Hello,
Thank you very much for looking at this. I have a "seasonal" user for R. I
teach my undergrads and graduates students statistics using R and often find
myself trying to solve problems to process student collected data in an
efficient way.
In this case, I have a data.frame with multiple observations. These are gas
concentrations in a chamber and are used to measure into rates, usually (not
not always), four or five observations per chamber.
Data are from several sites and multiple dates. I'd like to run a regression
to calculate the rate of emissions, for each date and site.
The regression is using concentration ~ Sample_interval (which is in
seconds).
lm(Concentration ~ Sample_interval, data=df)
The data.frame looks something like this:
Date Time Site
Sample_interval Concentration
10/03/09 5:00 Site 1
0 334
10/03/09 5:00 Site 1
566 355
10/03/09 5:00 Site 1
1005 367
10/03/09 5:00 Site 1
1244 384
10/03/09 5:00 Site 2
0 434
10/03/09 5:00 Site 2
466 455
10/03/09 5:00 Site 2
1005 437
10/03/09 5:00 Site 2 1349
474
10/12/09 5:00 Site 1
0 354
10/12/09 5:00 Site 1
506 359
10/12/09 5:00 Site 1
1065 377
10/12/09 5:00 Site 1
1184 394
10/12/09 5:00 Site 2
0 424
10/12/09 5:00 Site 2
396 495
10/12/09 5:00 Site 2 1022
497
10/12/09 5:00 Site 2
1304 574
I tried this:
bylist.lm <- by(df, list(df$Date, df$Site),
function(x) lm(Concentration~Sample_interval, data=x))
Then, I get a list of stuff...which seems hard very exact much...
I tried this...
rate <- (sapply(bylist.lm, coef)[2,])
and got, the rates, but I can't figure out how to line them up with the "by"
variables.
So... In a perfect world, I would like to get a data frame with the
intercept, slope, r.square, p.value for each date, site, so the question
involves extracting from a "by" class, and mode "list". Granted, I have been
confused for a few years on how to think about classes and modes...so some
insight there would also be quite appreciated...
--
Marc Los Huertos
Assistant Professor
Science and Environmental Policy
100 Campus Drive
Seaside CA, 93955
831-582-3209
[[alternative HTML version deleted]]
______________________________________________
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.
