{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T22:13:39Z","timestamp":1777414419365,"version":"3.51.4"},"reference-count":45,"publisher":"Cambridge University Press (CUP)","issue":"5","license":[{"start":{"date-parts":[[2009,10,1]],"date-time":"2009-10-01T00:00:00Z","timestamp":1254355200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Econom. Theory"],"published-print":{"date-parts":[[2009,10]]},"abstract":"<jats:p>Difficulties with inference in predictive regressions are generally attributed to strong persistence in the predictor series. We show that the major source of the problem is actually the nuisance intercept parameter, and we propose basing inference on the restricted likelihood, which is free of such nuisance location parameters and also possesses small curvature, making it suitable for inference. The bias of the restricted maximum likelihood (REML) estimates is shown to be approximately 50% less than that of the ordinary least squares (OLS) estimates near the unit root, without loss of efficiency. The error in the chi-square approximation to the distribution of the REML-based likelihood ratio test (RLRT) for no predictability is shown to be<jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"gif\" mimetype=\"image\" xlink:type=\"simple\" xlink:href=\"S0266466608090464_eqi1\"><jats:alt-text>$({\\textstyle{3 \\over 4}} - \\rho ^2)n^{ - 1} (G_3 (\\cdot) - G_1 (\\cdot)) + O(n^{ - 2}),$<\/jats:alt-text><\/jats:inline-graphic>where |<jats:italic>\u03c1<\/jats:italic>| &lt; 1 is the correlation of the innovation series and<jats:italic>G<jats:sub>s<\/jats:sub><\/jats:italic>(\u00b7) is the cumulative distribution function (c.d.f.) of a<jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"gif\" mimetype=\"image\" xlink:type=\"simple\" xlink:href=\"S0266466608090464_eqi2\"><jats:alt-text>$\\chi _s^2 $<\/jats:alt-text><\/jats:inline-graphic>random variable. This very small error, free of the autoregressive (AR) parameter, suggests that the RLRT for predictability has very good size properties even when the regressor has strong persistence. The Bartlett-corrected RLRT achieves an<jats:italic>O<\/jats:italic>(<jats:italic>n<\/jats:italic><jats:sup>\u22122<\/jats:sup>) error. Power under local alternatives is obtained, and extensions to more general univariate regressors and vector AR(1) regressors, where OLS may no longer be asymptotically efficient, are provided. In simulations the RLRT maintains size well, is robust to nonnormal errors, and has uniformly higher power than the Jansson and Moreira (2006,<jats:italic>Econometrica<\/jats:italic>74, 681\u2013714) test with gains that can be substantial. The Campbell and Yogo (2006,<jats:italic>Journal of Financial Econometrics<\/jats:italic>81, 27\u201360) Bonferroni Q test is found to have size distortions and can be significantly oversized.<\/jats:p>","DOI":"10.1017\/s0266466608090464","type":"journal-article","created":{"date-parts":[[2009,9,3]],"date-time":"2009-09-03T10:25:18Z","timestamp":1251973518000},"page":"1143-1179","source":"Crossref","is-referenced-by-count":33,"title":["BIAS REDUCTION AND LIKELIHOOD-BASED ALMOST EXACTLY SIZED HYPOTHESIS TESTING IN PREDICTIVE REGRESSIONS USING THE RESTRICTED LIKELIHOOD"],"prefix":"10.1017","volume":"25","author":[{"given":"Willa W.","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit S.","family":"Deo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"56","published-online":{"date-parts":[[2009,10,1]]},"reference":[{"key":"S0266466608090464_ref40","doi-asserted-by":"publisher","DOI":"10.2307\/3315411"},{"key":"S0266466608090464_ref20","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/67.3.525"},{"key":"S0266466608090464_ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF02491500"},{"key":"S0266466608090464_ref21","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/61.2.383"},{"key":"S0266466608090464_ref26","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-0262.2006.00679.x"},{"key":"S0266466608090464_ref41","doi-asserted-by":"publisher","DOI":"10.2307\/3314722"},{"key":"S0266466608090464_ref19","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9892.2005.00452.x"},{"key":"S0266466608090464_ref14","doi-asserted-by":"publisher","DOI":"10.1080\/07474939608800361"},{"key":"S0266466608090464_ref36","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1111\/j.2517-6161.1996.tb02101.x","article-title":"A conditional likelihood approach to residual maximum likelihood estimation in generalized linear models","volume":"58","author":"Smyth","year":"1996","journal-title":"Journal of the Royal Statistical Society, Series B"},{"key":"S0266466608090464_ref1","doi-asserted-by":"publisher","DOI":"10.1017\/S0022109000003227"},{"key":"S0266466608090464_ref4","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/40.1-2.12"},{"key":"S0266466608090464_ref7","first-page":"22","article-title":"Valid asymptotic expansions for the likelihood ratio statistic and other perturbed chi-square variables","volume":"41","author":"Chandra","year":"1979","journal-title":"Sankhya, Series A"},{"key":"S0266466608090464_ref29","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176325490"},{"key":"S0266466608090464_ref38","first-page":"259","article-title":"Application of maximum likelihood methods to finite samples","volume":"37","author":"Sprott","year":"1975","journal-title":"Sankhya, Series B"},{"key":"S0266466608090464_ref5","unstructured":"Campbell J. & Yogo M. (2005) Implementing the Econometric Methods in \u201cEfficient Tests of Stock Return Predictability.\u201d Available at http:\/\/finance.wharton.upenn.edu\/~yogo\/."},{"key":"S0266466608090464_ref17","volume-title":"Statistical Methods and Scientific Inference","author":"Fisher","year":"1973"},{"key":"S0266466608090464_ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF02532797"},{"key":"S0266466608090464_ref3","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/75.2.374"},{"key":"S0266466608090464_ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2005.08.002"},{"key":"S0266466608090464_ref39","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/67.3.515"},{"key":"S0266466608090464_ref10","unstructured":"Chen W. & Deo R. (2007) The Chi-Square Approximation of the Restricted Likelihood Ratio Test for the Sum of Autoregressive Coefficients with Interval Estimation. Working paper, Texas A & M and New York University."},{"key":"S0266466608090464_ref12","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/74.2.265"},{"key":"S0266466608090464_ref23","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/62.2.451"},{"key":"S0266466608090464_ref42","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-405X(99)00041-0"},{"key":"S0266466608090464_ref16","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176343282"},{"key":"S0266466608090464_ref31","volume-title":"Testing Statistical Hypotheses, 3rd ed","author":"Lehmann","year":"2005"},{"key":"S0266466608090464_ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfineco.2005.05.008"},{"key":"S0266466608090464_ref22","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1977.10480998"},{"key":"S0266466608090464_ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4076(91)90080-W"},{"key":"S0266466608090464_ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-3758(02)00239-2"},{"key":"S0266466608090464_ref43","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1111\/j.2517-6161.1989.tb01745.x","article-title":"On the use of marginal likelihood in time series model estimation","volume":"51","author":"Tunnicliffe Wilson","year":"1989","journal-title":"Journal of the Royal Statistical Society, Series B"},{"key":"S0266466608090464_ref45","unstructured":"van Giersbergen N. (2006) Bartlett Correction in the Stable AR(1) Model with Intercept and Trend. Working paper, Universiteit van Amsterdam."},{"key":"S0266466608090464_ref37","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/60.3.457"},{"key":"S0266466608090464_ref33","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176350167"},{"key":"S0266466608090464_ref32","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/41.3-4.390"},{"key":"S0266466608090464_ref35","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-4076(97)00052-3"},{"key":"S0266466608090464_ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfineco.2002.11.002"},{"key":"S0266466608090464_ref2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.2006.00887.x"},{"key":"S0266466608090464_ref9","unstructured":"Chen W. & Deo R. (2006) A Smooth Transition to the Unit Root Distribution via the Chi-Square Distribution with Interval Estimation for Nearly Integrated Autoregressive Processes. Working paper, Texas A & M and New York University."},{"key":"S0266466608090464_ref27","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1111\/j.2517-6161.1970.tb00830.x","article-title":"Application of likelihood methods to models involving large numbers of parameters","volume":"32","author":"Kalbfleisch","year":"1970","journal-title":"Journal of the Royal Statistical Society, Series B"},{"key":"S0266466608090464_ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2005.10.005"},{"key":"S0266466608090464_ref8","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2000.10474318"},{"key":"S0266466608090464_ref44","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9892.00122"},{"key":"S0266466608090464_ref13","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/81.4.709"},{"key":"S0266466608090464_ref11","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/82.2.433"}],"container-title":["Econometric Theory"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0266466608090464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T23:40:59Z","timestamp":1739317259000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0266466608090464\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,10]]},"references-count":45,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2009,10]]}},"alternative-id":["S0266466608090464"],"URL":"https:\/\/doi.org\/10.1017\/s0266466608090464","relation":{},"ISSN":["0266-4666","1469-4360"],"issn-type":[{"value":"0266-4666","type":"print"},{"value":"1469-4360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,10]]}}}