31:
768:
455:
763:{\displaystyle {\begin{aligned}(3)\qquad &\operatorname {mean} (\ln({\text{wages}}_{A}))-\operatorname {mean} (\ln({\text{wages}}_{B}))\\={}&b_{A}\operatorname {mean} (X_{A})-b_{B}\operatorname {mean} (X_{B})\\={}&b_{A}(\operatorname {mean} (X_{A})-\operatorname {mean} (X_{B}))+\operatorname {mean} (X_{B})(b_{A}-b_{B})\end{aligned}}}
371:
805:
found in a paper entitled, "School
Quality and Black-White Relative Earnings: A Direct Assessment" that improvements in the quality of schools for Black men born in the Southern states of the United States between 1915 and 1966 increased the return to education for these men, leading to narrowing of
814:
coefficient reflected a difference in the quality of education for Black workers which could have otherwise been interpreted as an effect of direct discrimination; differences in the quality of education for Black workers would reflect historical or 'indirect' discrimination against them.
157:
126:
who proposed a similar approach in the same year. Oaxaca's original research question was the wage differential between two different groups of workers (male vs. female), but the method has since been applied to numerous other topics.
460:
797:(against women in Oaxaca's application). This is because other explanatory variables not included in the regression (e.g. because they are unobserved) may also account for wage differences. For example,
366:{\displaystyle {\begin{aligned}(1)\qquad \ln({\text{wages}}_{A_{i}})&=X_{A_{i}}\beta _{A}+\mu _{A_{i}}\\(2)\qquad \ln({\text{wages}}_{B_{i}})&=X_{B_{i}}\beta _{B}+\mu _{B_{i}}\end{aligned}}}
162:
793:
The unexplained differential in wages for the same values of explanatory variables should not be interpreted as the amount of the difference in wages due only to
1065:
1157:
1118:
34:
Using
Blinder-Oaxaca decomposition one can distinguish between "change of mean" contribution (purple) and "change of effect" contribution
806:
the black-white earnings gap. In terms of wage regressions, the poor quality of schools for Black men had meant a lower value of the
107:
between two groups by decomposing the gap into within-group and between-group differences in the effect of the explanatory variable.
1095:
972:
832:
889:
1192:
1187:
823:
Oaxaca and
Sierminska argued that the Blinder–Oaxaca decomposition is a generalization of the Kitagawa decomposition.
1197:
773:
The first part of the last line of (3) is the impact of between-group differences in the explanatory variables
781:. The second part is the differential not explained by these differences in observed characteristics
136:
30:
1167:
446:
403:
119:
965:
Analyzing Health Equity Using
Household Survey Data: A Guide to Techniques and Their Implementation
794:
1020:
1012:
941:
906:
869:
111:
104:
1153:
1114:
1106:
1091:
1087:
1081:
1077:
968:
960:
380:
is a vector of explanatory variables such as education, experience, industry, and occupation,
1066:"MIT Graduate Labor Economics 14.662 Spring 2015 Lecture Note 1: Wage Density Decompositions"
989:
810:
coefficient on years of schooling for Black men than for White men. Thus, some of this lower
1145:
1132:
1004:
933:
898:
861:
45:
135:
The following three equations illustrate this decomposition. Estimate separate linear wage
122:
and eventually published in 1973. The decomposition technique also carries the name of
1149:
1181:
1128:
1024:
924:
Blinder, A. S. (1973). "Wage
Discrimination: Reduced Form and Structural Estimates".
115:
17:
802:
123:
798:
887:
Oaxaca, R. (1973). "Male-Female Wage
Differentials in Urban Labor Markets".
852:
Kitagawa, Evelyn M. (1955). "Components of a
Difference Between Two Rates".
1136:
1016:
990:"School Quality and Black-White Relative Earnings: A Direct Assessment"
910:
873:
945:
1008:
902:
865:
1039:
937:
29:
100:
118:
introduced this method in economics in his doctoral thesis at
99:, is a statistical method that explains the difference in the
66:
1105:
Cahuc, Pierre; Carcillo, Stéphane; Zylberberg, André (2014).
961:"Explaining Differences between Groups: Oaxaca Decomposition"
87:
81:
72:
1071:. Massachusetts Institute of Technology: MIT OpenCourseWare.
57:
110:
The method was introduced by sociologist and demographer
1107:"Decomposition Methods: The Case of the Gender Wage Gap"
1086:(Second ed.). Boston: Irwin McGraw-Hill. pp.
458:
160:
84:
69:
60:
63:
54:
51:
78:
75:
48:
1040:"Oaxaca-Blinder Meets Kitagawa: What Is the Link?"
762:
365:
1172:Journal of the American Statistical Association
854:Journal of the American Statistical Association
819:Differences between Kitagawa and Blinder–Oaxaca
967:. World Bank Publications. pp. 147–158.
777:, evaluated using the coefficients for group
8:
427:be respectively the regression estimates of
1113:. Cambridge: MIT Press. pp. 504–514.
1168:The Generalized Oaxaca-Blinder Estimator.
1131:; Lemieux, Thomas; Firpo, Sergio (2011).
747:
734:
718:
690:
665:
643:
635:
619:
600:
584:
565:
557:
538:
533:
499:
494:
459:
457:
449:in a linear regression is zero, we have:
351:
346:
333:
321:
316:
294:
289:
284:
252:
247:
234:
222:
217:
195:
190:
185:
161:
159:
1166:Kevin Guo & Guillaume Basse. 2021. "
959:O'Donnell, Owen A.; et al. (2008).
844:
7:
1133:"Decomposition Methods in Economics"
988:Card, David; Krueger, Alan (1992).
445:. Then, since the average value of
25:
1064:Autor, David (January 30, 2015).
398:are vectors of coefficients and
44:
1038:Oaxaca; Sierminska (May 2023).
472:
273:
174:
997:Quarterly Journal of Economics
833:Standardization (demographics)
753:
727:
724:
711:
699:
696:
683:
671:
658:
649:
625:
612:
590:
577:
547:
544:
529:
520:
508:
505:
490:
481:
469:
463:
302:
280:
270:
264:
203:
181:
171:
165:
1:
1150:10.1016/S0169-7218(11)00407-2
890:International Economic Review
1144:. Elsevier. pp. 1–102.
40:Oaxaca-Blinder decomposition
1138:Handbook of Labor Economics
1214:
1078:"Measuring Discrimination"
1076:Borjas, George J. (2000).
926:Journal of Human Resources
764:
367:
97:Kitagawa decomposition
35:
1049:. IZA DP No. (16188).
1047:IZA Discussion Papers
765:
368:
33:
456:
158:
120:Princeton University
18:Oaxaca decomposition
1193:Observational study
1188:Regression analysis
860:(272): 1168–1194.
760:
758:
363:
361:
112:Evelyn M. Kitagawa
105:dependent variable
36:
27:Statistical method
1159:978-0-444-53450-7
1120:978-0-262-02770-0
536:
497:
287:
188:
95:), also known as
16:(Redirected from
1205:
1198:Causal inference
1163:
1143:
1124:
1101:
1072:
1070:
1051:
1050:
1044:
1035:
1029:
1028:
994:
985:
979:
978:
956:
950:
949:
921:
915:
914:
884:
878:
877:
849:
769:
767:
766:
761:
759:
752:
751:
739:
738:
723:
722:
695:
694:
670:
669:
648:
647:
636:
624:
623:
605:
604:
589:
588:
570:
569:
558:
543:
542:
537:
534:
504:
503:
498:
495:
372:
370:
369:
364:
362:
358:
357:
356:
355:
338:
337:
328:
327:
326:
325:
301:
300:
299:
298:
288:
285:
259:
258:
257:
256:
239:
238:
229:
228:
227:
226:
202:
201:
200:
199:
189:
186:
139:for individuals
94:
93:
90:
89:
86:
83:
80:
77:
74:
71:
68:
65:
62:
59:
56:
53:
50:
21:
1213:
1212:
1208:
1207:
1206:
1204:
1203:
1202:
1178:
1177:
1160:
1141:
1127:
1121:
1111:Labor Economics
1104:
1098:
1083:Labor Economics
1075:
1068:
1063:
1060:
1058:Further reading
1055:
1054:
1042:
1037:
1036:
1032:
1009:10.2307/2118326
992:
987:
986:
982:
975:
958:
957:
953:
923:
922:
918:
903:10.2307/2525981
886:
885:
881:
866:10.2307/2281213
851:
850:
846:
841:
829:
821:
791:
757:
756:
743:
730:
714:
686:
661:
639:
637:
629:
628:
615:
596:
580:
561:
559:
551:
550:
532:
493:
473:
454:
453:
444:
435:
426:
417:
397:
388:
360:
359:
347:
342:
329:
317:
312:
305:
290:
283:
261:
260:
248:
243:
230:
218:
213:
206:
191:
184:
156:
155:
133:
47:
43:
28:
23:
22:
15:
12:
11:
5:
1211:
1209:
1201:
1200:
1195:
1190:
1180:
1179:
1176:
1175:
1164:
1158:
1129:Fortin, Nicole
1125:
1119:
1102:
1096:
1073:
1059:
1056:
1053:
1052:
1030:
1003:(1): 151–200.
980:
973:
951:
938:10.2307/144855
932:(4): 436–455.
916:
897:(3): 693–709.
879:
843:
842:
840:
837:
836:
835:
828:
825:
820:
817:
795:discrimination
790:
789:Interpretation
787:
771:
770:
755:
750:
746:
742:
737:
733:
729:
726:
721:
717:
713:
710:
707:
704:
701:
698:
693:
689:
685:
682:
679:
676:
673:
668:
664:
660:
657:
654:
651:
646:
642:
638:
634:
631:
630:
627:
622:
618:
614:
611:
608:
603:
599:
595:
592:
587:
583:
579:
576:
573:
568:
564:
560:
556:
553:
552:
549:
546:
541:
531:
528:
525:
522:
519:
516:
513:
510:
507:
502:
492:
489:
486:
483:
480:
477:
474:
471:
468:
465:
462:
461:
440:
431:
422:
413:
393:
384:
374:
373:
354:
350:
345:
341:
336:
332:
324:
320:
315:
311:
308:
306:
304:
297:
293:
282:
279:
276:
272:
269:
266:
263:
262:
255:
251:
246:
242:
237:
233:
225:
221:
216:
212:
209:
207:
205:
198:
194:
183:
180:
177:
173:
170:
167:
164:
163:
132:
129:
26:
24:
14:
13:
10:
9:
6:
4:
3:
2:
1210:
1199:
1196:
1194:
1191:
1189:
1186:
1185:
1183:
1173:
1169:
1165:
1161:
1155:
1151:
1147:
1140:
1139:
1134:
1130:
1126:
1122:
1116:
1112:
1108:
1103:
1099:
1097:0-07-231198-3
1093:
1089:
1085:
1084:
1079:
1074:
1067:
1062:
1061:
1057:
1048:
1041:
1034:
1031:
1026:
1022:
1018:
1014:
1010:
1006:
1002:
998:
991:
984:
981:
976:
974:9780821369340
970:
966:
962:
955:
952:
947:
943:
939:
935:
931:
927:
920:
917:
912:
908:
904:
900:
896:
892:
891:
883:
880:
875:
871:
867:
863:
859:
855:
848:
845:
838:
834:
831:
830:
826:
824:
818:
816:
813:
809:
804:
800:
796:
788:
786:
784:
780:
776:
748:
744:
740:
735:
731:
719:
715:
708:
705:
702:
691:
687:
680:
677:
674:
666:
662:
655:
652:
644:
640:
632:
620:
616:
609:
606:
601:
597:
593:
585:
581:
574:
571:
566:
562:
554:
539:
526:
523:
517:
514:
511:
500:
487:
484:
478:
475:
466:
452:
451:
450:
448:
443:
439:
434:
430:
425:
421:
416:
412:
407:
405:
401:
396:
392:
387:
383:
379:
352:
348:
343:
339:
334:
330:
322:
318:
313:
309:
307:
295:
291:
277:
274:
267:
253:
249:
244:
240:
235:
231:
223:
219:
214:
210:
208:
196:
192:
178:
175:
168:
154:
153:
152:
150:
146:
142:
138:
130:
128:
125:
121:
117:
116:Ronald Oaxaca
113:
108:
106:
102:
98:
92:
41:
32:
19:
1171:
1137:
1110:
1082:
1046:
1033:
1000:
996:
983:
964:
954:
929:
925:
919:
894:
888:
882:
857:
853:
847:
822:
811:
807:
803:Alan Krueger
792:
782:
778:
774:
772:
441:
437:
432:
428:
423:
419:
414:
410:
408:
399:
394:
390:
385:
381:
377:
375:
148:
144:
140:
134:
124:Alan Blinder
109:
96:
39:
37:
137:regressions
1182:Categories
839:References
799:David Card
404:error term
143:in groups
1025:150859258
741:−
709:
681:
675:−
656:
610:
594:−
575:
527:
518:
512:−
488:
479:
447:residuals
344:μ
331:β
278:
245:μ
232:β
179:
114:in 1955.
827:See also
1088:362–366
1017:2118326
911:2525981
874:2281213
1156:
1117:
1094:
1023:
1015:
971:
946:144855
944:
909:
872:
402:is an
376:where
131:Method
1142:(PDF)
1069:(PDF)
1043:(PDF)
1021:S2CID
1013:JSTOR
993:(PDF)
942:JSTOR
907:JSTOR
870:JSTOR
535:wages
496:wages
286:wages
187:wages
103:of a
101:means
1154:ISBN
1115:ISBN
1092:ISBN
969:ISBN
801:and
706:mean
678:mean
653:mean
607:mean
572:mean
515:mean
476:mean
436:and
418:and
409:Let
389:and
147:and
38:The
1146:doi
1005:doi
1001:107
934:doi
899:doi
862:doi
1184::
1170:"
1152:.
1135:.
1109:.
1090:.
1080:.
1045:.
1019:.
1011:.
999:.
995:.
963:.
940:.
928:.
905:.
895:14
893:.
868:.
858:50
856:.
785:.
524:ln
485:ln
406:.
275:ln
176:ln
151::
88:ɑː
82:ɑː
73:ɑː
67:ər
58:aɪ
1174:.
1162:.
1148::
1123:.
1100:.
1027:.
1007::
977:.
948:.
936::
930:8
913:.
901::
876:.
864::
812:β
808:β
783:X
779:A
775:X
754:)
749:B
745:b
736:A
732:b
728:(
725:)
720:B
716:X
712:(
703:+
700:)
697:)
692:B
688:X
684:(
672:)
667:A
663:X
659:(
650:(
645:A
641:b
633:=
626:)
621:B
617:X
613:(
602:B
598:b
591:)
586:A
582:X
578:(
567:A
563:b
555:=
548:)
545:)
540:B
530:(
521:(
509:)
506:)
501:A
491:(
482:(
470:)
467:3
464:(
442:B
438:β
433:A
429:β
424:B
420:b
415:A
411:b
400:μ
395:B
391:β
386:A
382:β
378:Χ
353:i
349:B
340:+
335:B
323:i
319:B
314:X
310:=
303:)
296:i
292:B
281:(
271:)
268:2
265:(
254:i
250:A
241:+
236:A
224:i
220:A
215:X
211:=
204:)
197:i
193:A
182:(
172:)
169:1
166:(
149:B
145:A
141:i
91:/
85:k
79:h
76:ˈ
70:w
64:d
61:n
55:l
52:b
49:ˈ
46:/
42:(
20:)
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.