R basics demo

R basics

Working Directory

setwd("/Volumes/EDMS451/Spring 2022/Software Instructions")

Load R packages

library(psych)
library(tidyverse)

Load Data

load("Undergrad_Survey_Database.rda")

Manually Enter Data

dat <- data.frame(var1 = c(4, 5, 7, 8, 9, 3, 1,
                           6, 7, 6, 5, 9, 2, 5,
                           5, 1, 2, 5, 7, 8, 3))
colnames(dat) <- "var1"

print(dat)

   var1
1     4
2     5
3     7
4     8
5     9
6     3
7     1
8     6
9     7
10    6
11    5
12    9
13    2
14    5
15    5
16    1
17    2
18    5
19    7
20    8
21    3

Frequency Table

# function to produce the frequency table 
cum_freq_tab <- function(x){
  freq <- table(x)
  cumfreq <- cumsum(freq)
  propfreq <- freq/sum(freq)
  cumpropfreq <- cumfreq/sum(freq)
  
  freq_tab <- as.data.frame(cbind(noquote(row.names(freq)), freq, cumfreq, propfreq, cumpropfreq))
  colnames(freq_tab)[1] <- "value"
  freq_tab <- sapply(freq_tab, as.numeric)
  return(freq_tab)
}

freq_tab <- cum_freq_tab(dat$var1)

knitr::kable(round(freq_tab, 3))

value	freq	cumfreq	propfreq	cumpropfreq
1	2	2	0.095	0.095
2	2	4	0.095	0.190
3	2	6	0.095	0.286
4	1	7	0.048	0.333
5	5	12	0.238	0.571
6	2	14	0.095	0.667
7	3	17	0.143	0.810
8	2	19	0.095	0.905
9	2	21	0.095	1.000

Descriptive Statistics

mean(dat$var1)      # mean

[1] 5.142857

median(dat$var1)    # median

[1] 5

var(dat$var1)       # variance

[1] 6.128571

sd(dat$var1)        # standard deviation

[1] 2.475595

range(dat$var1)     # range

[1] 1 9

min(dat$var1)       # min

[1] 1

max(dat$var1)       # max

[1] 9

# find the mode
Mode <- function(x) {
  ux <- unique(x)
  ux[which.max(tabulate(match(x, ux)))]
}

Mode(dat$var1)

[1] 5

# get a summary of the descriptive statistics 
describe(dat)

   vars  n mean   sd median trimmed  mad min max range  skew kurtosis
X1    1 21 5.14 2.48      5    5.18 2.97   1   9     8 -0.14    -1.17
     se
X1 0.54

Histogram

hist(dat$var1, main = "Histogram", xlim = c(0, 10))

hist(dat$var1, main = "Histogram", prob = T, xlim = c(0, 10))   
lines(density(dat$var1), col = "red")   #overlay the density curve