library(pastecs) 
stat.desc(Vine)
##          country cardinal_direction      size_ha
## nbr.val       NA                 NA   819.000000
## nbr.null      NA                 NA     0.000000
## nbr.na        NA                 NA     0.000000
## min           NA                 NA     1.000000
## max           NA                 NA  2948.531000
## range         NA                 NA  2947.531000
## sum           NA                 NA 59276.768000
## median        NA                 NA    53.856000
## mean          NA                 NA    72.377006
## SE.mean       NA                 NA     4.467165
## CI.mean       NA                 NA     8.768457
## var           NA                 NA 16343.608099
## std.dev       NA                 NA   127.842122
## coef.var      NA                 NA     1.766336
summary(Vine)
##    country          cardinal_direction    size_ha       
##  Length:819         Length:819         Min.   :   1.00  
##  Class :character   Class :character   1st Qu.:  20.67  
##  Mode  :character   Mode  :character   Median :  53.86  
##                                        Mean   :  72.38  
##                                        3rd Qu.:  82.00  
##                                        Max.   :2948.53
options("scipen" = 100, "digits" = 3)
MoldovaData <- subset(Vine, country == "Moldova")
summary(MoldovaData)
##    country          cardinal_direction    size_ha     
##  Length:250         Length:250         Min.   :  1.0  
##  Class :character   Class :character   1st Qu.: 58.2  
##  Mode  :character   Mode  :character   Median : 71.0  
##                                        Mean   : 70.9  
##                                        3rd Qu.: 83.0  
##                                        Max.   :117.0
hist(MoldovaData$size_ha, main= "Moldava", xlab = "size of vineyard(ha)", col = 'gold')

FranceData <- subset(Vine, country == "France")
summary(FranceData)
##    country          cardinal_direction    size_ha     
##  Length:269         Length:269         Min.   : 2.00  
##  Class :character   Class :character   1st Qu.: 9.09  
##  Mode  :character   Mode  :character   Median :15.00  
##                                        Mean   :17.96  
##                                        3rd Qu.:24.30  
##                                        Max.   :57.87
hist(FranceData$size_ha, main= "France", xlab = "size of vineyard(ha)", col = 'pink')

library(EnvStats)
## 
## Attaching package: 'EnvStats'
## The following objects are masked from 'package:stats':
## 
##     predict, predict.lm
## The following object is masked from 'package:base':
## 
##     print.default
qqPlot(MoldovaData$size_ha, xlab="Theoretical Quantiles",ylab="Sample Size Quantiles",main="Moldova Q-Q Plot",)

qqPlot(FranceData$size_ha, xlab="Theoretical Quantiles",ylab="Sample Size Quantiles",main="France Q-Q Plot",)

shapiro.test(MoldovaData$size_ha)
## 
##  Shapiro-Wilk normality test
## 
## data:  MoldovaData$size_ha
## W = 1, p-value = 0.2
shapiro.test(FranceData$size_ha)
## 
##  Shapiro-Wilk normality test
## 
## data:  FranceData$size_ha
## W = 0.9, p-value = 0.000000000005
library(nortest)
lillie.test(MoldovaData$size_ha)
## 
##  Lilliefors (Kolmogorov-Smirnov) normality test
## 
## data:  MoldovaData$size_ha
## D = 0.05, p-value = 0.1
lillie.test(FranceData$size_ha)
## 
##  Lilliefors (Kolmogorov-Smirnov) normality test
## 
## data:  FranceData$size_ha
## D = 0.1, p-value = 0.000000006
library(car)
## Loading required package: carData
## 
## Attaching package: 'car'
## The following object is masked from 'package:EnvStats':
## 
##     qqPlot
leveneTest(MoldovaData$size_ha, MoldovaData$cardinal_direction,center=mean)
## Warning in leveneTest.default(MoldovaData$size_ha,
## MoldovaData$cardinal_direction, : MoldovaData$cardinal_direction coerced to
## factor.
## Levene's Test for Homogeneity of Variance (center = mean)
##        Df F value Pr(>F)
## group   3    0.91   0.43
##       246
leveneTest(FranceData$size_ha, FranceData$cardinal_direction,center=mean)
## Warning in leveneTest.default(FranceData$size_ha,
## FranceData$cardinal_direction, : FranceData$cardinal_direction coerced to
## factor.
## Levene's Test for Homogeneity of Variance (center = mean)
##        Df F value Pr(>F)
## group   3    1.23    0.3
##       265
FranceData$sizelog <- log10(FranceData$size_ha)
summary(FranceData$sizelog)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   0.301   0.958   1.176   1.154   1.386   1.762
hist(FranceData$sizelog, col = 'darkblue')

library(EnvStats)
qqPlot(FranceData$sizelog, xlab="Theoretical Quantiles",ylab="Sample Size Quantiles",main="France Q-Q Plot",)

## [1] 1 2
shapiro.test(FranceData$sizelog)
## 
##  Shapiro-Wilk normality test
## 
## data:  FranceData$sizelog
## W = 1, p-value = 0.002
lillie.test(FranceData$sizelog)
## 
##  Lilliefors (Kolmogorov-Smirnov) normality test
## 
## data:  FranceData$sizelog
## D = 0.07, p-value = 0.004
FranceData$sizenatlog <- log(FranceData$size_ha)
summary(FranceData$sizenatlog)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   0.693   2.207   2.708   2.658   3.191   4.058
hist(FranceData$sizenatlog)

library(EnvStats)
qqPlot(FranceData$sizenatlog, xlab="Theoretical Quantiles",ylab="Sample Size Quantiles",main="France Q-Q Plot",)

## [1] 1 2
shapiro.test(FranceData$sizenatlog)
## 
##  Shapiro-Wilk normality test
## 
## data:  FranceData$sizenatlog
## W = 1, p-value = 0.002
lillie.test(FranceData$sizenatlog)
## 
##  Lilliefors (Kolmogorov-Smirnov) normality test
## 
## data:  FranceData$sizenatlog
## D = 0.07, p-value = 0.004
FranceData$sizesqrt <- sqrt(FranceData$size_ha)
summary(FranceData$sizesqrt)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1.41    3.01    3.87    4.01    4.93    7.61
hist(FranceData$sizesqrt, col = 'darkred')

library(EnvStats)
qqPlot(FranceData$sizesqrt, xlab="Theoretical Quantiles",ylab="Sample Size Quantiles",main="France Q-Q Plot",)

## [1] 268 269
shapiro.test(FranceData$sizesqrt)
## 
##  Shapiro-Wilk normality test
## 
## data:  FranceData$sizesqrt
## W = 1, p-value = 0.0004
lillie.test(FranceData$sizesqrt)
## 
##  Lilliefors (Kolmogorov-Smirnov) normality test
## 
## data:  FranceData$sizesqrt
## D = 0.05, p-value = 0.07

#franceflaghists