MAIL SURVEYS FOR ELECTION FORECASTING - AN EVALUATION OF THE COLUMBUSDISPATCH POLL

Because of slow turnaround time and typically low response rates, mail surveys have generally been considered of little value in election fo recasting, However, statewide mail surveys conducted by the Columbus D ispatch newspaper since 1980 have made remarkably accurate forecasts o f Ohio election outcomes. In comparison to statewide surveys by two ot her organizations employing conventional telephone interview methods, the mail surveys were consistently more accurate and were generally le ss susceptible to sources of inaccuracy such as high roll-off and low publicity. The mail survey's advantage is attributable at least in par t to larger sample sizes, sampling and response procedures that yielde d more representative samples of voters, lack of the need to allocate undecided respondents, and superior questionnaire design, These findin gs suggest that mail surveys not only may be viable alternatives to te lephone surveys but may actually be superior to them under some condit ions. Furthermore, these results demonstrate that surveys with low res ponse rates are not necessarily low in validity.