-1

[I have to solve some questions with the following data:

c(ages)
  [1] 29 29 19 25 22 29 24 23 28 33 30 21 22 27 32 25 25 23 33 22 31 32 26 27 23 27 16 21 18 17 27 23 29 26 25 27 26 29
 [39] 25 26 22 31 21 22 19 25 29 21 21 25 24 33 25 28 23 26 23 23 28 26 22 26 26 28 23 29 31 28 23 23 21 27 20 24 27 20
 [77] 30 27 21 29 21 24 27 23 30 24 26 29 24 30 24 23 28 25 33 26 24 25 26 32

c(genders)
  [1] "male"   "female" "female" "female" "male"   "male"   "male"   "male"   "female" "female" "female" "male"  
 [13] "male"   "male"   "male"   "male"   "female" "female" "male"   "male"   "female" "female" "female" "female"
 [25] "female" "female" "female" "female" "female" "female" "female" "female" "female" "female" "male"   "male"  
 [37] "female" "female" "male"   "male"   "female" "male"   "female" "male"   "male"   "male"   "male"   "male"  
 [49] "female" "male"   "male"   "male"   "male"   "female" "male"   "male"   "male"   "male"   "male"   "male"  
 [61] "female" "male"   "male"   "female" "male"   "female" "male"   "male"   "female" "female" "male"   "male"  
 [73] "female" "male"   "female" "male"   "male"   "female" "male"   "female" "female" "female" "female" "male"  
 [85] "male"   "male"   "female" "female" "male"   "male"   "female" "male"   "female" "male"   "female" "female"
 [97] "male"   "female" "male"   "male"

I thought if I use mean(ages[genders=male]), I can get the average age for males, but I got the following error message

Error in mean(ages[gender = male]) : object 'male' not found

Are there additional steps I should have done? what am I doing wrong??

For reference: the full list of questions I have to solve are as follows:

  1. Are the men younger on average than the women or vice versa?
  2. How many women are in the sample?
  3. How many men are in the sample?
  4. How old is the youngest man in the sample?
  5. How old is the youngest woman in the sample?
Sandy
  • 1,100
  • 10
  • 18
Han Shin
  • 19

1 Answers1

0

Welcome to SO.

Firstly, your data seems to be row wise. I am not that familiar with this structure. So, after reading in the data into rows as below:

df = read.csv("give the complete path of your file", header = F)

The dput(df) is:

structure(list(V1 = structure(1:2, .Label = c("ages", "genders"), class = "factor"), V2 = structure(1:2, .Label = c("29", "male"), class = "factor"), V3 = structure(1:2, .Label = c("29", "female"), class = "factor"), V4 = structure(1:2, .Label = c("19", "female"), class = "factor"), V5 = structure(1:2, .Label = c("25", "female"), class = "factor"), V6 = structure(1:2, .Label = c("22", "male"), class = "factor"), V7 = structure(1:2, .Label = c("29", "male"), class = "factor"), V8 = structure(1:2, .Label = c("24", "female"), class = "factor"), V9 = structure(1:2, .Label = c("23", "female"), class = "factor"), V10 = structure(1:2, .Label = c("28", "female"), class = "factor"), V11 = structure(1:2, .Label = c("33", "male"), class = "factor"), V12 = structure(1:2, .Label = c("30", "male"), class = "factor"), V13 = structure(1:2, .Label = c("21", "male"), class = "factor"), V14 = structure(1:2, .Label = c("22", "male"), class = "factor"), V15 = structure(1:2, .Label = c("27", "female"), class = "factor"), V16 = structure(1:2, .Label = c("32", "female"), class = "factor"), V17 = structure(1:2, .Label = c("25", "female"), class = "factor"), V18 = structure(1:2, .Label = c("25", "male"), class = "factor"), V19 = structure(1:2, .Label = c("23", "male"), class = "factor"), V20 = structure(1:2, .Label = c("33", "male"), class = "factor"), V21 = structure(1:2, .Label = c("22", "male"), class = "factor"), V22 = structure(1:2, .Label = c("31", "male"), class = "factor"), V23 = structure(1:2, .Label = c("32", "female"), class = "factor"), V24 = structure(1:2, .Label = c("26", "female"), class = "factor"), V25 = structure(1:2, .Label = c("27", "male"), class = "factor"), V26 = structure(1:2, .Label = c("23", "male"), class = "factor"), V27 = structure(1:2, .Label = c("27", "female"), class = "factor"), V28 = structure(1:2, .Label = c("16", "female"), class = "factor"), V29 = structure(1:2, .Label = c("21", "female"), class = "factor"), V30 = structure(1:2, .Label = c("18", "female"), class = "factor"), V31 = structure(1:2, .Label = c("17", "female"), class = "factor"), V32 = structure(1:2, .Label = c("27", "female"), class = "factor"), V33 = structure(1:2, .Label = c("23", "female"), class = "factor"), V34 = structure(1:2, .Label = c("29", "female"), class = "factor"), V35 = structure(1:2, .Label = c("26", "female"), class = "factor"), V36 = structure(1:2, .Label = c("25", "female"), class = "factor"), V37 = structure(1:2, .Label = c("27", "female"), class = "factor"), V38 = structure(1:2, .Label = c("26", "female"), class = "factor"), V39 = structure(1:2, .Label = c("29", "female"), class = "factor"), V40 = structure(1:2, .Label = c("25", "female"), class = "factor"), V41 = structure(1:2, .Label = c("26", "male"), class = "factor"), V42 = structure(1:2, .Label = c("22", "male"), class = "factor"), V43 = structure(1:2, .Label = c("31", "female"), class = "factor"), V44 = structure(1:2, .Label = c("21", "female"), class = "factor"), V45 = structure(1:2, .Label = c("22", "male"), class = "factor"), V46 = structure(1:2, .Label = c("19", "male"), class = "factor"), V47 = structure(1:2, .Label = c("25", "female"), class = "factor"), V48 = structure(1:2, .Label = c("29", "male"), class = "factor"), V49 = structure(1:2, .Label = c("21", "female"), class = "factor"), V50 = structure(1:2, .Label = c("21", "male"), class = "factor"), V51 = structure(1:2, .Label = c("25", "male"), class = "factor"), V52 = structure(1:2, .Label = c("24", "male"), class = "factor"), V53 = structure(1:2, .Label = c("33", "male"), class = "factor"), V54 = structure(1:2, .Label = c("25", "male"), class = "factor"), V55 = structure(1:2, .Label = c("28", "female"), class = "factor"), V56 = structure(1:2, .Label = c("23", "male"), class = "factor"), V57 = structure(1:2, .Label = c("26", "male"), class = "factor"), V58 = structure(1:2, .Label = c("23", "male"), class = "factor"), V59 = structure(1:2, .Label = c("23", "male"), class = "factor"), V60 = structure(1:2, .Label = c("28", "female"), class = "factor"), V61 = structure(1:2, .Label = c("26", "male"), class = "factor"), V62 = structure(1:2, .Label = c("22", "male"), class = "factor"), V63 = structure(1:2, .Label = c("26", "male"), class = "factor"), V64 = structure(1:2, .Label = c("26", "male"), class = "factor"), V65 = structure(1:2, .Label = c("28", "male"), class = "factor"), V66 = structure(1:2, .Label = c("23", "male"), class = "factor"), V67 = structure(1:2, .Label = c("29", "female"), class = "factor"), V68 = structure(1:2, .Label = c("31", "male"), class = "factor"), V69 = structure(1:2, .Label = c("28", "male"), class = "factor"), V70 = structure(1:2, .Label = c("23", "female"), class = "factor"), V71 = structure(1:2, .Label = c("23", "male"), class = "factor"), V72 = structure(1:2, .Label = c("21", "female"), class = "factor"), V73 = structure(1:2, .Label = c("27", "male"), class = "factor"), V74 = structure(1:2, .Label = c("20", "male"), class = "factor"), V75 = structure(1:2, .Label = c("24", "female"), class = "factor"), V76 = structure(1:2, .Label = c("27", "female"), class = "factor"), V77 = structure(1:2, .Label = c("20", "male"), class = "factor"), V78 = structure(1:2, .Label = c("30", "male"), class = "factor"), V79 = structure(1:2, .Label = c("27", "female"), class = "factor"), V80 = structure(1:2, .Label = c("21", "male"), class = "factor"), V81 = structure(1:2, .Label = c("29", "female"), class = "factor"), V82 = structure(1:2, .Label = c("21", "male"), class = "factor"), V83 = structure(1:2, .Label = c("24", "male"), class = "factor"), V84 = structure(1:2, .Label = c("27", "female"), class = "factor"), V85 = structure(1:2, .Label = c("23", "male"), class = "factor"), V86 = structure(1:2, .Label = c("30", "female"), class = "factor"), V87 = structure(1:2, .Label = c("24", "female"), class = "factor"), V88 = structure(1:2, .Label = c("26", "female"), class = "factor"), V89 = structure(1:2, .Label = c("29", "female"), class = "factor"), V90 = structure(1:2, .Label = c("24", "male"), class = "factor"), V91 = structure(1:2, .Label = c("30", "male"), class = "factor"), V92 = structure(1:2, .Label = c("24", "male"), class = "factor"), V93 = structure(1:2, .Label = c("23", "female"), class = "factor"), V94 = structure(1:2, .Label = c("28", "female"), class = "factor"), V95 = structure(1:2, .Label = c("25", "male"), class = "factor"), V96 = structure(1:2, .Label = c("33", "male"), class = "factor"), V97 = structure(1:2, .Label = c("26", "female"), class = "factor"), V98 = structure(1:2, .Label = c("24", "male"), class = "factor"), V99 = structure(1:2, .Label = c("25", "female"), class = "factor"), V100 = structure(1:2, .Label = c("26", "male"), class = "factor"), V101 = structure(1:2, .Label = c("32", "female"), class = "factor")), class = "data.frame", row.names = c(NA, -2L))

I tried to make things easier, by converting this row wise data into column wise data frame. This conversion is based on a code shared by @Ricardo Oliveros-Ramos here: Reading a CSV file organized horizontally

For convenience I'm copying it here:

read.tcsv = function(file, header=TRUE, sep=",", ...) 
{

   n = max(count.fields(file, sep=sep), na.rm=TRUE)
   x = readLines(file)

   .splitvar = function(x, sep, n) {
   var = unlist(strsplit(x, split=sep))
   length(var) = n
   return(var)
 }

x = do.call(cbind, lapply(x, .splitvar, sep=sep, n=n))
x = apply(x, 1, paste, collapse=sep) 
out = read.csv(text=x, sep=sep, header=header, ...)
return(out)

}

Then you simply run the above function onto your csv row wise file:

df2 = read.tcsv("give the complete path of your file")

For reference, the dput of this is as below:

dput(df2)

structure(list(ages = c(29L, 29L, 19L, 25L, 22L, 29L, 24L, 23L, 28L, 33L, 30L, 21L, 22L, 27L, 32L, 25L, 25L, 23L, 33L, 22L, 31L, 32L, 26L, 27L, 23L, 27L, 16L, 21L, 18L, 17L, 27L, 23L, 29L, 26L, 25L, 27L, 26L, 29L, 25L, 26L, 22L, 31L, 21L, 22L, 19L, 25L, 29L, 21L, 21L, 25L, 24L, 33L, 25L, 28L, 23L, 26L, 23L, 23L, 28L, 26L, 22L, 26L, 26L, 28L, 23L, 29L, 31L, 28L, 23L, 23L, 21L, 27L, 20L, 24L, 27L, 20L, 30L, 27L, 21L, 29L, 21L, 24L, 27L, 23L, 30L, 24L, 26L, 29L, 24L, 30L, 24L, 23L, 28L, 25L, 33L, 26L, 24L, 25L, 26L, 32L), genders = structure(c(2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L), .Label = c("female", "male"), class = "factor")), class = "data.frame", row.names = c(NA, -100L))

The next and more important step is the functionality you want to achieve:

# for mean by gender using the base R functionality
mean(df2$ages[which(df2$genders == 'male')])
mean(df2$ages[which(df2$genders == 'female')])

Please note the == sign here, which means comparison and also not the ' ' around male which specifies this data is a character type.

# for finding the youngest by gender
min(df2$ages[which(df2$genders == 'male')])
min(df2$ages[which(df2$genders == 'female')])

And lastly, to count how many men or how many women in the group:

sum(df2$genders == 'male')
sum(df2$genders == 'female')

This checks for equality and sums or counts the TRUE cases.

Sandy
  • 1,100
  • 10
  • 18