Data Editing

The first task in data processing is the editing. It is the process by which data are prepared for subsequent coding. As it is a very subjective process, it is necessary that persons, who are well qualified and trained in the job of editing, should alone be entrusted with this responsibility.

Editing is the process of examining errors and omissions in the collected data and making necessary corrections in the same. This is desirable when there is some inconsistency in the response or responses as entered in the questionnaire or when it contains only a partial or a vague answer. A few examples will indicate how editing can be helpful.

The respondent has given answers which are inconsistent with each other. In such a case, the editor has to change one of the answers so as to make it consistent with the others. He has to use his judgment to decide which answer is correct so that the other one can be suitably changed.

If the respondent has marked two answers instead of one for a particular question In such a case, the editor has to carefully examine which of the two answers would be more accurate. Sometimes, when a decision cannot be made categorically, he may prefer to code ‘no information’ for that question.

The respondent has answered a question by checking one of the many possible categories contained in the questionnaire. In addition, the respondent has written some remarks in the margin. These remains do not go well with the particular category marked by the respondent. The editor has to look into this and may have to change the category to better represent the remarks made by the respondent.

Sometimes the questionnaires contain imaginary and fictitious data. This may be due to cheating by the interviewers who may fill in the entries in the questionnaire without actually interviewing the respondent. This may also happen in case of a mail questionnaire, where the respondent has given an arbitrary answer without exercising any care. If the responses indicate obvious inaccuracy, they may be either dropped or suitably modified if they are to be retained. The editor has to exercise his judgment in this regard.

In all cases where editorial corrections are to be made, it is necessary that these should be kept distinct from the changes made either by the respondent or by the interviewer. This can be ensured by the editor by using a different colored pencil for editing the raw data.

Editing can be undertaken both at the time when the field survey is in progress and when it has been completed. In the former case, it is known as field editing. When the interviewer fills in the information at the time of the interview, he often uses several abbreviations due to the paucity of time. These need to be spelt out fully later. It is advisable for the interviewer to carefully look into the questionnaire at the earliest possible opportunity after the interview so that he can enter the proper responses or complete the partial answers.

Another type of editing is central editing, which is undertaken after the questionnaires have been received at the headquarters. As far as possible, a single editor should carry out this task so that consistency in editing can be ensured. However, in the case of large studies, this may not be physically possible. When two or more editors are entrusted with the task of editing, it is necessary that they be given uniform guidelines so that maximum possible consistency in their approaches can be attained. An alternative way would be to split the entire task into two or more parts so that each part of the work can be looked after by one single editor. In such a case, chances of inconsistencies pertaining to the responses of a particular part can be almost fully avoided.

An editor should be well versed with the editing of questionnaires. It may be emphasized that editing a manuscript is different from the editing of a questionnaire or numeric data. People who are good at editing descriptive material may not be able to edit numeric data satisfactory. Persons who are quite efficient in detecting flaws or errors in the data in just one glance should be entrusted with this job. Enumerators with long experience and having a special aptitude for editing of data should be given preference over others.

When the services of more than one editor are required, it is advisable to give each one explicit editing instruction in order to ensure consistency in the editing of data.

Before undertaking the coding, tabulating and analysis of responses contained in questionnaires, they should be checked for completeness, accuracy and uniformity.

The first point to check is that questionnaires are complete and do not have any omissions or partial responses. Sometimes, the interviewer might have forgotten to record the answer. In such cases, it may be difficult to fill in the gap as the interviewer may be unable to recollect the answer given by the respondent. When several questions remain unanswered in a questionnaire, the whole questionnaire may have to be excluded. However, before doing so, all other alternatives should be exhausted and the questionnaire should be disposed of only it unavoidable.

The second point to check is that questionnaires contain accurate answers. The editor should look for inconsistent answers, which are sometimes so obvious that a little careful perusal may detect them. Such inconsistencies should be removed. Sometimes inaccuracies may be a result of the carelessness of the interviewer who may mark a wrong code or put the mark in such a way that it is not clear which of the two codes is intended. At times the respondent may give wrong or misleading answers deliberately. In all such cases the editor has to go over the answers carefully and try to remove the inconsistency in the best possible manner.

Finally, one should check whether the interviewers have interpreted questions and instructions uniformly. While going through the questionnaires filled in by different interviewers (or respondents in case of a mail questionnaire), the editor would be able to make out such inconsistencies.

In dealing with these three points – completeness, accuracy and uniformity, the editor should see that far too much time is not spent on trivial or relatively minor errors.