|
Journal of Postgraduate Medicine
Medknow Publications and Staff Society of Seth GS Medical College and KEM Hospital, Mumbai, India
ISSN: 0022-3859 EISSN: 0972-2823
Vol. 51, Num. 2, 2005, pp. 153-153
|
Journal of Postgraduate Medicine, Vol. 51, No. 2, April-June, 2005, pp. 153
Letters
Authors' Reply
Tayeb M., Raza Syed Ahsan, Khan M.R., Azami R.
Department of Surgery, Faculty of Health Sciences, The Aga Khan University, Stadium Road, P.O. Box 3500, Karachi
Correspondence Address: Department of Surgery, Faculty of Health Sciences,
The Aga Khan University, Stadium Road, P.O. Box 3500, Karachi, ahsan.raza@aku.edu
Code Number: jp05061
Sir,
We appreciate the comments by Dr. Bhattacharya on our paper to identify the risk factors for conversion to open cholecystectomy (OC). Male gender though pointed out as a major risk factor for conversion; was not identified in our study[1] as a potential risk factor. Hence, we did not include it in the final multivariate model. The goal of our analysis using logistic regression was to present the best fitting yet the most parsimonious model describing the independent relationship of factors with conversion to OC. The criteria for selection of possible factors was based on a p value of less than 0.25 on univariate analysis,[2] and therefore ′gender′ was not a good variable to be selected ( P value = 0.39) for the final model. Use of p value of 0.25 as a screening criterion for selection of candidate factor is based on work by Mickey and Greenland on logistic regression. These authors have shown that the use of a more traditional P value of 0.05 on univariate analysis often fails to identify the factors that are known to be important.[3],[4]
Dr. Bhattacharya has in fact extended and clarified other potential risk factors for OC very well. We believe that well-designed trials are needed that will present these risk factors in a more lucid way.
REFERENCES
| 1. | Tayeb M, Ahsan RS, Khan MR, Azami R. Conversion from laparoscopic to open cholecystectomy : Multivariate analysis of preoperative risk factors. J Postgrad Med 2005;51:17-20. Back to cited text no. 1 |
| 2. | Lemeshow S, Hosmer DW, Jr. A review of goodness of fit statistics for use in the development of logistic regression models. Am J Epidemiol 1982;115:92-106. Back to cited text no. 2 |
| 3. | Greenland S, Mickey RM. Re: The impact of confounder selection criteria on effect estimation. Am J Epidemiol 1989;130:1066. Back to cited text no. 3 [PUBMED] |
| 4. | Mickey RM, Greenland S. The impact of confounder selection criteria on effect estimation. Am J Epidemiol 1989;129:125-37. Back to cited text no. 4 [PUBMED] |
Copyright 2005 - Journal of Postgraduate Medicine
|
