This corpus-based study examines the diachronic development of the that/zero alternation with three verbs of cognition, viz. think, believe, and suppose by means of a stepwise logistic regression analysis. The data comprised a total of (n = 9,720) think, (n=4,767) believe, and (n=4,083) suppose tokens from both spoken and written corpora from 1560 to 2012. We test the effect of 11 structural features that have been claimed to predict the presence of the zero complementizer form. Taking our cue from previous research suggesting that there has been a diachronic increase in zero use and applying a rigorous quantitative method to a large set of diachronic data, we examine (i) whether there is indeed a diachronic trend toward more zero use, (ii) whether the conditioning factors proposed in the literature indeed predict the zero form, (iii) to what extent these factors interact, and (iv) whether the predictive power of the conditioning factors becomes stronger or weaker over time. The analysis shows that, contrary to the aforementioned belief that the zero form has been on the increase, there is in fact a steady decrease in zero use. The extent of this decrease is not the same for all verbs. Also, the analysis of interactions with verb type indicates differences between verbs in terms of the predictive power of the conditioning factors. Additional significant interactions emerged, notably with verb, mode (i.e., spoken or written data), and period. The interactions with period show that certain factors that are good predictors of the zero form overall lose predictive power over time.