Basic Statistics in R

R basic statistics.r

#  ------------------------------------------------------------------
#  |PROGRAM NAME: R basic statistics
#  |DATE: 2/20/17
#  |CREATED BY: MATT BOGARD 
#  |PROJECT FILE:              
#  |----------------------------------------------------------------
#  | PURPOSE: BASIC STATISTICS IN R          
#  |----------------------------------------------------------------

# create some toy data

GARST <- c(150,140,145,137,141,145,149,153,157,161) 
PIO <- c(160,150,146,138,142,146,150,154,158,162)
MYC <- c(137,148,151,139,143,120,115,136,130,129)
DEK <- c(150,149,145,140,144,148,152,156,160,164)
PLOT <- c(1,2,3,4,5,6,7,8,9,10)
BT <- c('Y','Y','N','N','N','N','Y','N','Y','Y')
RR <- c('Y','N','Y','N','N','N','N','Y','Y','N')

yield_data <- data.frame(GARST,PIO,MYC,DEK,PLOT,BT,RR)


# create GMO trait field

yield_data$GMO <- ifelse(yield_data$BT == 'Y'  &  yield_data$RR == 'Y','Stacked Trait',
 ifelse(yield_data$RR == "Y" , 'Single Trait ', 
 ifelse(yield_data$BT =="Y",'Single Trait ', 'Non-GMO    '))) 

#--------------------------------
# summary statistics
#--------------------------------

summary(yield_data)

#by processing
by(yield_data, yield_data$GMO, summary) 

#frequencies
table(yield_data$GMO)

#----------------------------
# graphics
#----------------------------

#histogram
hist(yield_data$GARST)

#scatterplot
plot(yield_data$GARST,yield_data$PIO)


#-----------------------------------
# t-tests
#----------------------------------- 

# independent samples t-test

t.test(yield_data$GARST,yield_data$PIO,var.equal=TRUE ) # difference in GARST vs PIO yields from yield_data file

#Welch's 2 sample ttest
t.test(yield_data$GARST,yield_data$PIO,var.equal=FALSE) # this is default

# run as if paired ttest
t.test(yield_data$GARST,yield_data$PIO,paired=TRUE) # not actually appropriate but notice the difference in the results from the previous t-test on 											        # GARST and PIO


#-------------------------------
# correlations
#-------------------------------

cor(yield_data$GARST,yield_data$PIO, method="pearson") 

#-------------------------------
# regression
#-------------------------------

summary(lm(GARST~PIO,data=yield_data))