RT Journal Article T1 Asymptotic distribution-free tests for semiparametric regressions with dependent data A1 Escanciano, Juan Carlos A1 Pardo Fernández, Juan Carlos A1 Keilegom, Ingrid van K1 12 Matemáticas K1 1209 Estadística AB This article proposes a new general methodology for constructing nonparametricand semiparametric Asymptotically Distribution-Free (ADF) testsfor semiparametric hypotheses in regression models for possibly dependentdata coming from a strictly stationary process. Classical tests based on the differencebetween the estimated distributions of the restricted and unrestrictedregression errors are not ADF. In this article, we introduce a novel transformationof this difference that leads to ADF tests with well-known criticalvalues. The general methodology is illustrated with applications to testingfor parametric models against nonparametric or semiparametric alternatives,and semiparametric constrained mean–variance models. Several Monte Carlostudies and an empirical application show that the finite sample performanceof the proposed tests is satisfactory in moderate sample sizes. PB The Annals of Statistics SN 00905364 YR 2018 FD 2018-06 LK http://hdl.handle.net/11093/1031 UL http://hdl.handle.net/11093/1031 LA eng NO The Annals of Statistics, 46(3): 1167-1196 (2018) NO Ministerio de Economía y Competitividad. GrantMTM2014-55966-P DS Investigo RD 12-feb-2025