## 來自你的消息:

Crowding

Although contemporary critics of the slave trade widely regarded crowding

or "tight packing" of slaves as unhealthy, early regulations limited crowding,

and connections between density and mortality are inherently plausible within

a framework of the spread of infectious disease, recent quantitative studies

fail to establish a connection between slaves per ton and mortality.34 This

paper demonstrates that variations in crowding were crucial to variations in

death rates during loading. The contrasting results are reconcilable by

Figure 1, which shows that the chances of deaths changed little with increasing density above 1.5 slaves per ton. Admittedly Figure 1 does not extend to

densities in the area of 2 to 3 slaves per ton that prevailed outside the era

of regulation, but findings by others that overall mortality varied little

across voyages within the higher ranges are consistent with the hypothesis

that the relationship changed little across high densities. It appears that

Dolben's Act may have had little effect on mortality because the limits on

crowding were not sufficiently restrictive.

## 來自ChatAI的消息:

擁擠

盡管對奴隸貿(mào)易的當(dāng)代批評家普遍認(rèn)為擁擠或"緊密裝載"奴隸是不健康的，早期法規(guī)限制了擁擠，并且密度與死亡率之間的聯(lián)系在傳染病傳播的框架內(nèi)是合理的，但最近的量化研究未能證明單位噸奴隸與死亡率之間存在聯(lián)系。這篇論文證明了在裝載過程中，擁擠變化對死亡率變化至關(guān)重要。這些對立的結(jié)果可以通過圖1得到調(diào)和，該圖顯示，隨著密度超過每噸1.5名奴隸的增加，死亡幾率幾乎沒有變化。值得承認(rèn)的是，圖1沒有延伸到每噸2到3名奴隸的密度范圍，而這種密度在法規(guī)管控之外普遍存在，但其他人的研究結(jié)果表明，在較高范圍內(nèi)航程的整體死亡率變化不大，這與假設(shè)相一致，即在高密度下，這種關(guān)系幾乎沒有改變?？雌饋?，多爾本法案可能對死亡率影響不大，因?yàn)閷頂D的限制不夠嚴(yán)格。

## 來自你的消息:

Voyage Length

It has been widely, though not universally, noted that the share of the

cargo dying increased with time at sea.35 Whether there should have been a

positive relationship has not been debated. Instead controversy centers on

the profile of mortality within the voyage, and specifically on the relative

importance of high mortality rates at the beginning as opposed to the end of

24

the journey. It has been argued that the former would have been associated

with poor conditions in Africa and the latter with poor conditions on the voy age, especially near the end of unusually long voyages. Neither of these pat terns is supported by this study, at least not for the major causes of death

studied in detail. This research suggests that high density possibly aggre—

vated by poor health before loading and poor nutrition during the voyage led

to high death rates from gastrointestinal diseases near the middle of the voy age.

These results suggest directions for further research. Data on voyage

length and share of slaves who died may be inadequate for measuring the im portance of provisioning because the diseases involved are crucial to the ar gument; specifically, if there was screening before loading one would expect

deaths from epidemic diseases having relatively long incubation periods (such

as smallpox and measles, in which it is about two weeks) to accumulate near

the end of the voyage. Furthermore, deaths resulting from reduced provisions

need not have been concentrated at the end of the voyage. Delays in voyages

crossing the equator occurred frequently in the doldrums off the coast of

Africa. Ship captains probably adjusted provisions as a function of where the

ship was in relation to where it was expected to be.36 Thus, rations could

have been cut early in the voyage and restored near the end of an unusually

long journey Even with "normal provisions the journey was probably debili tating, and thus the rise in death rates from respiratory diseases and scurvy

reported in Table 3 is consistent with the argument that conditions on the

ship were important to health.37 Third, high death rates early in the voyage

may be consistent with poor conditions in Africa, but low death rates early in

the voyage do not necessarily irrply that conditions in Africa were goodu;

25

captains and surgeons may have avoided areas with epidemics and may have been

successful in screening slaves in poor health. Finally, greater attention

shoud be given to the interaction of conditions in Africa with those on the

ship. One of the contributions of the study of heights has been to alert

researchers to the nature and extent of interaction among nutrition, disease,

and growth.3A Thus, for example, the effects of famines in Africa on mortality during the voyage may have been a function of crowding, provisioning, and

voyage length

## 來自ChatAI的消息:

航行時(shí)間長度

已廣泛注意到，盡管不是普遍的，但貨物死亡率隨著航行時(shí)間增加而增加。是否應(yīng)該存在正向關(guān)系并未受到爭議。相反，爭議集中在航行過程中的死亡情況，尤其是在旅程開始和結(jié)束時(shí)死亡率的相對重要性。有人認(rèn)為前者可能與非洲的惡劣條件有關(guān)，而后者可能與航行中惡劣條件有關(guān)，特別是在異常長的航程接近尾聲時(shí)。這項(xiàng)研究并未支持這兩種模式，至少對于詳細(xì)研究的主要死因而言。該研究表明，高密度可能加劇了裝載前的糟糕健康狀況和航行期間的營養(yǎng)不良，導(dǎo)致了航行中段發(fā)生胃腸疾病的高死亡率。

這些結(jié)果為進(jìn)一步研究提供了方向。由于所涉及的疾病對于論證至關(guān)重要，可能無法準(zhǔn)確衡量供給的重要性，航行時(shí)間長度和死亡奴隸的份額的數(shù)據(jù)可能不足；具體而言，如果裝載前進(jìn)行了篩查，那么預(yù)期較長潛伏期（例如天花和麻疹，其潛伏期約為兩周）的流行病性疾病的死亡人數(shù)可能會在航行結(jié)束時(shí)累積。此外，由于航行穿越赤道時(shí)常常在非洲沿岸的無風(fēng)區(qū)遇到延誤，造船長官可能會根據(jù)船位于預(yù)期位置的相對位置來調(diào)整供給。因此，在異常漫長的航程末端可能會削減口糧，并在航程接近尾聲時(shí)恢復(fù)。即使有了“正常供給”，旅程可能仍然會削弱身體健康，因此表3中報(bào)告的呼吸系統(tǒng)疾病和壞血病的死亡率上升與船上的環(huán)境條件與健康狀況的論點(diǎn)是一致的。第三，在旅程開始階段的高死亡率可能與非洲的惡劣條件一致，但旅程開始階段的低死亡率并不一定意味著非洲的條件良好；船長和外科醫(yī)生可能會避開流行病區(qū)域，并且可能成功地篩選出健康狀況差的奴隸。最后，應(yīng)更加關(guān)注非洲條件與船上條件的相互作用。研究身高的一個(gè)貢獻(xiàn)在于提醒研究人員營養(yǎng)、疾病和生長之間的相互作用的性質(zhì)和程度。因此，例如，非洲的饑荒對航行期間的死亡率可能受到擁擠、供給和航行時(shí)間長度的影響。

## 來自你的消息:

Age and Sex

Studies examining differential mortality by age have usually found that

rates were higher for children.39 No systematic pattern has emerged involving

males versus females. Findings in this study that chances of deaths from gas trointestinal diseases during loading were higher for children and females are

generally consistent with previous work.

Epidemics

Although the role of epidemics are difficult to appraise from aggregate

measures such as the share of slaves embarked who died, it is clear from qual itative evidence for the entire slave trade that the spread of infectious

diseases such as dysentery, smallpox, and measles were important in overall

mortality. As many as 20 to 30 percent or more of the ships in some trades,

especially those of the seventeenth and early eighteenth centuries, had deaths

as a share of slaves embarked in excess of 15 percent.40 In these data the

average share of slaves who died was 2.4 percent, the share exceeded 4 percent

for only 10 out of 92 vessels (the distribution is given in Table 11 of the

appendix) and the highest share in the sample was 13.8 percent. The favorable

26

record stems in part from the lack of deaths from smallpox and measles. It also appears that the spread of dysentery may have been contained in these

data relative to vessels that had high mortality rates; only 60 percent of the

ships in the sample reported one or more and only 33 percent reported two or

more deaths from gastrointestinal diseases.

## 來自ChatAI的消息:

年齡和性別

研究發(fā)現(xiàn)，在考察按年齡劃分的死亡率時(shí)，兒童的死亡率通常較高。關(guān)于男性與女性之間的差異，尚未出現(xiàn)明確的模式。本研究發(fā)現(xiàn)，在裝載過程中，兒童和女性患上胃腸疾病導(dǎo)致死亡的機(jī)會較高，這與之前的研究結(jié)果一致。

流行病

雖然很難根據(jù)總體統(tǒng)計(jì)的指標(biāo)來評估流行病的作用，例如登船死亡率，但從整個(gè)奴隸貿(mào)易的質(zhì)性證據(jù)來看，傳染性疾病如痢疾、天花和麻疹的傳播在整體死亡率中是重要的。在某些貿(mào)易中，特別是在17世紀(jì)和18世紀(jì)早期的貿(mào)易中，多達(dá)20%至30%或更多的船只中，登船奴隸死亡率超過了15%。在這些數(shù)據(jù)中，死亡比例的平均值是2.4%，只有10艘船的死亡比例超過了4%（詳見附錄的表11），樣本中的最高死亡比例為13.8%。這記錄部分歸因于沒有天花和麻疹導(dǎo)致的死亡。此外，據(jù)推測，在這些數(shù)據(jù)中，痢疾的傳播可能相對于死亡率較高的船只得到了控制；樣本中只有60%的船只報(bào)告了一次或更多次胃腸疾病導(dǎo)致的死亡，只有33%的船只報(bào)告了兩次或更多次。

## 來自你的消息:

Slaves and Crew

The issues of slave and crew mortality involve comparative levels and the

extent of interrelation. The few data available on these questions indicate

that crew mortality exceed that for slaves and that the two were positively,

though, weakly, correlated.41 The fact that slaves and crew tended to die

from different causes would lead one to expect at most a weak positive corre

lation between overall slave and crew death rates. This study suggests that

passage of gastrointestinal diseases from slaves to crews during the voyage

was a source of that correlation. Though minor in these data, respiratory

diseases and scurvy may have been important causes of death common to slaves

and crew in earlier eras of the trade.

Although the literature on the slave trade seldom includes estimates of

crew mortality, West Africa acquired a reputation among Europeans as the

uwhite man's grave." Crew death rates probably remained high until progress

was made against malaria and yellow fever beginning in the mid—nineteenth

century. Thus the finding in this paper that the annual death rate during

loading and the voyage combined was 229.5 per thousand for the crew is not

surprising in light of other studies. The comparable figure among slaves of

82.8 per thousand is surprising for the extent to which it was below that for

the crew. The next section discusses the low death rate for slaves.

27

## 來自ChatAI的消息:

奴隸和船員

奴隸和船員死亡率的問題涉及相對水平和相互關(guān)系的程度。有關(guān)這些問題的少量數(shù)據(jù)表明，船員的死亡率超過了奴隸的死亡率，而且兩者呈微弱的正相關(guān)。奴隸和船員往往因不同的原因而死亡，這使人們預(yù)期奴隸和船員整體死亡率之間最多只存在微弱的正相關(guān)。此研究表明，在航行期間，奴隸傳染胃腸疾病給船員是這種相關(guān)性的一個(gè)原因。盡管這些數(shù)據(jù)中的呼吸道疾病和壞血病是次要原因，但它們可能是早期貿(mào)易時(shí)期奴隸和船員共同死亡的重要原因之一。

盡管奴隸貿(mào)易文獻(xiàn)中很少包含船員死亡率的估計(jì)數(shù)據(jù)，但西非在歐洲人中獲得了"白人的墳?zāi)?#34;的聲譽(yù)。直到19世紀(jì)中葉針對瘧疾和黃熱病的進(jìn)展取得了進(jìn)展之前，船員死亡率可能一直很高。因此，本文發(fā)現(xiàn)在裝載和航行期間的年死亡率為每千人229.5，對于其他研究來說并不令人意外。而奴隸的相應(yīng)數(shù)字則是每千人82.8，令人驚訝的是它比船員的死亡率低得多。下一部分將討論奴隸的低死亡率。

27

## 來自你的消息:

CONCLUDING REMARKS

Using data giving date and cause of death this study has found that

fevers and gastrointestinal diseases were the major cause of death for slaves

and crew in the English slave trade to the West Indies during the late 1700s.

The crew died primarily from fevers (mostly malaria) contracted in Africa, and

gastrointestinal diseases such as dysentery that spread during the voyage were

the major cause of slave deaths. The chances of slave and crew deaths varied

systematically by region of origin in Africa, season of the year, and day of

the voyage; for slaves alone by density on board ship, age, and sex; and for

the crew alone by recent occurrence of slave deaths from gastrointestinal

diseases during the voyage.

The incidence of mortality as measured by the number of deaths as a share

of slaves embarked was low in these data compared to the slave trade in other

times, which raises the question of the generality of these results. In light

of this study, why might death rates have been higher elsewhere? There are

several possible explanations. First, diseases such as smallpox and measles

that were prevalent in other times were virtually absent from these data.

Inoculation may have been effective in reducing the incidence of smallpox on

the ships of the surgeons' logs. Second, knowledge and experience involving

health and mortality in the slave trade had accumulated by the late 1700s.

Practices at this time were not guided by a germ theory of disease, but pre sumably trial, error, and observation had eliminated some practices that con tributed to deaths. One would expect that the rise in slave prices that

occurred from the late 1600s provided an incentive for innovation in health

care.42 Third, Dolben's Act may have lowered mortality. To the extent that

limits on capacity allowed room for more provisions, health may have

improved.43 The fact that deaths from respiratiory diseases and scurvy were

28

low in these data is consistent with this explanation. In addition, the

incentives of the act may have encouraged surgeons to screen carefully slaves

in poor health. Fourth, conditions on slave ships were unhealthy, and the

less time spent in this environment, the lower the share of slaves who died.

Loading times and voyage length declined from the seventeenth through the end

of the eighteenth century.44 Finally, nutritional and demographic conditions

in Africa could have changed in ways that led to slaves who were in better

health before loading. Additional studies of slave mortality that make use of

data on date and cause of death and conditions in Africa may shed light on

these issues.

## 來自ChatAI的消息:

結(jié)論

根據(jù)提供死亡日期和死因的數(shù)據(jù)，本研究發(fā)現(xiàn)在18世紀(jì)晚期的英國奴隸貿(mào)易中，發(fā)燒和胃腸疾病是奴隸和船員死亡的主要原因。船員主要因在非洲感染的發(fā)燒?。ㄖ饕钳懠玻┒劳?，而旅途中傳播的痢疾等胃腸疾病是奴隸死亡的主要原因。奴隸和船員的死亡幾率因非洲的起源地、年份的季節(jié)和航程的日子而有系統(tǒng)地變化；僅針對奴隸，還有船上的密度、年齡和性別；僅對船員來說，還有奴隸在航行中死于胃腸疾病的最近發(fā)生情況。

根據(jù)奴隸登船人數(shù)中死亡人數(shù)的比例作為死亡率的衡量標(biāo)準(zhǔn)來看，相對于其他時(shí)期的奴隸貿(mào)易數(shù)據(jù)而言，這些數(shù)據(jù)中的死亡率較低，這引發(fā)了關(guān)于這些結(jié)果適用性的問題。考慮到這項(xiàng)研究，為什么其他地方的死亡率可能更高呢？有幾種可能的解釋。首先，在其他時(shí)期流行的天花和麻疹等疾病在這些數(shù)據(jù)中幾乎不存在。接種疫苗可能在減少船上天花發(fā)生率方面起了作用，而船醫(yī)日志記錄可能證明了這一點(diǎn)。第二，到18世紀(jì)晚期，奴隸貿(mào)易中圍繞健康和死亡的知識和經(jīng)驗(yàn)已經(jīng)積累。這個(gè)時(shí)期的做法并不是以病原體理論為指導(dǎo)的，但可以推測試驗(yàn)、錯誤和觀察已經(jīng)消除了一些導(dǎo)致死亡的做法。可以預(yù)期，從17世紀(jì)末開始奴隸價(jià)格的上漲為創(chuàng)新醫(yī)療提供了激勵。第三，Dolben法案可能降低了死亡率。從容量限制的角度來看，提供更多的物資可能有助于改善健康。這些數(shù)據(jù)中呼吸道疾病和壞血病的死亡率較低與這一解釋一致。此外，該法案的激勵可能鼓勵船醫(yī)仔細(xì)篩選健康狀況不佳的奴隸。第四，奴隸船上的條件不健康，越少時(shí)間待在這種環(huán)境中，死亡比例就越低。從17世紀(jì)到18世紀(jì)末，裝貨時(shí)間和航程長度都有所減少。最后，非洲的營養(yǎng)和人口狀況可能會發(fā)生改變，導(dǎo)致在裝船前處于較好健康狀態(tài)的奴隸。進(jìn)一步利用有關(guān)死亡日期和死因以及非洲情況的奴隸死亡的研究可能會對這些問題有所啟示。

## 來自你的消息:

Studies of modern labor markets show that workers receive higher wages

for jobs that, other things being equal, are unpleasant or dangerous.45 The

acquisition of crew members for slave ships constitutes an economic laboratory

fr t"j of employment under very hazardou conditions. Interest'ng ques

tions about this labor market include the size of compensating wage differen tials, whether higher wages were received for destinations to the higher mor tality regions of Africa, the extent to which prospective crew members were

informed about the risks, and the nature of compensation. With regard to the

last point one might expect that crew members who were knowledgeable about the

risks would have insisted on some compensation in the form of a signing bonus

that was spendable before the hazardous journey began.

Comparative studies of mortality rates on ocean voyages would help to

place the slave trade in perspective and to elucidate causes of mortality on

slave and non—slave voyages.46 Data on non-slave voyages to the U.S. are

available, for example, from passenger lists and from forms required by the Pas senger Act of 1819. The agenda for research on these questions should include

the relationship of health before departure to health and mortality during the

29

voyage, the influence of provisioning on mortality, crowding and mortality,

seasonal patters of mortality, age and sex distributions and mortality, the

course of death rates during the voyage, and the time trend in mortality.

## 來自ChatAI的消息:

現(xiàn)代勞動市場研究顯示，工人在其他條件相等的情況下，從事令人不愉快或危險(xiǎn)的工作會獲得更高的工資。45 外國奴隸船的船員選拔構(gòu)成了一個(gè)經(jīng)濟(jì)實(shí)驗(yàn)室，處于極其危險(xiǎn)的工作條件下。關(guān)于這個(gè)勞動市場的有趣問題包括補(bǔ)償工資差異的大小、是否因?yàn)榍巴侵掭^高死亡率地區(qū)而獲得更高工資、潛在船員對風(fēng)險(xiǎn)了解的程度以及補(bǔ)償?shù)男问?。關(guān)于最后一點(diǎn)，可以預(yù)期那些了解風(fēng)險(xiǎn)的船員在危險(xiǎn)旅程開始之前會堅(jiān)持要求一筆可支配的簽約獎金作為補(bǔ)償。

比較海上旅行的死亡率研究有助于正確看待奴隸貿(mào)易，并闡明奴隸和非奴隸航行中死亡率的原因。46 例如，可以從乘客名單和1819年《旅客法》要求的表格中獲取關(guān)于前往美國的非奴隸航行的數(shù)據(jù)。關(guān)于這些問題的研究議程應(yīng)包括出發(fā)前健康狀況與航行期間的健康和死亡率之間的關(guān)系、供應(yīng)對死亡率的影響、擁擠與死亡率、季節(jié)性死亡模式、年齡和性別分布與死亡率、航行期間死亡率的變化以及死亡率的時(shí)間趨勢。

## 來自你的消息:

30

Appendix: Discussion of the Data

Origins

"An act to regulate, for a limited time, the shipping and carrying of

slaves in British vessels from the coast of Africa," also known as flolben's

Act, emerged from the parliamentary debates over the slave trade in 1788.

The act limited vessels to five slaves for every three tons of burden up to

201 tons, and one slave per ton for every ton above 201.48 Ship captains ex ceeding this limit were subject to a fine of ￡ 30 per slave above the limit.

Surgeons on board slave ships were required to maintain a journal encompassing

slave loading, slave and crew deaths, and causes of death. The law specified

that the collector at the port of destination was to administer on oath to the

surgeon attesting the truth of the journal. Captains received ￡ 100 and sur geons received ￡ 50 if deaths as a fraction of the largest number of slaves on

board did not exceed 2 percent. The awards were ￡ 50 and ￡ 25, respectively,

if the rate did not exceed 3 percent.

Characteristics

An extensive search of the House of Lords Record Office and the Public

Record Office produced 92 surgeons logs that are substantially complete.49

The typical journal begins with a brief description of the vessel (name, names

of master and surgeon, home port and tonnage) followed by sections on loading

and unloading by day in categories of men, women, boys, and girls: chronologi cal lists of slave and crew deaths; and the oath signed by the surgeon.

The dates of departure from Africa of the ships in the sample span the

period from 1792 to 1796. Roughly one-third of the departures occurred in

1793 and only 9 voyages took place in 1794. The typical vessel loaded for 119

days, (s.d. = 92 days) but the range of experience encompassed 1 to 529 days.

31

Approximately 28,770 slaves departed from Africa, of whom 63.7 percent were

males and 9.6 percent were children. The average ship carried 313 slaves and

had a capacity of 222 tons. All the major regions of supply along the west

coast of Africa are represented in the sample; 3 originated from Senegambia,

11 from Sierra Leone, 2 from the Windward Coast, 13 from the Gold Coast, 7

from the Bight of Benin, 8 from the Bight of Biafra, 18 from Congo—Angola, and

the area of origin for 30 vessels is unknown. The typical voyage took 56 days

(s.d. = 15.3 days) and the range was from 23 to 105 days. All the slaves were

destined for the British West Indies and three—quarters of the ships went to

Jamai ca.

## 來自ChatAI的消息:

附錄：數(shù)據(jù)討論

來源

《一項(xiàng)調(diào)控有限期限內(nèi)英國船只從非洲海岸運(yùn)送奴隸的法案》，俗稱弗洛本法案，起源于1788年關(guān)于奴隸貿(mào)易的議會辯論。該法案規(guī)定，船只負(fù)載量在201噸以下，每3噸負(fù)載可以搭載5名奴隸；超過201噸的每1噸負(fù)載可以搭載1名奴隸。超過限制的船長將被罰款30英鎊每名超過限制的奴隸。奴隸船上的醫(yī)生需要記錄奴隸裝載情況、奴隸和船員的死亡以及死因的日志。法律規(guī)定，目的港口的收稅員要對醫(yī)生進(jìn)行宣誓并證明日志的真實(shí)性。如果船上的死亡比例不超過最大奴隸數(shù)量的2%，船長將獲得100英鎊的獎勵，醫(yī)生將獲得50英鎊的獎勵。如果比例不超過3%，獎勵分別為50英鎊和25英鎊。

特點(diǎn)

在上議院記錄辦公室和公共記錄辦公室進(jìn)行了廣泛搜索，找到了92份基本完整的醫(yī)生日志。典型的日志以對船只的簡要描述（名稱、船長和醫(yī)生的姓名、母港和噸位）開始，然后是按日進(jìn)行的裝載和卸載的部分，分為男性、女性、男孩和女孩的類別；接下來是奴隸和船員死亡的按時(shí)間順序的列表；最后是醫(yī)生簽署的宣誓。樣本中船只從非洲起航的日期跨越了1792年至1796年。大約三分之一的航程發(fā)生在1793年，只有9次航行在1794年進(jìn)行。典型的船只裝載工作持續(xù)了119天（標(biāo)準(zhǔn)差=92天），但經(jīng)驗(yàn)范圍從1天到529天不等。大約有28,770名奴隸從非洲出發(fā)，其中63.7%為男性，9.6%為兒童。平均每艘船載有313名奴隸，載重量為222噸。樣本中涵蓋了非洲西海岸沿線所有主要供應(yīng)地區(qū)：塞內(nèi)加爾-岡比亞地區(qū)有3艘船，塞拉利昂有11艘船，廣島海岸有2艘船，黃金海岸有13艘船，貝寧灣有7艘船，比亞弗拉灣有8艘船，剛果-安哥拉有18艘船，而有30艘船的起源地不詳。典型航程耗時(shí)為56天（標(biāo)準(zhǔn)差=15.3天），范圍從23到105天不等。所有奴隸都被運(yùn)往英屬西印度群島，四分之三的船只前往牙買加。

## 來自你的消息:

Bi ases

The logs of 16 vessels specify the day of arrival at the port of destina tion. Arrival times for 71 vessel were inferred from the day the surgeon's

oath was signed. Arrival information is incomplete or lacking for 5 logs.

Presumably the surgeon ceased to record deaths when the vessel reached port.50

If the oath was administered after the day the vessel reached port, then death

rates calculated for the end of the voyage would be biased downwards because

the number of days at risk for recording deaths would be overstated.

Fortunately 12 vessels reported the actual day of arrival and have the

oath. In this sample the average lag between the day of the oath and the

reported day of arrival is 2.1 days, and the range is from 0 to 5 days. The

distortion to calculated death rates is relatively minor if the experience of

these vessels applied to those for which we lack information.

Throughout the period of the slave trade entrepreneurs commonly rewarded

masters, surgeons, and certain members of the crew for efforts to maintain the

health of the cargo. Bonuses took the form of shares of the sales receipts,

32

head money, and privilege slaves.51 The extent to which Dolben's Act may

have contributed to total incentives is not clear; entrepreneurs could have

allowed legislated incentives to substitute for their own.

Table 11 shows the frequency distribution of recorded deaths as a share

of slaves exported from Africa. The clusters of observations at or below 2

percent and 3 percent combined with the cut-off point for bonuses under Dol—

ben's Act raise the suspicion that some deaths may not have been recorded.

The observation that death rates in the Atlantic slave trade were rela tively low during the 1790s appears to support the underreporting thesis.52

In defense of the data, however, it should be recognized that good reasons

exist for the low death rate (see the concluding section of the paper). While

substantial underreporting cannot be entirely ruled out, the favorable situa tion with respect to epidemic diseases of smallpox and measles, for example,

makes the calculated aeath rates plausible.

Even if there was substantial underreporting, the implications for our

understanding of determinants of mortality heavily depends upon selectivity of

underreporting. If deaths were not reported at random, for example, then many

conclusions about regional influences, seasonal patterns, and the course of

events during the voyage remain largely intact.

A selective form of underreporting perhaps worth discussion involves the

end of the voyage. The decline in calculated death rates after the middle of

the voyage combined with the chronological organization of the journals sug gests that a simple strategy for collecting bonuses under Dolben's Act for

ships that were near the margin for collection was to neglect to report deaths

near the end of the voyage. Since all slaves loaded had to he accounted for,

33

this required falsification of loading records. While this form of underreporting may have existed, it is relevant to note that the time profile of

deaths (available for gastrointestinal diseases only) on vessels that exceeded

the 3 percent minimum reached a peak on day 35 of the voyage and then declined

at a rate similar to that for the entire sample shown in Figure 2.

## 來自ChatAI的消息:

在16艘船的日志中，指定了抵達(dá)目的港的日期。從醫(yī)生宣誓簽署的日期可以推斷出其他71艘船的抵達(dá)時(shí)間。其中5艘船的抵達(dá)信息不完整或缺失。推測醫(yī)生在船到港后停止記錄死亡情況。如果醫(yī)生宣誓的日期在船到港之后，那么根據(jù)航行末期計(jì)算的死亡率會有向下的偏差，因?yàn)橛涗浰劳銮闆r的風(fēng)險(xiǎn)天數(shù)會被夸大。幸運(yùn)的是，有12艘船報(bào)告了實(shí)際的抵達(dá)日期和醫(yī)生宣誓的日期。在這個(gè)樣本中，醫(yī)生宣誓日期與報(bào)告的抵達(dá)日期之間的平均差距為2.1天，范圍為0至5天。如果這些船只的經(jīng)驗(yàn)適用于我們?nèi)狈π畔⒌拇?，那么對?jì)算的死亡率的扭曲相對較小。在奴隸貿(mào)易時(shí)期，企業(yè)家常常獎勵船長、醫(yī)生和某些船員為維持貨物健康所做的工作。獎金以銷售收據(jù)的份額、頭錢和特權(quán)奴隸的形式存在。德爾本法可能對總獎勵做出了貢獻(xiàn)，但目前還不清楚；企業(yè)家可能已經(jīng)允許法定的激勵取代了他們自己的激勵。表11顯示了記錄的死亡人數(shù)占從非洲出口的奴隸的比例的頻數(shù)分布。觀察到在2%和3%的水平以及德爾本法規(guī)定的獎金截止點(diǎn)以下的聚集現(xiàn)象使人懷疑可能有一些死亡未被記錄。大西洋奴隸貿(mào)易在1790年代的死亡率相對較低似乎支持了低報(bào)告率的觀點(diǎn)。然而，在捍衛(wèi)數(shù)據(jù)的同時(shí)，應(yīng)該認(rèn)識到低死亡率存在充分的理由（參見本文的結(jié)論部分）。即使存在相當(dāng)大的低報(bào)告率，對我們理解死亡率決定因素的影響還嚴(yán)重依賴于隨機(jī)性的低報(bào)告率選擇性。例如，如果死亡率不是隨機(jī)報(bào)告的，那么關(guān)于地區(qū)影響、季節(jié)模式和航行過程的許多結(jié)論基本上仍然成立。一個(gè)值得討論的選擇性低報(bào)告形式涉及航程的結(jié)束。航程中期后計(jì)算的死亡率下降與日志的時(shí)間順序組織結(jié)合起來，暗示了在接近收集邊際的船只中，一種簡單的獲得德爾本法獎金的策略是忽視航程末期的死亡情況報(bào)告。由于所有上船的奴隸都必須核對，這就需要虛假記錄裝載信息。雖然可能存在這種類型的低報(bào)告，但值得注意的是，那些超過3%最低要求的船只上的死亡情況（僅有胃腸疾病可得數(shù)據(jù)）在航程第35天達(dá)到頂峰，然后以與整個(gè)樣本相似的速率下降（見圖2）。