MATH2270 Assignment 2

Student Details

Mai Nguyen (s3639386)

Problem statement:

I have spent most of my reading time on “Social Science”. As a young girl and prepare to have my own family in the near future, I reall go into deep with the issue of how to live longer and longer.

And in this assignment, I would like to show you how a woman having less children can live longer and how the fertility rate was changing through years and its trend. In other word, having two or one children a family is one of the best policy that has seen as an effective catalyst to the improvement in terms of woman’s life expectancy and their health. My report is aimed to refer to Asean countries, specifically.

In my assignment, I would like to use the data from WDI package, starts from 1990 to 2015, with two indicators namely : * “SP.DYN.LE00.FE.IN” is Life expectancy of women(years) * “SP.DYN.TFRT.IN” is Fertility rate or the number of children per woman.

# Loading packages
library(ggplot2)
library(ggthemes)
library(tidyverse)

## Loading tidyverse: tibble
## Loading tidyverse: tidyr
## Loading tidyverse: readr
## Loading tidyverse: purrr
## Loading tidyverse: dplyr

## Conflicts with tidy packages ----------------------------------------------

## filter(): dplyr, stats
## lag():    dplyr, stats

library(scales)

## 
## Attaching package: 'scales'

## The following object is masked from 'package:purrr':
## 
##     discard

## The following objects are masked from 'package:readr':
## 
##     col_factor, col_numeric

library(ggrepel)
library(WDI)

## Loading required package: RJSONIO

library(googleVis)

## 
## Welcome to googleVis version 0.6.1
## 
## Please read the Google API Terms of Use
## before you start using the package:
## https://developers.google.com/terms/
## 
## Note, the plot method of googleVis will by default use
## the standard browser to display its output.
## 
## See the googleVis package vignettes for more details,
## or visit http://github.com/mages/googleVis.
## 
## To suppress this message use:
## suppressPackageStartupMessages(library(googleVis))

library(plyr)

## -------------------------------------------------------------------------

## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)

## -------------------------------------------------------------------------

## 
## Attaching package: 'plyr'

## The following objects are masked from 'package:dplyr':
## 
##     arrange, count, desc, failwith, id, mutate, rename, summarise,
##     summarize

## The following object is masked from 'package:purrr':
## 
##     compact

library(dplyr)
library(gridExtra)

## 
## Attaching package: 'gridExtra'

## The following object is masked from 'package:dplyr':
## 
##     combine

theme_set(theme_minimal())

Data

# Loading the WDIcache to find indicators then loading data: 
d <- WDIcache()
d1 <- data.frame(d[[1]])
d2 <- data.frame(d[[2]])

lifeExpectancy= WDI(indicator='SP.DYN.LE00.FE.IN', country="all",start=1990, end=2015)
childPerwoman = WDI(indicator='SP.DYN.TFRT.IN', country="all",start=1990, end=2015)

names(lifeExpectancy)[3]="lifeExp"
names(childPerwoman)[3]="fertility"

# Join two seperate datasets into one new dataset called mydf
j1 <- join(childPerwoman,lifeExpectancy)

## Joining by: iso2c, country, year

j2 <- merge(j1, d2, by= "country", all.x=TRUE)
mydf <- j2[-c(2,6,7,9,10,11,13)]
inter <- intersect(j2$country, d2$country)

# Filter mydf as removing missing data
mydf <- mydf %>% 
  filter(country %in% inter) %>% 
  arrange(country) %>% 
  mutate(country = as.character(country,is.na))
mydf <- na.omit(mydf)
# Create the list of Asian countries that joined the Asean Group:
asean <- c("Brunei", "India", "China","Cambodia","Indonesia", "Laos","Malaysia","Myanmar", "Philippines","Singapore", "Thailand")


# Create a new data files called "mf" which just contains specific countries: 
mf <- mydf %>% filter(country %in% c( "China","Malaysia","Singapore", "Thailand", "Vietnam"))
mf %>% na.omit()

##       country fertility year lifeExp              region
## 1       China     1.617 2015  77.667 East Asia & Pacific
## 2       China     1.610 2014  77.503 East Asia & Pacific
## 3       China     1.604 2013  77.342 East Asia & Pacific
## 4       China     1.599 2012  77.180 East Asia & Pacific
## 5       China     1.594 2011  77.015 East Asia & Pacific
## 6       China     1.590 2010  76.837 East Asia & Pacific
## 7       China     1.586 2009  76.641 East Asia & Pacific
## 8       China     1.581 2008  76.418 East Asia & Pacific
## 9       China     1.577 2007  76.166 East Asia & Pacific
## 10      China     1.572 2006  75.884 East Asia & Pacific
## 11      China     1.565 2005  75.569 East Asia & Pacific
## 12      China     1.554 2004  75.223 East Asia & Pacific
## 13      China     1.540 2003  74.853 East Asia & Pacific
## 14      China     1.524 2002  74.469 East Asia & Pacific
## 15      China     1.508 2001  74.079 East Asia & Pacific
## 16      China     1.497 2000  73.693 East Asia & Pacific
## 17      China     1.494 1999  73.320 East Asia & Pacific
## 18      China     1.503 1998  72.967 East Asia & Pacific
## 19      China     1.527 1997  72.637 East Asia & Pacific
## 20      China     1.571 1996  72.334 East Asia & Pacific
## 21      China     1.639 1995  72.060 East Asia & Pacific
## 22      China     1.739 1994  71.816 East Asia & Pacific
## 23      China     1.868 1993  71.595 East Asia & Pacific
## 24      China     2.021 1992  71.388 East Asia & Pacific
## 25      China     2.187 1991  71.192 East Asia & Pacific
## 26      China     2.350 1990  71.002 East Asia & Pacific
## 27   Malaysia     2.056 2015  77.543 East Asia & Pacific
## 28   Malaysia     2.074 2014  77.376 East Asia & Pacific
## 29   Malaysia     2.092 2013  77.200 East Asia & Pacific
## 30   Malaysia     2.110 2012  77.014 East Asia & Pacific
## 31   Malaysia     2.129 2011  76.820 East Asia & Pacific
## 32   Malaysia     2.149 2010  76.624 East Asia & Pacific
## 33   Malaysia     2.169 2009  76.434 East Asia & Pacific
## 34   Malaysia     2.191 2008  76.253 East Asia & Pacific
## 35   Malaysia     2.217 2007  76.085 East Asia & Pacific
## 36   Malaysia     2.249 2006  75.930 East Asia & Pacific
## 37   Malaysia     2.293 2005  75.783 East Asia & Pacific
## 38   Malaysia     2.355 2004  75.637 East Asia & Pacific
## 39   Malaysia     2.438 2003  75.487 East Asia & Pacific
## 40   Malaysia     2.539 2002  75.324 East Asia & Pacific
## 41   Malaysia     2.657 2001  75.147 East Asia & Pacific
## 42   Malaysia     2.784 2000  74.955 East Asia & Pacific
## 43   Malaysia     2.913 1999  74.749 East Asia & Pacific
## 44   Malaysia     3.036 1998  74.533 East Asia & Pacific
## 45   Malaysia     3.145 1997  74.311 East Asia & Pacific
## 46   Malaysia     3.238 1996  74.084 East Asia & Pacific
## 47   Malaysia     3.313 1995  73.853 East Asia & Pacific
## 48   Malaysia     3.372 1994  73.618 East Asia & Pacific
## 49   Malaysia     3.422 1993  73.379 East Asia & Pacific
## 50   Malaysia     3.466 1992  73.134 East Asia & Pacific
## 51   Malaysia     3.510 1991  72.884 East Asia & Pacific
## 52   Malaysia     3.554 1990  72.627 East Asia & Pacific
## 53  Singapore     1.240 2015  84.900 East Asia & Pacific
## 54  Singapore     1.250 2014  84.800 East Asia & Pacific
## 55  Singapore     1.190 2013  84.500 East Asia & Pacific
## 56  Singapore     1.290 2012  84.300 East Asia & Pacific
## 57  Singapore     1.200 2011  84.100 East Asia & Pacific
## 58  Singapore     1.150 2010  84.000 East Asia & Pacific
## 59  Singapore     1.220 2009  83.700 East Asia & Pacific
## 60  Singapore     1.280 2008  83.300 East Asia & Pacific
## 61  Singapore     1.290 2007  82.900 East Asia & Pacific
## 62  Singapore     1.280 2006  82.600 East Asia & Pacific
## 63  Singapore     1.260 2005  82.500 East Asia & Pacific
## 64  Singapore     1.260 2004  82.000 East Asia & Pacific
## 65  Singapore     1.270 2003  81.600 East Asia & Pacific
## 66  Singapore     1.370 2002  80.600 East Asia & Pacific
## 67  Singapore     1.410 2001  80.300 East Asia & Pacific
## 68  Singapore     1.600 2000  80.000 East Asia & Pacific
## 69  Singapore     1.470 1999  79.600 East Asia & Pacific
## 70  Singapore     1.480 1998  79.400 East Asia & Pacific
## 71  Singapore     1.610 1997  79.100 East Asia & Pacific
## 72  Singapore     1.660 1996  78.900 East Asia & Pacific
## 73  Singapore     1.670 1995  78.600 East Asia & Pacific
## 74  Singapore     1.710 1994  78.400 East Asia & Pacific
## 75  Singapore     1.740 1993  78.300 East Asia & Pacific
## 76  Singapore     1.720 1992  78.200 East Asia & Pacific
## 77  Singapore     1.730 1991  77.900 East Asia & Pacific
## 78  Singapore     1.830 1990  77.600 East Asia & Pacific
## 79   Thailand     1.498 2015  78.953 East Asia & Pacific
## 80   Thailand     1.512 2014  78.747 East Asia & Pacific
## 81   Thailand     1.524 2013  78.505 East Asia & Pacific
## 82   Thailand     1.534 2012  78.226 East Asia & Pacific
## 83   Thailand     1.542 2011  77.910 East Asia & Pacific
## 84   Thailand     1.547 2010  77.561 East Asia & Pacific
## 85   Thailand     1.551 2009  77.182 East Asia & Pacific
## 86   Thailand     1.553 2008  76.788 East Asia & Pacific
## 87   Thailand     1.557 2007  76.393 East Asia & Pacific
## 88   Thailand     1.561 2006  76.010 East Asia & Pacific
## 89   Thailand     1.568 2005  75.654 East Asia & Pacific
## 90   Thailand     1.580 2004  75.339 East Asia & Pacific
## 91   Thailand     1.595 2003  75.067 East Asia & Pacific
## 92   Thailand     1.616 2002  74.840 East Asia & Pacific
## 93   Thailand     1.641 2001  74.657 East Asia & Pacific
## 94   Thailand     1.671 2000  74.513 East Asia & Pacific
## 95   Thailand     1.705 1999  74.400 East Asia & Pacific
## 96   Thailand     1.742 1998  74.305 East Asia & Pacific
## 97   Thailand     1.781 1997  74.214 East Asia & Pacific
## 98   Thailand     1.823 1996  74.118 East Asia & Pacific
## 99   Thailand     1.867 1995  74.018 East Asia & Pacific
## 100  Thailand     1.911 1994  73.923 East Asia & Pacific
## 101  Thailand     1.956 1993  73.831 East Asia & Pacific
## 102  Thailand     2.003 1992  73.735 East Asia & Pacific
## 103  Thailand     2.055 1991  73.616 East Asia & Pacific
## 104  Thailand     2.113 1990  73.439 East Asia & Pacific
## 105   Vietnam     1.958 2015  80.713 East Asia & Pacific
## 106   Vietnam     1.960 2014  80.555 East Asia & Pacific
## 107   Vietnam     1.959 2013  80.405 East Asia & Pacific
## 108   Vietnam     1.957 2012  80.263 East Asia & Pacific
## 109   Vietnam     1.953 2011  80.126 East Asia & Pacific
## 110   Vietnam     1.946 2010  79.992 East Asia & Pacific
## 111   Vietnam     1.936 2009  79.856 East Asia & Pacific
## 112   Vietnam     1.923 2008  79.714 East Asia & Pacific
## 113   Vietnam     1.911 2007  79.562 East Asia & Pacific
## 114   Vietnam     1.901 2006  79.395 East Asia & Pacific
## 115   Vietnam     1.894 2005  79.214 East Asia & Pacific
## 116   Vietnam     1.894 2004  79.019 East Asia & Pacific
## 117   Vietnam     1.901 2003  78.811 East Asia & Pacific
## 118   Vietnam     1.920 2002  78.593 East Asia & Pacific
## 119   Vietnam     1.954 2001  78.364 East Asia & Pacific
## 120   Vietnam     2.010 2000  78.122 East Asia & Pacific
## 121   Vietnam     2.096 1999  77.868 East Asia & Pacific
## 122   Vietnam     2.213 1998  77.599 East Asia & Pacific
## 123   Vietnam     2.359 1997  77.317 East Asia & Pacific
## 124   Vietnam     2.529 1996  77.022 East Asia & Pacific
## 125   Vietnam     2.714 1995  76.715 East Asia & Pacific
## 126   Vietnam     2.904 1994  76.399 East Asia & Pacific
## 127   Vietnam     3.089 1993  76.074 East Asia & Pacific
## 128   Vietnam     3.260 1992  75.743 East Asia & Pacific
## 129   Vietnam     3.415 1991  75.409 East Asia & Pacific
## 130   Vietnam     3.553 1990  75.072 East Asia & Pacific
##                  income
## 1   Upper middle income
## 2   Upper middle income
## 3   Upper middle income
## 4   Upper middle income
## 5   Upper middle income
## 6   Upper middle income
## 7   Upper middle income
## 8   Upper middle income
## 9   Upper middle income
## 10  Upper middle income
## 11  Upper middle income
## 12  Upper middle income
## 13  Upper middle income
## 14  Upper middle income
## 15  Upper middle income
## 16  Upper middle income
## 17  Upper middle income
## 18  Upper middle income
## 19  Upper middle income
## 20  Upper middle income
## 21  Upper middle income
## 22  Upper middle income
## 23  Upper middle income
## 24  Upper middle income
## 25  Upper middle income
## 26  Upper middle income
## 27  Upper middle income
## 28  Upper middle income
## 29  Upper middle income
## 30  Upper middle income
## 31  Upper middle income
## 32  Upper middle income
## 33  Upper middle income
## 34  Upper middle income
## 35  Upper middle income
## 36  Upper middle income
## 37  Upper middle income
## 38  Upper middle income
## 39  Upper middle income
## 40  Upper middle income
## 41  Upper middle income
## 42  Upper middle income
## 43  Upper middle income
## 44  Upper middle income
## 45  Upper middle income
## 46  Upper middle income
## 47  Upper middle income
## 48  Upper middle income
## 49  Upper middle income
## 50  Upper middle income
## 51  Upper middle income
## 52  Upper middle income
## 53          High income
## 54          High income
## 55          High income
## 56          High income
## 57          High income
## 58          High income
## 59          High income
## 60          High income
## 61          High income
## 62          High income
## 63          High income
## 64          High income
## 65          High income
## 66          High income
## 67          High income
## 68          High income
## 69          High income
## 70          High income
## 71          High income
## 72          High income
## 73          High income
## 74          High income
## 75          High income
## 76          High income
## 77          High income
## 78          High income
## 79  Upper middle income
## 80  Upper middle income
## 81  Upper middle income
## 82  Upper middle income
## 83  Upper middle income
## 84  Upper middle income
## 85  Upper middle income
## 86  Upper middle income
## 87  Upper middle income
## 88  Upper middle income
## 89  Upper middle income
## 90  Upper middle income
## 91  Upper middle income
## 92  Upper middle income
## 93  Upper middle income
## 94  Upper middle income
## 95  Upper middle income
## 96  Upper middle income
## 97  Upper middle income
## 98  Upper middle income
## 99  Upper middle income
## 100 Upper middle income
## 101 Upper middle income
## 102 Upper middle income
## 103 Upper middle income
## 104 Upper middle income
## 105 Lower middle income
## 106 Lower middle income
## 107 Lower middle income
## 108 Lower middle income
## 109 Lower middle income
## 110 Lower middle income
## 111 Lower middle income
## 112 Lower middle income
## 113 Lower middle income
## 114 Lower middle income
## 115 Lower middle income
## 116 Lower middle income
## 117 Lower middle income
## 118 Lower middle income
## 119 Lower middle income
## 120 Lower middle income
## 121 Lower middle income
## 122 Lower middle income
## 123 Lower middle income
## 124 Lower middle income
## 125 Lower middle income
## 126 Lower middle income
## 127 Lower middle income
## 128 Lower middle income
## 129 Lower middle income
## 130 Lower middle income

head(mydf)

##       country fertility year lifeExp     region     income
## 1 Afghanistan     4.802 2015  64.613 South Asia Low income
## 2 Afghanistan     4.981 2014  64.197 South Asia Low income
## 3 Afghanistan     5.174 2013  63.778 South Asia Low income
## 4 Afghanistan     5.380 2012  63.354 South Asia Low income
## 5 Afghanistan     5.595 2011  62.924 South Asia Low income
## 6 Afghanistan     5.816 2010  62.476 South Asia Low income

Visualisation

Viet nam is represented as the red bubble

# Checking correlation value of life expectancy and fertility
cor(mydf$lifeExp, mydf$fertility)

## [1] -0.8768023

=> The correlation value is negative and very high. That means, the living years a womancan be increased at a decrease of her fertility. And let’s use visualization to confirm that again:

# Visualization For 1990
h1 <- mydf %>% 
  ggplot(aes(fertility, lifeExp)) + 
  geom_point(alpha = 0.1, color = "purple") + 
  geom_point(
    data = mydf %>% filter(country == "Vietnam" & year == 1990), 
    color = "red", 
    size =  4
  ) + 
  geom_text_repel(
    data = mydf %>% filter(country == "Vietnam" & year == 1990), 
    aes(label = country), 
    force = 5
  ) + 
  geom_point(
    data = mydf %>% filter(country %in% asean & year == 1990), 
    color = "orange", 
    size =  2
  ) + 
  geom_text_repel(
    data = mydf %>% filter(country %in% asean & year == 1990), 
    aes(label = country), 
    force = 5, direction = "y"
    ) + 
  geom_smooth(method = "loess", fill = "blue", alpha = 0.2) + 
  labs(x = "Fertility", 
       y  = "Life Expectancy of woman at Birth", 
       title = "Vietnam and Asean Countries in 1990",
       caption = "Data Source: World Development Indicators")
h1

# Visualiation of those countries in 2014
h2 <- mydf %>% 
  ggplot(aes(fertility, lifeExp)) + 
  geom_point(alpha = 0.1, color = "purple") + 
  geom_point(
    data = mydf %>% filter(country == "Vietnam" & year == 2014), 
    color = "red", 
    size =  4
  ) + 
  geom_text_repel(
    data = mydf %>% filter(country == "Vietnam" & year == 2014), 
    aes(label = country), 
    force = 10
  ) + 
  geom_point(
    data = mydf %>% filter(country %in% asean & year == 2014), 
    color = "orange", 
    size =  2
  ) + 
  geom_text_repel(
    data = mydf %>% filter(country %in% asean & year == 2014), 
    aes(label = country), 
    force = 10, 
    direction = "y"
  ) + 
  geom_smooth(method = "loess", fill = "blue", alpha = 0.2) + 
  labs(x = "Fertility", 
       y  = "Life Expectancy of woman at Birth", 
       title = "Vietnam and Asean Countries in 2014",
       caption = "Data Source: World Development Indicators")

h2

# Grid two graphs to see the difference: 

grid.arrange(h1, h2, nrow = 1)

One thing easily can be seen from these graphs is the improvement of women’s ages in all countries. The fertility rate was changing so much. It is meant that if every woman has less than three children, they can live much longer. In 1990, the data distributed gradually along the line and there was a big gap between Asean countries in term of life expectancy at birth rate but they were getting closer in 2014. It is happy to say the average ages increased when the fertility decreased.

## Visualize the fertility 
h3 <- mf %>% 
  ggplot(aes(year, fertility, color = country)) + 
  geom_line(show.legend = FALSE) + 
  geom_point(show.legend = FALSE) + 
  facet_wrap(~country, scales = "free", nrow = 1) + 
  labs(x = NULL, y = NULL, 
       title = "Overall fertility rate through years( from 1990 to 2015) ",
       caption = "Data Source: WDI")
h3

My conclusion:

From this analysis, I do believe that every family in this world should have one or two children then mothers can live longer and healthier with their children.

This assignment was judged by my professor James Baglin, BAppSc (Psych - Hons), PhD Senior Lecturer, Statistics Program Manager, Master of Analytics and Master of Statistics and Operations Research School of Science, Mathematical Sciences, RMIT University Melbourne, Australia Office: Building 8, Level 9, Room 69, City campus Tel. +61 3 9925 6118 Fax: +61 3 9925 6107 Email: james.baglin@rmit.edu.au | LinkedIn | Profile Program Portal - MC242 & MC004 | Book a student consultation

Here is his comment: * You chose an interesting story and data set to explore. No need to mention the specifics of how the visualisation was created/data was modified - it’s alright to just mention the correlation values found, and focus on the visualisation itself. The plot used was appropriate, and including the regression lines with confidence bands was effective. Adjusting the labels in your x-axis for the time series plots would be a minor tweak to improve it. Just be a bit wary about making really direct statements for your conclusion.

MATH2270 Assignment 2

Visualising Open Data

Student Details

Problem statement:

Data

Visualisation