Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Seed, Paul" <paul.seed@kcl.ac.uk> |
To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
Subject | Re: st: Why many things have Normal distribution |
Date | Mon, 2 Sep 2013 17:59:51 +0000 |
Coming late to the party, can I point out that the main alternative in nature (and econometrics) to a Normal distribution is a logNormal distribution. This is so particularly for concentrations of biomarkers in blood, saliva, urine etc. It tends to apply whenever there is a clear lower bound at zero and no upper bound; but can also be explained by the rules of quantitative chemistry and the central limit theorem. The amount of the product from any reaction is in proportion to the products of the concentrations of the reactants. To put it another way, it is a matter of adding the logs. Hence, we expect the logs to be Normally distributed. In the case of incomes, just remember that most wage increase are a % of the current wage, not a fixed number of £,$ etc. per week. BW Paul T Seed, Senior Lecturer in Medical Statistics, Division of Women's Health, King's College London Women's Health Academic Centre, King's Health Partners (+44) (0) 20 7188 3642. * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/