Any advice on the required sample size, described below, would be appreciated. ----------------------------------------------------------------------- Mark A Mullee Senior Research Fellow in Medical Statistics Tel: +44 (0)23 8079 6570 / 4206 e-mail: [log in to unmask] Fax: +44 (0)23 8079 6529 ----- Original Message ----- From: "S.S.Salvi" <[log in to unmask]> To: <[log in to unmask]> Sent: Monday, May 26, 2003 11:23 AM > Dear Dr Mullee, > > I have worked in the Department of University Medicine with Professor Stephen > Holgate at Southampton from 1994 until 2002 and obtained a PhD from the > University in Clinical Medicine. I have now returned back to India and have > joined as Director and Head of Chest Research Foundation, a newly developed > research institute in the city of Pune dedicated for research in the field of > asthma and related airways disorders. I am also an honorary visiting clinical > research fellow at the University of Southampton. > > I am writing to you with a special request and advice on medical statistics and > I sincerely hope that you could give me some advice. At the Chest Research > Foundation in Pune, India we are planning to develop normal predictive values > for the standard lung function tests using spirometry for the Indian people. In > India we do not have these values. Several doctors have done small sample sized > studies in some Indian cities and use them for their predictive equations. Most > of them use European values with some conversion factor. We wanted to develop > these values at a national level from a sample size that represents the entire > nation. India is a large country with very diverse geography, different races > and different physical builds. Our main problem here is to determine the sample > size for such a study. I have gone through all the published literature where > they have calculated predicted values for the european population or the > american population, but none of them have given the sample size calculation. I > have also discusses with some experts in this field but none of them seem to > know how to go about this. Lung function increases with age until the age of 30 > and slowly declines over a period of time. The variables that determine > pulmonary function tests are age, sex, height, race and weight. > > I would be grateful if you could at least give me some direction as to how we > can go about this. We were planning to do the study in around 10-15 different > centres in India but do not know what sample size we should use. Your help > would be much appreciated. > > I would be most grateful for your response. > > With kind regards and best wishes. > > Yours sincerely, > > Dr Sundeep Salvi MD, DNB, PhD (UK) > Director and Head > Chest Research Foundation > Marigold Premises > Kalyaninagar > Pune 411 014 > INDIA > > > > > Dr Sundeep Salvi MD, DNB, PhD > University Medicine > Level D Centre Block > Southampton General Hospital > Southampton SO16 6YD > UK > > Tel No: + 44 2380 776029 > Fax No: +44 2380 701771 > E Mail: [log in to unmask] or [log in to unmask] >