Tree Ring Lab 1
JTK
April 13, 2017
Run a multiple regression on each of the data categories as predictors of ring witdth index. This will output that is as follows: \(RWI = X_1 + X_2 + X_3 + X_4 + ... + X_8 + \epsilon\) Where \(X_n\) is each climate variable.
my.data <- read.csv(file="E:\\Flash Drive\\ESCI 407\\Data\\PRISM_climate_data.csv", header=TRUE, sep=",")
library(MASS)
par(mfrow=c(1:2))#set the plotting window to two figures side by side
#
# Here is the R code for the non-averaged models.
#
all.lm <- lm(all ~ mint + maxt + meant + maxvpd + minvpd + dewpt + ppt + snow , data=my.data)
all_tsme.lm <- lm(all_tsme ~ mint + maxt + meant + maxvpd + minvpd + dewpt + ppt + snow, data=my.data)
all_abam.lm <- lm(all_abam ~ mint + maxt + meant + maxvpd + minvpd + dewpt + ppt + snow, data=my.data)Summary Stats - RWI ~ climate variables.
summary(all.lm)##
## Call:
## lm(formula = all ~ mint + maxt + meant + maxvpd + minvpd + dewpt +
## ppt + snow, data = my.data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.082968 -0.022826 0.002966 0.032854 0.085152
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.955e+00 5.319e-01 3.675 0.00173 **
## mint -1.600e-01 7.942e-02 -2.015 0.05907 .
## maxt -2.122e-01 9.179e-02 -2.312 0.03282 *
## meant 3.336e-01 1.720e-01 1.940 0.06827 .
## maxvpd 2.376e-02 2.611e-02 0.910 0.37497
## minvpd -2.234e-02 2.796e-02 -0.799 0.43474
## dewpt 2.401e-02 3.525e-02 0.681 0.50433
## ppt -3.443e-05 3.672e-05 -0.937 0.36093
## snow -1.166e-04 2.161e-04 -0.539 0.59616
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.0555 on 18 degrees of freedom
## Multiple R-squared: 0.4032, Adjusted R-squared: 0.138
## F-statistic: 1.52 on 8 and 18 DF, p-value: 0.2186Summary Stats - TSME-RWI ~ climate variables.
summary(all_tsme.lm)##
## Call:
## lm(formula = all_tsme ~ mint + maxt + meant + maxvpd + minvpd +
## dewpt + ppt + snow, data = my.data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.101471 -0.051069 0.007462 0.045290 0.111979
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.406e+00 7.445e-01 1.888 0.0753 .
## mint -1.701e-01 1.112e-01 -1.530 0.1434
## maxt -2.199e-01 1.285e-01 -1.711 0.1042
## meant 4.308e-01 2.407e-01 1.790 0.0904 .
## maxvpd 3.027e-04 3.655e-02 0.008 0.9935
## minvpd -2.942e-02 3.914e-02 -0.752 0.4619
## dewpt -2.258e-03 4.933e-02 -0.046 0.9640
## ppt -4.355e-05 5.140e-05 -0.847 0.4079
## snow 3.279e-04 3.024e-04 1.084 0.2926
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.07768 on 18 degrees of freedom
## Multiple R-squared: 0.3759, Adjusted R-squared: 0.09853
## F-statistic: 1.355 on 8 and 18 DF, p-value: 0.2802Summary Stats - ABAM-RWI ~ climate variables.
summary(all_abam.lm)##
## Call:
## lm(formula = all_abam ~ mint + maxt + meant + maxvpd + minvpd +
## dewpt + ppt + snow, data = my.data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.103099 -0.035559 0.000754 0.037666 0.090794
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.587e+00 5.772e-01 4.481 0.000289 ***
## mint -1.485e-01 8.618e-02 -1.723 0.102059
## maxt -2.034e-01 9.960e-02 -2.042 0.056112 .
## meant 2.216e-01 1.866e-01 1.188 0.250441
## maxvpd 5.072e-02 2.834e-02 1.790 0.090291 .
## minvpd -1.422e-02 3.034e-02 -0.469 0.644934
## dewpt 5.424e-02 3.825e-02 1.418 0.173189
## ppt -2.381e-05 3.985e-05 -0.598 0.557533
## snow -6.299e-04 2.345e-04 -2.687 0.015069 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.06022 on 18 degrees of freedom
## Multiple R-squared: 0.4946, Adjusted R-squared: 0.27
## F-statistic: 2.202 on 8 and 18 DF, p-value: 0.07831all.lm <- lm(all ~ maxvpd + minvpd + dewpt + ppt + snow , data=my.data)
all_tsme.lm <- lm(all_tsme ~ maxvpd + minvpd + dewpt + ppt + snow, data=my.data)
all_abam.lm <- lm(all_abam ~ maxvpd + minvpd + dewpt + ppt + snow, data=my.data)Three year averages
Summary Stats Moving average of all RWI ~ climate variables
Caluclate the three year moving averages for each variable
ma3 <- filter(x=my.data$all, filter=rep(x=1/3,times=3), sides=2)
ma_tsme3 <- filter(x=my.data$all_tsme, filter=rep(x=1/3,times=3), sides=2)
ma_abam3 <- filter(x=my.data$all_abam, filter=rep(x=1/3,times=3), sides=2)
maless_3 <- filter(x=my.data$less_3, filter=rep(x=1/3,times=3), sides=2)
magreater_3 <- filter(x=my.data$greater_3, filter=rep(x=1/3,times=3), sides=2)ma_tsme3.lm <- lm(ma_tsme3 ~ mint + maxt + meant + maxvpd + minvpd + dewpt + ppt + snow, data=my.data)
summary(ma_tsme3.lm)##
## Call:
## lm(formula = ma_tsme3 ~ mint + maxt + meant + maxvpd + minvpd +
## dewpt + ppt + snow, data = my.data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.091417 -0.028796 0.002048 0.031995 0.050208
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.706e+00 5.008e-01 3.407 0.00361 **
## mint -1.273e-01 6.785e-02 -1.876 0.07905 .
## maxt -1.692e-01 8.161e-02 -2.073 0.05471 .
## meant 2.706e-01 1.474e-01 1.836 0.08499 .
## maxvpd 9.908e-03 2.500e-02 0.396 0.69705
## minvpd -2.090e-02 2.527e-02 -0.827 0.42039
## dewpt 1.671e-02 3.065e-02 0.545 0.59308
## ppt 2.008e-05 3.179e-05 0.632 0.53661
## snow 2.049e-04 1.862e-04 1.100 0.28745
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.04741 on 16 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.4313, Adjusted R-squared: 0.147
## F-statistic: 1.517 on 8 and 16 DF, p-value: 0.2272ma_abam3.lm <- lm(ma_abam3 ~ mint + maxt + meant + maxvpd + minvpd + dewpt + ppt + snow, data=my.data)
summary(ma_abam3.lm)##
## Call:
## lm(formula = ma_abam3 ~ mint + maxt + meant + maxvpd + minvpd +
## dewpt + ppt + snow, data = my.data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.051822 -0.020459 0.002884 0.019201 0.049999
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.049e+00 3.894e-01 5.261 7.77e-05 ***
## mint -9.409e-02 5.276e-02 -1.783 0.09350 .
## maxt -1.487e-01 6.346e-02 -2.343 0.03239 *
## meant 1.813e-01 1.146e-01 1.583 0.13306
## maxvpd 2.803e-02 1.944e-02 1.442 0.16860
## minvpd -3.020e-02 1.965e-02 -1.537 0.14381
## dewpt 2.025e-02 2.383e-02 0.850 0.40802
## ppt -1.835e-06 2.472e-05 -0.074 0.94177
## snow -5.135e-04 1.448e-04 -3.546 0.00269 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.03687 on 16 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.5996, Adjusted R-squared: 0.3994
## F-statistic: 2.995 on 8 and 16 DF, p-value: 0.02946ma3.all.lm <- lm(ma3 ~ mint + maxt + meant + maxvpd + minvpd + dewpt + ppt + snow, data=my.data)
summary(ma3.all.lm)##
## Call:
## lm(formula = ma3 ~ mint + maxt + meant + maxvpd + minvpd + dewpt +
## ppt + snow, data = my.data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.04859 -0.02378 0.00293 0.01978 0.04689
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.865e+00 3.442e-01 5.419 5.68e-05 ***
## mint -1.119e-01 4.664e-02 -2.399 0.0290 *
## maxt -1.597e-01 5.610e-02 -2.847 0.0117 *
## meant 2.292e-01 1.013e-01 2.263 0.0379 *
## maxvpd 1.832e-02 1.718e-02 1.066 0.3020
## minvpd -2.522e-02 1.737e-02 -1.452 0.1657
## dewpt 1.834e-02 2.107e-02 0.871 0.3968
## ppt 9.859e-06 2.185e-05 0.451 0.6579
## snow -1.285e-04 1.280e-04 -1.004 0.3302
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.03259 on 16 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.4858, Adjusted R-squared: 0.2287
## F-statistic: 1.89 on 8 and 16 DF, p-value: 0.1326Summary Stats Moving average of all DBH<3
RWI ~ climate variables
maless_3.lm <- lm(maless_3 ~ meant + maxt + mint + ppt + snow + maxvpd + minvpd + dewpt, data=my.data)
summary(maless_3.lm)##
## Call:
## lm(formula = maless_3 ~ meant + maxt + mint + ppt + snow + maxvpd +
## minvpd + dewpt, data = my.data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.050967 -0.012117 0.001116 0.019261 0.052472
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.286e+00 3.497e-01 6.537 6.85e-06 ***
## meant 2.710e-01 1.029e-01 2.634 0.01805 *
## maxt -2.060e-01 5.698e-02 -3.615 0.00232 **
## mint -1.533e-01 4.738e-02 -3.236 0.00517 **
## ppt 7.721e-06 2.220e-05 0.348 0.73250
## snow -2.338e-04 1.300e-04 -1.798 0.09100 .
## maxvpd 3.289e-02 1.745e-02 1.885 0.07777 .
## minvpd -2.199e-02 1.764e-02 -1.247 0.23040
## dewpt 3.840e-02 2.140e-02 1.794 0.09168 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.0331 on 16 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.6175, Adjusted R-squared: 0.4262
## F-statistic: 3.229 on 8 and 16 DF, p-value: 0.02196Summary Stats Moving average of all DBH>=3
RWI ~ climate variables
magreater_3.lm <- lm(magreater_3 ~ meant + maxt + mint + ppt + snow + maxvpd + minvpd + dewpt, data=my.data)
summary(magreater_3.lm)##
## Call:
## lm(formula = magreater_3 ~ meant + maxt + mint + ppt + snow +
## maxvpd + minvpd + dewpt, data = my.data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.055445 -0.025117 0.003493 0.021127 0.056964
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.501e+00 4.012e-01 3.742 0.00178 **
## meant 1.930e-01 1.181e-01 1.635 0.12154
## maxt -1.196e-01 6.539e-02 -1.829 0.08609 .
## mint -7.600e-02 5.436e-02 -1.398 0.18119
## ppt 1.169e-05 2.547e-05 0.459 0.65234
## snow -3.727e-05 1.492e-04 -0.250 0.80593
## maxvpd 5.698e-03 2.003e-02 0.285 0.77964
## minvpd -2.802e-02 2.024e-02 -1.384 0.18524
## dewpt 9.577e-04 2.456e-02 0.039 0.96937
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.03798 on 16 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.3038, Adjusted R-squared: -0.04434
## F-statistic: 0.8726 on 8 and 16 DF, p-value: 0.5585Plot 3 year moving average to make sure it looks correct.
plot(my.data$year,my.data$all,col="darkgrey",type="b")
lines(ma3~my.data$year,col="red",lwd=2)
ma3.lm <- lm(all ~ snow + maxt+ meant + minvpd, data=my.data)#linear modle
summary(ma3.lm)##
## Call:
## lm(formula = all ~ snow + maxt + meant + minvpd, data = my.data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.098685 -0.025107 0.004499 0.035017 0.091844
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.9047061 0.1966181 4.601 0.000139 ***
## snow -0.0001420 0.0002087 -0.680 0.503531
## maxt -0.0371202 0.0271478 -1.367 0.185328
## meant 0.0712457 0.0403706 1.765 0.091479 .
## minvpd -0.0139775 0.0178490 -0.783 0.441921
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.05827 on 22 degrees of freedom
## Multiple R-squared: 0.196, Adjusted R-squared: 0.04987
## F-statistic: 1.341 on 4 and 22 DF, p-value: 0.2863