Translate Wisely! An Evaluation of Close and Adaptive Translation Procedures in an Experiment Involving Questionnaire Translation

To challenge the commonly made assumption in cross-national survey projects that close translation yields more comparable data than adaptation, we implemented a translation experiment in the CROss-National Online Survey Panel. The English source questionnaire was split into three batches of 20 items each and was translated by three translation teams into Estonian and three teams into Slovene. The teams received specific instructions on how to translate each batch (either closely or adaptively) so that, by design, the teams translated two batches following one approach and one following the other approach. Respondents in the two countries (Estonia and Slovenia) were randomly assigned to three distinct questionnaire versions based on the same source questionnaire, each consisting of translations by all three teams and including close and adaptive translations. We developed an analytical framework to assess the translation potential of the source items (i.e., all theoretically possible translations of a specific item) and the actual translation scores (i.e., the degree of closeness vs. adaptiveness of a specific translation). We show that some items are more sensitive to the wording (small linguistic changes result in a different response behavior) while others are more robust (the meaning of the concept is retained despite linguistic changes).