STAT545a-2013-hw4_Liu

Lattice Graphs

Read data into R

getwd()

## [1] "C:/Users/Yan/Dropbox/Important_File/2013-2014Courses/545_R/exercise"

setwd("C:/Users/Yan/Dropbox/Important_File/2013-2014Courses/545_R/exercise")
library(plyr)
library(lattice)
library(xtable)
library(knitr)
# install.packages('locfit')
gDat <- read.delim("gapminderDataFiveYear.txt")
str(gDat)

## 'data.frame':    1704 obs. of  6 variables:
##  $ country  : Factor w/ 142 levels "Afghanistan",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ year     : int  1952 1957 1962 1967 1972 1977 1982 1987 1992 1997 ...
##  $ pop      : num  8425333 9240934 10267083 11537966 13079460 ...
##  $ continent: Factor w/ 5 levels "Africa","Americas",..: 3 3 3 3 3 3 3 3 3 3 ...
##  $ lifeExp  : num  28.8 30.3 32 34 36.1 ...
##  $ gdpPercap: num  779 821 853 836 740 ...

I. Choose your own adventure

xyplot(lifeExp ~ year | continent, gDat, type = c("p", "r"))

yearMin <- min(gDat$year)
fit <- lm(lifeExp ~ I(year - yearMin), gDat)
plot(fit)

plot(gDat$lifeExp ~ I(gDat$year - yearMin))
abline(fit)

II. Examine “typical” life expectancy for different years. The median and trimed mean of life expectancy over years

# par(mfrow=c(2,2))
Medlif <- as.data.frame(ddply(gDat, ~year, summarize, median = round(median(lifeExp), 
    2)))
xyplot(median ~ year, Medlif, layout = c(4, 2), type = c("p", "g", "r"))

Meanlif <- as.data.frame(ddply(gDat, ~year, summarize, trimean = round(mean(lifeExp, 
    trim = 0.05), 2)))
xyplot(trimean ~ year, Meanlif, layout = c(4, 2), type = c("p", "g", "r"))

IV. How is life expectancy changing over time on different continents?

Medlifbycon <- as.data.frame(ddply(gDat, .(continent, year), summarize, median = round(median(lifeExp), 
    2)))
xyplot(median ~ year | continent, Medlifbycon, layout = c(4, 2), type = c("p", 
    "g", "r"))

Meanlifbycon <- as.data.frame(ddply(gDat, .(continent, year), summarize, trimean = round(mean(lifeExp, 
    trim = 0.05), 2)))
xyplot(trimean ~ year | continent, Meanlifbycon, layout = c(4, 2), type = c("p", 
    "g", "r"))

V. Depict the maximum and minimum of GDP per capita for all continents in 2007.

hDat <- subset(gDat, year %in% 2007)
# table(hDat$year);head(hDat)
ddply(hDat, ~continent, function(x) {
    theMin <- which.min(x$gdpPercap)
    x[theMin, c("country", "year", "continent", "gdpPercap")]
})

##            country year continent gdpPercap
## 1 Congo, Dem. Rep. 2007    Africa     277.6
## 2            Haiti 2007  Americas    1201.6
## 3          Myanmar 2007      Asia     944.0
## 4          Albania 2007    Europe    5937.0
## 5      New Zealand 2007   Oceania   25185.0

stripplot(gdpPercap ~ continent, hDat, jitter.data = TRUE, grid = "h", type = c("p", 
    "a"), fun = min)

ddply(hDat, ~continent, function(x) {
    theMax <- which.max(x$gdpPercap)
    x[theMax, c("country", "year", "continent", "gdpPercap")]
})

##         country year continent gdpPercap
## 1         Gabon 2007    Africa     13206
## 2 United States 2007  Americas     42952
## 3        Kuwait 2007      Asia     47307
## 4        Norway 2007    Europe     49357
## 5     Australia 2007   Oceania     34435

stripplot(gdpPercap ~ continent, hDat, jitter.data = TRUE, grid = "h", type = c("p", 
    "a"), fun = max)

VI.Look at the spread of GDP per capita within the continents in 2007.

ddply(hDat, ~continent, function(x) {
    dispersion <- sd(x$gdpPercap)
    x[dispersion, c("continent", "gdpPercap")]
})

##   continent gdpPercap
## 1      <NA>        NA
## 2      <NA>        NA
## 3      <NA>        NA
## 4      <NA>        NA
## 5      <NA>        NA

ddply(hDat, ~continent, function(x) {
    thesd <- sd(x$gdpPercap)
    x[thesd, c("country", "year", "continent", "lifeExp")]
})

##   country year continent lifeExp
## 1    <NA>   NA      <NA>      NA
## 2    <NA>   NA      <NA>      NA
## 3    <NA>   NA      <NA>      NA
## 4    <NA>   NA      <NA>      NA
## 5    <NA>   NA      <NA>      NA

sdGDP <- ddply(hDat, ~continent, summarize, sd = round(sd(gdpPercap), 2), median = round(mad(gdpPercap), 
    2), Quantile = round(IQR = round(IQR(gdpPercap), 2)))

stripplot(gdpPercap ~ continent, hDat, jitter.data = TRUE, grid = "h", type = c("p", 
    "a"))