Dear sir, In the four parameter logistic model used in MEDME algorithm, M = f mCpGwbini, (a,b,c,d) + Ɛ         =  b +       c - b              + Ɛ                      1 + expa∗(log mCpGwbini - logd) What do the symbol "Ɛ" and parameters a,b,c,d signify?Could you kindly explain this formula?also,the reason for using the exponential form in the denominator instead of natural logarithm? Thanking you in anticipation, Susan Student,Masters in Molecular Biology and Human Genetics, Manipal Life Sciences Center, Manipal,India The INTERNET now has a personality. YOURS! See your Yahoo! Homepage. [[alternative HTML version deleted]]

On Thu, Nov 12, 2009 at 7:00 AM, Susan Bosco <susanbosco86@yahoo.com> wrote: > Dear sir, > In the four parameter logistic model used in MEDME algorithm, > > .... > > What do the symbol "Ɛ" and parameters a,b,c,d signify?Could you kindly > explain this formula?also,the reason for using the exponential form in the > denominator instead of natural logarithm? > > Hi, Susan. If you do this in R, you can get the citation for the paper which might contain an answer: library(MEDME) citation('MEDME') Sean [[alternative HTML version deleted]]

epsilon is the error term in the model and represents the slop in estimating the model terms (a,b,c,d) as far as using exp in the denominator, look closer; they're forcing a quantity to be positive. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2556264/?tool=pubmed neat paper, hadn't seen it before On Thu, Nov 12, 2009 at 4:00 AM, Susan Bosco <susanbosco86@yahoo.com> wrote: > Dear sir, > In the four parameter logistic model used in MEDME algorithm, > M = f mCpGwbini, > (a,b,c,d) + Ɛ > > > > > > > > > > > > > = b + c - b + Ɛ > 1 + > expa∗(log mCpGwbini - logd) > > What do the symbol "Ɛ" and parameters a,b,c,d signify?Could you kindly > explain this formula?also,the reason for using the exponential form in the > denominator instead of natural logarithm? > > Thanking you in anticipation, > Susan > Student,Masters in Molecular Biology and Human Genetics, > Manipal Life Sciences Center, > Manipal,India > > > The INTERNET now has a personality. YOURS! See your Yahoo! Homepage. > [[alternative HTML version deleted]] > > > _______________________________________________ > Bioconductor mailing list > Bioconductor@stat.math.ethz.ch > https://stat.ethz.ch/mailman/listinfo/bioconductor > Search the archives: > http://news.gmane.org/gmane.science.biology.informatics.conductor > > -- Statisticians, like artists, have a bad habit of falling in love with their models. --George Box [[alternative HTML version deleted]]