Comparison of forced-choice and subjective probability scales measuring behavioral intentions

Three surveys compared the accuracy of predictions based on forced-choice a nd subjective probability scales. The latter produced significantly more ac curate election predictions and significantly reduced the percentage of und ecided, or "Don't Know" responses, compared to forced-choice scales in all three surveys. Analysis indicates subjective probability scales decrease sa mpling error and confirms there is an inherent source of error in tradition al forced-choice questions about voting intentions not attributable to samp ling error. The results are discussed with respect to (1) sampling and meas urement errors in forced-choice and subjective probability scales measuring behavioral intentions, (2) their practical application, and (3) cognitive theory, especially support theory.