PLEASE REMOVE THIS MESSAGE AND PREVIOUS COPIES ! - Many thanks
Dear All, In the following simple case I can't seem to get an improved fit, despite trying all of the control possibilities. As there seem to be no examples anywhere which show use of functions such as "dnorm" within a formula, and as I am not confident at all that my formula is correctly configured, I would appreciate some feedback ! Many thanks in advance. library(minpack.lm) gg<-c(170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209) dd<-c(1673, 1659, 1738, 1687, 1882, 2010, 2202, 2248, 2409, 2417, 2215, 2279, 2539, 2479, 2341, 2395, 2314, 2404, 2369, 2254, 2048, 1899, 1892, 1744, 1333, 1183, 982, 772, 526, 451, 335, 253, 157, 108, 67, 44, 26, 12, 10, 0) dd100000 <- dd * 0.00001 dd100000gg <- data.frame(dd100000, gg) ## modLM4: modLM4 <- nlsLM(dd100000 ~ dnorm(gg, mu,sigma, log = FALSE), data = dd100000gg, start = c(mu = 190, sigma = 10), trace = TRUE) windows() ## plot data plot(gg, dd100000, main = "modLM4") ## plot fitted values lines(gg, fitted(modLM4), col = 2, lwd = 2) On Thu, Nov 21, 2013 at 11:57 AM, Jeremy Clark <jeremyclark...@gmail.com> wrote: > Dear All, > > In the following simple case I can't seem to get an improved fit, > despite trying all of the control possibilities. As there seem to be > no examples anywhere which show use of functions such as "dnorm" > within a formula, and as I am not confident at all that my formula is > correctly configured, I would appreciate some feedback ! Many thanks > in advance. > > library(minpack.lm) > > gg<-c(170, 171, 172, 173, 174, 175, > 176, 177, 178, 179, 180, 181, 182, > 183, 184, 185, 186, 187, 188, 189, > 190, 191, 192, 193, 194, 195, 196, > 197, 198, 199, 200, 201, 202, > 203, 204, 205, 206, 207, 208, 209) > > dd<-c(1673, 1659, 1738, 1687, 1882, 2010, 2202, > 2248, 2409, 2417, 2215, 2279, 2539, 2479, 2341, > 2395, 2314, 2404, 2369, 2254, 2048, 1899, > 1892, 1744, 1333, 1183, 982, 772, 526, > 451, 335, 253, 157, 108, 67, 44, > 26, 12, 10, 0) > > dd100000 <- dd * 0.00001 > > dd100000gg <- data.frame(dd100000, gg) > > ## modLM4: > > modLM4 <- nlsLM(dd100000 ~ dnorm(gg, mu,sigma, log = FALSE), data = > dd100000gg, start = c(mu = 190, sigma = 10), trace = TRUE) > > windows() > ## plot data > plot(gg, dd100000, main = "modLM4") > ## plot fitted values > lines(gg, fitted(modLM4), col = 2, lwd = 2) -- MEDIMEL, www.plastic-surgery-poland.co.uk www.chirurgia-szczecin.pl Jeremy Clark. Address: ul. Klonowica 45/2, 71-249 Szczecin, Poland. ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.