Importing the data set

library(readr)
slemsa_ca <- read_csv("~/soil loss/slemsa_ca.csv")
## Parsed with column specification:
## cols(
##   Country = col_character(),
##   Site = col_character(),
##   Agroeco = col_character(),
##   Farmer_Name = col_character(),
##   Drainage_class = col_character(),
##   Season = col_character(),
##   Treatment = col_double(),
##   Treatment_description = col_character(),
##   System = col_character(),
##   Cropping_Systems = col_character(),
##   Intercepted = col_double(),
##   Crop_Canopy = col_double(),
##   Seasonal_rainfall_energy = col_double(),
##   Erodability_Factor = col_double(),
##   Topographic_ratio = col_double(),
##   Soil_loss = col_double(),
##   Residue_cover = col_double(),
##   rainfall = col_double(),
##   slope = col_double()
## )
View(slemsa_ca)
attach(slemsa_ca)

Defining th factor variables

Country=as.factor(Country)
Site=as.factor(Site)
Farmer_Name=as.factor(Farmer_Name)
Agroeco=as.factor(Agroeco)
Season=as.factor(Season)
Drainage_class=as.factor(Drainage_class)
Treatment=as.factor(Treatment)
Treatment_description=as.factor(Treatment_description)
System=as.factor(System)
Cropping_Systems=as.factor(Cropping_Systems)

Loading the required packages

library(ggplot2)
library(maps)
library(ggalt)
library(extrafontdb)
library(MASS)
library(pscl)
## Classes and Methods for R developed in the
## Political Science Computational Laboratory
## Department of Political Science
## Stanford University
## Simon Jackman
## hurdle and zeroinfl functions by Achim Zeileis
library(psych)
## 
## Attaching package: 'psych'
## The following objects are masked from 'package:ggplot2':
## 
##     %+%, alpha
library(gridExtra)
describeBy(Soil_loss,Cropping_Systems)
## 
##  Descriptive statistics by group 
## group: CA_INT
##    vars   n mean   sd median trimmed  mad min  max range skew kurtosis
## X1    1 300 0.72 1.23   0.44    0.54 0.32   0 17.3  17.3 9.47   115.36
##      se
## X1 0.07
## -------------------------------------------------------- 
## group: CA_ROT
##    vars   n mean   sd median trimmed  mad min   max range skew kurtosis
## X1    1 610 1.94 2.98   0.81    1.27 0.92   0 23.72 23.72  3.3    13.55
##      se
## X1 0.12
## -------------------------------------------------------- 
## group: CA_SOLE
##    vars   n mean   sd median trimmed  mad min   max range skew kurtosis
## X1    1 544 2.07 3.14   0.93    1.37 1.11   0 29.31 29.31 3.45    16.97
##      se
## X1 0.13

Plots

theme_set(theme_gray(base_size = 14))
ggplot(data=slemsa_ca,aes(x=Cropping_Systems,y=Soil_loss,color=Country))+
geom_boxplot(outlier.size=0,width=0.5,shape=20)+xlab("CA Cropping Systems")+ylab("Soil Loss [t/ha]")+theme(legend.position = c(0.82, 0.84))

theme_set(theme_gray(base_size = 14))
ggplot(data=slemsa_ca,aes(x=Cropping_Systems,y=Soil_loss,color=Country))+ geom_boxplot(outlier.size=0,width=0.5,shape=20)+facet_grid(Agroeco~.)+xlab("CA Cropping Systems")+ylab("Soil Loss [t/ha]")+
  theme(legend.position = c(0.82, 0.84))

Soil loss and rainfall intercepted

#soil loss and rainfall intercepted 
theme_set(theme_gray(base_size = 14))
p <- ggplot(data=slemsa_ca,aes(y=Soil_loss,x=Intercepted, color=Agroeco))
p + geom_smooth()+xlab("Rainfall Intercepted [i(%)]")+ylab("Soil Loss [t/ha]")+
  theme(legend.position = c(0.82, 0.84))
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'