Consider the following questionnaire item:

The instructor's verbal facility is: 1) Much below average 2) Below average 3) Average 4) Above average 5) Much above average

Associating scale values of 1 through 5 to these categories can yield highly misleading results. The mean for all instructors on this item might be 4.1, which, possibly ludicrously, might suggest that the average instructor was above average. Unless there were evidence that most of the instructors in question were actually better than average with respect to some reference group, the charge of "lying with statistics" might well be raised.

A related difficulty arises with items like:

The instructor grades fairly. 1) Agree 2) Tend to agree 3) Undecided 4) Tend to disagree 5) Disagree

There is no assurance whatsoever that a subject choosing the middle scale position harbors a neutral opinion. A subject's choice of the scale midpoint may result from:

• Ignorance--the subject has no basis for judgment.
• Uncooperativeness--the subject does not want to go to the trouble of formulating an opinion.
• Reading difficulty--the subject may choose "Undecided" to cover up inability to read.
• Reluctance to answer--the subject may wish to avoid displaying his/her true opinion.
• Inapplicability--the question does not apply to the subject.

In all the above cases, the investigator's best hope is that the subject will not respond at all. Unfortunately, the seemingly innocuous middle position counts, and, when a number of subjects choose it for invalid reasons, the average response level is raised or lowered erroneously (unless, of course, the mean of the valid responses is exactly at the scale midpoint).

The reader may well wonder why neutral response positions are so prevalent on questionnaires. One reason is that, in the past, crude computational methods were unable to cope with missing data. In such cases, nonresponses were actually replaced with neutral response values to avoid this problem. The need for such a makeshift solution has long been supplanted by improved computational methods, but the practice of offering a neutral response position seems to have a life of its own.

Responders sometimes tend to resist making a choice in one direction or the other. In the absence of a neutral option, the following strategies may alleviate this problem:

• Encourage omission of a response when a decision cannot be reached.
• Word responses so that a firm stand may be avoided, e.g., "tend to disagree."
• If possible, help responders with reading or interpretation problems, but take care to do so impartially and carefully document the procedure so that it may be inspected for possible introduction of bias.
• Include options explaining inability to respond, such as "not applicable," "no basis for judgment," "prefer not to answer."

The preceding discussion notwithstanding, there are some items that virtually require a neutral position. Examples are:

How much time do you spend on this job now? 1) Less than before 2) About the same 3) More time

The amount of homework for this course was 1) too little. 2) reasonable. 3) too great.

It would be unrealistic to expect a responder to judge a generally comparable or satisfactory situation as being on one side or another of the scale midpoint.