Homework3 Reproduce the plot on the NLSY 86 example by completing the R script using the data file in wide format.

1 Data management

# input data
dta <- read.csv("C:/Users/Ching-Fang Wu/Documents/data/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

2 Long data format

#寬資料轉長資料
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
library(tidyr)

long_grade <- dta %>% gather (key = grade_y, value = grade, grade86:grade92)
longgrade <- long_grade[,c("id","sex","race","grade_y","grade")]

long_ageyear <- dta %>% gather (key = age_y, value = ageyear, age86year:age92year)
longageyear <- long_ageyear[,c("id","sex","race","age_y","ageyear")]

long_agemonth <- dta %>% gather (key = age_m, value = agemonth, age86month:age92month)
longagemonth <- long_agemonth[,c("id","sex","race","age_m","agemonth")]

long_math <- dta %>% 
        gather (key = math_y, value = math, math86:math92)

longmath <- long_math[,c("id","sex","race","math_y","math")]

long_read <- dta %>% gather (key = read_y, value = read, read86:read92)
longread <- long_read[,c("id","sex","race","read_y","read")]

longdta <- cbind ((longgrade[,c("id","sex","race","grade_y","grade")]),
                      (longageyear[,c("id","age_y","ageyear")]),
                      (longagemonth[,c("id","age_m","agemonth")]), 
                      (longmath[,c("id","math_y","math")]), 
                      (longread[,c("id","read_y","read")]),by= "id")

longdtafinal <- longdta[,c("id","sex","race","ageyear","agemonth","math","read")]

head(longdtafinal)
##      id    sex     race ageyear agemonth      math      read
## 1 23901 Female Majority       6       67 14.285714 19.047619
## 2 25601 Female Majority       6       66 20.238095 21.428571
## 3 37401 Female Majority       6       67 17.857143 21.428571
## 4 40201   Male Majority       5       60  7.142857  7.142857
## 5 63501   Male Majority       7       78 29.761905 30.952381
## 6 70301   Male Majority       5       62 14.285714 17.857143

3 plot

library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --
## √ ggplot2 3.3.2     √ purrr   0.3.4
## √ tibble  3.0.4     √ stringr 1.4.0
## √ readr   1.3.1     √ forcats 0.5.0
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
ggplot(data=longdtafinal, aes(x=agemonth, y=read, group=id)) +
 geom_point(size=rel(.5)) +
 stat_smooth(mapping = NULL,
             data = NULL,
             geom = "smooth",
             position = "identity",
             method ="lm", 
             formula= y ~ x,
             se=F, 
             fullrange = FALSE,
             level = 0.95,
             color="skyblue2", 
             linetype=1, 
             size=rel(.1)) +
  facet_grid(rows = vars(race),
             cols = vars(sex),
             scales = "free",
             space = "free",
             shrink = T,
             labeller = "label_value",
             as.table = T,
             switch = NULL,
             drop = T,
             margins = T, #F就變成原本的四格圖
             facets = NULL)  +
  labs(x="Month", y="Reading score") +
  theme_bw()

ggplot(data=longdtafinal, aes(x=agemonth, y=read, group=id)) +
 geom_point(size=rel(.5)) +
 stat_smooth(mapping = NULL,
             data = NULL,
             geom = "smooth",
             position = "identity",
             method ="lm", 
             formula= y ~ x,
             se=F, 
             fullrange = FALSE,
             level = 0.95,
             color="skyblue2", 
             linetype=1, 
             size=rel(.1)) +
  facet_grid(rows = vars(race),
             cols = vars(sex),
             scales = "free",
             space = "free",
             shrink = T,
             labeller = "label_value",
             as.table = T,
             switch = NULL,
             drop = T,
             margins = F, 
             facets = NULL)  +
  labs(x="Month", y="Reading score") +
  theme_bw()

5 The end