedures#XXЫy#  $f" Weappliedqualityassuranceproceduresthroughoutthecreationofthisreport.They &P!$ encompassedhowwedeterminedstudymethods,createdspecificationsforprojectprocedures &<"% andsoftware,designedandreviewedcomputersystems,developedclericalandcomputer '(#& procedures,analyzeddata,andpreparedthisreport(U.S.CensusBureau,2000). ($'     XX  *%) 6Oa y[ xOa  6 y6 xy x  hOa3.LIMITS#XX  #   Whilethisexperimentwasconductedduringadecennialcensus,itwasconductedusingasmall  sampleoftheentirepopulation.Ifextendedtotheentirenation,resultsofsucharequestwould  likelybeverydifferentbecausethemediaattentionconcerningtheprivacyissuesofaskingfor  SSNwouldlikelybemagnified. t  Theplannedanalysisofthecharacteristicsofhouseholdsthatprovideanddonotprovidethe L  SSN,theaccuracyofhouseholdsreconstructedfromadministrativerecords,andtheeffectof 8  havingandnothavingtheSSNinhouseholdreconstructionwasnotundertakenbecauseof $ t  decennialresourceconstraints .InconjunctionwiththeaccuracyoftheSSNs,thisanalysiswould `  beanindicatorofthequalityofdataandusefulnessofcollectingSSNinfuturesurveysand L  censuses.    "  8      XX4.RESULTS#XX P#  8  D ЫXX4.1AretheSSNsprovidedaccurate?#XXЫ#  8 AccurateSSNsforthisstudyarethevalidSSNs!thosewheretheSSNandnameprovidedbythe " respondentmatchanSSN,name,and,asneeded,yearofbirthandgenderontheCensus  Numidentfile.TherearefivecategoriesofvalidoutcomesthatresultedfromtheSSN  verificationmatchingprocess.Foreach,theSSNmatchesandtheB  Ȑd(1,pages1015,R34)ȐdC  :Ȑd  Ȑd! ! (Axx"3"  32A3  0    parsednamematchestheNumident.Aparsednameisonethatisplacedintofirst,middle, n andlastnamefields,ifavailable.Thismatchisflaggedasa 1.3݌Z(#(# Ќ  "3"  3A2A3  0    parsednamematchesthealternatenameontheNumident.Analternatenameisanyprevious 2 namesuchasamaidennameoranamebeforeanamechange.Thismatchisflaggedasa n  2.3An݌ Z(#(# Ќ  "3"  32A3  0    parsednamematchestheconcatenatednameontheNumident.Aconcatenatednameisone  2 whereallthelettersinthefirst,middle,andlastnamearemergedtogetherwithnospaces. ! Thismatchisflaggedasa 3.3 ݌"  (#(# Ќ  "3"  32A3  0    standardizednamematchestheNumident.Astandardizednameisamoreformalversionof $" aname,forexample,DebbieisstandardizedtoDeborahandJimtoJames.Thismatchis ~% # flaggedasa 5.3݌j&!$(#(# Ќ  "3"  3>2A3  0    standardizednamematchestheconcatenatednameontheNumident.Thismatchisflagged V'"% asa 7.3>k݌B(#&(#(# Ќ  Notethatdirectmatchesaredefinedasflags1and2and,forthisstudy,areconsideredstronger *j%( matchesthanindirectmatches,flags3,5,and7. +V&)  +B'* #gOa~OaOahOa# g ~g ~ h h  Invalid(notaccurate)SSNsare:  "3"  3#2A3  0    invalidentry.ThelasttwodigitsoftheSSNarenonnumeric.(Recordswithfewerthannine  digitsorallninedigitsoftheSSNblankarenotinuniverse.)Theseareflaggedasa 0.3#P݌t(#(# Ќ  "3"  32A3  0    theSSNisnotintheNumident.Theseareflaggedasan A.3݌L (#(# Ќ  "3"  32A3  0    theSSNisintheNumidentbutthenamedoesntmatch.Theseareflaggedasa B.3݌$ t(#(# Ќ  Table2confirmsourexpectationthattheSSNverificationratesforvalidSSNsarehighoverall  L  andforeachpanel.  8   Table2.SSNverificationratesbypanel B  Ȑd(20,page3,R35)ȐdC     *-V.dddd dd dd dd dd  V!(#(#, dd ,dd ,dd ,dd ,edd ,edd +  6VV%   6` XXVerificationStatus @VV/!"VV @All B Panels @VV/!"VV @Panel1 0  (All B SSNs) @VV/!"VV @Panel2 0  (One B  SSN) @VV/!!"VV @Panel3 n # (AllSSNs, 0 $ general B% notification) @VV/!&"VV @Panel4 n ( (AllSSNs, 0 ) specific B* notification) N='+" VV N#XX `m#` XX SSNValid: #XX `#9XX @/!v, @ F5!v-3 F L;'v.3 L L;'v/3 L L;'v03 L TC-v13  TЀ Directmatch: @/!82 @ F5!833 F L;'843 L L;'853 L L;'863 L TC-873  T#XX9 #` XXԀ1=parsednamematchedNumident @/!<8 @93.65% F5!<93 F93.66% L;'<:3 L94.57% L;'<;3 L92.84% L;'<<3 L94.05% TC-<=3  TЀ2=parsednamematchedalternate > 0 @ nameonNumident J9+t?@@ J0.68% F5!tA3 F0.63% L;'tC3 L0.83% L;'tE3 L0.73% L;'tG3 L0.60% TC-tI3  T#XX `#9XXԀ Indirectmatch: @/!8J @ F5!8K3 F L;'8L3 L L;'8M3 L L;'8N3 L TC-8O3  T#XX9a#` XXԀ3=parsednamematchedconcatenated <P 0 @ nameonNumident J9+Q@@ J0.17% F5!S3 F0.20% L;'U3 L0.26% L;'W3 L0.11% L;'Y3 L0.16% TC-[3  TЀ5=standardizednamematched t\ 0 @ Numident J9+8]@@ J0.26% F5!8_3 F0.34% L;'8a3 L0.40% L;'8c3 L0.28% L;'8e3 L0.11% TC-8g3  TЀ7=standardizednamematched Lh ЀconcatenatednameonNumident @/!i @0.01% F5!k3 F0.00% L;'m3 L0.00% L;'o3 L0.00% L;'q3 L0.03% YH-s3  Y#XX `z#` XX SSNInvalid: #XX `#9XX @/!t @ F5!u3 F L;'v3 L L;'w3 L L;'x3 L YH2y3   Y#XX9#` XXԀ0=Invalidentry @/!Kz @0.16% F5!K{3 F0.08% L;'K|3 L0.15% L;'K}3 L0.31% L;'K~3 L0.09% TC-K3  TЀA=SSNnotinNumident @/!_ @2.03% F5!_3 F2.04% L;'_3 L0.93% L;'_3 L2.53% L;'_3 L2.00% TVC-_3  TЀB=SSNinNumident,namedidnt # 0 @ match JV9+ @@V J3.04% FV5! 3V F3.04% FV5' 3V F2.87% FV5! 3V F3.20% LV;' 3V L2.97%=31 3 V =#XX `#AsshowninTable3,whenexaminingthedirectandindirectmatchesofthevalidSSNentries,it G" isclearthatmostaredirectmatcheswithanoverallmatchrateof94.33percentcomparedtothe 3# overallindirectmatchrateof0.44percent.InvalidSSNsarequitelowwithanoverallrateof $o 5.23percent.  %[    &3" mOa m m  [OaTable3.VerificationratesforvalidandinvalidSSNsbypanel B  Ȑd(21,page1,R36)ȐdC    */V0d d dd dd dd dd edd eedd e-V.(#(#, dd ,dd ,dd ,dd ,edd ,edd +  6VV% 6` XXVerificationStatus @VV/!"VV @All 2  Panels @VV/! "VV @Panel1  p (All 2 SSNs) @VV/!"VV @Panel2  p (One 2 SSN) @VV/!"VV @Panel3 ^ (AllSSNs,  p general 2 notification) @VV/!"VV @Panel4 ^ (AllSSNs,  p specific 2 notification) N='" VV N SSNValid: @/!f   @94.77% F5!f !3 F94.83% L;'f "3 L96.05% L;'f #3 L93.96% L;'f $3 L94.94% TC-f %3  TЀ Directmatch @/!( x& @94.33% F5!( x'3 F94.29% L;'( x(3 L95.40% L;'( x)3 L93.57% L;'( x*3 L94.65% TC-( x+3  TЀ Indirectmatch @/! >, @0.44% F5! >-3 F0.54% L;' >.3 L0.65% L;' >/3 L0.39% L;' >03 L0.29% YVH- >13  Y SSNInvalid @V/! 2V @5.23% FV5! 33V F5.17% LV;' 43V L3.95% LV;' 53V L6.04% LV;' 63V L5.06%B86 73   V B#XX `I# ЫXX4.2.AretheredifferencesinSSNverificationratesbetweenHCAsandLCAs?#XXЫ@#  !  g 8 Table4showsthatthevalidSSNratesforbothHCAandLCAareveryhighatover90percent. Q : Asexpected,thedifferencebetweenthemissmall;therateforHCAis2.35percentagepoints = ; higherthanLCAandthisdifferenceisstatisticallysignificant.B  Ȑd(23,page2,R38)ȐdC   )y <  Table4.SSNverificationratesbymailout/mailbackareasinallexperimentalpanels B  Ȑd(22, U> page2,R37)ȐdC   Q> *2V3dd dd dd dd dd edd eedd e/V0(#(#,7dd ,dd ,9dd ,9dd +  2V%=?=  2` XXVerificationStatus <V/!A" V  <AllPanels <V/!C" V  < @F HCA <V/!E" V  <LCA NV='G"  V N SSNValid: @V/!qHV @94.77% FV5!qI3V F95.15% LV;'qJ3V L92.80% TC-qK3 V TЀ Directmatch: @/!3L @ F5!3M3 F L;'3N3 L TC-3O3  TЀ1=parsednamematchedNumident @/!IP @93.65% F5!IQ3 F94.04% L;'IR3 L91.66% TC-IS3  TЀ2=parsednamematchedalternatenameonNumident @/! T @0.68% F5! U3 F0.68% L;' V3 L0.64% TC- W3  TЀ Indirectmatch: @/!X @ F5!Y3 F L;'Z3 L TC-[3  TЀ3=parsednamematchedconcatenatednameonNumident @/!G\ @0.17% F5!G]3 F0.14% L;'G^3 L0.31% TC-G_3  TЀ5=standardizednamematchedNumident @/! [` @0.26% F5! [a3 F0.28% L;' [b3 L0.18% TC- [c3  TЀ7=standardizednamematchedconcatenatednameonNumident @/!d @0.01% F5!e3 F0.01% L;'f3 L0.01% YH-g3  Y SSNInvalid: @/!h @5.23% F5!i3 F4.85% L;'j3 L7.20% YH2k3   YЀ0=Invalidentry @/!Zl @0.16% F5!Zm3 F0.15% L;'Zn3 L0.20% TC-Zo3  TЀA=SSNnotinNumident @/!np @2.03% F5!nq3 F1.88% L;'nr3 L2.82% TVC-ns3  TЀB=SSNinNumident,namedidntmatch @V/!2tV @3.04% FV5!2u3V F2.82% LV;'2v3V L4.18%=312w3 V =#XX `# ЫXX4.3AretheredifferencesinthevalidSSNratesbetweenthetwostrategiesfor x obtainingSSNandthetwodifferentlywordednotificationsofadministrative  y recordsuse?#XXЫ)#   "  N  z  [        D      L  !z InordertoexamineforsignificancethedifferencesinthevalidSSNratesbetweenthetwo x#| strategiesforobtainingSSNXXXXԀ(SSNrequestedforallhouseholdmembersversusonlyforthe d$} personcompletingtheform)#XXXXL+#andthetwodifferentlywordednotificationsofadministrative P% ~ recordsuseXXXX(generalnotificationthattheCensusBureaumayusestatisticaldatafromother <&! federalagenciesversusmorespecificnotificationwhereagenciesarenamed)#XXXX[,#,pairwise ('x" comparisonsofPerson1validSSNratesareconsideredamongthepanelsforwhichthis (d# informationisrequested(Panels14).SincePanel2requestedSSNonlyforPerson1,our )P$ pairwisecomparisonislimitedtoPerson1.Eachofthesefourpanelsreceivessomedegreeof )<% notificationofthepossibilityofadministrativerecorduseduetothestatementinthecoverletter *(& explainingtherequestforSSN.AsshowninTable5,therateofvalidSSNsforPerson1ineach +'  jOavOa j vj v  panelisveryhigh,rangingfrom96.01percentto96.93percent,adifferenceoflessthanone  percentagepoint.   Table5.ValidSSNratesforPerson1bypanel B  Ȑd(24,page2,R39)ȐdC   t *$V'd d7dd 7dd 9dd 99dd 92V3(#(#, dd ,dd +  6VV%`` 6` XXPanel @VV/!" r"VV @ValidationRate N='" r" VV NPanel1(allSSNs) @/! 4  @96.93% N=' 4 3  NPanel2(oneSSN) @/!   @96.06% N='  3  NPanel3(allSSNs,generalnotification) @/!l   @96.14% NV='l 3  NPanel4(allSSNs,specificnotification) @V/!0 V @96.01%7-+0 3  V 7#XX `E2#Table6showstheresultsofthepairwisecomparisons.Thereisnosignificantdifferenceinthe  0  validSSNratewhenthepanelrequestingonlyoneSSNiscomparedtothepanelrequestingall   SSNs.FromtheperspectiveofPerson1,theseformsdonotdifferintheirrequestforSSNand,   therefore,nodifferenceinresponsetothisitemisexpected.Further,thedistinctionbetween   generalandspecificnotificationhasnomeasurableinfluenceonvalidresponsestotheSSNitem   forPerson1. |   Theseresultswereunexpected;however,theyconfirmthefindingsfromthe1992SQT, T discussedinthenextsection. @  Table6.MultiplecomparisonsofvalidSSNratesforPerson1bypanelB  Ȑd(25,pages2,3,R40)ȐdC   h *(V*ddLdd ,dd $V'(#(#,dd ,dd ,dd +  6VV%TT 6` XXPairwiseComparison @VV/!"VV @Difference @VV/! "VV @SEofDifference N='"" VV NPanel1(allSSNs)Panel2(oneSSN) @/!# @ @X 0.88% hW!$3 HzG?0.54HzG?h0.54 udN%3 HzG?0.54 HzG? uPanel1(allSSNs)Panel3(allSSNs,generalnotification) @/!L& @0.79% hW!L'3 p= ף?0.52p= ף?h0.52 udNL(3 p= ף?0.52 p= ף? uPanel1(allSSNs)Panel4(allSSNs,specificnotification) @/!`) @0.92% hW!`*3 = ףp=?0.57= ףp=?h0.57 udN`+3 = ףp=?0.57 = ףp=? uPanel2(oneSSN)Panel3(allSSNs,generalnotification) @/!$, @Є0.09% hW!$-3 zG?0.59zG?h0.59 udN$.3 zG?0.59 zG? uPanel2(oneSSN)Panel4(allSSNs,specificnotification) @/!/ @0.04% hW!03 ?0.65?h0.65 uVdN13 ?0.65 ? uPanel3(allSSNs,generalnotification)Panel4(allSSNs,specific \2 notification) @V/! p3V @0.14% hVW! p53V ףp= ?0.62ףp= ?h0.62^TR p73 ףp= ?0.62  ףp= ?V ^#XX `:#        "  N  z  [        D      L    ! Table7showsthevalidSSNratesforPersons26forthepanelsthatrequestedit.Again,valid  8 SSNratesforeachpersonaresimilarineachpanel.Forexample,thePerson2validSSNrates  9 areallover95percent.Weseethateachofthepanelsshowhighvalidationratesforallpersons !: and,asexpected,formost,thereisasteadydeclineineachpanelfromPerson2throughPerson6 "; (theexceptionisaslightincreaseforPerson5inPanel4). #<  Table7.ValidSSNratesforPersons26bypanel *B  Ȑd(24,pages37,R41)ȐdC   X% > *SVTdddd dd dd (V*(#(#,[dd ,9dd ,9dd ,9dd ,9dd ,9dd +  6VV%H&!?H&! 6` XXPanel @VV/! 'Z"A"VV @Person2 @VV/! 'Z"C"VV @  Person3 @VV/! 'Z"EVV @  Person4 @VV/! 'Z"GVV @Person5 @VV/! 'Z"I"VV @Person6 N=' 'Z"K" VV NAllPanels @/!'#L @95.45% @/!'#M3 @92.90% @/!'#N3 @89.08% @/!'#O3 @87.53% @/!'#P3 @82.80% N=''#Q3  NPanel1(allSSNs) @/!(#R @95.34% @/!(#S3 @93.87% @/!(#T3 @89.82% @/!(#U3 @85.33% @/!(#V3 @84.38% N='(#W3  NPanel3(allSSNs,generalnotification) @/!T)$X @95.03% @/!T)$Y3 @91.93% @/!T)$Z3 @86.60% @/!T)$[3 @86.46% @/!T)$\3 @80.23% NV='T)$]3  NPanel4(allSSNs,specificnotification) @V/!*h%^V @95.98% @V/!*h%_3V @93.15% @V/!*h%`3V @90.75% @V/!*h%a3V @91.07% @V/!*h%b3V @83.48%7-+*h%c3  V 7#XX `"I#` XX*Panel2requestedSSNforPerson1only *,&c #XX `CR# +&d Oa    ЫXX4.4HowdotheSSNvalidationratesfortheCensus2000SPANcomparetothe1992  SQTSSNvalidationrates?#XXЫS#   Aspartofthe1992NationalCensusTestI,the1992SQTSSNvalidationprojectincludeda  panelthatrequestedtheSSNforeachpersonlivinginthehousingunit.TheSSAvalidatedthe  SSNscollectedduringthetestbymatchingthemtotheirNUMIDENT(NumericalIdentification) p  file.TheSSAsNUMIDENTfileisatransactionfileofSSNapplications.Itcontainsarecord \  foreachupdatemadetopersonsdataassociatedwithanSSN.Thisincludesfullname,dateof H  birth,race,andgender.B  Ȑd(10,page2,R42)ȐdC   4  The1992SQTpanelismostliketheCensus2000SPANPanel1whereSSNwasrequestedfor  \  allhouseholdmembersandgeneralorspecificnotificationofadministrativerecordusewasnot H  included.TheCensusBureausNumidentfilematchusedmatchingvariablessimilartothe1992 4  SQTmatch(SSN,name,dateofbirth,andgender),buttheverificationprocesswasdifferent.   Forexample,the1992SQTmatchedonfullnameandtheCensus2000SPANPanel1matchfor   nameincludedparsed,alternate,standardized,andconcatenatednamesinitsmatch.These   differenceslimittheextenttowhichthe1992SQTresultscanbecomparedtotheCensus2000  SPANPanel1results.  Table8showsthat,generally,thevalidSSNratesarehighandtheinvalidratesarelowforboth X the1992SQTandCensus2000Panel1.Basedontheseresults,wecansaythatrespondentsdo D agoodjobreportingaccurateSSNswhentheychoosetoreportanSSN. 0    Table8.Comparisonof1992SQTandCensus2000Panel1validandinvalidSSNrates  X *+V,dd[dd [9dd 99dd 99dd 99dd 99dd 9SVT(#(#,dd ,rdd ,rdd +  6VV%DD 6` XX @@ VerificationStatus @VV/!"VV @ȐdB  ԍ(10,p5,R43)C  Ȑd1992SQT*Ȑd @VV/!"VV @ȐdB  Ȑd(21,p1,R50)ȐdC  Census2000Panel1 N='" VV N Valid (SSNandnamematched;dateofbirthandgender x matchedasrequiredbymatchingprocess) @/!>  @@@*91.00% F5!x!3 F94.83% TVC-x"3  T Invalid (SSN,name,orothernonmatch) @V/!R#V @@@+9.00% FV5!R$3V F5.17%=31R%3  V =#XX `]#` XX*Raceisnotincludedasamatchingvariable.#XX `8a# %         "  N @*    XX5.RECOMMENDATIONS#XX 'b#  x ' bThispapershowsthat,ifreported,SSNsareaccurate.Thereisasmallbutstatistically x") significantdifferencebetweenHCAandLCA.ThereisnoevidencethatrequestingSSNfor d#* Person1only,allpersonsinhousehold,orinclusionofgeneralorspecificnotificationof P$+ administrativerecordsuseaffectsthequalityofthereportedSSN. <% , However,toassesstheusefulnessofrequestingSSNwithintheuniqueenvironmentofa 'd". decennialcensus,wemustalsoconsiderthereductioninmailresponsewhenSSNisrequested, (P#/ increasedSSNitemnonresponse,theextenttowhichhavingavalidSSNallowsustolinkto (<$0 otherfiles,andtheextenttowhichweareabletoobtaincorrectinformationfromsuchalink. )(%1 Tothisend,werecommendthefollowingresearch: *&2  +'3 [    "3"  3f2A3  0    LookatthecumulativenonresponsetoSSN(unitnonresponse,SSNitemnonresponse,and  SSNinvalidrates)toobtainanindicatoroftheextenttowhichmatchingtoadministrative  recordscouldtakeplace.3ff݌(#(# Ќ  "3 "  3\h2A3  0    Conductanalysisofthecharacteristicsofhouseholdsthatprovideanddonotprovidethe ` SSN,theaccuracyofhouseholdsreconstructedfromadministrativerecords,andtheeffectof L  havingandnothavingtheSSNinhouseholdreconstruction.Inconjunctionwiththeaccuracy 8  oftheSSNs,thisanalysiswouldbeanindicatorofthequalityofdatawemightexpect.3\hh݌$ t(#(# Ќ  "3 "  3j2A3  0    UsethecumulativenonresponsetoSSNandtheresultsofotherresearchtoconductacost  L  benefitanalysistodeterminetheextenttowhichwecoulduseadministrativerecordsdatato  8  completehouseholdenumeration(assumingdecennialcensuspopulationandhousingunit $  universeswithindecennialcensustimeconstraints).3jj݌ (#(# Ќ  "3 "  3l2A3  0    ConductfocusgroupsorresearchsimilartotheSurveyofPrivacyAttitudeslaterinthe   decade.XXXXThisSurveyofPrivacyAttitudesexaminedpattensofattitudechangeinthepublics   privacyconcernsbetween1996,1999,and2000.#XXXXm#GiventheprofoundimpactofSeptember p 11,2001,wemayexpectchangingviewsonprivacyattitudes.3lm݌\(#(# Ќ  "3 "  3ro2A3  0    ContinuetoworkcloselywiththePrivacyOfficeandprivacyadvocatestostayinformedof 4 trendsintheprivacyandconfidentialityarena.3roo݌ p(#(# Ќ  @*  ЫXXAcknowledgments#XXЫp#  H pIwishtothankDebbieBoltonandRandallNeugebauerfortheirinitiation,design,and 2 implementationofthisCensus2000experiment;HenryWoltman,JoanHill,JenniferGuarino,  CourtneyStapleton,andJasonMachowskiforthestatisticalexpertiseandguidance;Dean   JudsonandDebbieWagnerforprocessingtheSSNverificationdata;andGeorgeTrainand  JacquesWilmoreforprocessingtheverificationdataforanalysis.          "  N  z  [        D      L   ЫXXReferences#XXЫ2t#  j  #tAdministrativeRecordsStaff. StatisticalAdministrativeRecordsSystem,1999!SocialSecurity T"  NumberVerificationProgrammingSpecification,U.S.CensusBureau;Planning,Research,and @#! EvaluationDivision.October12,2000. ,$|" AguirreInternational. PublicConcernsAbouttheUseofAdministrativeRecords,Contractors &T!$ report,July1995.XXXX &@"% Bates,N. RevisedItemNonresponseResultsforSocialSecurityNumberFromtheSimplified ($' QuestionnaireTest(SQT),MemorandumtoRobertD.TorturaandSusanM.Miskura,dated )%( June18,1992. *%) #XXXX`v#XXXXDeMaio,T.J.,andBates,N.A.(1990) WhoFillsOuttheCensusForm?,Proceedingsofthe x,'+ SurveyResearchMethodsSectionoftheAmericanStatisticalAssociation. d-(, ЇDillman,DonA.,Sinclair,MichaelD.,andClark,JohnR.(1993) EffectsofQuestionnaire  Length,RespondentFriendlyDesign,andaDifficultQuestiononResponseRatesforOccupant  AddressedCensusMailSurveys,PublicOpinionQuarterly,Vol.57,pp289304.  #XXXXw#Gates,G.W.,andBolton,D.(1998) PrivacyResearchInvolvingExpandedStatisticalUsesof ` AdministrativeRecords,ProceedingsoftheSectiononGovernmentStatisticsandSectionon L  SocialSciencesoftheAmericanStatisticalAssociation. 8  XXXXGuarino,J.A.,Hill,J.M.,andWoltman,H.F. AnalysisoftheSocialSecurityNumber  ` NotificationComponentoftheSocialSecurityNumber,PrivacyAttitudes,andNotification  L  Experiment.U.S.CensusBureau;Planning,Research,andEvaluationDivision.July3,2001.  8  Kulka,R.A.,Holt,N.A.,Carter,W.,andDowd,K.L.(1991) SelfReportsofTimePressures,   ConcernsforPrivacy,andParticipationinthe1990MailCensus,ProceedingsoftheAnnual   ResearchConference.   Leslie,TheresaF.,andTreat,JamesB. ResultsFromtheVerificationofSocialSecurity p NumbersCollectedDuringthe1992NationalContentTestI.U.S.CensusBureau;Decennial \ ManagementDivisionandDecennialStatisticalStudiesDivision.December14,1994. H QXXXXX5XXXX XXX5  #XX XXb{#XXXXQ<  Neugebauer,Randall, Census2000ExperimentationProgramMasterPlan:TheSocialSecurity  p Number,PrivacyAttitudes,andNotificationExperiment.U.S.CensusBureau;Planning,  \ Research,andEvaluationDivision.November5,1999.Q<݌ H ЌXXXXXXXXXXXX  ȐdȐdSinger,E.1978. InformedConsent:ConsequencesforResponseRateandResponseQualityin   SocialSurveys,AmericanSociologicalReview,Vol.43,Issue2,pp144162.   #XXXX#XXXXSinger,E.,Mathiowetz,N.A.,andCouper,M.(1993) TheImpactofPrivacyandConfidentiality  ConcernsonSurveyParticipation:TheCaseofthe1990U.S.Census,PublicOpinion  Quarterly,Vol57,pp465482. l Singer,E.,VanHoewyk,J.,Tourangeau,R.,Steiger,D.M.,Montgomery,M.,Montgomery,R., D!  19992000SurveysofPrivacyAttitudes.U.S.CensusBureau;Planning,Research,and 0"  EvaluationDivision.December10,2001. #l! #XXXXт#XXXXStapleton,CourtneyN.(2002) TheEffectofAdministrativeRecordUseNotificationonSocial $D # SecurityNumberReports,ProceedingsoftheSurveyResearchMethodsSectionofthe %0!$ AmericanStatisticalAssociation.#XXXXL#XXXX &"% #XXXX#U.S.CensusBureau. Census2000EvaluationProgramQualityAssuranceProcess.Decennial (#' StatisticalStudiesDivisionandPlanning,Research,andEvaluationDivision.July31,2000. )$(   |*%) Oa    р ЫXXAppendix:AbbreviatedSocialSecurityNumberVerificationProcedures l#  3         #XXЫ=#B  Ȑd(1,pages1015,R34)C  Ȑd UsingthelasttwodigitsoftheSSN,invalidentries(nonnumeric)areflaggedandnotrun  throughtheverificationprogram.  Theremaininginputrecordsgothroughthefollowingprocess: `   (Axx "3"  32A3  0    Inputrecordsarestandardized,thatis,thenamesare:3݌8 (#(# Ќ  0  1)parsed(placedintofirst,middle,andlastnamefields,ifavailable) ` (#(# 0  2)standardizednamesareadded(forexample,DebbieisstandardizedtoDeborah;Jimto 8  James)$ (#(# "3"  32A3  0    SSNfortheinputrecordismatchedtotheNumident.NonmatchesareassignedanAflag.3݌ (#(# Ќ  "3"  32A3  0    SSNontheinputfilematchestheNumidentfile.Theinputrecordisrunthroughaseriesof  matchesuntilitisflagged.(Eachsubsequentmatchimpliesthattheinputrecordwasa p nonmatchatthepreviousstep.Forexample,arecordthatdoesnotmatchtheNumident \ name,goestothematchfortheNumidentalternatename.IfitmatchestheNumident H alternatename,itisassigneda2flaganddoesnotgotonextmatch.)3*݌4(#(# Ќ  "3"    32A3  0    TheparsednameontheinputrecordismatchedtotheNumidentasfollows:3݌ \(#(# Ќ  "3"  0  0(#(#32A3  0(#(#  MatchedtotheNumidentname!amatchonallorpartofthenamegoestoa 4 decisionlogictablethatincludesbirthyear(+2)andgender.Ifcertainconditions   aremet,itisassigneda1flag3݌ (#(# Ќ  "3"  0  0(#(#32A3  0(#(#  MatchedtotheNumidentalternate(previous)names!amatchonallorpartofthe  namegoestoadecisionlogictablethatincludesbirthyearandgender.Ifcertain  conditionsaremet,itisassigneda2flag.3ӓ݌l (#(# Ќ  "3"  0  0(#(#3b2A3  0(#(#  Theparsednameontheinputrecordisconcatenated(thatis,allnamesarejoined D"  togetherwithnospaces)andmatchedtotheNumident!amatchonallorpartofthe 0#! namegoestoadecisionlogictablethatincludesbirthyear.Ifcertainconditionsare $l" met,itisassigneda3flag.3b݌%X #(#(# Ќ  0  0(#(# &0"%(#(# 0  0(#(#"3"  32A3  0(#(#  TheparsednameontheinputrecordisconcatenatedandmatchedtotheNumident  alternatenames!amatchonallorpartofthenamegoestoadecisionlogictablethat  includesbirthyear.Ifcertainconditionsaremet,itisassigneda4flag.3)݌(#(# Ќ  ݀"3"    3ܙ2A3  0    ThestandardizednameontheinputrecordismatchedtotheNumidentasfollows:3ܙ݌`(#(# Ќ  "3 "  0  0(#(#32A3  0(#(#  MatchedtotheNumidentname!amatchonallorpartofthenamegoestoa 8  decisionlogictablethatincludesbirthyearandgender.Ifcertainconditionsare $ t met,itisassigneda5flag3=݌ `(#(# Ќ  "3 "  0  0(#(#32A3  0(#(#  MatchedtotheNumidentalternate(previous)names!amatchonallorpartofthe  8  namegoestoadecisionlogictablethatincludesbirthyearandgender.Ifcertain $  conditionsaremet,itisassigneda6flag.3݌ (#(# Ќ  "3 "  0  0(#(#32A3  0(#(#  Thestandardizednameontheinputrecordisconcatenated(thatis,allnamesare   joinedtogetherwithnospaces)andmatchedtotheNumident!amatchonallorpart   ofthenamegoestoadecisionlogictablethatincludesbirthyear.Ifcertain p conditionsaremet,itisassigneda7flag.3ޞ݌\(#(# Ќ  "3 "  0  0(#(#3Ҡ2A3  0(#(#  Thestandardizednameontheinputrecordisconcatenatedandmatchedtothe 4 Numidentalternatenames!amatchonallorpartofthenamegoestoadecision  p logictablethatincludesbirthyear.Ifcertainconditionsaremet,itisassignedan8  \ flag.3Ҡ݌H(#(# Ќ  0  0(#(# (#(# "3 "  0  3!2A3  0(#(#  Ifthereisnosuccessfulnamematch,therecordisassignedaBflag.