CHATGPT翻譯，因?yàn)閳D片掃描，可能部分漏譯，不過(guò)應(yīng)該不影響大致意思

## 來(lái)自你的消息:

NBER WORKING PAPER SERIES

DETERMINANTS OF SLAVE AND CREW

MORTALITY IN THE ATLANTIC SLAVE TRADE

Richard H. Steckel

Richard A. Jensen

Working Paper No. 15140

NATIONAL BUREAU OF ECONOMIC RESEARCH

1050 Massachusetts Avenue

Cambridge, MA 02138

January 1985

We have benefitted from the comments or help of Raymond Cohn,

Philip Curtin, David Eltis, Stanley Engerman, Roderick Floud,

Donald Haurin, Kenneth Kiple, Robert Margo, Jerry Thursby, and

seminar participants at Brigham Young University. Judy Collingwood

and Cheryl Zinker provided valuable research assistance The

research reported here is part of the NBER's research program in

Development of the American Economy. Any opinions expressed are

those of the authors and not those of the National Bureau of

Economic Research.

NBER Working Paper #1540

January 1985

Determinants of Slave and Crew

Mortality in the Atlantic Slave Trade

ABSTRACT

This paper measures and. analyzes death rates that prevailed in the

Atlantic slave trade during the late 1700s. Crew members died primarily

from fevers (probably malaria) and slaves died primarily from gastrointestinal

diseases. Annual death rates in this activity were 230 per thousand

among the crew and 83 per thousand among slaves. The lack of immunities

to the African disease environment contributed to the high death rates

among the crew. The spread of dysentery among slaves during the voyage

was probably exacerbated by congestion and. poor nutrition. Death rates

differed systematically by region of origin in Africa and. season of the

year. There was little interaction between the incidence of slave and.

crew deaths. The high death rates make the slave trade a demographic

laboratory for study of health and mortality ad an economic laboratory

for study of markets for free labor.

Richard H. Steckel

Economics Department

Ohio State University

Columbtis, Ohio 1132l0

(6lI) 422-50Q8

and

Richard A. Jensen

Economics Department

Ohio State University

Columbus, Ohio 132lO

(61)-i.) Li.229339

## 來(lái)自ChatAI的消息:

工作文件系列NBER

大西洋奴隸貿(mào)易中奴隸和船員死亡率的決定因素

Richard H. Steckel

Richard A. Jensen

工作文件編號(hào)15140

美國(guó)國(guó)家經(jīng)濟(jì)研究局

馬薩諸塞州劍橋市馬薩諸塞大道1050號(hào)

1985年1月

我們受益于Raymond Cohn、Philip Curtin、David Eltis、Stanley Engerman、Roderick Floud、Donald Haurin、Kenneth Kiple、Robert Margo、Jerry Thursby以及布里格漢姆青年大學(xué)的研討會(huì)與研究人員的評(píng)論和幫助。Judy Collingwood和Cheryl Zinker提供了有價(jià)值的研究幫助。此處報(bào)告的研究是NBER發(fā)展美國(guó)經(jīng)濟(jì)研究計(jì)劃的一部分。任何觀點(diǎn)均屬作者個(gè)人觀點(diǎn)，而非美國(guó)國(guó)家經(jīng)濟(jì)研究局的觀點(diǎn)。

NBER工作文件編號(hào)1540

1985年1月

大西洋奴隸貿(mào)易中奴隸和船員死亡率的決定因素

摘要

本文測(cè)量和分析了18世紀(jì)后期大西洋奴隸貿(mào)易中的死亡率。船員主要死于熱?。赡苁钳懠玻`主要死于胃腸道疾病。在這項(xiàng)活動(dòng)中，每年船員的死亡率為千分之230，奴隸的死亡率為千分之83。在船員中，由于缺乏對(duì)非洲疾病環(huán)境的免疫力，死亡率較高。奴隸在航行期間蔓延的痢疾可能受到了擁擠和營(yíng)養(yǎng)不良的加重影響。死亡率在非洲起源地區(qū)和季節(jié)間有明顯差異。奴隸和船員死亡率之間的交互作用很少。高死亡率使得奴隸貿(mào)易成為一個(gè)研究健康和死亡率的人口學(xué)實(shí)驗(yàn)室，也是研究自由勞動(dòng)市場(chǎng)的經(jīng)濟(jì)實(shí)驗(yàn)室。

Richard H. Steckel

俄亥俄州立大學(xué)經(jīng)濟(jì)系

哥倫布, 俄亥俄州11321

(6lI) 422-50Q8

和

Richard A. Jensen

俄亥俄州立大學(xué)經(jīng)濟(jì)系

哥倫布, 俄亥俄州13210

(61)-i.) Li.229339

## 來(lái)自你的消息:

I NTRODUCTI ON

One of the early political expressions of opposition to slavery occurred

in the late 1700s when Parliament considered proposals to ameliorate condi tions in the slave trade. The treatment and mortality of slaves emerged as

central questions in deliberations and the debate led to collection and study

of evidence on conditions in Africa, the middle passage, and the New World.

Legislation in 1788 took the form of limits on the slave—carrying capacity of

vessels; the requirement that slave vessels carry a surgeon who cared for

slaves and who monitored conditions through a journal that noted deaths and

causes of death: and a system of bonuses to ship captains and surgeons.

Controversy over the health and mortality of persons involved in the

slave trade has persisted from the era of the campaign against slavery to the

present. The debate continues in part because the rhetoric, the charges and

counter-charges, and the tactics of the supporters and foes of the institution

often obscured the underlying realities. More fundamental to modern research,

however, are the facts that substantially limited information on these ques tions survives to the present and the levels and determinants of health and

mortality are central to larger questions such as the economic costs of the

slave trade to Western Europe, the profitability of slavery and the slave

trade, and the impact of legislation on the slave trade.

Studies of mortality in the Atlantic slave trade have relied extensively

on data from company records, newspapers, and government sources such as port

records, papers required by legislation monitoring or regulating the trade,

and the results of special inquiries.' The measure of mortality commonly con structed from these sources is the ratio of slave deaths to the number of

slaves embarked, although some authors have used the ratio divided by voyage

2

length multiplied by 1000.2 The central questions of research have included

mortality differences by region of departure from Africa, the effect of crowding on mortality, voyage length and the probability of death, the secular

trend in mortality rates, and the importance of vessels that had an unusually

high number of deaths.

## 來(lái)自ChatAI的消息:

引言

在18世紀(jì)末期，議會(huì)考慮了改善奴隸貿(mào)易條件的提案，這是對(duì)奴隸制度反對(duì)的早期政治表達(dá)之一。在討論中，奴隸的待遇和死亡率成為核心問(wèn)題，這場(chǎng)辯論促使人們收集和研究了有關(guān)非洲、中途海程和新世界的情況的證據(jù)。1788年的立法限制了船只承載奴隸的能力，要求奴隸船只攜帶一名醫(yī)生負(fù)責(zé)照顧奴隸，并通過(guò)一份記錄死亡和死亡原因的日志來(lái)監(jiān)測(cè)情況，還設(shè)立了一套對(duì)船長(zhǎng)和醫(yī)生的獎(jiǎng)勵(lì)制度。

從反對(duì)奴隸制度的運(yùn)動(dòng)時(shí)期到現(xiàn)在，關(guān)于奴隸貿(mào)易中涉及的人員健康和死亡率的爭(zhēng)論一直存在。這場(chǎng)辯論持續(xù)存在的原因部分是因?yàn)橹С终吆头磳?duì)者之間的修辭、指責(zé)和反指責(zé)以及策略經(jīng)常掩蓋了潛在的現(xiàn)實(shí)。然而，對(duì)于現(xiàn)代研究來(lái)說(shuō)，更重要的是，迄今為止，這些問(wèn)題上存在著極為有限的信息，并且健康和死亡的水平和決定因素對(duì)于諸如西歐奴隸貿(mào)易的經(jīng)濟(jì)成本、奴隸制度和奴隸貿(mào)易的盈利能力以及立法對(duì)奴隸貿(mào)易的影響等更大的問(wèn)題具有重要意義。

對(duì)大西洋奴隸貿(mào)易死亡率的研究在很大程度上依賴于公司記錄、報(bào)紙和政府來(lái)源（如港口記錄、監(jiān)督或規(guī)范貿(mào)易所需的文件，以及特別調(diào)查的結(jié)果）的數(shù)據(jù)3。通常從這些來(lái)源構(gòu)建的死亡率衡量標(biāo)準(zhǔn)是奴隸死亡人數(shù)與上船奴隸數(shù)的比率，盡管一些作者使用了這個(gè)比率除以航行時(shí)間乘以1000的結(jié)果2。研究的核心問(wèn)題包括根據(jù)非洲離港地區(qū)的死亡率差異、擁擠對(duì)死亡率的影響、航程長(zhǎng)度和死亡的概率、死亡率的長(zhǎng)期趨勢(shì)以及具有異常高死亡人數(shù)的船只的重要性。

## 來(lái)自你的消息:

This paper extends work in the area by analyzing 92 surgeons' logs

required by Dolben's Act of 178R. The ships in the sample originated from the

major supply regions in Africa and span the years 1792 to 1796. The excep tional value of the logs for measuring levels and studying determinants of

mortality stems from the combination of information on dates of death, causes

of death, and records for slaves as well as crew. Because dates of death and

the number of persons at risk are available, true death rates can be calcu lated. The death rates are relevant for comparisons with the mortality expe riences of other populations. The chronological record also permits study of

death rates by day during loading and during the voyage as opposed to study of

the journey as a whole that is common in previous work. Although the diagnos tic capabilities of ship surgeons were primitive by modern standards, the

symptoms of several diseases or disease categories common in the slave trade

were sufficiently distinctive to be useful. This combined with the systematic

enumeration of causes enables a statistical examination of causes of mortality

that is more detailed then previously undertaken. The mortality records of

the crew furnish a backdrop against which slave mortality can be compared and

cont rasted.

The analysis begins with death rates by cause of death, The results of

this inquiry suggest a plan of action for study of major causes of death

during loading and during the voyage. The next portion compares the findings

of this paper with previous work, and the last section considers the general ity of the results. The analysis generally accepts the data at face value;

3

the hazards of doing this and features of the data are discussed in the appendix.

DEATH RATES BY CAUSE OF DEATH

## 來(lái)自ChatAI的消息:

本文通過(guò)分析178R年Dolben法案要求的92位外科醫(yī)生的日志擴(kuò)展了該領(lǐng)域的工作。樣本中的船只來(lái)自非洲主要供應(yīng)地區(qū)，時(shí)間跨度為1792年至1796年。這些日志通過(guò)提供死亡日期、死因和奴隸以及船員的記錄的信息的組合，為測(cè)量水平和研究死亡率的決定因素提供了異常的價(jià)值。由于有死亡日期和風(fēng)險(xiǎn)人數(shù)的數(shù)據(jù)，可以計(jì)算出真實(shí)的死亡率。死亡率與其他人群的死亡經(jīng)歷進(jìn)行比較是相關(guān)的。時(shí)間記錄還允許研究裝載期間和航行期間的每天死亡率，而不是像以前的研究中那樣研究整個(gè)航程。雖然與現(xiàn)代標(biāo)準(zhǔn)相比，船醫(yī)的診斷能力是原始的，但在奴隸貿(mào)易中常見的幾種疾病或疾病類別的癥狀足夠獨(dú)特以被使用。這與對(duì)死因的系統(tǒng)計(jì)數(shù)結(jié)合起來(lái)，使得對(duì)死亡原因的統(tǒng)計(jì)研究更加詳細(xì)。船員的死亡記錄為對(duì)比和對(duì)照奴隸死亡提供了背景。

分析從死因的死亡率開始。該研究的結(jié)果為研究裝載期間和航行期間的主要死因提供了行動(dòng)計(jì)劃。接下來(lái)的部分將本文的研究結(jié)果與以前的研究進(jìn)行比較，最后一節(jié)考慮了結(jié)果的普遍性。這項(xiàng)分析通常接受數(shù)據(jù)的表面價(jià)值；對(duì)此存在的風(fēng)險(xiǎn)以及數(shù)據(jù)的特點(diǎn)在附錄中進(jìn)行了討論。

按死因分組的死亡率

## 來(lái)自你的消息:

Construction

The surgeon maintained a chronological journal of loadings and unload—

ings, usually in categories of men, women, boys, and girls, although sometimes

only males and females or men and women were enumerated. Slaves were frequently held on board until departure for the West Indies. Slaves unloaded

include those sold to other vessels and pawns (captives held as security

before transactions were completed) and sick slaves returned to shore.3 Slave

sales or transfers to other ships were extensive on a few vessels. A computer

program written for these data tabulates the number at risk each day from

first loading to the final destination in the West Indies.

Muster rolls establish the crew size at the time of departure from

England for 45 out of 92 vessels in the sample. Crew size for the remaining

vessels was estimated from a regression of crew size on tons.4 The available

muster rolls show that relatively few crew members left the ship or were taken

on board before the ship reached the West Indies. As an approximation it was

assumed that crew size changed only through deaths. Thus the estimated number

of crew at risk may be inaccurate for particular vessels.

Death rates were calculate from the chronological record of deaths and

data on the average number of person-years at risk during a particular time

period.5 The tables express results in annual rates per 1000 to facilitate

comparisons with other populations.

## 來(lái)自ChatAI的消息:

施工

該外科醫(yī)生保持了對(duì)裝載和卸載過(guò)程的時(shí)間順序記錄，通常按照男性、女性、男孩和女孩的類別進(jìn)行分類，盡管有時(shí)只列舉男性和女性或男人和女人。奴隸通常被留在船上，直到前往西印度群島。卸下的奴隸包括出售給其他船只和抵押品（在交易完成之前作為抵押品拘留的俘虜），以及返回岸上的患病奴隸。一些船只進(jìn)行了大量的奴隸銷售或轉(zhuǎn)移。為了這些數(shù)據(jù)編寫了一個(gè)計(jì)算機(jī)程序，以確定從首次裝載到西印度群島的最終目的地之間每天處于風(fēng)險(xiǎn)狀態(tài)的人數(shù)。

在樣本中，通過(guò)船舶登記簿可以確定92艘船中有45艘在離開英國(guó)時(shí)的船員規(guī)模。其余船只的船員規(guī)模是根據(jù)噸位和船員規(guī)模的回歸估計(jì)出來(lái)的。可用的船舶登記簿顯示，在船只抵達(dá)西印度群島之前，只有很少數(shù)量的船員離開船只或上船。作為近似，假設(shè)船員規(guī)模僅通過(guò)死亡而改變。因此，對(duì)于特定船只，估計(jì)的處于風(fēng)險(xiǎn)狀態(tài)的船員人數(shù)可能不準(zhǔn)確。

死亡率是根據(jù)死亡的時(shí)間記錄和特定時(shí)間段內(nèi)處于風(fēng)險(xiǎn)狀態(tài)的人數(shù)的平均數(shù)計(jì)算出來(lái)的。表格以每1000人年的年度比率表示結(jié)果，以便與其他人群進(jìn)行比較。

## 來(lái)自你的消息:

Medical Knowledge

The information available on casues of death must be approached cau tiously given the rudimentary medical knowledge of the late 1700s.6 The

4

difficulties stem from the lack of a germ theory of disease to guide inquiry

and from the poor state of medical instruments and procedures necessary for

precise diagnosis. In making a diagnosis that would guide treatment the surgeons drew upon visible symptoms of the patient. Unfortunately not all important symptoms of a particular disease were visible, the symptoms may have

changed over time as the disease ran its course, and some diseases with distinctly different causes have symptoms in common. The problems of identification were compounded if the patient had more than one disease.

Medical diagnosis of cause or causes of death is important for investigation of socioeconomic and epidemiological factors in mortality. Knowledge of

the disease or diseases involved conveys information about the net influence

of the prevalence or pathogens, mechanisms of transmission, and the susceptibility of individuals in the population. Unfortunately the surgeons recorded

few visible detals and their observations were often grouped under broad headings such as "fevers," "dysentery," and "diarrhea." The fevers no doubt

included malaria and probably yellow fever and the gastrointestinal diseases

no doubt included shigellosis (bacillary dysentery)and possibly amoebic

dysentery.7 However, fever sometimes acconpanies gastrointestinal diseases

and vomiting and diarrhea may acconpany malaria and yellow fever.8 Thus it is

not safe to conclude that "fevers" were confined entirely to diseases spread

by mosquitoes or that gastrointestinal diseases such as "diarrhea" were confined entirely to diseases spread by ingestion of contaminated matter.

## 來(lái)自ChatAI的消息:

醫(yī)學(xué)知識(shí)

考慮到18世紀(jì)末的基礎(chǔ)醫(yī)學(xué)知識(shí)，對(duì)死因的信息必須謹(jǐn)慎處理。困難源于缺乏引導(dǎo)調(diào)查的病原體理論以及醫(yī)療儀器和診斷程序的不完善。在進(jìn)行診斷以指導(dǎo)治療時(shí)，外科醫(yī)生主要依靠患者的可見癥狀。然而，特定疾病的一些重要癥狀可能不可見，隨著疾病進(jìn)展，癥狀可能會(huì)發(fā)生變化，而一些不同原因引起的疾病可能有共同的癥狀。如果患者有多種疾病，辨識(shí)問(wèn)題就更加復(fù)雜。

了解死因或死因的醫(yī)學(xué)診斷對(duì)于研究社會(huì)經(jīng)濟(jì)和流行病學(xué)因素對(duì)死亡率的影響至關(guān)重要。有關(guān)所涉及疾病的知識(shí)可以傳達(dá)有關(guān)流行病原的凈影響、傳播機(jī)制以及人群中個(gè)體的易感性的信息。然而，外科醫(yī)生只記錄了少量可見細(xì)節(jié)，他們的觀察經(jīng)常被歸為廣泛的范疇，如“發(fā)熱”、“痢疾”和“腹瀉”。毫無(wú)疑問(wèn)，“發(fā)熱”可能包括瘧疾，很可能還有黃熱病，“胃腸道疾病”很可能包括志賀氏菌痢疾和可能的阿米巴痢疾。然而，發(fā)熱有時(shí)會(huì)伴隨胃腸道疾病，嘔吐和腹瀉可能會(huì)伴隨瘧疾和黃熱病。因此，出于安全考慮，不能得出“發(fā)熱”完全限于通過(guò)蚊蟲傳播的疾病或“腹瀉”完全限于通過(guò)攝入污染物造成的疾病的結(jié)論。

## 來(lái)自你的消息:

Patterns

Tables 1—4 show the death rates calculated for slaves and crew during

loading and the voyage. Comparisons involving the overall rates given in the

last row of the third column of each table demonstrate that loading and the

5

voyage were extraordinarily hazardous to life. The rates are exceptional when

placed in the proper perspective of the probable age range of the slaves and

crew. Death rates are ordinarily highest during infancy, then decline during

childhood and reach a minimum just before or during adolescence, The rates

usually rise gradually for many years beyond the minimum and then accelerate

upwards in the 60s and beyond. Under ordinary circumstances most deaths were

confined to the very young and the old. Typical eighteenth—century Western

European populations in the age range 10—34, for example, probably had average

annual death rates not exceeding roughly 1 percent.9 Furthermore, the upper

limit of recorded experience for this age group when not living under severe

circumstances such as war or famine is less than 2 percent.10 The slaves and

crew faced death rates several times higher than their contemporaries engaged

in ordinary activities. The slave trade therefore provides a laboratory for

study of health and mortality under extreme circumstances.

The slave trade was relatively hazardous for the crew, particularly

during loading. Compared to slaves the death rates of the crew were more than

5 times higher during loading and nearly twice as high during the voyage. The

absolute levels of crew death rates were on the low to middle range of magnitudes reported by others for European populations residing in western Africa

during the eighteenth and nineteenth centuries.1' The surgeons logs support

the view that western Africa was the "white man's grave." The extraordinary

death rates for the crew raise interesting questions about the operation of

markets for free labor that engaged in the slave trade, Comparisons of the

slave trade with other types of voyages would add a dimension of perspective

to the slave trade and may provide insights into causes of mortality.

## 來(lái)自ChatAI的消息:

圖表1至4顯示了裝載和航行期間計(jì)算出的奴隸和船員的死亡率。通過(guò)比較每個(gè)表的第三列最后一行給出的總體死亡率，可以看出裝載和航行對(duì)生命極為危險(xiǎn)?？紤]到奴隸和船員可能的年齡范圍，這些死亡率是異常的。死亡率通常在嬰兒期最高，然后在童年期下降，在青春期之前或期間達(dá)到最低點(diǎn)。在最低點(diǎn)之后，死亡率通常在接下來(lái)的許多年逐漸上升，然后在60多歲及以上急劇加速。在普通情況下，大多數(shù)死亡都局限在幼兒和老年人中。例如，典型的十八世紀(jì)西歐10-34歲年齡范圍的人口，平均每年的死亡率可能不超過(guò)1%。此外，當(dāng)這個(gè)年齡組的人沒(méi)有生活在戰(zhàn)爭(zhēng)或饑荒等嚴(yán)重環(huán)境下時(shí)，記錄經(jīng)驗(yàn)的上限不到2%。奴隸和船員面臨的死亡率是從事普通活動(dòng)的同時(shí)代人數(shù)倍之高。因此，奴隸貿(mào)易為研究極端環(huán)境下的健康和死亡提供了一個(gè)實(shí)驗(yàn)室。

相對(duì)而言，奴隸貿(mào)易對(duì)船員而言相對(duì)危險(xiǎn)，特別是在裝載期間。與奴隸相比，在裝載期間船員的死亡率要高出5倍以上，在航行期間幾乎是其兩倍。船員死亡率的絕對(duì)水平處于報(bào)告的18世紀(jì)和19世紀(jì)西非居民的水平中等偏低范圍內(nèi)。外科醫(yī)生的記錄支持西非是“白人的墳?zāi)埂钡挠^點(diǎn)。船員的異常死亡率對(duì)從事奴隸貿(mào)易的自由勞動(dòng)力市場(chǎng)的運(yùn)作提出了有趣的問(wèn)題。將奴隸貿(mào)易與其他類型的航行進(jìn)行比較，可以從不同角度觀察奴隸貿(mào)易，并可以提供有關(guān)死亡原因的見解。

## 來(lái)自你的消息:

The chances of death changed considerably during the course of loading

and the voyage. mong slaves the safest period occurred about 3 to 6 months

6

before departure; the death rate at this time was 22.8 per thousand, or in the

neighborhood of twice the rate expected for settled populations not facing

severe circumstances. From this low the rate nearly tripled to 64.5 per thou sand during the four weeks before departure, continued to rise during the

early part of the voyage, and reached a peak of 145.9 per thousand during days

29—42 of the voyage. Slave death rates followed an inverted—U shape during

the voyage and differed by a factor of roughly 2 to 1. Compared to slaves,

crew death rates were less volatile during loading and reached a plateau of

nearly 350 per thousand in weeks 5-12. Over three-quarters of all crew deaths

during the voyage occurred within the first four weeks.

During the operations of loading and the voyage over 60 percent of the

crew deaths were from fevers and over 40 percent of the slave deaths were frOm

gastrointestinal diseases. The share of crew deaths from fevers was slightly

higher during loading (68%) compared to the voyage (54%). Among slaves thQ

shares of deaths from gastrointestinal diseases were approximately constant

during loading (38%) and the voyage (41%). Gastrointestinal diseases claimed

16 percent of crew deaths and fevers amounted to 8 percent of slave losses.

The minor causes of slave deaths included respiratory diseases (5%), sui cide (3%), scurvy (2%), insurrection (2%), and accidents. Among crew deaths 8

percent involved accidents (primarily drowning), 2 percent scurvy, 1 percent

respiratory, and 1 percent insurrection. The fotheru category includes well—

defined but relatively infrequent ailments such as yaws and dropsy, several

poorly—described diseases (e.g. sudden death," "sulks," "fits," "delirium,"

and "relaxed"), and many illegible entries. Most of the slave deaths from

respiratory diseases (89%) and scurvy (88%) occurred on the voyage, particu larly near the middle and the end of the trip, which is consistent with claims

7

and evidence that the voyage was debilitating. The low death rates from

scurvy suggest that measures sometimes taken as early as the late eighteenth

century to include vitamin C in the diet through foods such as lime juice may

have been used.12 Information on exact dates of death available in the logs

indicates that slave suicides were concentrated during or shortly after

slaves were first loaded and at the time the ship left Africa.

## 來(lái)自ChatAI的消息:

在裝載和航行過(guò)程中，死亡機(jī)率發(fā)生了顯著變化。在奴隸群體中，最安全的時(shí)期是在出發(fā)前的3到6個(gè)月；此時(shí)的死亡率為每千人中22.8人，大約是非受嚴(yán)峻條件影響的定居人口的兩倍。從這個(gè)低點(diǎn)開始，死亡率在出發(fā)前的四周內(nèi)幾乎增加了兩倍，繼續(xù)在航行初期上升，到達(dá)航行的第29至42天期間達(dá)到每千人中145.9人的峰值。奴隸的死亡率在航行過(guò)程中呈倒U型變化，差異大致為2比1。與奴隸相比，船員的死亡率在裝載期間波動(dòng)較小，并在第5至12周達(dá)到每千人近350人的穩(wěn)定水平。航行期間，四分之三以上的船員死亡事件發(fā)生在頭四周內(nèi)。

在裝載和航行過(guò)程中，超過(guò)60%的船員死于發(fā)熱病，超過(guò)40%的奴隸死于胃腸疾病。與航行相比，裝載期間船員死于發(fā)熱病的比例略高（68%對(duì)54%）。奴隸死于胃腸疾病的比例在裝載（38%）和航行（41%）期間幾乎保持不變。胃腸疾病占船員死亡的16%，而發(fā)熱病占奴隸死亡的8%。

奴隸死亡的其他原因包括呼吸道疾病（5%）、自殺（3%）、壞血病（2%）、起義（2%）和事故。船員死亡中8%是事故（主要是溺水）、2%是壞血病，1%是呼吸道疾病，1%是起義。其他原因包括定義明確但相對(duì)較少見的疾病，例如雞麻風(fēng)和水腫，以及許多無(wú)法辨認(rèn)的記錄。大多數(shù)呼吸道疾?。?9%）和壞血?。?8%）導(dǎo)致的奴隸死亡發(fā)生在航行期間，特別是在航行中期和結(jié)束時(shí)，這與航行具有消耗性的特點(diǎn)相符。由于壞血病的死亡率較低，這表明可能在18世紀(jì)末期就開始采取措施，如在飲食中添加維生素C（例如酸橙汁）。記錄中關(guān)于死亡確切日期的信息表明，奴隸的自殺行為主要集中在奴隸首次被裝載和船只離開非洲的時(shí)期。

## 來(lái)自你的消息:

It is important to note that smallpox and measles were virtually absent

as causes of death in these data. Inoculation against smallpox was practiced

in England as early as the mid 1700s, and the availability of the technology

suggests that it may have been used on slaves.13 It is also possible that

native Africans practiced inoculation.14 Because the logs pertain to only to

a few years (1792-1796), it is also possible that epidemic conditions for this

disease were temporarily favorable.

Implications

Because the underlying causes and methods of transmission of many

diseases are quite different, the investigation of determinants of mortality

will be undertaken by disease category. The data in Tables 1-4make it clear

that fevers and gastrointestinal diseases should be the focus of attention.

Other causes of death are relevant to the entire picture, but their frequency

of occurrence——even for the most important minor causes such as accidents

among the crew and respiratory diseases among slaves-—is so low that syste—

matic study is not feasible with these data.

The configurations of death rates by day of loading, day before depar ture, and day of voyage suggest that determinants of mortality substantially

involved a time—dependent process. The importance of time is easily seen for

gastrointestinal diseases involving slaves; death rates more than doubled from

8

the beginning to the end of loading and continued to climb, reaching a peak

during the third to the fifth week of the voyage. The pattern of death rates

resembles the beginning, height, and end of an epidemic.

The concepts of agent, host, environment, and incubation period as

employed by epidemiologists are useful for understanding mortality from dysentery.'5 The spread of an infectious disease depends upon the probability of

contact between an infectious agent and individuals, and the susceptibility of

individuals. The amount of infectious material in the environment is a function of the number of infected individuals or hosts of the agent, the duration

and extent to which infectious material is expelled by hosts3 the rate of survival of the agent in the environment, the route of entry into the host, and

the existence of alternative reservoirs or hosts of the agent. The availability of hosts varies with the mobility and interpersonal contact within the

population group, and the immunityor other means of resistence to the agent

by individuals. The incubation period is the interval of time between contact

with an infectious agent and the onset of illness. Each disease has a characteristic incubation period, which may vary among individuals. The discussion

so far has assumed a situation with case—to-case transmission of disease, but

the concepts can easily be extended to include the spread of infection from a

central source such as contaminated food or liquid.

## 來(lái)自ChatAI的消息:

需要注意的是，在這些數(shù)據(jù)中，天花和麻疹幾乎沒(méi)有作為死因出現(xiàn)。英國(guó)在18世紀(jì)中葉就開始實(shí)行天花接種，技術(shù)的可用性表明它可能被用于奴隸身上。同時(shí)，土著非洲人也有可能實(shí)行接種。由于這些日志只涉及到幾年（1792年至1796年），因此這種疾病的流行狀況在這段時(shí)間內(nèi)可能是有利的。

影響

由于許多疾病的根本原因和傳播方法相當(dāng)不同，對(duì)死亡率決定因素的研究將按疾病類別進(jìn)行。從表格1-4可以看出，發(fā)熱和胃腸道疾病應(yīng)該是關(guān)注的焦點(diǎn)。其他死因?qū)φ麄€(gè)情況也有影響，但是它們的發(fā)生頻率，即使對(duì)于最重要的次要原因，如機(jī)組事故和奴隸呼吸道疾病，也是如此低，以至于這些數(shù)據(jù)不適合進(jìn)行系統(tǒng)研究。

裝載日、出發(fā)前一天和航程中的死亡率配置表明死亡率的決定因素在很大程度上涉及時(shí)間相關(guān)的過(guò)程。從奴隸在裝載開始到結(jié)束期間，胃腸道疾病的死亡率增加了一倍以上，并繼續(xù)上升，在航行的第三到第五周達(dá)到了峰值。死亡率的模式類似于一個(gè)流行病的開始、高峰和結(jié)束。

流行病學(xué)家使用的代理、宿主、環(huán)境和潛伏期等概念對(duì)于理解痢疾死亡率很有用。傳染病的傳播取決于傳染劑與個(gè)體之間的接觸概率和個(gè)體的易感性。環(huán)境中傳染物質(zhì)的數(shù)量取決于感染個(gè)體或傳染劑的寄主及其排泄傳染物質(zhì)的持續(xù)時(shí)間和范圍、傳染劑在環(huán)境中的存活率、進(jìn)入宿主的途徑以及傳染劑的替代儲(chǔ)存庫(kù)或宿主的存在。寄主的可用性因人群內(nèi)部的移動(dòng)性和人際接觸而有所不同，個(gè)體的免疫或其他抵抗傳染劑的手段也如此。潛伏期是接觸傳染劑和發(fā)病之間的時(shí)間間隔。每種疾病都有特定的潛伏期，可能在個(gè)體之間有所不同。到目前為止的討論假定了一種情況，即病例間的傳播，但是這些概念很容易擴(kuò)展到包括從一個(gè)中心源（如被污染的食物或液體）傳播感染的情況。

## 來(lái)自你的消息:

The epidemiology of malaria and yellow fever involve intermediate hosts.

The parasites responsible for these infections spend part of their life cycle

inhabiting mosquitoes and so the path of transmission is from man (or other

host) in his infectious stage, to mosquito, and subsequently from mosquito to

man. These diseases therefore involve populations of mosquitoes and humans

(or other hosts), each with its own set of susceptible and infective hosts.

9

African natives were ordinarily infected with malaria as children, and those

who survived had a limited immunity to further symptoms, but could act as

hosts.'6 Thus malaria was hyperendemic in coastal areas of western Africa,

and the spread of the disease among European newcomers resembled a stochastic

version of contamination from a central source. Unlike malaria, yellow fever

kills the victim within 5 to 7 days or follows by rapid recàvery and life—long

immunity that prevents the individual from acting again as a host. The yellow

fever parasite occasionally died out in parts of .Africa, particularly in iso

lated areas, but the chances of an epidemic increased as the nonimmune popula tion grew and as contacts with the outside carried the disease. Europeans may

have contributed to periodic yellow fever epidemics as noninimune hosts.

The spread of infectious disease is a complex process that can be summa rized using mathematical models.'7 In a simple deterministic model of an epi demic, for example, disease spreads by contact between infectives and suscept ibles, there is no removal from circulation by death, recovery, or isolation,

and infections remain contagious throughout the epidemic. The epidemic curve

shows the rate at which new cases accrue over time under the conditions or

parameters specified by the model. The time pattern of deaths is derivable

from the epidemic curve by incorporating magnitudes for the share of those

infected who fail to survive and the delay from the onset of symptoms to

death. More complex models can involve infection and removal, intermediate

hosts, geographical spread, stochastic phenomena, latent and infectious peri ods, and lost immunity. The a priori formulation of a model appropriate for

slaves or crew would be difficult in part because many conditions relevant to

the model are unknown. Indeed, the relevant conditions are an important

object of investigation. Nevertheless, an epidemic model is a useful frame work for thought. Some of the parameters in such a model were given and

10

others were under the control or influence of slave traders, ship captains,

and surgeons. The extent and nature of control are topics for the next section of the paper.

## 來(lái)自ChatAI的消息:

瘧疾和黃熱病的流行病學(xué)涉及中間宿主。引起這些感染的寄生蟲在其生命周期的一部分中寄生在蚊子身上，因此傳播路徑是從人類（或其他宿主）的傳染階段到蚊子，然后再?gòu)奈米觽鹘o人類。因此，這些疾病涉及蚊子和人類（或其他宿主）的人群，每個(gè)人群都有自己一組易感和感染性宿主。非洲原住民通常在兒童時(shí)期感染瘧疾，幸存下來(lái)的人對(duì)進(jìn)一步出現(xiàn)癥狀具有有限的免疫力，但可以作為宿主。因此，瘧疾在非洲西部沿海地區(qū)是高度流行的，而在歐洲新來(lái)者中的疾病傳播類似于從中心源頭進(jìn)行污染的隨機(jī)版本。與瘧疾不同，黃熱病會(huì)在5到7天內(nèi)殺死患者，或者出現(xiàn)快速康復(fù)和終生免疫，從而防止個(gè)體再次充當(dāng)宿主。黃熱病病原體有時(shí)會(huì)在非洲的某些地區(qū)消失，尤其是在孤立的地區(qū)，但隨著免疫不全人口的增長(zhǎng)和與外界的接觸，流行病的機(jī)會(huì)增加。歐洲人可能是黃熱病周期性流行的非免疫宿主的原因之一。傳染疾病的傳播是一個(gè)復(fù)雜的過(guò)程，可以用數(shù)學(xué)模型來(lái)概括。例如，在一個(gè)簡(jiǎn)單的確定性流行病模型中，疾病通過(guò)感染者和易感者之間的接觸傳播，沒(méi)有通過(guò)死亡、康復(fù)或隔離從環(huán)境中消除，感染在整個(gè)流行病期間都具有傳染性。流行病曲線顯示了在模型指定的條件或參數(shù)下隨著時(shí)間積累的新病例率。死亡的時(shí)間模式可以通過(guò)將被感染者中未能幸存的比例和從癥狀發(fā)作到死亡的延遲納入流行病曲線來(lái)推導(dǎo)。更復(fù)雜的模型可以涉及感染和消除、中間宿主、地理傳播、隨機(jī)現(xiàn)象、潛伏和傳染期，以及失去免疫力。針對(duì)奴隸或船員的先驗(yàn)?zāi)Ｐ椭贫ㄔ谝欢ǔ潭壬蠒?huì)存在困難，因?yàn)閷?duì)于模型的許多相關(guān)條件是未知的。事實(shí)上，相關(guān)條件是研究的重要對(duì)象。然而，流行病模型是一種有用的思維框架。這樣一個(gè)模型中的一些參數(shù)已經(jīng)給出，而另一些參數(shù)則受到奴隸販子、船長(zhǎng)和外科醫(yī)生的控制或影響?？刂频某潭群托再|(zhì)是本文的下一節(jié)的主題。