Calibration directly to population control totals, bypassing any explicit nonresponse adjustments, is one option for correcting for nonresponse bias. Poststratification, raking, and general regression estimation are alternative methods for single-step nonresponse adjustment through calibration. The models that underlie the response mechanism and the structure of outcome variables collected in a survey both affect the efficacy of these estimators. Consistent with earlier literature, we demonstrate that the model for the outcome variables is most important in determining bias, standard errors, and confidence interval coverage. However, if the predictive power of the model for an outcome variable is weak, properties of the aforementioned estimators of totals will be very similar.