This paper examines two- to five-year-old children's knowledge of inversion in English yes/no questions through a new experimental study. It challenges the view that the syntax for inversion develops slowly in child English and tests the hypothesis that grammatical competence for inversion is present from the earliest testable ages of the child's sentence production. The experimental design is based on the premise that a valid test of this hypothesis must dissociate from inversion various language-specific aspects of English grammar, including its inflectional system. An elicited imitation method was used to test parallel, lexically-matched declarative and question structures across several different verb types in a design which dissociated subject-auxiliary inversion from the English-specific realization of the inflectional/auxiliary system. Using this design, the results showed no significant difference in amount or type of children's errors between declarative (non-inverted) and question (inverted) sentences with modals or auxiliary be, but a significant difference for sentences with main verbs (requiring reconstruction of inflection through do-support) and copula be. The results from sentences with auxiliary be and those with modals indicate that knowledge of inversion is present throughout our very young sample and does not develop during this time. We argue that these results indicate that the grammar of inversion is present from the youngest ages tested. Our results also provide evidence of development relevant to the English-specific inflectional system. We conclude with a new developmental hypothesis: development in question formation occurs in integrating language-specific knowledge related to inflection with the principles of Universal Grammar which allow grammatical inversion.