Professional Documents
Culture Documents
(Download PDF) Modern Mathematical Statistics With Applications Jay L Devore Online Ebook All Chapter PDF
(Download PDF) Modern Mathematical Statistics With Applications Jay L Devore Online Ebook All Chapter PDF
https://textbookfull.com/product/modern-mathematical-statistics-
with-applications-3rd-edition-jay-l-devore/
https://textbookfull.com/product/probability-and-statistics-for-
engineering-and-the-sciences-jay-l-devore/
https://textbookfull.com/product/mathematical-statistics-with-
applications-in-r-third-edition-kandethody-m-ramachandran/
https://textbookfull.com/product/mathematical-statistics-
borovkov-a-a/
Water waves the mathematical theory with applications
Stoker
https://textbookfull.com/product/water-waves-the-mathematical-
theory-with-applications-stoker/
https://textbookfull.com/product/mathematical-statistics-1st-
edition-dieter-rasch/
https://textbookfull.com/product/mathematical-modeling-
applications-with-geogebra-1st-edition-jonas-hall/
https://textbookfull.com/product/essentials-of-modern-business-
statistics-with-microsoft-excel-7th-edition-david-anderson/
https://textbookfull.com/product/essentials-of-modern-business-
statistics-with-microsoft-excel-8th-edition-david-anderson/
Modern
Mathematical
Statistics with
Applications
Second Edition
Jay L. Devore
California Polytechnic State University
Kenneth N. Berk
Illinois State University
Jay L. Devore Kenneth N. Berk
California Polytechnic State University Illinois State University
Statistics Department Department of Mathematics
San Luis Obispo California Normal Illinois
USA USA
jdevore@calpoly.edu kberk@ilstu.edu
2 Probability 50
Introduction 50
2.1 Sample Spaces and Events 51
2.2 Axioms, Interpretations, and Properties of Probability 56
2.3 Counting Techniques 66
2.4 Conditional Probability 74
2.5 Independence 84
3 Discrete Random Variables and Probability Distributions 96
Introduction 96
3.1 Random Variables 97
3.2 Probability Distributions for Discrete Random Variables 101
3.3 Expected Values of Discrete Random Variables 112
3.4 Moments and Moment Generating Functions 121
3.5 The Binomial Probability Distribution 128
3.6 Hypergeometric and Negative Binomial Distributions 138
3.7 The Poisson Probability Distribution 146
4 Continuous Random Variables and Probability Distributions 158
Introduction 158
4.1 Probability Density Functions and Cumulative Distribution Functions 159
4.2 Expected Values and Moment Generating Functions 171
4.3 The Normal Distribution 179
4.4 The Gamma Distribution and Its Relatives 194
4.5 Other Continuous Distributions 202
4.6 Probability Plots 210
4.7 Transformations of a Random Variable 220
Content
The book certainly does include core material in probability (Chapter 2), random
variables and their distributions (Chapters 3–5), and sampling theory (Chapter 6).
But our desire to balance theory with application/data analysis is reflected in the
way the book starts out, with a chapter on descriptive and exploratory statistical
techniques rather than an immediate foray into the axioms of probability and their
consequences. After the distributional infrastructure is in place, the remaining
statistical chapters cover the basics of inference. In addition to introducing core
ideas from estimation and hypothesis testing (Chapters 7–10), there is emphasis on
checking assumptions and examining the data prior to formal analysis. Modern
topics such as bootstrapping, permutation tests, residual analysis, and logistic
regression are included. Our treatment of regression, analysis of variance, and
categorical data analysis (Chapters 11–13) is definitely more oriented to dealing
with real data than with theoretical properties of models. We also show many
examples of output from commonly used statistical software packages, something
noticeably absent in most other books pitched at this audience and level.
Mathematical Level
The challenge for students at this level should lie with mastery of statistical
concepts as well as with mathematical wizardry. Consequently, the mathematical
prerequisites and demands are reasonably modest. Mathematical sophistication and
quantitative reasoning ability are, of course, crucial to the enterprise. Students with
a solid grounding in univariate calculus and some exposure to multivariate calculus
should feel comfortable with what we are asking of them. The several sections
where matrix algebra appears (transformations in Chapter 5 and the matrix approach
to regression in the last section of Chapter 12) can easily be deemphasized or
skipped entirely.
Our goal is to redress the balance between mathematics and statistics by
putting more emphasis on the latter. The concepts, arguments, and notation
contained herein will certainly stretch the intellects of many students. And a solid
mastery of the material will be required in order for them to solve many of the
roughly 1,300 exercises included in the book. Proofs and derivations are included
where appropriate, but we think it likely that obtaining a conceptual understanding
of the statistical enterprise will be the major challenge for readers.
Recommended Coverage
There should be more than enough material in our book for a year-long course.
Those wanting to emphasize some of the more theoretical aspects of the subject
(e.g., moment generating functions, conditional expectation, transformations, order
statistics, sufficiency) should plan to spend correspondingly less time on inferential
methodology in the latter part of the book. We have opted not to mark certain
sections as optional, preferring instead to rely on the experience and tastes of
individual instructors in deciding what should be presented. We would also like
to think that students could be asked to read an occasional subsection or even
section on their own and then work exercises to demonstrate understanding, so that
not everything would need to be presented in class. Remember that there is never
enough time in a course of any duration to teach students all that we’d like them to
know!
Acknowledgments
We gratefully acknowledge the plentiful feedback provided by reviewers and
colleagues. A special salute goes to Bruce Trumbo for going way beyond his
mandate in providing us an incredibly thoughtful review of 40+ pages containing
many wonderful ideas and pertinent criticisms. Our emphasis on real data would
not have come to fruition without help from the many individuals who provided us
with data in published sources or in personal communications. We very much
appreciate the editorial and production services provided by the folks at Springer, in
particular Marc Strauss, Kathryn Schell, and Felix Portnoy.
A Final Thought
It is our hope that students completing a course taught from this book will feel as
passionately about the subject of statistics as we still do after so many years in the
profession. Only teachers can really appreciate how gratifying it is to hear from a
student after he or she has completed a course that the experience had a positive
impact and maybe even affected a career choice.
Jay L. Devore
Kenneth N. Berk
CHAPTER ONE
Overview
and Descriptive
Statistics
Introduction
Statistical concepts and methods are not only useful but indeed often indis-
pensable in understanding the world around us. They provide ways of gaining
new insights into the behavior of many phenomena that you will encounter in your
chosen field of specialization.
The discipline of statistics teaches us how to make intelligent judgments
and informed decisions in the presence of uncertainty and variation. Without
uncertainty or variation, there would be little need for statistical methods or statis-
ticians. If the yield of a crop were the same in every field, if all individuals reacted
the same way to a drug, if everyone gave the same response to an opinion survey,
and so on, then a single observation would reveal all desired information.
An interesting example of variation arises in the course of performing
emissions testing on motor vehicles. The expense and time requirements of the
Federal Test Procedure (FTP) preclude its widespread use in vehicle inspection
programs. As a result, many agencies have developed less costly and quicker tests,
which it is hoped replicate FTP results. According to the journal article “Motor
Vehicle Emissions Variability” (J. Air Waste Manage. Assoc., 1996: 667–675), the
acceptance of the FTP as a gold standard has led to the widespread belief that
repeated measurements on the same vehicle would yield identical (or nearly
identical) results. The authors of the article applied the FTP to seven vehicles
characterized as “high emitters.” Here are the results of four hydrocarbon and
carbon dioxide tests on one such vehicle:
D L L L D L L D L L
We have bivariate data when observations are made on each of two variables.
Our data set might consist of a (height, weight) pair for each basketball player on
a team, with the first observation as (72, 168), the second as (75, 212), and so on.
If a kinesiologist determines the values of x ¼ recuperation time from an injury and
y ¼ type of injury, the resulting data set is bivariate with one variable numerical
and the other categorical. Multivariate data arises when observations are made
on more than two variables. For example, a research physician might determine
the systolic blood pressure, diastolic blood pressure, and serum cholesterol level
for each patient participating in a study. Each observation would be a triple of
numbers, such as (120, 80, 146). In many multivariate data sets, some variables
are numerical and others are categorical. Thus the annual automobile issue of
Consumer Reports gives values of such variables as type of vehicle (small, sporty,
compact, midsize, large), city fuel efficiency (mpg), highway fuel efficiency
(mpg), drive train type (rear wheel, front wheel, four wheel), and so on.
Branches of Statistics
An investigator who has collected data may wish simply to summarize and
describe important features of the data. This entails using methods from descriptive
statistics. Some of these methods are graphical in nature; the construction of
histograms, boxplots, and scatter plots are primary examples. Other descriptive
methods involve calculation of numerical summary measures, such as means,
4 CHAPTER 1 Overview and Descriptive Statistics
Example 1.1 Charity is a big business in the United States. The website charitynavigator.
com gives information on roughly 5500 charitable organizations, and there are
many smaller charities that fly below the navigator’s radar screen. Some charities
operate very efficiently, with fundraising and administrative expenses that are
only a small percentage of total expenses, whereas others spend a high percentage
of what they take in on such activities. Here is data on fundraising expenses as
a percentage of total expenditures for a random sample of 60 charities:
6.1 12.6 34.7 1.6 18.8 2.2 3.0 2.2 5.6 3.8
2.2 3.1 1.3 1.1 14.1 4.0 21.0 6.1 1.3 20.4
7.5 3.9 10.1 8.1 19.5 5.2 12.0 15.8 10.4 5.2
6.4 10.8 83.1 3.6 6.2 6.3 16.3 12.7 1.3 0.8
8.8 5.1 3.7 26.3 6.0 48.0 8.2 11.7 7.2 3.9
15.3 16.6 8.8 12.0 4.7 14.7 6.4 17.0 2.5 16.2
Without any organization, it is difficult to get a sense of the data’s most promi-
nent features: what a typical (i.e., representative) value might be, whether values
are highly concentrated about a typical value or quite dispersed, whether there
are any gaps in the data, what fraction of the values are less than 20%, and so on.
Figure 1.1 shows a histogram. In Section 1.2 we will discuss construction and
interpretation of this graph. For the moment, we hope you see how it describes the
40
30
Frequency
20
10
0
0 10 20 30 40 50 60 70 80 90
FundRsng
way the percentages are distributed over the range of possible values from 0 to 100.
Of the 60 charities, 36 use less than 10% on fundraising, and 18 use between 10%
and 20%. Thus 54 out of the 60 charities in the sample, or 90%, spend less than 20%
of money collected on fundraising. How much is too much? There is a delicate
balance; most charities must spend money to raise money, but then money spent on
fundraising is not available to help beneficiaries of the charity. Perhaps each
individual giver should draw his or her own line in the sand. ■
Example 1.2 Human measurements provide a rich area of application for statistical methods.
The article “A Longitudinal Study of the Development of Elementary School Chil-
dren’s Private Speech” (Merrill-Palmer Q., 1990: 443–463) reported on a study of
children talking to themselves (private speech). It was thought that private speech
would be related to IQ, because IQ is supposed to measure mental maturity, and it
was known that private speech decreases as students progress through the primary
grades. The study included 33 students whose first-grade IQ scores are given here:
082 096 099 102 103 103 106 107 108 108 108 108 109 110 110 111 113
113 113 113 115 115 118 118 119 121 122 122 127 132 136 140 146
Suppose we want an estimate of the average value of IQ for the first graders
served by this school (if we conceptualize a population of all such IQs, we are
trying to estimate the population mean). It can be shown that, with a high degree
of confidence, the population mean IQ is between 109.2 and 118.2; we call this
a confidence interval or interval estimate. The interval suggests that this is an above
average class, because the nationwide IQ average is around 100. ■
from the population are posed and answered. In a statistics problem, characteristics
of a sample are available to the experimenter, and this information enables the
experimenter to draw conclusions about the population. The relationship between
the two disciplines can be summarized by saying that probability reasons from
the population to the sample (deductive reasoning), whereas inferential statistics
reasons from the sample to the population (inductive reasoning). This is illustrated
in Figure 1.2.
Probability
Population Sample
Inferential
statistics
Before we can understand what a particular sample can tell us about the
population, we should first understand the uncertainty associated with taking a
sample from a given population. This is why we study probability before statistics.
As an example of the contrasting focus of probability and inferential statis-
tics, consider drivers’ use of manual lap belts in cars equipped with automatic
shoulder belt systems. (The article “Automobile Seat Belts: Usage Patterns in
Automatic Belt Systems,” Hum. Factors, 1998: 126–135, summarizes usage
data.) In probability, we might assume that 50% of all drivers of cars equipped in
this way in a certain metropolitan area regularly use their lap belt (an assumption
about the population), so we might ask, “How likely is it that a sample of 100 such
drivers will include at least 70 who regularly use their lap belt?” or “How many
of the drivers in a sample of size 100 can we expect to regularly use their lap belt?”
On the other hand, in inferential statistics we have sample information available; for
example, a sample of 100 drivers of such cars revealed that 65 regularly use their lap
belt. We might then ask, “Does this provide substantial evidence for concluding that
more than 50% of all such drivers in this area regularly use their lap belt?” In this
latter scenario, we are attempting to use sample information to answer a question
about the structure of the entire population from which the sample was selected.
Suppose, though, that a study involving a sample of 25 patients is carried out
to investigate the efficacy of a new minimally invasive method for rotator cuff
surgery. The amount of time that each individual subsequently spends in physical
therapy is then determined. The resulting sample of 25 PT times is from a popula-
tion that does not actually exist. Instead it is convenient to think of the population as
consisting of all possible times that might be observed under similar experimental
conditions. Such a population is referred to as a conceptual or hypothetical popula-
tion. There are a number of problem situations in which we fit questions into the
framework of inferential statistics by conceptualizing a population.
Sometimes an investigator must be very cautious about generalizing from
the circumstances under which data has been gathered. For example, a sample of
five engines with a new design may be experimentally manufactured and tested to
investigate efficiency. These five could be viewed as a sample from the conceptual
population of all prototypes that could be manufactured under similar conditions,
but not necessarily as representative of the population of units manufactured once
regular production gets under way. Methods for using sample information to draw
1.1 Populations and Samples 7
Collecting Data
Statistics deals not only with the organization and analysis of data once it has been
collected but also with the development of techniques for collecting the data. If data
is not properly collected, an investigator may not be able to answer the questions
under consideration with a reasonable degree of confidence. One common problem
is that the target population—the one about which conclusions are to be drawn—
may be different from the population actually sampled. For example, advertisers
would like various kinds of information about the television-viewing habits of
potential customers. The most systematic information of this sort comes from
placing monitoring devices in a small number of homes across the United States.
It has been conjectured that placement of such devices in and of itself alters viewing
behavior, so that characteristics of the sample may be different from those of the
target population.
When data collection entails selecting individuals or objects from a list, the
simplest method for ensuring a representative selection is to take a simple random
sample. This is one for which any particular subset of the specified size (e.g., a
sample of size 100) has the same chance of being selected. For example, if the list
consists of 1,000,000 serial numbers, the numbers 1, 2, . . . , up to 1,000,000 could
be placed on identical slips of paper. After placing these slips in a box and
thoroughly mixing, slips could be drawn one by one until the requisite sample
size has been obtained. Alternatively (and much to be preferred), a table of random
numbers or a computer’s random number generator could be employed.
Sometimes alternative sampling methods can be used to make the selection
process easier, to obtain extra information, or to increase the degree of confidence
in conclusions. One such method, stratified sampling, entails separating the
population units into nonoverlapping groups and taking a sample from each one.
For example, a manufacturer of DVD players might want information about
customer satisfaction for units produced during the previous year. If three different
models were manufactured and sold, a separate sample could be selected from each
of the three corresponding strata. This would result in information on all three
models and ensure that no one model was over- or underrepresented in the entire
sample.
Frequently a “convenience” sample is obtained by selecting individuals or
objects without systematic randomization. As an example, a collection of bricks
may be stacked in such a way that it is extremely difficult for those in the center to
be selected. If the bricks on the top and sides of the stack were somehow different
from the others, resulting sample data would not be representative of the popula-
tion. Often an investigator will assume that such a convenience sample approx-
imates a random sample, in which case a statistician’s repertoire of inferential
methods can be used; however, this is a judgment call. Most of the methods
discussed herein are based on a variation of simple random sampling described in
Chapter 6.
8 CHAPTER 1 Overview and Descriptive Statistics
Example 1.3 An article in the New York Times (January 27, 1987) reported that heart attack risk
could be reduced by taking aspirin. This conclusion was based on a designed
experiment involving both a control group of individuals, who took a placebo
having the appearance of aspirin but known to be inert, and a treatment group
who took aspirin according to a specified regimen. Subjects were randomly
assigned to the groups to protect against any biases and so that probability-based
methods could be used to analyze the data. Of the 11,034 individuals in the control
group, 189 subsequently experienced heart attacks, whereas only 104 of the 11,037
in the aspirin group had a heart attack. The incidence rate of heart attacks in the
treatment group was only about half that in the control group. One possible
explanation for this result is chance variation, that aspirin really doesn’t have the
desired effect and the observed difference is just typical variation in the same way
that tossing two identical coins would usually produce different numbers of heads.
However, in this case, inferential methods suggest that chance variation by itself
cannot adequately explain the magnitude of the observed difference. ■
a. Are the scores from the SI group a sample from bathrooms, distance to the nearest school, and
an existing population? If so, what is it? If not, so on. How might she select a sample of single-
what is the relevant conceptual population? family homes that could be used as a basis for this
b. What do you think is the advantage of randomly analysis?
dividing the students into the two groups rather
8. The amount of flow through a solenoid valve in an
than letting each student choose which group to
automobile’s pollution-control system is an impor-
join?
tant characteristic. An experiment was carried out
c. Why didn’t the investigators put all students in
to study how flow rate depended on three factors:
the treatment group? [Note: The article “Supple-
armature length, spring load, and bobbin depth.
mental Instruction: An Effective Component of
Two different levels (low and high) of each factor
Student Affairs Programming” J. Coll. Stud.
were chosen, and a single observation on flow was
Dev., 1997: 577–586 discusses the analysis of
made for each combination of levels.
data from several SI programs.]
a. The resulting data set consisted of how many
6. The California State University (CSU) system con- observations?
sists of 23 campuses, from San Diego State in the b. Does this study involve sampling an existing
south to Humboldt State near the Oregon border. population or a conceptual population?
A CSU administrator wishes to make an inference
9. In a famous experiment carried out in 1882,
about the average distance between the hometowns
Michelson and Newcomb obtained 66 observations
of students and their campuses. Describe and dis-
on the time it took for light to travel between two
cuss several different sampling methods that might
locations in Washington, D.C. A few of the mea-
be employed.
surements (coded in a certain manner) were 31, 23,
7. A certain city divides naturally into ten district 32, 36, 22, 26, 27, and 31.
neighborhoods. A real estate appraiser would like a. Why are these measurements not identical?
to develop an equation to predict appraised value b. Does this study involve sampling an existing
from characteristics such as age, size, number of population or a conceptual population?
Notation
Some general notation will make it easier to apply our methods and formulas to
a wide variety of practical problems. The number of observations in a single
sample, that is, the sample size, will often be denoted by n, so that n ¼ 4 for
the sample of universities {Stanford, Iowa State, Wyoming, Rochester} and also
for the sample of pH measurements {6.3, 6.2, 5.9, 6.5}. If two samples are
simultaneously under consideration, either m and n or n1 and n2 can be used to
denote the numbers of observations. Thus if {3.75, 2.60, 3.20, 3.79} and {2.75,
1.20, 2.45} are grade point averages for students on a mathematics floor and the rest
of the dorm, respectively, then m ¼ 4 and n ¼ 3.
1.2 Pictorial and Tabular Methods in Descriptive Statistics 21
TEA AS A STIMULANT.
“Life without stimulants would be a dreary waste,” remarks some
modern philosopher, which, if true, the moderate use of good tea,
properly prepared and not too strong, will be found less harmful than
the habitual resort to alcoholic liquors. The impression so long
existing that vinous or alcoholic beverages best excite the brain and
cause it to produce more or better work is rapidly being exploded,
healthier and more beneficial stimulants usurping their place. But
while the claims made in favor of the “wine cup” must be admitted, it
cannot for a moment be denied that as excellent literary work has
been accomplished under the influence of tea, in our own times,
particularly when the poet, the essayist, the historian, the statesman
and the journalist no longer work under the baneful influence of
spirituous stimulants. Mantegaza, an Italian physiologist of high
repute, who has given the action of tea and other stimulants careful
study, confirms this claim by placing tea above all other stimulants,
his enthusiasm for it being almost unbounded, crediting it with “the
power of dispelling weariness and lessening the annoyances of life,
classing it as the greatest friend to the man of letters by enabling him
to work without fatigue, and to society as an aid to conversation,
rendering it more easy and pleasant, reviving the drooping
intellectual activity and the best stimulus to exertion, and finally
pronouncing it to be one of the greatest blessings of Providence to
man.”
Tea was Johnson’s only stimulant, he loved it as much as Porson
loved gin, drinking it all times and under all circumstances, in bed
and out, with his friends and alone, more particularly while compiling
his famous dictionary. Boswell drank cup after cup, as if it had been
the “Heliconian spring.” While Hazlitt, like Johnson, was a prodigious
tea-drinker, Shelley’s favorite beverage was water, but at the same
time tea was always grateful to him. Bulwer’s breakfast was
generally composed of dry toast and cold tea, and De Quincy states
that he invariably drank tea from eight o’clock at night until four in the
morning, when engaged in his literary labors, and knew whereof he
spoke when he named tea “the beverage of the intellectual.” Kent
usually had a cup of tea and a pipe of tobacco, on which he worked
eight hours at a stretch, and Motley, the historian tells us that he
“usually rose at seven, and with the aid of a cup of tea only, wrote
until eleven.” And Victor Hugo, as a general rule, used tea freely, but
fortifying it with a little brandy. Turning from literature to politics, we
find that Palmerston resorted to tea during the midnight sessions of
Parliament. Cobden declaring “the more work he had to do the more
tea he drank,” and Gladstone himself confesses to drinking large
quantities of tea between midnight and morning during the prolonged
parliamentary sittings, while Clemenceau, the leader of the French
Radicals, admits himself to be “an intemperate tea-drinker” during
the firey discussions of debate.
In moderation, tea is pre-eminently the beverage of the twilight hour,
when tired humanity seeks repose after a day of wearying labor.
Then the hot infusion with its alluring aroma refreshing and
stimulating, increasing the respiration, elevating the pulse, softening
the temper, producing tranquility in mind and body, and creating a
sense of repose peculiarly grateful to those who have been taxed
and tormented by the rush and routine of business cares and
vexations. What a promoter of sociability, what home comforts does
it not suggest, as, when Cowper, on a winter’s evening, draws a
cheerful picture of the crackling fire, the curtained windows, the
hissing urn and “the cup that cheers?” When, however, tea drinking
ceases to be the amusement of the leisure moment or resorted to in
too large quantities or strong infusions as a means of stimulating the
flagging energies to accomplish the allotted task, whatever it might
be, then distinct danger commences. A breakdown is liable to ensue
in more than one way, as not infrequently the stimulus which tea in
time fails to give is sought in alcoholic or other liquors, and the atonic
dyspepsia which the astringent decoction produced, by overdrawing
induces, helps to drive the victim to seek temporary relief in spirits
chloral or the morphine habit, which is established with extraordinary
rapidity. For it is a truth that as long as a person uses stimulants
simply for their taste he is comparatively safe, but as soon as he
begins to drink them for effect he is running into great danger. This
may be stating the case too forcibly for stimulants, but if this rule was
more closely adhered to we should have fewer cases of educated
people falling into the habit of secret intemperance or morphomania.
That Queen Anne ranked among its votaries is manifest from Pope’s
celebrated couplet:—
Johnson did not make verses in its honor, but he has drawn his own
portrait as “a hardened and shameless tea drinker, who for twenty
years diluted his meals with an infusion of this fascinating plant,
whose kettle had scarcely time to cool, who with tea amused the
evening, with tea solaced the night, and with tea welcomed the
morning.” While Brady, in his well-known metrical version of the
psalms, thus illustrates its advantages:—
That Coleridge, in his younger days, must have liked tea is inferred
from the following stanza:—
WORLD’S PRODUCTION
AND
CONSUMPTION.
The first direct importation of tea into England was in 1669, and
consisted of but “100 pounds of the best tea that could be procured.”
In 1678 this order was increased to 4,713 pounds, which appears to
have “glutted the market;” the following six years the total
importations amounting to only 410 pounds during that entire period.
How little was it possible from these figures to have foreseen that tea
would one day become one of the most important articles of foreign
productions consumed.
Up to 1864 China and Japan were practically the only countries
producing teas for commercial purposes. In that year India first
entered the list as an exporter of tea, being subsequently followed by
Java and Ceylon. In 1864, when India first entered the list of tea-
producing countries, China furnished fully 97 per cent. of the world’s
supply and India only 3, the latter increasing at such a marvelous
rate that it now furnishes 57, China declining to 43 per cent. of the
total.
TABLE 1.
ESTIMATED TEA PRODUCTION OF THE WORLD.
Countries. Production Exportation
(Pounds). (Pounds).
China, 1,000,000,000 300,000,000
Japan, 100,000,000 50,000,000
India, 100,000,000 95,000,000
Ceylon, 50,000,000 40,000,000
Java, 20,000,000 10,000,000
Singapore, 20,000 10,000
Fiji 30,000 20,000
Islands,
South 50,000 20,000
Africa,
—————— —————
Total, 1,270,100,000 495,050,000
From these estimates it will be noted that China ranks first in tea-
producing countries, followed by Japan, India, Ceylon and Java in
the order of their priority; the total product of the other countries
having little or no effect as yet on the world’s supply.
This most important food auxiliary is now in daily use as a beverage
by probably over one-half the population of the entire world, civilized
as well as savage, the following being the principal countries of
consumption:—
TABLE 2.
ESTIMATED TEA CONSUMPTION OF THE WORLD.
TABLE 3.
SUMMARY.
World’s 1,377,600,000
Production,
“ 1,307,130,000
Consumption,
—————
Surplus, 70,470,000
or
Quantity 503,100,000
exported,
Consumption in 432,630,000
non-producing
countries,
—————
Surplus, 70,470,000
In England, particularly, the increase in the consumption of tea in late
years borders on the marvelous, the figures for 1890 reaching
upwards of 195,000,000 pounds, which, at the present rate of
increase, will, in all probability, exceed 200,000,000 in 1892, as in
the quarter of a century between 1865 and 1890 the consumption
rose from 3½ to 5 pounds per capita of the population. But as in the
latter half of that period strong India teas were more freely used,
being increased appreciably by the similar Ceylon product in the
closing years of that time largely displacing the lighter liquored teas
of China, a larger consumption is indicated by the number of gallons
of liquid yielded. This is calculated on the moderate estimate formed
in a report to the Board of Custom to the effect that if one pound of
China leaf produces five gallons of liquor of a certain depth of color
and body, one pound of India tea will yield seven and a half gallons
of a similar beverage. Then by allowing for an apparent arrest of the
advancing consumption when the process of displacement was only
commencing, the increase in the consumption of tea in the British
Islands has not only been steady but rapid; thus, from 17 gallons per
head in 1865 to 24 in 1876, 28 in 1886, reaching 33½ gallons per
head per annum in 1890, the figures of last year almost exactly
doubling that of the first year of the series, so that in consequence of
the introduction of the stronger products of India and Ceylon the
people of Britain have been enabled to double their consumption of
the beverage, although the percentage of increase in the leaf has
been only from 3½ to 5 pounds during the same period. Ceylon tea,
which a decade ago was only beginning to intrude itself as a new
and suspiciously regarded competitor in the English market with
products so well known and established as the teas of China and
India, has recently made such rapid progress that its position in the
British market in 1890, rated by home consumption, occupying third
place on the list. India teas 52 per cent., China 30 per cent., Ceylon
18 per cent.
TABLE 4.
TABLE 5.
The earliest official record of the importation of Tea into the United
States is in 1790, the order of increase for its importation, value and
consumption in the country by decades since that year being as
follows:—
Year. Imports, Value. Consumption Average
Pounds. per capita. Import
Price.
1790, 3,022,983 ...... ... ...
1800, 5,119,341 ...... ... ...
1810, 7,708,208 ...... ... ...
1820, ...... ...... ... ...
1830, 8,609,415 $2,425,018 0.53 22.3
1840, 20,006,595 5,427,010 0.99 24.1
1850, 29,872,654 4,719,232 0.87 27.9
1860, 31,696,657 8,915,327 0.84 26.3
1870, 47,408,481 13,863,273 1.10 29.4
1880, 72,162,936 19,782,631 1.39 27.2
1890, 84,627,870 13,360,685 1.40 20.0
The first duty levied on tea by the United States was in 1789, when a
tax of 15 cents was imposed on all Black teas, 22 cents on Imperial
and Gunpowder, and 55 cents on Young Hyson. But in order to
stimulate American shipping these duties were reduced to 8, 13 and
26 cents respectively, the following year, when imported from Europe
in American vessels, and to 6, 10 and 20 cents when imported direct
from China in the same manner. In 1794, however, the rates were
increased 75 per cent. on direct importations, and 100 per cent. on
all teas shipped from Europe, but again reduced to 12,18 and 32
cents in 1796, the latter rates being doubled during the War of 1812.
In 1828 this tax was again reduced, being entirely removed in 1830,
except when imported in foreign bottoms, when a duty of 10 cents
per pound was collected. The latter rate continued in force up to the
outbreak of the Rebellion in 1861, when a uniform duty of 15 cents
per pound was placed on all teas, which was eventually increased to
20 cents and finally to 25 cents per pound. In January, 1871, this
duty was reduced to 15 cents, being entirely removed in July, 1872,
since which year tea has been uninterruptedly on the free list in the
United States.
TABLE 6.
Showing net imports, value and per capita consumption of tea in the
United States, from 1885 to 1891, inclusive:—
Year. Net Imports, Value. Per
Pounds. Capita,
Pounds.
1880, 69,894,760 $18,983,368 1.39
1881, 79,130,849 20,225,418 1.54
1882, 77,191,060 18,975,045 1.47
1883, 69,597,945 16,278,894 1.30
1884, 60,061,944 12,313,200 1.09
1885, 65,374,365 13,135,782 1.18
1886, 78,873,151 15,485,265 1.37
1887, 87,481,186 16,365,633 1.49
1888, 83,944,547 13,154,171 1.40
1889, 79,192,253 12,561,812 1.28
1890, 83,494,956 12,219,633 1.33
1891, 82,395,924 13,639,785 1.32
TABLE 7.
TABLE 8.