Data 606 Project Proposal

Research question

Does increased government expenditure on education improve youth literacy?

Cases

Each case represents a country with expenditure and literacy data for a given time period.

These cases are from the the Word Bank’s World Development Indicators.

This study will only focus on these two indicators:

• SE.XPD.TOTL.GB.ZS - Government expenditure on education, total (% of government expenditure)
• SE.ADT.1524.LT.ZS - Literacy rate, youth total (% of people ages 15-24)

The original dataset contains 415,436 rows of observations from 1960 to 2017.

There are 528 observations for the indicators mentioned above.

For this study, there are 91 complete country-period cases.

Data Collection

Data is collected by The World Bank. This dataset is part of the World Bank’s open data and is updated quarterly. The dataset used in this study has a release date of June 11, 2010 and was last updated on March 1, 2018.

Type of Study

This is an observational study.

Data Source

Source: https://datacatalog.worldbank.org/dataset/world-development-indicators Release Date: June 11, 2010 Lasted Updated: March 1, 2018

Response

The response variable is change in youth literacy rate.

Explanatory variable

The explanatory variable is the change in government expenditure in education.

Generate complete cases

A complete case is a country with available data for both selected indicators within a specific time period.

Selected indicators:

• SE.XPD.TOTL.GB.ZS - Government expenditure on education, total (% of government expenditure)
• SE.ADT.1524.LT.ZS - Literacy rate, youth total (% of people ages 15-24)

NOTE: Selecting one time period reference does not generate enough complete cases. For example, for the period 2010-2012, this only has 17 complete cases. In order to increase the number of cases for the study, several time periods are selected.

• period_1: 2015 - 2016 –> 00 complete cases
• period_2: 2014 - 2015 –> 05 complete cases
• period_3: 2013 - 2014 –> 09 complete cases
• period_4: 2012 - 2013 –> 14 complete cases
• period_5: 2011 - 2012 –> 15 complete cases
• period_6: 2010 - 2011 –> 17 complete cases
• period_7: 2009 - 2010 –> 15 complete cases
• period_8: 2008 - 2009 –> 16 complete cases

Preview of cases

Each case is assigned into one of two groups: Less-Expenditure or More-Expenditure.

Relevant summary statistics

Size of group with increased government expenditure on education: 47 cases Size of group with decreased government expenditure on education: 44

## [1] 47

## [1] 44

Group with increased expenditure on education:

describe(group_more_expend$Change.Educ_Expend)

##    vars  n mean   sd median trimmed  mad min  max range skew kurtosis   se
## X1    1 47 1.16 1.25   0.77    0.93 0.74   0 5.63  5.63 2.01     3.94 0.18

describe(group_more_expend$Change.Literacy)

##    vars  n mean   sd median trimmed mad   min  max range  skew kurtosis
## X1    1 47 0.35 0.92   0.12     0.3 0.2 -3.15 2.84  5.98 -0.15     3.91
##      se
## X1 0.13

Group with decreased expenditure on education:

describe(group_less_expend$Change.Educ_Expend)

##    vars  n mean   sd median trimmed  mad   min   max range  skew kurtosis
## X1    1 44 -0.8 0.62  -0.68   -0.74 0.56 -2.38 -0.07  2.31 -0.83    -0.31
##      se
## X1 0.09

describe(group_less_expend$Change.Literacy)

##    vars  n mean   sd median trimmed  mad  min  max range skew kurtosis
## X1    1 44 0.19 0.81   0.02    0.13 0.42 -1.8 2.71  4.51 0.87     1.64
##      se
## X1 0.12

Scatter plot

ggplot(data=educ_expend_literacy, aes(x=Change.Educ_Expend, y=Change.Literacy,
                        colour=Group)) + 
  geom_point(size=3, alpha=0.7) +
  labs(y="Change in literacy", x="Change in government expenditure on education", color="Group")

boxplot(educ_expend_literacy$Change.Literacy~Group, data=educ_expend_literacy, main="Change in Literacy", xlab = "Group", ylab="Change in Literacy")

Histogram of change in literacy

hist(educ_expend_literacy$Change.Literacy)