The　varying　coefficient　partially　linear　model　is　considered　in　this　paper　When　the　plug-in　estimators　of　coefficient　functions　are　used　the　resulting　smoothing　score　function　becomes　biased　due　to　the　slow　convergence　rate　of　nonparametric　estimations　To　reduce　the　bias　of　the　resulting　smoothing　score　function　a　profile-type　smoothed　score　function　is　proposed　to　draw　inferences　on　the　parameters　of　interest　without　using　the　quasi-likelihood　framework　the　least　favorable　curve　a　higher　order　kernel　or　under-smoothing　The　resulting　profile-type　statistic　is　still　asymptotically　Chi-squared　under　some　regularity　conditions　The　results　are　then　used　to　construct　confidence　regions　for　the　parameters　of　interest　A　simulation　study　is　carried　out　to　assess　the　performance　of　the　proposed　method　and　to　compare　It　with　the　profile　least-squares　method　A　real　dataset　is　analyzed　for　illustration　(C)　2010　Elsevier　Inc　All　rights　reserved