plot and lm (2)

group <- c(rep(1,4),rep(2,5), 1)
plot(x,y, col="blue", pch=19)
points(x[group==2], y[group==2], col="red", pch=19)
abline(lm(y ~ x, data=qu, subset=group==2), col="red")

Date: Sun, 23 Sep 2001 15:03:53 -0300
From: Antonio Olinto <aolinto at bignet.com.br>
To: R-help <r-help at stat.math.ethz.ch>, Rashid Nassar <rnassar at duke.edu>
Subject: plot and lm (2)

Thanks for your reply Nassar.

What I really want is to overlay (like add=TRUE) the plots 1 and 2. With
plots "at the same screen" I meant overlaid and not one beside the other,
i.e., only one plot with all the points (1 to 10) in blue (or any other
color), the points 5 to 9 in red and a regression line from points 5 to 9.

Best regards,

Antonio Olinto

----- Original Message -----
From: "Rashid Nassar" <rnassar at duke.edu>
To: "Antonio Olinto" <aolinto at bignet.com.br>
Sent: Sunday, September 23, 2001 2:20 PM
Subject: Re: [R] plot and lm

One way to do this (if I understand you correctly):

qu

    x   y
1   1 1.0
2   2 2.0
3   3 3.0
4   4 4.0
5   5 4.4
6   6 4.1
7   7 3.2
8   8 3.1
9   9 2.4
10 10 2.7

qu$group <- c(rep(1,4),rep(2,5), 1)
attach(qu)
opar <- par(mfcol=c(1,2), pty="s")   # use pty="m" (default) if you

                                       #don't want square plots.

plot(x,y, col="blue", pch=19)
title("Plot 1")
plot(x[group==2], y[group==2], col="red", pch=19, main="Plot 2")
abline(lm(y ~ x, data=qu, subset=group==2), col="red")
detach(qu)
par(opar)

I hope this helps.

Rashid Nassar

On Sun, 23 Sep 2001, Antonio Olinto wrote:

Date: Sun, 23 Sep 2001 13:16:46 -0300
From: Antonio Olinto <aolinto at bignet.com.br>
To: R-help <r-help at stat.math.ethz.ch>
Subject: [R] plot and lm

Hello R-list,

 I'm trying to make a scatter plot with two dependent variables and a
regression line only for one "y", but I'm having some problems. Well, I

will

explain better what I'm doing - it's a method used to estimate the total
mortality rate in fish stocks.

Suppose a I have the following data (dat):

dat

      x     y
1    1   1.0
2    2   2.0
3    3   3.0
4    4   4.0
5    5   4.4
6    6   4.1
7    7   3.2
8    8   3.1
9    9   2.4
10 10  2.7

With plot(x,y col="blue", pch=19) and identify(x,y) I can identify the

blue

points that follow a descendent trend (negative slope). They are points

5 to

9. Let's call this plot 1.

With dat2 <- dat[c(5:9),] I can make another data.frame and and using
attach(dat2), plot(x,y, col="red", pch=19), reg <- lm(y~x) and

abline(reg) I

have another plot (plot 2) with red points and the regression line.

I would like to have in one plot all the points (1 to 10) in blue, the
points 5 to 9 in red and a regression line from points 5 to 9. In other
words, plots 1 and 2 at the same screen. I'm sure that it's possible to

do

this plot but after several attempts I decide to ask for your help in

this

Sunday morning.

Thanks for any suggestion,

Antonio Olinto
Fisheries Institute
Sao Paulo - BRAZL

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.

-.-.-

r-help mailing list -- Read

http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html

Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch

_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._.
_._