Ronaldo Reis Jr. chrysopa at insecta.ufv.br
Fri Jun 21 18:48:56 CEST 2002

```Hi,
Sorry by this newbie stat doubt, but with some brains in the list anybody can
help-me.

I have a sistem composed by 3 quantitative variables.
The variables are:

The growth (Y in cm)
The nutrient (X1 in gram)
The water (X2 in ml)

Ok,
My doubt is:
Is correct or necessary make a iterations of the nutrient and water, or the
iteraction is intrinsical of the model.

glm(growth~nutrient+water)

or

glm(growth~nutrient+water+nutrient:water)

Working with one quantitative explanatory variable e one qualitative
explanatory variable (with some levels), I understandy the iteration of
quantitative x qualitative, for testing the curve inclination. But when I
have some quantitative explanatory variables, the iteration generate a new
vector by x1*x2 and the number generated by this vector is no sense
(30g*2ml=60 and 2g*30ml=60, but is very different).

I need to make iteraction or not?

A less important question:

How to make a plot with this and a curve of this?
the curve function use only one x, I have two or more x in same function.

Thanks and sorry again
Ronaldo
--
His mind is like a steel trap: full of mice.
-- Foghorn Leghorn
--
|   //|\\   [*****************************][*******************]
|| ( õ õ )  [Ronaldo Reis Júnior          ][PentiumIII-600     ]
|     V     [ESALQ/USP-Entomologia, CP-09 ][HD: 30 + 10 Gb     ]
||  / l \   [13418-900 Piracicaba - SP    ][RAM: 128 Mb        ]
|  /(lin)\  [Fone: 19-429-4199 r.229      ][Video: SiS620-8Mb  ]
||/(linux)\ [chrysopa at insecta.ufv.br      ][Modem: Pctel-onboar]
|/ (linux) \[ICQ#: 5692561                ][SO: CL 7.0 (2.2.19)]
||  ( x )   [*****************************][*******************]