Yes it should look like that... what i am doing is a variogram fit . But the data of course are spread almost all over.. I would guess might be problem with the data only? -- View this message in context: http://r.789695.n4.nabble.com/nls-singular-gradient-as-always-tp4669859p4669898.html Sent from the R help mailing list archive at Nabble.com.