How can we improve inferences from surveys? A new look at the convertible debt questions from the Graham and Harvey survey data

Abstract

We revisit the survey questions on convertible bond issue motives from the influential study of Graham and Harvey (2001). Our question-conditional analysis connecting survey answers with firm characteristics reveals that the conclusions on two of the four convertible debt theories from the original study need to be revised. More particularly, the delayed equity rationale and the sequential financing rationale on convertible bond issuance do not receive support from the question-conditional tests. Our results indicate that adding a question-conditional analysis is essential in obtaining correct inferences from survey data.