Displaying 4 results from an estimated 4 matches for "tohver".
2009 Aug 07
2
create separate plots by factors
...ALDER 10 7897.1
ALDER 20 9208.1
ALDER 50 10949.3
ALDER 100 12287.6
ALDER 200 13650.2
ALDER 500 15493.6
AMERI 5 43656.5
AMERI 10 51475.3
AMERI 20 58854.4
AMERI 50 68233.3
AMERI 100 75135.9
AMERI 200 81908.3
Ingrid M Tohver
Research Scientist, Climate Impacts Group
University of Washington
2009 Feb 26
1
T-test by groups
I would like to run a t-test within a "by" group function. My
dataset, "error", is organized as the following (I have 133 Sites):
Site week Dataset Region lat_map long_map mean_tsim diff20 diff40
diff80
ALFI 15 USACE UC 48.15625 -117.0938 8.87 1.34 1.90
2.98
ALFI 16 USACE UC 48.15625 -117.0938 10.28 0.57 1.08
2.27
ALFI 17
2008 May 29
1
cbind results to original data frame
I have the following script, which gives me a prediction for each of
my observations (> 49k), and subsets my data frame by site (n = 183):
ts <- (by(dem16,dem16['Site'],function(dat)
try(predict(nls(Tw ~ mu + ((alpha - mu)/
(1 + exp(gamma*(B - Mean_air)))),
data = dat,
start = list(mu = 0.8, alpha = 21.8, gamma = 0.22, B =
12.8),
2008 Jun 04
0
for loop or "by" group in EF function
Hello,
I would like to apply the EF function (a goodness of fit test between
predicted (ts2) and observed (Tw) values in the qualV package) to
each of the Sites in my data frame. However, when I try the following
script, R gives an error message that lists unused arguments, which
include the Tw and ts2 that are explicitly in the function:
nsc = by(tsdem16, tsdem16['Site'],