Chapter 16: Inference for Regression
Climate Change
The earth has been getting warmer. Most climate scientists agree that one important cause of the warming is
the increase in atmospheric levels of carbon dioxide (CO2), a green house gas. Here is part of a regression
analysis of the mean annual CO2 concentration (CO2) in the atmosphere, measured in parts per thousand
(ppt), at the top of Mauna Loa in Hawaii and the mean annual air temperature (Temp) over both land and
sea across the globe, in degrees Celsius.
Let’s first read the dataset into R
climate <- read.table('Climate_Change.txt', sep = '\t', header = TRUE)
and take a look at the data structure:
str(climate)
## 'data.frame': 29 obs. of 3 variables:
## $ year: int 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 ...
## $ Temp: num 14.2 14.3 14.1 14.3 14.1 ...
## $ CO2 : num 339 340 341 342 344 ...
We see three variables, which are year, Temp (mean annual air temperature) and CO2 (mean annual CO2
concentration), and there are 29 observations in each variable.
We now take Temp as the response variable and CO2 the predictor variable, to study their relationship. To see
if linear regression is appropriate, we make a scatterplot of Temp against CO2
plot(climate$CO2, climate$Temp, xlab = 'CO2 Concentration', ylab = 'Temperature')
340 350 360 370 380
1
4
.1
1
4
.3
1
4
.5
CO2 Concentration
Te
m
p
e
ra
tu
re
It seems reasonable to fit a linear model to the dataset, because both variables are quantitative, the data
points show a linear pattern, and there is no outlier. So, let’s fit the model:
imod <- lm(Temp ~ CO2, data = climate)
1
The summary of the fitted model is given by
summary(imod)
##
## Call:
## lm(formula = Temp ~ CO2, data = climate)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.16809 -0.07972 0.00194 0.07013 0.18532
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.707076 0.481006 22.260 < 2e-16 ***
## CO2 0.010062 0.001336 7.534 4.19e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.09847 on 27 degrees of freedom
## Multiple R-squared: 0.6776, Adjusted R-squared: 0.6657
## F-statistic: 56.76 on 1 and 27 DF, p-value: 4.192e-08
which contains a lot of information. We see that R2 = 0.6776 and the SD of residuals se = 0.09847 (the
estimator of population standard deviation σ) with 27 degrees of freedom. In Coefficients section we
see the intercept b0 = 10.71 and the slope b1 = 0.01. Their standard errors are SE(b0) = 0.481 and
SE(b1) = 0.00134. Their t-test statistics are t0 = b0/SE(b0) = 22.26 and t1 = b1/SE(b1) = 7.534. Their
corresponding (two-tailed) p-values are very small (<2e-16 and 4.19e-08). As a result, we reject H0 : β1 = 0
and conclude there is a positive correlation between Temp and CO2. The b1 = 0.01 can be interpreted as
follows: The air temperature will increase by 0.01 degrees Celsius on average if the CO2 concentration in the
atmosphere increases by 1 p ...
Chapter 16 Inference for RegressionClimate ChangeThe .docx
1. Chapter 16: Inference for Regression
Climate Change
The earth has been getting warmer. Most climate scientists
agree that one important cause of the warming is
the increase in atmospheric levels of carbon dioxide (CO2), a
green house gas. Here is part of a regression
analysis of the mean annual CO2 concentration (CO2) in the
atmosphere, measured in parts per thousand
(ppt), at the top of Mauna Loa in Hawaii and the mean annual
air temperature (Temp) over both land and
sea across the globe, in degrees Celsius.
Let’s first read the dataset into R
climate <- read.table('Climate_Change.txt', sep = 't', header =
TRUE)
and take a look at the data structure:
str(climate)
## 'data.frame': 29 obs. of 3 variables:
## $ year: int 1980 1981 1982 1983 1984 1985 1986 1987 1988
1989 ...
## $ Temp: num 14.2 14.3 14.1 14.3 14.1 ...
## $ CO2 : num 339 340 341 342 344 ...
We see three variables, which are year, Temp (mean annual air
temperature) and CO2 (mean annual CO2
concentration), and there are 29 observations in each variable.
We now take Temp as the response variable and CO2 the
2. predictor variable, to study their relationship. To see
if linear regression is appropriate, we make a scatterplot of
Temp against CO2
plot(climate$CO2, climate$Temp, xlab = 'CO2 Concentration',
ylab = 'Temperature')
340 350 360 370 380
1
4
.1
1
4
.3
1
4
.5
CO2 Concentration
Te
m
p
e
ra
tu
re
It seems reasonable to fit a linear model to the dataset, because
3. both variables are quantitative, the data
points show a linear pattern, and there is no outlier. So, let’s fit
the model:
imod <- lm(Temp ~ CO2, data = climate)
1
The summary of the fitted model is given by
summary(imod)
##
## Call:
## lm(formula = Temp ~ CO2, data = climate)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.16809 -0.07972 0.00194 0.07013 0.18532
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.707076 0.481006 22.260 < 2e-16 ***
## CO2 0.010062 0.001336 7.534 4.19e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.09847 on 27 degrees of freedom
## Multiple R-squared: 0.6776, Adjusted R-squared: 0.6657
## F-statistic: 56.76 on 1 and 27 DF, p-value: 4.192e-08
which contains a lot of information. We see that R2 = 0.6776
and the SD of residuals se = 0.09847 (the
estimator of population standard deviation σ) with 27 degrees of
freedom. In Coefficients section we
see the intercept b0 = 10.71 and the slope b1 = 0.01. Their
4. standard errors are SE(b0) = 0.481 and
SE(b1) = 0.00134. Their t-test statistics are t0 = b0/SE(b0) =
22.26 and t1 = b1/SE(b1) = 7.534. Their
corresponding (two-tailed) p-values are very small (<2e-16 and
4.19e-08). As a result, we reject H0 : β1 = 0
and conclude there is a positive correlation between Temp and
CO2. The b1 = 0.01 can be interpreted as
follows: The air temperature will increase by 0.01 degrees
Celsius on average if the CO2 concentration in the
atmosphere increases by 1 ppt. If only focus on the coefficients
we may do
summary(imod)$coefficients
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.70707624 0.48100637 22.259739 6.641063e-
19
## CO2 0.01006241 0.00133563 7.533828 4.191615e-08
To obtain the confidence interval for each regression
coefficient, we may do
confint(imod, level = 0.95)
## 2.5 % 97.5 %
## (Intercept) 9.72013269 11.69401978
## CO2 0.00732192 0.01280289
The 95% (default confidence level) confidence interval for the
slope of CO2 is (0.0073, 0.0128). We are 95%
confident that as CO2 concentration increases by 1 ppt the air
temperature on average will increase by the
amount between 0.0073 and 0.0128 degrees Celsius.
We now need to check if the fitted model meets the
assumptions. From the scatterplot we can see the linearity
assumption is satisfied. Because the data are a time series, we
need to plot the residuals against the time
5. (year) to check independence assumption. We also need to plot
the residuals against fitted values ŷ (or
x-values) to check constant variance assumptions. Let’s produce
both plots:
par(mfrow = c(1, 2))
plot(climate$year, imod$residuals, xlab = 'Time', ylab =
'Residual')
abline(a = 0, b = 0)
2
plot(imod$fitted.values, imod$residuals, xlab = 'Fitted value',
ylab = 'Residual')
abline(a = 0, b = 0)
1980 1990 2000
−
0
.1
5
−
0
.0
5
0
.0
5
0
7. .1
5
Fitted value
R
e
si
d
u
a
l
The two residual plots are almost identical. Both of them show
no pattern and equal spread across the
x-values, so the independence and constant variance
assumptions are met. To check the Normal distribution
assumption we may use histogram and Q-Q plot of residuals
par(mfrow = c(1,2))
hist(imod$residuals, xlab = 'Residual', main = 'Histogram of
Residuals')
qqnorm(imod$residuals)
qqline(imod$residuals)
Histogram of Residuals
Residual
F
re
q
9. .1
5
Normal Q−Q Plot
Theoretical Quantiles
S
a
m
p
le
Q
u
a
n
til
e
s
The histogram shows a potential right-skewness in the
distribution. The Q-Q plot shows a slight departure
from the straight line especially at two ends. The assumption is
not seriously violated, but the regression
3
analysis should proceed with caution. Note that it is not easy to
10. check the normality assumption with only
29 observations. More data should be collected for this purpose.
Now we want to predict the air temperature when the CO2
concentration level is at 355 ppt. First, we need
to make sure that the 355 ppt is in the range of sampled x-
values
range(climate$CO2)
## [1] 338.67 384.84
Then, we create a new dataset for prediction
new <- data.frame(CO2 = c(355))
Suppose we are interested in the mean temperature of all years
with the CO2 concentration at 355 ppt. We
therefore build a 95% confidence interval for the mean
temperature:
predict(imod, newdata = new, interval = 'confidence', level =
0.95)
## fit lwr upr
## 1 14.27923 14.2394 14.31906
The predicted mean temperature ŷν = 14.279 and its confidence
interval is (14.239, 14.319). We are 95%
confident that the mean air temperature of all years with CO2
concentration at 355 ppt is between 14.239
and 14.319 (degrees Celsius).
Suppose the CO2 concentration is estimated to be 355 ppt next
year. What are the predicted temperature
and the 95% prediction interval for that temperature for next
year?
predict(imod, newdata = new, interval = 'prediction', level =
0.95)
11. ## fit lwr upr
## 1 14.27923 14.07329 14.48517
The predicted temperature for next year ŷν = 14.279, and its
prediction interval is (14.073, 14.485). We are
95% confident that the temperature for next year is between
14.073 and 14.485 (degrees Celsius) if the CO2
concentration is at 355 ppt. Note that the prediction interval is
wider than the confidence interval.
It is interesting to build a confidence band and a prediction
band, and plot them to see how the predicted
values and their uncertainties dynamically change with all
possible x-values. To do so, we first need to create
a new sequence of possible x-values within the range of
sampled data:
xx <- seq(min(climate$CO2), max(climate$CO2), length.out =
100)
and create a new dataset for prediction based on xx
new.band <- data.frame(CO2 = xx)
Then, we build confidence interval and prediction interval for
each value in new.band
conf <- predict(imod, newdata = new.band, interval =
'confidence', level = .95)
pred <- predict(imod, newdata = new.band, interval =
'prediction', level = .95)
To make the plot we first draw the data points and the
regression line, and then add confidence and prediction
bands to the plot
plot(climate$CO2, climate$Temp, xlab = 'CO2 Concentration',
ylab = 'Temperature')
abline(imod)
12. lines(xx, conf[, 'lwr'], lty = 2, col = 'red')
lines(xx, conf[, 'upr'], lty = 2, col = 'red')
lines(xx, pred[, 'lwr'], lty = 3, col = 'blue')
lines(xx, pred[, 'upr'], lty = 3, col = 'blue')
4
340 350 360 370 380
1
4
.1
1
4
.3
1
4
.5
CO2 Concentration
Te
m
p
e
ra
tu
13. re
As we can see, the prediction band is much wider than the
confidence band, and it covers all the data points.
Note that the prediction interval is NOT parallel, although it
seems to be so. Both intervals actually get
narrower as x-values approach their average, but wider as the x-
values move away from it.
5
Climate Change
See discussions, stats, and author profiles for this publication
at: https://www.researchgate.net/publication/6314977
Public Health, Culture, and Colonial Medicine: Smallpox and
Variolation in
Palestine During the British Mandate
Article in Public Health Reports · May 2007
DOI: 10.1177/003335490712200314 · Source: PubMed
CITATIONS
8
READS
89
2 authors, including:
Some of the authors of this publication are also working on
14. these related projects:
Public health ethics View project
Private-public mix and commodification of health View project
Nadav Davidovitch
Ben-Gurion University of the Negev
155 PUBLICATIONS 1,074 CITATIONS
SEE PROFILE
All content following this page was uploaded by Nadav
Davidovitch on 25 December 2015.
The user has requested enhancement of the downloaded file.
https://www.researchgate.net/publication/6314977_Public_Healt
h_Culture_and_Colonial_Medicine_Smallpox_and_Variolation_
in_Palestine_During_the_British_Mandate?enrichId=rgreq-
de905fe25f0f316bab33c2623e32a5dd-
XXX&enrichSource=Y292ZXJQYWdlOzYzMTQ5Nzc7QVM6M
zEwNTc4NTgzNjcwNzkzQDE0NTEwNTkxMTI3NjY%3D&el=1
_x_2&_esc=publicationCoverPdf
https://www.researchgate.net/publication/6314977_Public_Healt
h_Culture_and_Colonial_Medicine_Smallpox_and_Variolation_
in_Palestine_During_the_British_Mandate?enrichId=rgreq-
de905fe25f0f316bab33c2623e32a5dd-
XXX&enrichSource=Y292ZXJQYWdlOzYzMTQ5Nzc7QVM6M
zEwNTc4NTgzNjcwNzkzQDE0NTEwNTkxMTI3NjY%3D&el=1
_x_3&_esc=publicationCoverPdf
https://www.researchgate.net/project/Public-health-ethics-
2?enrichId=rgreq-de905fe25f0f316bab33c2623e32a5dd-
XXX&enrichSource=Y292ZXJQYWdlOzYzMTQ5Nzc7QVM6M
16. XXX&enrichSource=Y292ZXJQYWdlOzYzMTQ5Nzc7QVM6M
zEwNTc4NTgzNjcwNzkzQDE0NTEwNTkxMTI3NjY%3D&el=1
_x_10&_esc=publicationCoverPdf
Public Health Chronicles
398 Public Health Reports / May–June /
Volume 122
PubliC HealtH, Culture, and
Colonial MediCine: SMallPox and
Variolation in PaleStine during
tHe britiSH Mandate
Nadav Davidovitch, MD, MPH, PhD
Zalman Greenberg, MPH, MSc, PhD
In December 1921, in the Arab village of
Duwaimeh
near Hebron, an epidemic of smallpox broke out
fol-
lowing variolation of the population. This practice of
variolation included taking material from the
blister
of a sick person and purposely inoculating
another
healthy individual. It was carried out mainly by
local
healers and was a common practice among the
local
population at the time.
This article reviews the history of smallpox in
Palestine during the British Mandate, focusing on
the smallpox outbreak in Duwaimeh and the
17. inter-
relationship between the local population and British
Mandate authorities in the course of dealing with
the
epidemic. Vintage photos from the period found at
the
Israeli Public Health Central Laboratories in
Jerusalem
reveal that attempts by Mandatory physicians to
carry
out a mass vaccination of villagers were met
initially
by fierce opposition. In the course of the
vaccination
campaign, village children were hidden in caves
and
other hideaways in the vicinity out of fear of
their
being vaccinated.
Among all the colonial powers around the
world,
public health and addressing outbreaks of contagious
diseases were among key issues of concern in
the
handling of local administration for both colonial
regimes and the medical community. Much has been
written in recent years about the link between
health
and colonialism, recognizing the tension that existed
between Western and local medicine as an important
dimension of the history of colonialism.1–3 This
article
analyzes these aspects by examining how various
par-
ties reacted to the outbreak in the context of
18. their
different understandings of the disease and its
possible
prevention. It is also an opportunity to reconstruct
the
Palestinian rural context that existed in Palestine
at
the turn of the 20th century and almost disappeared
after the establishment of Israel.
Colonial MediCine in Context
As historians of colonial medicine have shown,
colonial
medicine occupied a place within a more
expansive
ideological order of the empires.1–4 Colonial efforts
to
deal with the health of developing regions were
closely
linked to the economic interests of the
colonizers.
Health was not an end in itself, but rather a
prereq-
uisite for colonial development. Colonial medicine,
or “tropical medicine,” as it was called during the
late
19th century, was concerned primarily with
maintaining
the health of Europeans living in the tropics,
because
these individuals were viewed as essential to the
colonial
project’s success. The health of the colonized
subjects
was normally only considered when their ill
19. health
threatened colonial economic enterprises or the health
of the Europeans. Accordingly, the success or
failure
of health interventions was measured more in terms
of
the colonies’ production than by measuring the
levels
of health among the native population.
Another aspect of this logic was that colonial
govern-
ments usually did little to build rural health
services for
the general native populations. Rural services,
when
they did exist, were run by missionaries and
focused
primarily on maternal and child health. For most
rural
inhabitants, contact with Western medical services
was limited to occasional medical campaigns such
as
mass vaccinations during infectious disease epidemics.
Yet, though this policy left a broad field for
action by
local traditional healers, colonial medical authorities
generally discounted the medical knowledge of
local
populations, and at times persecuted indigenous
health practitioners. Though there were important
exceptions to this pattern—such as in colonial India,
where British doctors drew on local knowledge
both
for identification of local illnesses and for
expanding
20. their pharmaceutical knowledge by incorporating local
plants and herbs—in general, disapproval of
knowledge
and practices was the rule.5
Another characteristic of colonial medicine was that
it tended to be narrowly technical in both its
design
and implementations. Health was defined during the
pre–World War II era as mainly the absence of
disease,
and could therefore be achieved by understanding
and developing methods for attacking specific dis-
eases, mainly those that were infectious, one at a
time.
This narrow “disease” approach to health and
illness
appeared to be cheaper and more manageable
than
efforts to improve the general health and well-being
of
Public Health Chronicles 399
Public Health Reports / May–June 2007 / Volume
122
colonial subjects through social and economic
develop-
ment. Colonial authorities viewed both the
provision
of broad-based health care and efforts to deal with
the
underlying social and economic determinants of
21. illness
as both impractical and unnecessary.
HealtH in PaleStine
At the turn of the 20th century, Palestine was
a dis-
tant part of the Ottoman Empire. Infectious
disease
rates were high. Malaria and trachoma were common
ailments.6–8 As several historians of medicine
have
described in their work on the everyday
experiences
of health and disease, we should remember that
“epi-
demic streets” were an everyday encounter in
many
places for the local population, in Palestine as
well
as in other parts of the world.9 High infant
mortality
rates, as well as infectious diseases such as
cholera,
dysentery, malaria, and tuberculosis, had a strong
impact on daily life.7
On several levels, circumstances in Palestine were
conducive to illness and disease. The geography
did
not provide an easy living, comprising a relatively
small
area with both swamps and deserts. This territory
was
on the Islamic pilgrims’ path on their way to
and
22. from Mecca, providing the opportunity for a
steady
influx of disease carriers. During the 19th
century,
the population of Palestine suffered from repeated
cholera epidemics transmitted by pilgrims returning
from Mecca and, during the First World War, by
Turkish
soldiers crossing the country. Most of the
epidemics
occurred in the old cities such as Jerusalem,
Tiberias,
and Jaffa, where infrastructure was inadequate.10
Pov-
erty, backwardness, absenteeism of the local elite,
and
the frequent incompetence and indifference of the
central government, with its resulting lack of
effective
social administration, further prepared the ground for
an easy spread of diseases.
Based on their patterns of life, the local Arab
Pal-
estinian population belonged to three distinct ethnic
groups: peasants (fallahin), the urbanized (hadar),
and nomads and semi-nomad Bedouin tribes (badu).11
During the Ottoman rule, the local population relied
mainly on traditional medicine, including herbal
medicine, bone-setting, cauterization, blood-letting,
leeching, cupping, as well as amulet writers,
midwives,
and male religious healers.12
The Ottoman public health system was influenced by
increasing contact between the Ottoman Empire and
23. the European military, commerce, and science, which
triggered various reform movements (Tanzimat). While
reforms regarding health-care institutions were hardly
felt in Palestine, the economy experienced a marked
improvement. Coastal towns in particular benefited
from the increasing European influence and improved
infrastructure.13,14 However, the overwhelming majority
of Palestinians remained peasants, vulnerable to social
and economic inadequacies. At the beginning of
the
20th century, the area was still relatively
underdevel-
oped even within an Arab context.6,8
The First World War, in which Palestine was one
of
the battlegrounds, disrupted local life. Ottoman
author-
ities arrested both Arab and Jewish Zionist leaders,
kill-
ing some; they conscripted tens of thousands of
Arab
farmers, deforested large areas, and commandeered
crops and livestock. As a result, the population
declined
substantially. Those that remained faced starvation
and political chaos and were therefore easy prey
to
infectious diseases. Many health institutions, especially
those that offered free treatment, shut down or
limited
their operation drastically due to lack of resources
and
budgetary constraints. The local population had to
rely
24. primarily on their traditional medicine.12
On December 9, 1917, as World War I neared
its
end, Jerusalem surrendered to the British forces.
This
act marked the end of four centuries of Ottoman
rule.
British officials arriving in Palestine were
confronted
with a poverty-stricken population of approximately
600,000 Arabs and 85,000 Jews. The most
immediate
task of the occupying British forces was to
provide
food and medical supplies and to restore social
and
economic order.15
According to the Interim Report on the Civil Adminis-
tration of Palestine, the British forces found “a country
exhausted by war. The population had been depleted;
the people of the towns were in severe distress;
much
cultivated land was left untilled; the stocks of
cattle
and horses had fallen to a low ebb; the
woodlands,
always scanty, had almost disappeared; orange groves
had been ruined by lack of irrigation; commerce
had
long been at a standstill.”16
In July 1920, the British Mandate civil
administration
took over from the military. Public health was
25. among
the first concerns of the new rule, as expressed in
vari-
ous early written reports: “Both the Military
and the
Civil Administrations have paid the closest attention
to
measures for safeguarding the health of the
population.
The Department of Public Health has a fully
organized
central and local establishment. The sanitation of the
towns is efficiently supervised. A quarantine service
is
maintained . . . at the present time the
Government
maintains 15 hospitals, 21 dispensaries, eight
clinics,
and five epidemic posts.”16
The British government focused first and foremost
on ridding Palestine of infectious diseases. The
govern-
ment embarked on installing new sewage and
drain-
400 Public Health Chronicles
Public Health Reports / May–June 2007 / Volume
122
age systems, invested in swamp drainage projects
and
hygiene education campaigns, and established a school
26. hygiene service. It also instituted the registration of
all
cases of infectious diseases and decreed several
ordi-
nances related to medical and public health matters,
such as licensing of various health-care
professions,
instituting pharmaceutical and food regulations, and
strengthening quarantine measures.17 All of these
measures, however, were only partially implemented
or limited in scope, and investment was restricted.
The
British administration did not hesitate to rely on
out-
side sources for the advancement of public health.18
Although state hospitals that treated mostly Arab
populations in urban areas were scarce at first,
during
the British mandate the system was gradually
expanded
due to demand from the local Arab
population.12
Where access to state hospitals was problematic,
the
Arab population depended on the Christian missionary
health services. Interestingly, the Jewish community
developed its own medical services as part of the
Zionist
enterprise, which included other welfare aspects. The
two main Jewish health-care organizations,
Hadassah
and the General Sick Fund (Kupat Holim
Clalit),
also treated Arabs. But in general, medical
relations
27. between Arabs and Jews during the Mandate
were
informal, based mainly on private initiatives.
Jewish
physicians treated private Arab patients in towns and
villages, especially where state hospitals and clinics
were
scarce. Sometime Jews, especially of Oriental descent,
were treated by Arab physicians.11
Although Palestine was not a British colony, it
was
run like a colony, without local representation
and
under tight supervision from London. British authori-
ties proceeded to govern the area much like a
regular
colony, though incorporating it fully into its
empire.
The British Mandate in Palestine hopelessly tried
to
accomplish two contradictory goals: to create a
Jewish
national home while also protecting the rights of
the
local Arab population. The inconsistency within Brit-
ish policy and contradicting expectation of Palestinian
Arabs and the Zionist Jewish community were
expressed
already in the Balfour Declaration, a letter
dated
November 2, 1917, from the British Foreign
Secretary
Arthur James Balfour, which supported Zionist
plans
for a Jewish “national home” in Palestine.
28. According
to the Palestinian Arab community interpretation,
this letter contradicted other British promises that
supported the Arab vision for Palestine after the
war.
This tension continued to exist over the whole
Man-
date period, when both sides—Arab and Jewish—were
dissatisfied with the British administration’s treatment
of Palestine.19 Apart from that, what makes the
British
Mandate period a unique case study is the side-by-
side
coexistence of the British administration, the
Zionist
bodies with their health organizations such as Hadas-
sah and the General Sick Fund (Kupat Holim
Clalit),
religious-related health institutions, and other interna-
tional health enterprises, each with its own agenda
and
strong emphasis on public health issues. If we add
to
that the local Palestinian Arab inhabitants, as
well as
Jewish people and their interaction, we have an
intri-
cate network that demands its investigation for
studying
the complexities of the country’s social history.
Meanwhile, the Arab and the growing Jewish com-
munities cooperated to some extent with British
insti-
tutions, but in parallel retained and built up
29. internal
quasi-governmental bodies. To sum up the
situation:
“Interwar Palestine was one territory, inhabited by
two
ethnic communities of three religions, governed
by
four administrative structures.”6
In the next sections, we will take a specific
case
study to illuminate these complexities. We describe
a
unique smallpox outbreak and its control by the
British
authorities as it unfolded. But first, we provide
some
background on smallpox in Palestine and the British
Public Health Administration.
SMallPox in PaleStine
Smallpox, a viral disease that was officially
eradicated
in 1980, was a significant infectious disease
throughout
history.20 It is very contagious, resulting in about
30%
mortality. It was also the first disease against
which a
vaccine was developed—by Edward Jenner in 1796
as
an empirical tool, as the cause of the disease
was as
yet unknown.
30. In Palestine, several outbreaks were recorded during
the 19th and early 20th centuries, as well as
sporadic
cases imported from endemic areas.21,22 The British
phy-
sician Ernst Masterman wrote of “an utterly
unchecked
epidemic” of smallpox in Jerusalem in 1900.23
As described previously, similar to other infectious
diseases, one of the main routes of infection
was the
Moslem pilgrimage to Mecca.17 During the
Ottoman
rule, vaccinations against smallpox were carried
out
only sporadically. According to an estimate, only
about
10% of the local population was ever vaccinated.22
The British Health Services for Palestine commenced
its activities in December 1917 after the occupation
of
Jerusalem and Jaffa, when the military campaign
in
Palestine was still not completed. According to
the
annual report of the British Department of
Health,
“There were few relics to be found of any
preexisting
Government Heath Services, and the testimony of
pre-war residents confirmed the absence of any
such
organization.”17 While this British description can
be
31. Public Health Chronicles 401
Public Health Reports / May–June 2007 / Volume
122
regarded as biased, it is reasonable to say that
due to
lack of comprehensive and coordinated medical
ser-
vices under Ottoman rule and the harsh
conditions
during the First World War, British officials arriving
in
Palestine were confronted with a poverty- and
disease-
stricken population. In 1922, the British undertook
the first census of the mandate. The population
was
752,048, comprising 589,177 Muslims (78%),
83,790
Jews (11%), 71,464 Christians (10%), and 7,617
people
(1%) belonging to other groups.24 As described
previ-
ously, both Jewish and Arab communities
exhibited
a high incidence of disease and famine that
raised
mortality rates among all segments of society:
Muslim,
Christian, and Jewish.
The British administration in Palestine was quick
32. to adopt public health legislation. By May 16,
1918,
Public Health Ordinance No. 1 was released to
“regu-
late the General Health Service of the country
such
as the practice of medicine; notification of infectious
diseases and births and deaths; vaccination;
burials;
and general sanitation.”17
Soon after, more public health legislation followed
with quarantine regulations, pharmacy, anti-malarial
ordinances, water sanitation, and more. Government
hospitals with infections annexes were secured in
large cities. These legislations, together with
other
administrative regulations, served as the basis for
put-
ting public health measures into action. One of
these
administrative regulations was related to the
sanita-
tion of villages and the health duties of
Mukhtars.
The Mukhtars, the traditional heads of the
village,
had in the British administration (as well as
during
the Ottoman period) important responsibilities in
sanitation and hygiene, such as in reporting
infectious
diseases and implementing isolation or quarantine as
needed. Following the British Annual Health
Report
of 1921, we can reconstruct the formal
33. relationship
between the Mandate public health officers and
the
local Mukhtars:
All villages are inspected at regular periods by
Medical
Officers. In addition, Sanitary Sub-Inspectors make
regular visits [ND, ZG: the sub-inspectors were
usually
Palestinians Arabs as opposed to medical officers
who
were typically British] . . . Orders in villages are
given to
the Mukhtar. A number of simple sanitary
regulations
have been drawn and published. The points raised
in
the regulations are examined on each visit. Mukhtars
are provided in all cases with books of
notification
forms of births, deaths, and infectious diseases.
Vil-
lage Registers are kept in each village . . .
In cases
of necessity warning notices are given to
Mukhtars
to abate nuisances; and in case of
noncompliance
legal administrative action is taken against offenders.
(Annual Report of the Department of Health,
Govern-
ment of Palestine for the Year 1921, p. 24)
As implied in the text cited, The Mukhtars’
34. willing-
ness to cooperate with the British Health Department
was subject to local variations and there were cases
of
noncompliance. These tensions between the health
administration and local communities were expressed
in the smallpox epidemic that broke out in
December
1921 in the southern part of Palestine, in a small
village
called Duwaimeh.
Duwaimeh at that time was a small Arab village
lying
“among the western foothills of the Judean
range,
four hours ride from Hebron.” The people there
were
described as “strong and healthy and well-suited
for
the pursuit on which a large number of them
depend
for a livelihood, for they are thieves of
considerable
distinction.”25 The Duwaimeh population, according
to the 1922 census, comprised 2,441 inhabitants,
all
of them Muslims.24
On December 19, 1921, a delegation of British
public health workers visited Duwaimeh, following
the
notification of a smallpox case in the village.
There
were no public health services in Duwaimeh.
Health
35. care was given by the local traditional healer, and
the
Mukhtar, the head of the village, was
responsible for
disease notification. As there were no roads connect-
ing to the village, the delegation arrived there
riding
their horses. After conducting their investigation, the
public health officers were satisfied to hear that
there
was no other new case of smallpox. After
examining
the smallpox patient, the public health delegation
left
the village. At the time, they had not known that
dur-
ing their visit, 300 children were kept hidden
in the
village and surrounding caves.
These children were variolated by Shaheen, the local
village healer, following the Mukhtar’s order.
Variolation
is the historical practice of inducing immunity
against
smallpox by scratching the skin with the purulency
from
smallpox skin pustules taken from a smallpox
patient.
Although an ancient custom, in the modern
period
Lady Mary Wortley Montagu introduced this practice
into England from Turkey in 1721. Variolation
was
discarded by the medical community after the
intro-
36. duction of the smallpox vaccine by Edward Jenner
in
1796, yet variolation continued to be practiced to
the
20th century mainly by local healers. Many
techniques
existed and there were local variations according to
the
local custom. Shaheen, Duwaimeh’s local healer, took
lymph from pocks of the original first case, a
female
servant of Hussein the Mukhtar, and inoculated
the
children on the dorsal aspect of the hand
between
the thumb and forefinger according to the
“traditional
402 Public Health Chronicles
Public Health Reports / May–June 2007 / Volume
122
method of the country.”17 The servant was first
seen
by a physician on December 13, 1921. She was
already
in a pustular stage, taken into isolation in a tent
some
distance from the village. What was not known by
the
public health administration was that 300 children
had already been inoculated by the local healer
using
37. infected matter from the initial case.
According to the Lancet article describing the
Duwaimeh’s epidemic and the British annual
report
of the Department of Health from 1922, 120
children
out of 300 who were variolated (40%)
developed
smallpox.25,26 Another 37 children were secondary
and
tertiary cases, infected either from the index
case or
from other ill children. Overall, there were 158
cases
of smallpox in the village, including the index
case,
out of a population of 2,441 (6.5%). As we do
not have
the total number of children in the village, age-
specific
rates cannot be calculated. Interestingly, out of the
120
children who were variolated and developed smallpox,
10 children died (case fatality rate of 12.3%),
while
out of the 37 naturally occurring cases, six
children
died (case fatality rate of 16.2%). These data
reflect
the known fact that in the past, variolation
carried
with it lower fatality rates than in naturally
occurring
cases. This difference became irrelevant after the
38. Shaheen inoculating a child. Attached to the original
photograph is a thorn that was used for the
inoculation.
This photograph and the other three presented in
this
article are part of a collection found at the Israeli
Central
Laboratories. It can also be found at the Wellcome
Library for the History of Medicine contained in an
album of photographs (photograph #7) documenting
the
Duwaimeh outbreak. Lettering in the front of the
album:
“Anti-smallpox campaign, Dawaimeh—Hebron. January—
February 1922”. There is also a typed note stating
that the
album was presented by Dr. Reginald Sibley.
introduction of the much safer technique of smallpox
vaccination.
The rumors on the variolated children were spread
by the Mukhtar’s enemies, and a hospital was
quickly
established in the Mukhtar’s house staffed by a
doc-
tor, nurses, a cook, and servants. The British
Health
Department wanted to initiate an immediate vaccina-
tion campaign. According to John MacQueen,
“The
work of vaccination was pushed on, and in a short
time
most of the inhabitants had been vaccinated.”25
Yet the vaccination campaign did not proceed
39. according to the original British public health
officials’
plan. The British group needed to make a
“systematic
house-to-house inspection” and also to search in
“close
caves, corn bins, roofs, gardens . . . every hole
had to be
searched.”25 Public health workers were actually
playing
hide and seek with the children from the village.
Prob-
ably the adults were not satisfied either with these
new
intruders and did not make their efforts easier.
Public health officer getting a child out of a corn-
stone. Photograph from the Israeli Central
Laboratories
collection.
Public Health Chronicles 403
Public Health Reports / May–June 2007 / Volume
122
In addition to the practical difficulties of
convinc-
ing the village community to vaccinate their children
in order to control the smallpox outbreak,
another
problem emerged. According to the official
reports,
apparently the vaccination lymph “proved quite unsat-
40. isfactory.” Only 172 out of 2,754 vaccinations
showed
positive results. The smallpox vaccinations were
not
produced by the British Health Department, which
had just recently started its work in the
country. The
Health Department was cooperating with the exist-
ing Pasteur Institute in Palestine, established by
Dr.
Leo Boehm. In 1913, Dr. Boehm, a young
Zionist
doctor who had emigrated from Russia to
Palestine,
established the Pasteur Institute for Health, Medicine
and Biology in Palestine. The laboratory was
part of
an international health complex that also included a
mother and child health center operated by Hadassah
and sponsored by the Jewish New York
philanthropists
Nathan Strauss. Boehm, who borrowed Pasteur’s name
without the knowledge of the French laboratory,
visited
Palestine in 1906 and was astonished by the
fact that
under prevailing circumstances at the time,
anyone
Child with smallpox. Photograph acquired from the
Israeli Central Laboratories collection.
suspected of having been exposed to rabies
needed
to be sent to Cairo or Constantinople.27 During
the
41. First World War, Boehm’s laboratory produced rabies,
smallpox, and cholera vaccines for the disease-
stricken
Palestine population, which were also used by
the
Turkish army.
After the poor results of Boehm’s vaccines,
fresh
lymph was obtained from Egypt with much better
out-
come and acceptance from the local population: “The
natives themselves were struck by its greater
potency
and came forward readily enough even to be
vaccinated
for the third time . . . Vaccination with the
‘Cairo’
lymph marked the turning point in the
campaign.”25
It is hard to tell whether this description
accurately
reflects the response of the Duwaimeh villagers, as
no
written material documenting their reaction to the
continuous vaccination efforts remains with us.
Yet,
probably the new vaccine’s higher “take,” meaning
its
greater scarification effect, left its impression.
An important fact to consider is that the local
healer
who executed the variolation of the village’s
children,
which brought with it grave consequences, still
42. retained
404 Public Health Chronicles
Public Health Reports / May–June 2007 / Volume
122
his respectable position in the community.
Shaheen,
the local healer, was described in the British report
of
the outbreak as a “distinguished looking
gentleman
of over 50 years of age.” He was part of
a family of
traditional healers. It is clear from his descriptions
by
the public health officers involved that they
respected
his work. Even among the Bedouin, he was
considered
powerful: “He was held as to have skill and
experience
in his profession.” Nevertheless, Shaheen was sent
to
prison for a month “as a result of his misguided
efforts
to limit the spread of the disease.” According
to the
British testimony, his reputation was by no
means
lessened, but rather considerably enhanced by his
performance in Duwaimeh and especially after his
imprisonment.25,26
43. During the British Mandate rule, smallpox was
observed mainly in the Arab population of Palestine,
invariably following importation from the surround-
ing Arab states. In 1924, another small cluster
of 19
smallpox cases following variolation was observed
in
Palestine. According to British sources, smallpox vac-
cination campaigns were generally well accepted.
In
1935, the British Health Department was able to
state
that “. . . in consequence of the high percentage
of the
House-to-house inspection. Photograph from the Israeli
Central Laboratories collection.
population protected by vaccination, there is little
fear
of a serious spread of the disease resulting
from any
imported cases from neighboring infected countries.”
In early 1949, shortly after the establishment of
the
Israeli state, the appearance of smallpox in Tel
Aviv
among Jewish immigrants from Yemen led to the
first
and last mass smallpox vaccination campaign carried
out by the Israel Ministry of Health. No cases
were
observed in Israel after 1950.21
ConCluSion
44. Scholarship focusing on the Palestinian Arab popula-
tion during the Mandate period mainly centers
on
the politics of Palestinian nationalism. Public
health
remains a relatively unexplored topic. Given the
cur-
rent political situation, it is not hard to
understand
how it is that the literature that does exist
on Pales-
tinian Arab health and medicine focuses mainly
on
contemporary health conditions. Another problem in
the historiography of health in Palestine is that
most
of the studies of the history of public health focus
on
Zionist efforts. For the most part, they take an
uncriti-
cal stance toward Western medicine. Many of
them
Public Health Chronicles 405
Public Health Reports / May–June 2007 / Volume
122
remain in the realm of institutional history, failing
to
emphasize the colonial dimension of health in
that
period and how the Palestinian Arab community took
45. part in this process.
We should remember that Western medicine was
already entering Palestine from the 19th century, but
it would be simplistic to perceive this entrance
as a
smooth, victorious conquest. Similar to David
Arnold’s
observation on the history of colonial medicine
in
India, “There was nothing inevitable about this
pro-
cess of medical colonization, nor was it
uncontested.”4
Part of the power of the colonial medicine
discourse
of the period lay in the manner in which
medicine
self-consciously conceived of itself as a science,
based
on careful local observation and eschewing the
ill-
informed speculation of the past and the rank
super-
stition associated with local traditional concepts
of
disease and healing.
Palestine, as in other places, continued to have side
by side an impressive collection of healers,
conven-
tional and unconventional, traditional, and a
strong
tradition of self-help. As shown in the case
study of
the Duwaimeh outbreak, traditional healers had a
46. fundamental position within the local social fabric
that was challenged by the British administration.
Yet
both the local population and even some of the
health
personnel who worked in the field, comprised also
of
local physicians and nurses, respected the local
heal-
ers. Hence, the tensions between different medical
worldviews should be framed as a complicated
context
of struggles and negotiations among those involved
in
public health-related disputes: the local populations,
health-care workers, and British administrators. The
entrance of Western medicine into Palestine, as in
other
colonial regimes, had its own political dimensions.
The
civilizing power of medicine and public health
was a
crucial part of colonial regimes, and within this
scheme,
vaccinations had an advantageous position. Yet this
was
not a simple and uncontested process.
Although vaccinations are considered one of the
most important achievements of medicine in the
20th century, even before the discovery of
antibiotics,
through the course of history of medicine immuniza-
tion has, more than once, engendered opposition
that has even reached the level of a civil
rebellion.28–30
47. Recently, there has been a growing recognition
of
the potential embodied in historical research on
opposition to vaccination, especially in its ability
to
serve as a vehicle for gaining better understanding
of
the politics of the human body and its relation to
the
modern state.31–33
The fact that for a long time the issue of
vaccinations
was an important component in the colonial system
is
an important point for historical understanding of
the
relationships among the state, public health personnel,
and the population. Westerners brought with them
various vaccines with which they wanted to
vaccinate
local populations. Despite their good intentions, many
times this fact caused local populations to identify
the
vaccination policy Westerners wanted to institute with
a repressive and foreign regime.
While we should not underestimate the tensions
and controversies among the various healers in
Pal-
estine—conventional vs. traditional, Jewish, Muslim,
or Christian, European or local—in general the
private aspects of health (i.e., self-help, networks
of
health, and traditional healers) continued to exist
48. and have a strong influence on everyday life, and
still
do today.34–36
Recently, health as a historical category has
been
integrated more fully into the Palestine/Israel
histo-
riographies. Many times, concerns of medicine
and
disease were overshadowed by the more
immediate
interest of scholars of the Middle East and
Zionism
in the political and diplomatic histories of Palestine/
Israel. Much of this scholarship seeks to
understand
the origins and dynamics of the Palestinian-Israeli
conflict and the development that precipitated the
emergence of the state of Israel. The
exploration of
medicine and health can capture broad issues,
cutting
across a variety of policy areas, in a way that
can help
reconstruct a richer social history of Palestine/Israel.
Public health and medicine were an important part
of
the Zionist project and Palestinian historiography. The
intersection of health, politics, and colonialism
can
enable the construction of a sociocultural history
of
disease in Palestine. In contrast to the simplistic
view
that Western medicine “conquered the hearts of
49. the
natives,” in fact reciprocal relationships between colo-
nizers and local populations were far more
complex
in regard to perceptions of sickness and health.
The
Duwaimeh outbreak can also help us to
reconstruct
an almost forgotten history of rural Palestine in
the
pre-Israeli state era. Interestingly, public health
reports
that meticulously survey the land and its
inhabitants,
mainly in relation to then-prevalent infectious
diseases
such as malaria, trachoma, or smallpox, can
serve as
extraordinary documents describing the social and cul-
tural context of Palestine and its population.
Physicians,
public health officials, and local healers described
the
life of their patients in a way that can
provide social
historians rich materials with which to work.
As shown in the Duwaimeh smallpox outbreak,
despite the fact that the outbreak was contained
and
stamped out, various narratives continued to circulate
among the sides vis-à-vis the event. Although the
local
50. 406 Public Health Chronicles
Public Health Reports / May–June 2007 / Volume
122
healer in the village was accused of being the
agent
responsible for spreading the disease and causing
the death of many children, the healer’s
incarcera-
tion by the British for his conduct did not
adversely
affect his popularity among his neighbors; rather,
just
the opposite occurred. In addition to the
Duwaimeh
outbreak, understanding the variolation of more than
300 children gives us the opportunity to analyze
the
last large smallpox epidemic resulting from
variola-
tion documented and recorded in details during
the
20th century.
Nadav Davidovitch is a Senior Lecturer at the
Department of
Health Systems Management, Faculty of Health
Sciences, Ben-
Gurion University of the Negev, Beer-Sheva, Israel,
and Adjunct
Lecturer at the Center for the History and Ethics
of Public
Health, Mailman School of Public Health, Columbia
University,
New York, NY. Zalman Greenberg is the former
51. head of the Israeli
Public Health Laboratory, Ministry of Health,
Jerusalem, Israel.
Address correspondence to: Nadav Davidovitch, MD,
MPH,
PhD, Department of Health Systems Management,
Faculty of
Health Sciences, Ben-Gurion University of the Negev,
P.O. Box
653, Beer-Sheva, Israel 84105; tel. +972-8-6477421;
fax +972-8-
6477634; e-mail <[email protected]>.
reFerenCeS
1. Cunningham A, Andrews B, editors. Western
medicine as contested
knowledge. Manchester (England): Manchester
University Press;
1997.
2. Marks S. What is colonial about colonial
medicine? And what has hap-
pened to imperialism and health? Soc Hist Med
1997;10:205-19.
3. Anderson W. Where is the postcolonial history
of medicine? Essay
review. Bull Hist Med 1998;72:522-30.
4. Arnold D. Colonizing the body: state medicine
and epidemic disease
in nineteenth-century India. Berkeley (CA): University
of California
Press; 1993.
52. 5. Packard RM. Post-colonial medicine. In:
Cooter R, Pickstone J,
editors. Companion to medicine in the twentieth
century. London
and New York: Routledge; 2000. p. 97-112.
6. Borowy I, Davidovitch N. Health in
Palestine, 1850–2000. In:
Borowy I, Davidovitch N, editors. Health in Palestine
and the Middle
Eastern context. Dynamis 2005;25:315-27.
7. Sufian S. An introduction to the history of
Arab health care during
the British Mandate, 1920–1947. In: Barnea T,
Husseini R, editors.
Separate and cooperate, cooperate and separate: the
disengagement
of the Palestine health care system from Israel and
its emergence
as an independent system. Westport (CT) and
London: Praeger;
2002.
8. Waserman MJ, Kottek SS, editors. Health and
disease in the Holy
Land: studies in the history and sociology of
medicine from ancient
times to the present. Lewiston (NY): Edwin Mellen
Press; 1996.
9. Hardy A. The epidemic streets: infectious
disease and the rise of
preventive medicine, 1856–1900. Oxford (England):
Oxford Uni-
53. versity Press; 1993.
10. Schwartz E, Bar-El D, Schur N. The
history of cholera epidemics
in Israel. Harefuah 2005;144:363-70, 381.
11. Karakrah M. Development of public health
services to the Palestin-
ians under the British Mandate, 1918–1948 [master’s
thesis]. Mount
Carmel, Haifa: University of Haifa; 1992.
12. Abu-Rabia A. Bedouin health services in
Mandated Palestine. Middle
Eastern Studies 2005;41:421-9.
13. Schölch A. European penetration and the
economic development
of Palestine, 1856–82. In: Owen R, editor. Studies
in the economic
and social history of Palestine in the nineteenth
and twentieth
centuries. Oxford (England): Macmillan Press; 1982.
p. 10-87.
14. Kark R. The rise and decline of coastal
towns in Palestine. In:
Gil-bar GG, editor. Ottoman Palestine, 1800–1914:
studies in eco-
nomic and social history. Leiden (Netherlands): E.
J. Brill; 1990.
p. 69-89.
15. Smith CD. Palestine and the Arab-Israeli
conflict. 2nd edition. New
York: Palgrave Macmillan; 1992.
54. 16. An interim report on the civil administration
of Palestine during the
period 1st July, 1920–30th June 1921. United
Nations Information
System on the Question of Palestine [cited 2006
Jan 18]. Available
from: URL: http://domino.un.org/UNISPAL.NSF
17. Annual report of the Department of Health,
Government of Pal-
estine for the Year 1921.
18. Shepherd N. Ploughing sand: British rule in
Palestine, 1917–1948.
New Brunswick (NJ): Rutgers University Press; 2000.
19. Segev T. One Palestine, complete: Jews and
Arabs under the British
Mandate. New York: Henry Holt; 2000.
20. Fenner F, editor. Smallpox and its eradication.
Geneva, Switzerland:
World Health Organization; 1988.
21. Slater PE, Leventhal A, Anis E. The
elimination of smallpox from
Israel. Isr Med Assoc J 2001;3:71-2.
22. Stuart G, Krikorian KS. Anti-variolous measures
in Palestine. The
Annals of Tropical Medicine & Parasitology
1930;24:527-44.
23. Masterman EWG. A smallpox epidemic in
Jerusalem. St. Bar-
55. tholomew’s Hospital Journal 1900;19-21.
24. Palestine, Report and General Abstracts of
the Census of 1922.
Taken on the 23rd of October, 1922. Jerusalem:
Greek Convent
Press; 1923.
25. MacQueen J. Smallpox and variolation in a
village in Palestine.
Lancet 1926;207:212-5.
26. Annual Report of the Department of Health,
Government of Pal-
estine for the Year 1922.
27. Davidovitch N. Pasteur in Palestine: the politics
of the laboratory.
Proceedings of the annual conference of the
Israeli Association
for the History and Philosophy of Science; 2004
Mar 17; Van Leer
Institute, Jerusalem, Israel.
28. Walzer Leavitt J. The healthiest city: Milwaukee
and the politics of
health reform. Princeton (NJ): Princeton University
Press; 1982.
p. 76-121.
29. Durbach N. ‘They might as well brand us’.
Working-class resistance
to compulsory vaccination in Victorian England.
Soc Hist Med
2000;13:45-62.
56. 30. Colgrove J. Between persuasion and compulsion:
smallpox control
in Brooklyn and New York, 1894–1902. Bull
Hist Med 2004;78:
349-78.
31. Davidovitch N. Negotiating dissent: homeopathy
and anti-
vaccinationism at the turn of the twentieth
century. In: Johnston
RD, editor. The politics of healing: a history of
alternative medicine
in twentieth-century North America. New York:
Routledge; 2004.
32. Johnston RD. Contemporary anti-vaccination
movements in his-
torical perspective. In: Johnston RD, editor. The
politics of heal-
ing: histories of alternative medicine in twentieth-
century North
America. New York: Routledge; 2004.
33. Colgrove J. “Science in a democracy”: the
contested status of vacci-
nation in the Progressive Era and the 1920s. Isis
2005;96:167-91.
34. Fadlon J. Negotiating the holistic turn: the
domestication of alter-
native medicine. Albany (NY): State University of
New York Press;
2005.
35. Lev E. Ethno-diversity within current ethno-
pharmacology as part of
57. Israeli traditional medicine—a review. J Ethnobiol
Ethnomedicine
2006;2:4.
36. O’Connor BB. Healing traditions: alternative
medicine and the
health professions. Philadelphia: University of
Pennsylvania Press;
1995.
View publication statsView publication stats
https://www.researchgate.net/publication/6314977
R Homework for Chapter 16
The product manager at a subsidiary of Kraft Foods, Inc. is
interested in learning how sensitive sales are to
changes in the unit price of a frozen pizza in Dallas, Denver,
Baltimore, and Chicago. The product manager
has been provided data on both Price and Sales volume every
fourth week over a period of nearly four years
for the four cities.
You can find the data file on Blackboard. Download it and put it
in the same folder as your R program file.
Then, use the following command to read in the data
pizza <- read.table('Frozen_Pizza.txt', sep = 't', header =
TRUE)
and answer the questions below.
1. Let’s take Sales as response variable and Price as predictor
58. variable. Fit a linear regression model to each
of the four cities. Write down the four fitted models. In which
city the pizza sales seem to be more sensitive
to price than in others? Explain.
2. For each of the models fitted above produce a residual plot in
the time order, a residual plot against the
fitted values, and a Q-Q plot. Is there any regression assumption
violated in each model? Explain.
3. For the remaining questions let’s focus on the model for city
Dallas. Show a 90% confidence interval for
the slope of Price and interpret it. Based on the interval can we
say there is a statistically significant linear
relationship between Price and Sales volume? Explain.
4. Conduct a hypothesis test to see if there is a significant
negative correlation between Price and Sales
volume in city Dallas, i.e., test H0 : β1 = 0 vs Ha : β1 < 0. State
your test conclusion.
5. For city Dallas estimate the mean Sales if the Price is $2.50
and $3.00 using 95% confidence intervals.
Interpret both intervals. Can we also estimate the mean Sales if
the Price is $3.50? Explain.
6. For city Dallas we know the pizza price was $2.77 in the last
week of 1996. Suppose the price would increase
to $2.99 in the following week. Can you predict the sales for
that week and account for the uncertainty of
your prediction? Do you think the resulting prediction is useful?
Explain.
1
WeekBaltimore VolumeBaltimore PriceDallas VolumeDallas