Effect of Items Direction (Positive or Negative) on the Factorial Construction and Criterion related Validity in Likert Scale

Abstract

Developers of attitudinal questionnaires/ scales (of which questionnaires that compute satisfaction with usability are one type) are trained to consider questionnaire response styles such as extreme response bias and acquiescence bias. In acquiescence bias, respondents tend to agree with all or almost all statements in a questionnaire (Lewis and Sauro, 2009). The acute response bias is the inclination to mark the extremes of rating scales rather than points near the middle of the scale. To the amount that these biases exist, the affected responses do not provide a true measure of an attitude. Acquiescence bias is of particular apprehension because it leads to an upward error in measurement, giving researchers too positive a picture of whatever attitude they are measuring.