348:
224:
135:
421:
239:
477:
385:
444:
561:
43:
have any power in explaining the response variable, the model is misspecified in the sense that the data generating process might be better approximated by a
60:
604:
55:
540:; Trivedi, Pravin K. (1993). "Some Specification Tests for the Linear Regression Model". In Bollen, Kenneth A.; Long, J. Scott (eds.).
143:
549:
517:
628:
28:
78:
559:
Thursby, J. G.; Schmidt, P. (1977). "Some
Properties of Tests for Specification Error in a Linear Regression Model".
35:
model. More specifically, it tests whether non-linear combinations of the explanatory variables help to explain the
623:
475:
Ramsey, J. B. (1969). "Tests for
Specification Errors in Classical Linear Least Squares Regression Analysis".
455:
343:{\displaystyle y=\alpha x+\gamma _{1}{\hat {y}}^{2}+\cdots +\gamma _{k-1}{\hat {y}}^{k}+\varepsilon ,}
40:
390:
360:
590:
578:
486:
505:
600:
545:
513:
426:
231:
36:
32:
570:
51:
617:
537:
574:
594:
446:
coefficients are zero is rejected, then the model suffers from misspecification.
44:
20:
39:. The intuition behind the test is that if non-linear combinations of the
582:
490:
354:
219:{\displaystyle (\beta x)^{2},(\beta x)^{3},\ldots ,(\beta x)^{k}}
25:
Ramsey
Regression Equation Specification Error Test (RESET) test
506:"Classical model selection through specification error tests"
599:(Sixth ed.). Cengage Learning. pp. 273–278.
429:
393:
363:
242:
146:
81:
478:Journal of the Royal Statistical Society, Series B
438:
415:
379:
342:
218:
129:
130:{\displaystyle {\hat {y}}=E\{y\mid x\}=\beta x.}
562:Journal of the American Statistical Association
230:. This is executed by estimating the following
596:Introductory Econometrics – A Modern Approach
8:
512:. New York: Academic Press. pp. 13–47.
112:
100:
16:Statistical test for model misspecification
423:are zero. If the null-hypothesis that all
428:
401:
392:
368:
362:
325:
314:
313:
300:
281:
270:
269:
262:
241:
210:
182:
160:
145:
83:
82:
80:
61:Journal of the Royal Statistical Society
467:
47:or another non-linear functional form.
7:
58:in 1968, and later published in the
353:and then testing, by a means of an
140:The Ramsey test then tests whether
54:as part of his Ph.D. thesis at the
542:Testing Structural Equation Models
14:
544:. London: Sage. pp. 66–110.
56:University of Wisconsin–Madison
575:10.1080/01621459.1977.10480627
416:{\displaystyle ~\gamma _{k-1}}
319:
275:
207:
197:
179:
169:
157:
147:
88:
1:
380:{\displaystyle \gamma _{1}~}
226:has any power in explaining
508:. In Zarembka, Paul (ed.).
645:
50:The test was developed by
510:Frontiers in Econometrics
439:{\displaystyle \gamma ~}
629:Regression diagnostics
591:Wooldridge, Jeffrey M.
504:Ramsey, J. B. (1974).
440:
417:
381:
344:
220:
131:
441:
418:
382:
345:
221:
132:
41:explanatory variables
427:
391:
361:
240:
144:
79:
456:Harvey–Collier test
72:Consider the model
436:
413:
377:
340:
216:
127:
624:Statistical tests
606:978-1-305-27010-7
435:
396:
376:
322:
278:
232:linear regression
91:
68:Technical summary
37:response variable
33:linear regression
636:
610:
586:
555:
524:
523:
501:
495:
494:
472:
445:
443:
442:
437:
433:
422:
420:
419:
414:
412:
411:
394:
386:
384:
383:
378:
374:
373:
372:
349:
347:
346:
341:
330:
329:
324:
323:
315:
311:
310:
286:
285:
280:
279:
271:
267:
266:
229:
225:
223:
222:
217:
215:
214:
187:
186:
165:
164:
136:
134:
133:
128:
93:
92:
84:
644:
643:
639:
638:
637:
635:
634:
633:
614:
613:
607:
589:
558:
552:
536:
533:
531:Further reading
528:
527:
520:
503:
502:
498:
474:
473:
469:
464:
452:
425:
424:
397:
389:
388:
364:
359:
358:
312:
296:
268:
258:
238:
237:
227:
206:
178:
156:
142:
141:
77:
76:
70:
52:James B. Ramsey
17:
12:
11:
5:
642:
640:
632:
631:
626:
616:
615:
612:
611:
605:
587:
556:
550:
538:Long, J. Scott
532:
529:
526:
525:
518:
496:
485:(2): 350–371.
466:
465:
463:
460:
459:
458:
451:
448:
432:
410:
407:
404:
400:
371:
367:
351:
350:
339:
336:
333:
328:
321:
318:
309:
306:
303:
299:
295:
292:
289:
284:
277:
274:
265:
261:
257:
254:
251:
248:
245:
213:
209:
205:
202:
199:
196:
193:
190:
185:
181:
177:
174:
171:
168:
163:
159:
155:
152:
149:
138:
137:
126:
123:
120:
117:
114:
111:
108:
105:
102:
99:
96:
90:
87:
69:
66:
15:
13:
10:
9:
6:
4:
3:
2:
641:
630:
627:
625:
622:
621:
619:
608:
602:
598:
597:
592:
588:
584:
580:
576:
572:
568:
564:
563:
557:
553:
551:0-8039-4506-X
547:
543:
539:
535:
534:
530:
521:
519:0-12-776150-0
515:
511:
507:
500:
497:
492:
488:
484:
480:
479:
471:
468:
461:
457:
454:
453:
449:
447:
430:
408:
405:
402:
398:
369:
365:
356:
337:
334:
331:
326:
316:
307:
304:
301:
297:
293:
290:
287:
282:
272:
263:
259:
255:
252:
249:
246:
243:
236:
235:
234:
233:
211:
203:
200:
194:
191:
188:
183:
175:
172:
166:
161:
153:
150:
124:
121:
118:
115:
109:
106:
103:
97:
94:
85:
75:
74:
73:
67:
65:
63:
62:
57:
53:
48:
46:
42:
38:
34:
31:test for the
30:
29:specification
27:is a general
26:
22:
595:
566:
560:
541:
509:
499:
482:
476:
470:
352:
139:
71:
59:
49:
24:
18:
569:: 635–641.
618:Categories
462:References
45:polynomial
21:statistics
431:γ
406:−
399:γ
366:γ
335:ε
320:^
305:−
298:γ
291:⋯
276:^
260:γ
250:α
201:β
192:…
173:β
151:β
119:β
107:∣
89:^
64:in 1969.
593:(2016).
450:See also
387:through
357:whether
583:2286231
491:2984219
603:
581:
548:
516:
489:
434:
395:
375:
355:F-test
23:, the
579:JSTOR
487:JSTOR
601:ISBN
546:ISBN
514:ISBN
571:doi
19:In
620::
577:.
567:72
565:.
483:31
481:.
609:.
585:.
573::
554:.
522:.
493:.
409:1
403:k
370:1
338:,
332:+
327:k
317:y
308:1
302:k
294:+
288:+
283:2
273:y
264:1
256:+
253:x
247:=
244:y
228:y
212:k
208:)
204:x
198:(
195:,
189:,
184:3
180:)
176:x
170:(
167:,
162:2
158:)
154:x
148:(
125:.
122:x
116:=
113:}
110:x
104:y
101:{
98:E
95:=
86:y
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.