Evidence-Based Survey Design: The Use of Negatively Worded Items in Surveys

Abstract

A close examination of the literature on including positively and negatively worded items in structured survey questionnaires revealed that contrary to the traditional wisdom, it is better not to use a mix of positively and negatively worded items because doing so can create threats to validity and reliability of the survey instrument. If mixing is done, it is recommended to use strategies derived from research to improve the quality of data and the instrument's validity and reliability.