Session set
## ggplot2 knitr
## TRUE TRUE
Dataset
dat = read.csv("diego.csv", dec = "," , sep="\t", na = ".", header = TRUE)
names(dat)
## [1] "cont_flor" "parche" "alt_gas" "lai_prim" "psmac_prim" "pse_prim" "nmac_prim"
## [8] "lai_oto" "mac_oto" "nvos_ver" "superv"
dat[,-c(1:2)] <-round(dat[,-c(1:2)],2) #the "-1" excludes column 1
dat
## cont_flor parche alt_gas lai_prim psmac_prim pse_prim nmac_prim lai_oto mac_oto nvos_ver superv
## 1 cf alto 29.73 3.91 2.53 8.60 2275 2.41 2275 98 96
## 2 cf medio 21.40 1.57 1.39 5.76 3647 2.05 2686 373 63
## 3 cf bajo 13.60 0.58 0.80 3.69 1588 0.90 627 176 28
## 4 cf alto 29.80 4.17 2.41 8.63 3275 2.90 2431 1569 26
## 5 cf medio 21.93 1.34 1.01 4.95 3882 1.90 1941 294 42
## 6 cf bajo 13.33 0.73 0.87 3.45 1941 0.79 1667 216 75
## 7 cf alto 23.67 3.42 1.99 7.56 4843 2.83 NA NA NA
## 8 cf medio 14.80 1.28 1.47 4.91 3510 2.00 2275 1157 32
## 9 cf bajo 8.20 0.87 0.95 3.76 1980 1.14 725 216 26
## 10 cf alto 23.93 3.32 3.03 8.61 2569 3.69 1216 20 NA
## 11 cf medio 16.67 1.08 1.22 4.20 3000 1.88 NA NA NA
## 12 cf bajo 10.80 0.39 0.93 3.39 2039 0.87 NA NA NA
## 13 ncf alto 35.80 4.95 2.68 9.56 2059 4.12 1725 98 32
## 14 ncf medio 21.73 1.66 1.01 5.52 4137 1.38 2314 333 48
## 15 ncf bajo NA NA NA NA NA 0.69 NA NA NA
## 16 ncf alto 32.93 4.78 3.83 9.53 2922 3.01 NA NA NA
## 17 ncf medio 25.67 2.24 2.22 6.22 3176 2.09 NA NA NA
## 18 ncf bajo 15.33 1.22 1.25 3.98 2882 1.03 NA NA NA
## 19 ncf alto 31.27 4.75 2.74 9.07 2980 3.13 2176 157 68
## 20 ncf medio 20.07 1.93 0.98 5.44 3275 1.88 2314 471 56
## 21 ncf bajo 9.47 0.57 0.71 3.03 2333 0.67 804 176 27
str(dat)
## 'data.frame': 21 obs. of 11 variables:
## $ cont_flor : Factor w/ 2 levels "cf","ncf": 1 1 1 1 1 1 1 1 1 1 ...
## $ parche : Factor w/ 3 levels "alto","bajo",..: 1 3 2 1 3 2 1 3 2 1 ...
## $ alt_gas : num 29.7 21.4 13.6 29.8 21.9 ...
## $ lai_prim : num 3.91 1.57 0.58 4.17 1.34 0.73 3.42 1.28 0.87 3.32 ...
## $ psmac_prim: num 2.53 1.39 0.8 2.41 1.01 0.87 1.99 1.47 0.95 3.03 ...
## $ pse_prim : num 8.6 5.76 3.69 8.63 4.95 3.45 7.56 4.91 3.76 8.61 ...
## $ nmac_prim : num 2275 3647 1588 3275 3882 ...
## $ lai_oto : num 2.41 2.05 0.9 2.9 1.9 0.79 2.83 2 1.14 3.69 ...
## $ mac_oto : num 2275 2686 627 2431 1941 ...
## $ nvos_ver : num 98 373 176 1569 294 ...
## $ superv : num 96 63 28 26 42 75 NA 32 26 NA ...
Explora
# panel.smooth function is built in.
# panel.cor puts correlation in upper panels, size proportional to correlation
panel.cor <- function(x, y, digits=2, prefix="", cex.cor, ...)
{
usr <- par("usr"); on.exit(par(usr))
par(usr = c(0, 1, 0, 1))
r <- abs(cor(x, y))
txt <- format(c(r, 0.123456789), digits=digits)[1]
txt <- paste(prefix, txt, sep="")
if(missing(cex.cor)) cex.cor <- 0.8/strwidth(txt)
text(0.5, 0.5, txt, cex = cex.cor * r)
}
# Plot #2: same as above, but add loess smoother in lower and correlation in upper
#names(dat)
pairs(~alt_gas + lai_prim + psmac_prim + pse_prim + nmac_prim + lai_oto + mac_oto + nvos_ver + superv, data=dat[-15,-2],
lower.panel=panel.smooth, upper.panel=panel.cor,
pch=20, main="Correlation plot")
Ej 1
names(dat)
## [1] "cont_flor" "parche" "alt_gas" "lai_prim" "psmac_prim" "pse_prim" "nmac_prim"
## [8] "lai_oto" "mac_oto" "nvos_ver" "superv"
ggplot(dat, aes(x = alt_gas, y = lai_prim, colour=cont_flor)) +
geom_point() +
stat_smooth(method="lm", se=T)
#facet_grid(~parche)
#labs(x="a", y="Ry")
mod1 <- lm(lai_prim ~ alt_gas * cont_flor, data=dat)
summary(mod1)
##
## Call:
## lm(formula = lai_prim ~ alt_gas * cont_flor, data = dat)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.07071 -0.36277 0.03703 0.40197 0.89744
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.483579 0.510473 -2.906 0.0103 *
## alt_gas 0.177578 0.025295 7.020 2.89e-06 ***
## cont_florncf -0.234542 0.813411 -0.288 0.7768
## alt_gas:cont_florncf 0.008852 0.035448 0.250 0.8060
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5989 on 16 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.8787, Adjusted R-squared: 0.8559
## F-statistic: 38.62 on 3 and 16 DF, p-value: 1.481e-07
#plot(mod1)