Increasingly, telephone interviewing has become the data collection procedure of choice in large-scale health services research surveys. Previous analyses indicate that excluding nontelephone households does not seriously affect most national parameter estimates, such as yearly estimates of number of ambulatory visits, mainly because the proportion of households without telephones is small. Moreover, if the exclusion of nontelephone households simply underestimates the proportions in the population with certain characteristics, such as age and ethnicity, and the "true" proportions are known, it is possible to appropriately weight the study group in order to mitigate the telephone-exclusion bias. However, regression analyses undertaken on three years of national Health Interview Surveys indicate, at least on some key measures such as having health insurance, that persons living in households with and without telephones represent different populations, and parameter estimates are distorted by excluding nontelephone households. Under these circumstances, it is not possible to adjust parameter estimates to take into account nontelephone households.