Muhammad Shahzad Shamim  ( Section of Neurosurgery, Department of Surgery, Aga Khan University Hospital, Karachi. )

We thank the author for his noteworthy comments on our paper.¹ It is not unusual for two group of researchers to differ in their categorization of a study design, and indeed there appear overlaps if one isn\\\'t careful in designing a particular study. In retrospect, we do see why it is felt that our published paper may be categorized as an observational study, but I would like to point out that a case control study is categorised on the basis of presence or absence of exposure, rather than outcome.
We also read with interest the second and third suggestions made by the author, especially the point where he mentions the presence of confounders. We agree that the small sample size is a definite limitation of our study, which not only limits drawing conclusions from it, but at the same time, overestimates the significance of p-value. We however disagree that the confounders have not been looked at. The two study groups were comparable both in terms of presence (or absence) of co-morbidities, and also the disease severity, as partly mentioned in the methodology. Other confounders were similarly looked at. Under these circumstances, a propensity score approach did not seem necessary. The details of the methodology may have been omitted due to editorial requirements of the journal. Controlling the confounders was perhaps easier to do, given the small sample size, which brings us to the same limitation of the study that is the sample size. We cannot emphasize enough the importance of bigger data, which naturally would have sorted out these problems. We cannot argue with the statement that randomisation would have been more reasonable.
We once again thank the author for his comments and hope the response clarifies some of the queries.


Reference

1. Shamim MS, Enam SA, Tahir MZ, Khan M. Prospective case control evaluation of epidural midazolam for improving pain and ambulation after microdiscectomy. J Pak Med Assoc 2012; 62: 561-5.