HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Email this article to a friend Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Blance, A. Search for Related Content PubMed PubMed Citation Articles by Blance, A.

The importance of being statistical

Journal of Orthodontics

In the previous Editorial (December, 2004), the Editor-in-Chief discussed the raison d’être of the journal. With specific regard to the scientific papers it contains, this purpose unarguably has to be the advancement of science—the ‘gospel’ that should lie behind every clinical decision made. The question then becomes ‘how best to aid this advancement?’ A reasonable answer would be to provide papers of the highest scientific quality. Study design, execution, analysis and reporting of the findings all then become central.

When undertaking research, collaborations as part of a multi-disciplinary team would seem to be sensible. Clinicians and statisticians (with other specialities as required, specific to each project), working in partnership, would appear to have the best potential for producing studies of a high scientific quality that are in line with the Declaration of Helsinki. One should remember that it is as unethical to conduct research using unsound statistical procedures, as it is with any other violation. High quality research, by definition, should be consistent with the philosophy of ethical approval, with the proposed study being able to answer the research question with the highest possible degree of scientific robustness.

The question posed by the Editor-in-Chief ‘would we get a statistician to do orthodontics on our patients?’ should hopefully be answered by a resounding and emphatic no. However, the situation is not so clear-cut for the clinician. Once a paper is published, it is ultimately the responsibility of the clinician to consider the science and act upon it accordingly. That again poses another question—how does the clinician ‘consider’ the science. Many may suggest that, after reading the title of a paper, the next step is to skip to the conclusion section and read the take-home message. Unfortunately, that is far from job done. Critical appraisal is a skill that practising clinicians should have in their arsenal and invariably requires an understanding of at least the most rudimentary medical statistics. The consequences of not carefully critically appraising the evidence can be disastrous—clinical practice may change without the sound evidence to support it.

In writing this, it would appear that the key word is ‘highest’. We all continually work to improve standards and, for things to improve, things must change. Hopefully, everyone is agreed that it is best that these changes are based on the ‘highest’ standards of evidence. By introducing a more rigorous statistical element to the peer review process, the journal hopes to prompt contributors to continually strive to undertake research of the highest scientific standard. In particular, we hope to stress the necessity for appropriate statistics. One consequence of this will hopefully be to provide the interested clinician with high quality scientific evidence, which they can then subject to their critical appraisal skills. We may not achieve our goal, but if we do not try we will never succeed.

This Article Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Email this article to a friend Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Blance, A. Search for Related Content PubMed PubMed Citation Articles by Blance, A.