# input data
dta <- read.csv("C:/Users/USER/Desktop/nlsy86wide.csv")
# inspect data structure
str(dta)
## 'data.frame': 166 obs. of 23 variables:
## $ id : int 23901 25601 37401 40201 63501 70301 72001 76101 76801 77001 ...
## $ sex : chr "Female" "Female" "Female" "Male" ...
## $ race : chr "Majority" "Majority" "Majority" "Majority" ...
## $ grade86 : int 0 0 0 0 1 0 0 0 0 0 ...
## $ grade88 : int 2 1 2 1 3 2 1 3 2 2 ...
## $ grade90 : int 3 3 5 2 4 3 3 4 5 4 ...
## $ grade92 : int 5 6 6 5 6 5 5 6 6 5 ...
## $ age86year : int 6 6 6 5 7 5 6 7 6 6 ...
## $ age88year : int 8 8 8 8 9 8 8 9 9 8 ...
## $ age90year : int 10 10 10 9 11 10 10 11 11 10 ...
## $ age92year : int 12 12 12 12 13 12 12 13 13 12 ...
## $ age86month: int 67 66 67 60 78 62 66 79 76 67 ...
## $ age88month: int 96 95 95 91 108 93 94 109 104 94 ...
## $ age90month: int 119 119 122 112 132 117 118 131 128 117 ...
## $ age92month: int 142 143 144 139 155 139 140 154 151 139 ...
## $ math86 : num 14.29 20.24 17.86 7.14 29.76 ...
## $ math88 : num 15.5 36.9 22.6 21.4 50 ...
## $ math90 : num 38.1 52.4 53.6 53.6 47.6 ...
## $ math92 : num 41.7 58.3 58.3 51.2 71.4 ...
## $ read86 : num 19.05 21.43 21.43 7.14 30.95 ...
## $ read88 : num 29.8 32.1 45.2 21.4 50 ...
## $ read90 : num 28.6 45.2 69 50 63.1 ...
## $ read92 : num 45.2 57.1 78.6 59.5 82.1 ...
# examine first 6 lines
head(dta)
## id sex race grade86 grade88 grade90 grade92 age86year age88year
## 1 23901 Female Majority 0 2 3 5 6 8
## 2 25601 Female Majority 0 1 3 6 6 8
## 3 37401 Female Majority 0 2 5 6 6 8
## 4 40201 Male Majority 0 1 2 5 5 8
## 5 63501 Male Majority 1 3 4 6 7 9
## 6 70301 Male Majority 0 2 3 5 5 8
## age90year age92year age86month age88month age90month age92month math86
## 1 10 12 67 96 119 142 14.285714
## 2 10 12 66 95 119 143 20.238095
## 3 10 12 67 95 122 144 17.857143
## 4 9 12 60 91 112 139 7.142857
## 5 11 13 78 108 132 155 29.761905
## 6 10 12 62 93 117 139 14.285714
## math88 math90 math92 read86 read88 read90 read92
## 1 15.47619 38.09524 41.66667 19.047619 29.76190 28.57143 45.23810
## 2 36.90476 52.38095 58.33333 21.428571 32.14286 45.23810 57.14286
## 3 22.61905 53.57143 58.33333 21.428571 45.23810 69.04762 78.57143
## 4 21.42857 53.57143 51.19048 7.142857 21.42857 50.00000 59.52381
## 5 50.00000 47.61905 71.42857 30.952381 50.00000 63.09524 82.14286
## 6 36.90476 55.95238 63.09524 17.857143 46.42857 64.28571 96.42857
library(tidyr)
l2dta<-gather(dta,
key=grade,value=Value2,
grade86,grade88,grade90,grade92)
head(l2dta)
## id sex race age86year age88year age90year age92year age86month
## 1 23901 Female Majority 6 8 10 12 67
## 2 25601 Female Majority 6 8 10 12 66
## 3 37401 Female Majority 6 8 10 12 67
## 4 40201 Male Majority 5 8 9 12 60
## 5 63501 Male Majority 7 9 11 13 78
## 6 70301 Male Majority 5 8 10 12 62
## age88month age90month age92month math86 math88 math90 math92
## 1 96 119 142 14.285714 15.47619 38.09524 41.66667
## 2 95 119 143 20.238095 36.90476 52.38095 58.33333
## 3 95 122 144 17.857143 22.61905 53.57143 58.33333
## 4 91 112 139 7.142857 21.42857 53.57143 51.19048
## 5 108 132 155 29.761905 50.00000 47.61905 71.42857
## 6 93 117 139 14.285714 36.90476 55.95238 63.09524
## read86 read88 read90 read92 grade Value2
## 1 19.047619 29.76190 28.57143 45.23810 grade86 0
## 2 21.428571 32.14286 45.23810 57.14286 grade86 0
## 3 21.428571 45.23810 69.04762 78.57143 grade86 0
## 4 7.142857 21.42857 50.00000 59.52381 grade86 0
## 5 30.952381 50.00000 63.09524 82.14286 grade86 1
## 6 17.857143 46.42857 64.28571 96.42857 grade86 0
library(tidyr)
l3dta<-gather(dta,
key=year,value=Value3,
age86year,age88year,age90year,age92year)
head(l3dta)
## id sex race grade86 grade88 grade90 grade92 age86month age88month
## 1 23901 Female Majority 0 2 3 5 67 96
## 2 25601 Female Majority 0 1 3 6 66 95
## 3 37401 Female Majority 0 2 5 6 67 95
## 4 40201 Male Majority 0 1 2 5 60 91
## 5 63501 Male Majority 1 3 4 6 78 108
## 6 70301 Male Majority 0 2 3 5 62 93
## age90month age92month math86 math88 math90 math92 read86 read88
## 1 119 142 14.285714 15.47619 38.09524 41.66667 19.047619 29.76190
## 2 119 143 20.238095 36.90476 52.38095 58.33333 21.428571 32.14286
## 3 122 144 17.857143 22.61905 53.57143 58.33333 21.428571 45.23810
## 4 112 139 7.142857 21.42857 53.57143 51.19048 7.142857 21.42857
## 5 132 155 29.761905 50.00000 47.61905 71.42857 30.952381 50.00000
## 6 117 139 14.285714 36.90476 55.95238 63.09524 17.857143 46.42857
## read90 read92 year Value3
## 1 28.57143 45.23810 age86year 6
## 2 45.23810 57.14286 age86year 6
## 3 69.04762 78.57143 age86year 6
## 4 50.00000 59.52381 age86year 5
## 5 63.09524 82.14286 age86year 7
## 6 64.28571 96.42857 age86year 5
library(tidyr)
l4dta<-gather(dta,
key=month,value=Value4,
age86month,age88month,age90month,age92month,)
head(l4dta)
## id sex race grade86 grade88 grade90 grade92 age86year age88year
## 1 23901 Female Majority 0 2 3 5 6 8
## 2 25601 Female Majority 0 1 3 6 6 8
## 3 37401 Female Majority 0 2 5 6 6 8
## 4 40201 Male Majority 0 1 2 5 5 8
## 5 63501 Male Majority 1 3 4 6 7 9
## 6 70301 Male Majority 0 2 3 5 5 8
## age90year age92year math86 math88 math90 math92 read86 read88
## 1 10 12 14.285714 15.47619 38.09524 41.66667 19.047619 29.76190
## 2 10 12 20.238095 36.90476 52.38095 58.33333 21.428571 32.14286
## 3 10 12 17.857143 22.61905 53.57143 58.33333 21.428571 45.23810
## 4 9 12 7.142857 21.42857 53.57143 51.19048 7.142857 21.42857
## 5 11 13 29.761905 50.00000 47.61905 71.42857 30.952381 50.00000
## 6 10 12 14.285714 36.90476 55.95238 63.09524 17.857143 46.42857
## read90 read92 month Value4
## 1 28.57143 45.23810 age86month 67
## 2 45.23810 57.14286 age86month 66
## 3 69.04762 78.57143 age86month 67
## 4 50.00000 59.52381 age86month 60
## 5 63.09524 82.14286 age86month 78
## 6 64.28571 96.42857 age86month 62
library(tidyr)
l5dta<-gather(dta,
key=math,value=Value5,
math86,math88,math90,math92,)
head(l5dta)
## id sex race grade86 grade88 grade90 grade92 age86year age88year
## 1 23901 Female Majority 0 2 3 5 6 8
## 2 25601 Female Majority 0 1 3 6 6 8
## 3 37401 Female Majority 0 2 5 6 6 8
## 4 40201 Male Majority 0 1 2 5 5 8
## 5 63501 Male Majority 1 3 4 6 7 9
## 6 70301 Male Majority 0 2 3 5 5 8
## age90year age92year age86month age88month age90month age92month read86
## 1 10 12 67 96 119 142 19.047619
## 2 10 12 66 95 119 143 21.428571
## 3 10 12 67 95 122 144 21.428571
## 4 9 12 60 91 112 139 7.142857
## 5 11 13 78 108 132 155 30.952381
## 6 10 12 62 93 117 139 17.857143
## read88 read90 read92 math Value5
## 1 29.76190 28.57143 45.23810 math86 14.285714
## 2 32.14286 45.23810 57.14286 math86 20.238095
## 3 45.23810 69.04762 78.57143 math86 17.857143
## 4 21.42857 50.00000 59.52381 math86 7.142857
## 5 50.00000 63.09524 82.14286 math86 29.761905
## 6 46.42857 64.28571 96.42857 math86 14.285714
library(tidyr)
l6dta<-gather(dta,
key=read,value=Value6,
read86,read88,read90,read92,)
head(l6dta)
## id sex race grade86 grade88 grade90 grade92 age86year age88year
## 1 23901 Female Majority 0 2 3 5 6 8
## 2 25601 Female Majority 0 1 3 6 6 8
## 3 37401 Female Majority 0 2 5 6 6 8
## 4 40201 Male Majority 0 1 2 5 5 8
## 5 63501 Male Majority 1 3 4 6 7 9
## 6 70301 Male Majority 0 2 3 5 5 8
## age90year age92year age86month age88month age90month age92month math86
## 1 10 12 67 96 119 142 14.285714
## 2 10 12 66 95 119 143 20.238095
## 3 10 12 67 95 122 144 17.857143
## 4 9 12 60 91 112 139 7.142857
## 5 11 13 78 108 132 155 29.761905
## 6 10 12 62 93 117 139 14.285714
## math88 math90 math92 read Value6
## 1 15.47619 38.09524 41.66667 read86 19.047619
## 2 36.90476 52.38095 58.33333 read86 21.428571
## 3 22.61905 53.57143 58.33333 read86 21.428571
## 4 21.42857 53.57143 51.19048 read86 7.142857
## 5 50.00000 47.61905 71.42857 read86 30.952381
## 6 36.90476 55.95238 63.09524 read86 17.857143
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
newdta <- l2dta %>%
select(id, sex, race, grade, Value2)
newdta2 <- l3dta %>%
select(year, Value3)
newdta3 <- l4dta %>%
select(month, Value4)
newdta4 <- l5dta %>%
select(math, Value5)
newdta5 <- l6dta %>%
select(read, Value6)
longdta<-cbind(newdta, newdta2, newdta3, newdta4, newdta5)
library(ggplot2)
ggplot(data=longdta, aes(x=month, y=read, group=id)) +
geom_point(size=rel(.5)) +
stat_smooth(method ="lm", formula=y ~ x, se=F) +
facet_grid(race ~ sex) +
labs(x="Month", y="Reading score") +
theme_bw()
###