R help - Feb 2011 - loop with model fitting pair of consecutive pair of variable: mailing all of you because it was last option

Dear R-users and experts

I want to create to analyse my data which looks like follows:( I have show
only 8 variables but original variables  much more number >1000)


*sub*

*ydata*

*X1*

*X2*

*X3*

*X4*

*X5*

*X6*

*X7*

*X8*

1

12

1

1

1

2

1

1

1

1

2

13

2

2

1

2

2

1

1

1

3

11

1

1

1

2

1

2

1

2

4

12

1

1

2

1

1

2

2

2

5

14

1

2

2

1

1

2

2

2

6

12

2

1

1

2

2

1

1

1

7

8

2

2

2

2

1

1

2

1

8

19

1

1

1

1

1

2

2

1

9

6

2

2

2

1

1

1

1

2

I want to create look to fit models like the following:

lme(ydata ~ X1+ X2, random= intercept)

lme(ydata ~ X3+X4, random= intercept)

lme(ydata ~ X5+ X6, random= intercept)

lme(ydata ~ X7 + X8, random= intercept)

means that the loop should read all the X variables in files, but I do not
want to avoid litting lme(ydata ~ X2+ X3) or lme(ydata ~ X4+X5) or lme(ydata
~ X6+X7). Also I want only output the P value to a vector so that I can plot
the graph with X versus P value.

I have hard time with picking lme output to a vector. If it is impossible
please just suggest in term of linear model (lm), in this type I had no
option than adopt the lm nor lme.

I am sorry to bother you all but it only option remaining !

Thanks;

John

	[[alternative HTML version deleted]]