Smoking: Cigarette consumption and life expectancy by country

In gmonette/p3d: Plot 3d Data and Fitted Surfaces

Cigarette consumption and life expectancy by country

Description

The variables for this data set were assembled from various web sources. They consist of life expectancy, cigarette consumption per capita and health expenditures per capita in 2004. The relationship between life expectancy and cigarette consumption is paradoxical leading to reflection on omitted variables and problems of causal inference with observational and aggregated data. The association between life expectancy and cigarette consumption could be termed an 'ecological correlation'.

Usage

data(Smoking)

Format

A data frame with 192 observations on the following 10 variables.

Country

a factor with 192 levels Afghanistan Albania Algeria Andorra ...

Continent

a factor with 6 levels Africa Asia Australia Europe North America South America

LE

Life expectancy (combining sexes – separate would be much more interesting), a numeric vector

CigCon

Annual cigarette consumption per capita, a numeric vector

LE.q

Life expectancy quartile, a factor with levels (28.6,40.2] (40.2,51.8] (51.8,63.4] (63.4,75]

Cont

short labels for Continent, a factor with levels Afrc Asia Astr Eurp NrtA SthA

Cont2

short labels for Continent, a factor with levels Africa Asia Australia Europe N.America S.America

HealthExpPC

Health expenditure per capita in US $, a numeric vector

Year

relevant year – all 2004, a numeric vector

HE

Health expenditure quartile, a factor with levels (152,476] (31.1,152] (476,6.1e+03] [0.3,31.1]

Details

Each row consists of the data for one country.

Source

http://www.nationmaster.com

Examples

## Not run: 
data(Smoking)
summary(Smoking)
head(Smoking)
fit1 <- lm( LE ~ CigCon, Smoking)
fit2 <- lm( LE ~ CigCon + HealthExpPC, Smoking)
summary(fit1)
summary(fit2) 
anova(fit1,fit2)

rownames(Smoking) <- Smoking$Country

Init3d(family = 'serif', cex = 1.5)
Plot3d( LE ~ CigCon + HealthExpPC | Continent, Smoking)
Axes3d()
Id3d(pad=1)

Fit3d(fit1)
Fit3d(fit2, col = 'green')

fit = lm( LE ~ CigCon + log(HealthExpPC) +I(CigCon^2) + I(log(HealthExpPC)^2) + I(CigCon*log(HealthExpPC)), Smoking)
Fit3d( fit , col = 'red')

# HealthExpPC is highly 'skewed': dense on left, long tail on right
require( lattice )
densityplot( Smoking$HealthExpPC )

# It can be useful to use a transformation to make 
# spread more even
#  e.g. log
# First make sure all values are positive:

sort( Smoking$HealthExpPC)

# Try a log transformation: 

Smoking$LogHE <- log(Smoking$HealthExpPC)    # create log HE

densityplot( Smoking$LogHE )

# Also useful to have categories:

Smoking$HECat <- cut(Smoking$LogHE, 7)       # create categories
summary(Smoking)

Plot3d( LE ~ CigCon + LogHE |Continent, Smoking )  # condition on level of HEpC
Axes3d()
Ell3d()
# Id3d(pad=1)

# Simple regression

Plot3d( LE ~ CigCon + LogHE |Continent, Smoking )  
fit.lin <- lm( LE ~ CigCon, Smoking)
Fit3d( fit.lin )

# Adjusting for LogHE with a linear model

fit.lin2 <- lm( LE ~ CigCon + LogHE, Smoking)
Fit3d( fit.lin2 , col = 'red')

Ell3d( use.groups = FALSE, partial = 3,
       partial.col = 'red', partial.lwd = 3)

# Note that the marginal model is determined by
# the projection of the 3d data ellipsoid on the 
# LE-CigCon plane.
# The slope wrt CigCon of the partial model 
# adjusting for LogHE is determined by the 
# red ellipse that is the frontal section of
# the 3d data ellipsoid through its center.
# 
# Simpson's paradox arises when the tilt of the
# frontal shadow of the 3d ellipsoid has the opposite
# direction to the tilt of its frontal section.
#
# i.e. the shadow and the slice of the ellipsoid
# tilt in different directions

# Stratifying on Continent
# No interaction

Plot3d( LE ~ CigCon + LogHE |Continent, Smoking )  
fit.add <- lm( LE ~ CigCon+Continent, Smoking)
Fit3d(fit.add)
Fit3d(fit.lin, col = 'black')

# With interaction

Plot3d( LE ~ CigCon + LogHE |Continent, Smoking ) 
fit.int<- lm( LE ~ CigCon*Continent, Smoking)
Fit3d( fit.int )

# Marginal without Africa

Plot3d( LE ~ CigCon + LogHE |Continent, Smoking ) 
fit.lin2 <- lm(LE ~ CigCon, subset(Smoking, Continent != "Africa"))
Fit3d( fit.lin2)


# Use multiple regression with quadratic surface

Plot3d( LE ~ CigCon + LogHE |Continent, Smoking ) 
fit = lm( LE ~ CigCon + I(LogHE^2) +I(CigCon^2) + I(LogHE^2) + I(CigCon*LogHE), Smoking)
Fit3d( fit, col = 'pink' )
# Pop3d(2)

# refit omitting Africa:

fit.na = lm( LE ~ CigCon + I(LogHE^2) +I(CigCon^2) + I(LogHE^2)
             + I(CigCon*LogHE), Smoking, subset = Continent != "Africa")
Fit3d( fit.na, col = 'red' )

# Marginal relationship

Pop3d(4)    # pop twice for each fit
fit.quad <- lm( LE ~ CigCon + I(CigCon^2) , Smoking)
Fit3d( fit.quad, col = 'green')

#  A quadratic surface within each Continent (overfitting?!)

fit2 = lm( LE ~ Continent*(CigCon + LogHE +I(CigCon^2) +
                             I(LogHE^2) + I(CigCon*LogHE)), Smoking)
Fit3d( fit2 )

## End(Not run)

gmonette/p3d documentation built on Nov. 16, 2023, 11:31 p.m.