大西洋奴隶贸易中奴隶和船员死亡率的决定因素（2）

2023-08-06 10:06 作者:四夕昭宇 0人读过 | 我要投稿

## 来自你的消息:

ANALYSIS OF MAJOR CAUSES OF DEATH

Approach

Given the importance of time in an epidemic process it is fortunate that

surgeons recorded information on a daily basis. The unit of observation

selected for a regression analysis of determinants of mortality is daily

information for a particular ship. We chose a logit model in which the depen—

dent variable takes on the value of 1 if there were one or more deaths from a

particular cause.18 Separate regressions are required for slaves and crew on

the grounds that these groups arrived with substantially different immunities

and lived under considerably different conditions. Because there was contact

with shore and provisions were available from shore during loading but not

during the voyage, it is appropriate to analyze mortality during loading sepa.-

rate from mortality during the voyage.

## 来自ChatAI的消息:

主要死因的分析

方法

鉴于在流行病过程中时间的重要性，幸运的是，外科医生每天记录信息。我们选择了一个特定船只每天信息作为回归分析死亡决定因素的观察单位。我们选择了一个逻辑模型，其中依赖变量在特定原因有一个或多个死亡时取值为1。对于奴隶和船员，需要进行单独的回归，因为这些群体的免疫力差异显著，并且生活条件也有很大差异。因为在装货时与岸上有接触并可获得来自岸上的供应，而航行期间没有供应，因此适当地将装货期间的死亡率与航行期间的死亡率分开进行分析。

## 来自你的消息:

The variables available for study of mortality during loading include

region of origin in Africa, slaves per ton on the ship, seas.on of the year,

and time. These variables are motivated below. Experiments with other varia bles are discussed at the end of this section.

Region. Differences in death rates by location could have been caused by

variations in the rate of exposure to pathogens, the number and virulence of

pathogens, and the immunities and other means of resistence by individuals to

disease. With regard to risks of exposure, the nature of activities required

by the crew while slaving may have differed by region. For example, the dis tance that the ship anchored from shore, whether the ship anchored along the

coast or in a river or delta, the amount of time spent by the crew on ship

versus the interior, and sources of food and water may have been important

determinants of mortality. kiong slaves the risks of exposure may have been

influenced by the duration of time from inland capture to loading, the loca tions of forts or prisons relative to sources of disease, the extent of crowd

ing while being held on shore, and sources of food and water. It is virtually

impossible to acquire reliable information about the number and virulence of

pathogens that existed in the late eighteenth century. However, it should be

recognized that differences could have existed as a function of climate,

topography, migration, and the extent of adaptation of pathogens to hosts.

The immunities of individuals were influenced by the degree of adaptation to a

diseäseenviroriment. Thus the extent to which slaves exported frc a particu lar port were acquired in regions remote or otherwise differing in disease

environment of the port of exit may have influenced mortality. Excluding the

few who had been to Africa or the West Indies previously, the crew generally

had little or no resistence to malaria or yellow fever. The general health

and diet of slaves and crew were important particularly for resistence to gas trointestinal diseases; nutrition apparently has little impact on the course

of malaria or yellow fever.19 Therefore the health of slaves at the time of

initial capture, exertions of the journey to the coast, and diet while being

held on the coast or on board ship may have influenced deaths from dysentery.

In conclusion, it should be recognized that the large number of possible

regional determinants of mortality and the lack of information about most of

them will make it difficult to identify specific sources of locational differ ences in mortality that may be found. It should be noted that the influence

of a particular region on mortality could have changed overtime, but that lack

of data restricts study of this issue.

## 来自ChatAI的消息:

加载中

用来研究装载期间死亡率的变量包括出生地的区域、每吨船上的奴隶数量、年份的季节和时间。下面将对这些变量进行说明。本节还讨论了与其他变量的实验。区域。造成不同地点死亡率差异的原因可能是受到病原体暴露率、病原体数量和毒力、个体对疾病的免疫力和其他抵抗手段的变化的影响。就暴露风险而言，奴隶贩运期间船员所需的活动性质可能因地区而异。例如，船远离海岸的距离，船只是在沿海停泊还是在河流或三角洲停泊，船员在船上与内地的停留时间之比，以及食物和水的来源可能是决定死亡率的重要因素。对奴隶来说，暴露风险可能受到从内地被捕到装船的时间长短、堡垒或监狱与疾病源的关系、在岸上滞留期间的拥挤情况以及食物和水的来源的影响。获取关于18世纪晚期存在的病原体数量和毒力的可靠信息几乎是不可能的。然而，应该认识到，由于气候、地形、迁移和病原体对宿主的适应程度等因素的作用，差异可能存在。个体的免疫力受到对特定疾病环境的适应程度的影响。因此，从特定港口出口的奴隶是否被获得于远隔地区或在疾病环境有所不同的地区可能会影响死亡率。除了少数曾经去过非洲或西印度群岛的人外，船员通常对疟疾或黄热病几乎没有抵抗力。奴隶和船员的一般健康和饮食对于抵抗胃肠道疾病尤为重要；营养对疟疾或黄热病的进展似乎几乎没有影响。因此，奴隶在被俘初期的健康状况、到达海岸的旅途的劳累，以及在岸上或船上的饮食可能会影响因痢疾而死亡的人数。总之，应该认识到，可能影响死亡率的地区决定因素众多，而且对大多数这些因素缺乏信息，这将使得很难确定可能存在的地区死亡率差异的具体原因。应该注意到，特定地区对死亡率的影响可能随时间变化，但因缺乏数据，对此问题的研究受到限制。

## 来自你的消息:

Slaves per Ton. Gastrointestinal diseases such as shigellosis are often

highly contagious.2° Transmission is common through the fecal-oral route,

usually by way of contaminated hands or food. Shigellosis does not confer

long—term immunity because reinfections are frequent, and the multiplicity of

strains precludes resistence to all varieties. Assuming that all instances of

gastrointestinal diseases were not acquired by contamination from a central

source such as food or water, the spread of these diseases would have varied

with density. Thus slaves per ton may have influenced slave death rates. To

the extent that the crew avoided slaves and slave living areas or had resist—

ence, death rates of the crew would have been unrelated to slaves per ton.

Season. The number of sites available for mosquito larvae, and therefore

the mosquito population, may have increased during the rainy season.21 In

addition, mosquitoes have may been more active and survived for longer periods

in humid as opposed to dry weather. Thus the chances of infection from mala ria may have increased during the rainy season. Some observers have noted an

increase in the incidence of 'fevers" during the rainy season.22 Rain and

high humidity may also have prolonged the survival and increased the probabil ity of transmission of bacteria responsible for gastrointestinal diseases.

Time. The spread of infectious disease inevitably involves time. Fac tors that may influence the profile of mortality over time include patterns of

activity that affect the chances of exposure to pathogens, the mechanism of

transmission, the incubation period of the disease, and the interval from the

onset of illness to death. Diseases have characteristic incubation periods

and intervals from the first symptoms to death. Given information about

causes of death, the time profile of mortality may be informative about the

mechanism of transmission and the patterns of activity that led to disease.

The results involving slaves and crew are given in Tables 5 and 6. Since

the chances of deaths should have been a function of the number of persons at

risk, the regressions include the number of slaves (or crew) as independent

variables. The values of -2 log A, where A is the likelihood ratio, show that

each regression is highly significant. Significance tests for groups of coefficients are given in the notes to the tables.

## 来自ChatAI的消息:

每吨奴隶数量。痢疾等肠胃疾病通常具有高传染性。2°传播通常通过粪口传播途径进行，通常是通过被污染的手和食物传播。痢疾并不具有长期免疫力，因为再次感染是频繁的，并且多样性的菌株使得对所有变种产生抵抗力成为不可能。假设所有的肠胃疾病实例都不是源自于中央来源（比如食物或水）的污染，这些疾病的传播将会随着密度而有所不同。因此，每吨奴隶数量可能会影响奴隶死亡率。如果船员避免与奴隶和奴隶居住区接触或具有抵抗力，船员的死亡率与每吨奴隶数量无关。季节。在雨季期间，蚊子幼虫的繁殖地点数量可能会增加，从而导致蚊子种群增加。此外，湿度较高的天气中，蚊子可能更加活跃并且存活时间更长。因此，在雨季期间感染疟疾的机会可能会增加。一些观察者指出，在雨季中发热的情况有所增加。22雨水和高湿度也可能延长细菌的存活时间，并增加导致肠胃疾病的细菌传播概率。时间。传染病的传播必然涉及时间。可能影响死亡率随时间变化的因素包括影响暴露于病原体机会的活动模式，传播机制，疾病的潜伏期以及发病到死亡的时间间隔。疾病具有特定的潜伏期和从出现症状到死亡的时间间隔。根据死因的信息，死亡率的时间分布可以揭示传播机制和导致疾病的活动模式。关于奴隶和船员的相关结果见表5和表6。由于死亡机会应该与处于风险中的人数有关，回归分析中包括奴隶（或船员）数量作为独立变量。-2 log A的值，其中A是似然比，表明每个回归都非常显著。关于系数组的显著性检验见表的注解。

## 来自你的消息:

Among slaves the deaths from fevers and gastrointestinal diseases by

region of origin were systematically higher in the Bight of Biafra, Compared

to other regions, the probability of deaths among slaves boarded in the Bight

of Biafra was 31 precent higher for gastrointestinal diseases and 58 percent

higher for fevers.23 The Bight of Biafra was also deadly for the crew,

especially for gastrointestinal diseases. However, the chances of crew deatris

from fevers were systematically highest on the Windward Coast and systemati cally lowest on the Gold Coast. The highest chances of crew deaths from gas trointestinal diseases occurred in Senegambia.

Crowding, or slaves per ton, was included in the regressions involving

fevers on the grounds that some gastrointestinal diseases may have been mis diagnosed as fevers. Because the relationship between crowding and mortality

may have been nonlinear, the regressions include a polynomial in slaves per

ton. The tests reported in the notes to Table 6 show that crowding had no

systematic influence on crew deaths. The explanation for the lack of associa tion is unclear, but if the diet and health of the crew was relatively good,

it would have imposed a gastric acid barrier to the spread of gastrointestinal

infections. It is also possible that the crew avoided contact and therefore

contamination from slaves, or that the crew was largely immune (i.e. the crew

was the source of slave gastrointestinal infections) to the diseases involved.

The tests reported in the notes to Table 5 establish that slave deaths were

systematically linked to crowding. Figure 1 shows that the chances of gastrointestinal infection implied by the regression increased roughly ten fold as

the ships approached carrying capacity. This pattern is consistent with

higher probabilities of transmitting infection through contact as density

increased. If some gastrointestinal diseases were misdiagnosed as fevers, it

is not surprising that the chances of deaths from "fevers would have been

related to slaves per ton. Figure 1 shows, however, that the chances of

deaths from fevers eventually declined as slaves per ton rose. The reason for

this pattern is unknown, but it is possible that some of the fevers were

caused by mosquitoes and that for reasons of safety and control of the cargo,

the ships anchored further from shore at hiijh defisities.

## 来自ChatAI的消息:

在奴隶中，来自比亚弗拉湾地区的热病和胃肠疾病的死亡率比其他地区普遍更高。与其他地区相比，在比亚弗拉湾登船的奴隶患胃肠疾病的死亡率高出31%，患热病的死亡率高出58%。比亚弗拉湾对船员来说也很危险，尤其是胃肠疾病方面。然而，来自热病的船员死亡率在风ward海岸上最高，而在黄金海岸上最低。来自胃肠疾病的船员死亡率最高的地区是塞内加尔加比亚。

在与热病相关的回归分析中，考虑到有些胃肠疾病可能被误诊为热病，考虑了人口密度（每吨奴隶数量）。因为人口密度与死亡率的关系可能是非线性的，回归中包括了奴隶每吨数量的多项式。表6附注中报告的检验结果显示，拥挤对船员死亡没有系统影响。对于这种缺乏关系的解释还不清楚，但如果船员的饮食和健康相对良好，那么可能会形成胃酸屏障，阻止胃肠感染的传播。也有可能船员避免与奴隶接触，避免污染，或者船员对所涉及的疾病有很强的免疫力（即船员是奴隶胃肠感染的来源）。

表5附注中报告的检验结果表明，奴隶死亡与拥挤情况有系统关联。图1显示，随着船只接近承载能力，通过回归推算的胃肠感染机会大致增加了十倍。这种模式与密度增加时通过接触传播感染的概率增加相一致。如果有些胃肠疾病被误诊为热病，那么死于"热病"的机会与奴隶每吨数量相关并不令人意外。然而，图1显示，随着奴隶每吨数量的增加，死于热病的机会最终下降。这一模式的原因尚不清楚，但有可能一些热病是由蚊子传播的，而出于安全和货物控制的原因，船只在高密度地区远离海岸停泊。

## 来自你的消息:

The chances of crew deaths from gastrointestinal diseases were not

systematically related to time as measured by a polynomial in day of loading.

The day of loading coefficients involving fevers were significantly different

from 0 at .10; deaths were systematically lower early in the loading process,

possibly because of the delay between infection and mortality for diseases

such as malaria

Slave deaths from gastrointestinal diseases were systematically higher

during the rainy season (June, July, and August north of the equator and

December, January, and February south of the equator).24 Rain apparently had

no influence on the chances of crew deaths from gastrointestinal causes or on

deaths from fevers. Infective mosquitoes may have been sufficiently prevalent

year-round that the chances of infection varied little by season of the year.

It is also possible t:hat infective mosquitoes were more prevalent during the

rainy season and that patterns of activity, such as expeditions to the

interior, were curtailed in ways that offset the greater risk of infection.

Experiments with other variables include a proxy for the price of slaves,

a measure of association between slave and crew deaths, measures of duration

that slaves had been on board, theage and sex ratios of slaves, recent loading of slaves, year of activity, and month of the year. Since bonuses and

other income received by the captain, the surgeon, and the crew varied with

the value of the cargo, there were incentives to improve care as a function of

slave prices. Unfortunately, reliable annual data on slave prices are lacking

or have not yet been assembled for the late eighteenth century. Experiments

using the price of sugar as a proxy for the price of slaves failed to uncover

any systematic relationship with slave mortality. The incentives at low

pricesmay have been sufficient to elicit all the care that they were willing

to exert, or were able to exert given the primitive state of health care knowledge. The reasons in theory why the price of slaves and the price of sugar

may not have been highly correlated also suggest that sugar prices may have

been a poor proxy for slave prices; for example, fluctuations in weather could

have changed the supply and therefore the price of sugar in ways that had

little influence on slave prices.

In an effort to investigate the possible transmission of gastrointestinal

diseases from slaves to the crew and vice versa, dummy variables representing

death of slaves (or crew) from gastrointestinal causes within the previous

week were included as explanatory variables in the regressions for gastrointestinal diseases. The results showed that there was no systematic interaction between slave and crew mortality.

## 来自ChatAI的消息:

船员因胃肠疾病死亡的机会没有与装船当天计为多项式的时间相关。涉及发热的装船当天系数在0.10时与0明显不同；在装船过程的早期，死亡率明显较低，可能是因为像疟疾这样的疾病的感染和死亡之间存在延迟。

奴隶因胃肠疾病的死亡率在雨季（北纬赤道以北的6月、7月和8月，南纬赤道以南的12月、1月和2月）期间明显较高。雨水显然不会影响船员因胃肠疾病而死亡的机会，亦不会影响由发热引起的死亡。感染性蚊虫可能在全年范围内普遍存在，因此年份的季节变化对感染机会的影响可能很小。

还有可能的情况是，感染性蚊虫在雨季更普遍，而活动模式（如对内陆的探险）可能被削减，以抵消更大的感染风险。对其他变量的实验包括奴隶价格的代理变量，奴隶和船员死亡之间的关联度，奴隶在船上的停留时间，奴隶的年龄和性别比例，最近的奴隶装载情况，活动年份和月份。由于船长、医生和船员所得的奖金和其他收入随货物价值而变化，因此他们有动机根据奴隶价格改善护理。不幸的是，关于十八世纪末奴隶价格的可靠年度数据是缺乏或尚未整理的。使用糖价作为奴隶价格的代理变量的实验未能发现与奴隶死亡率之间的任何系统关系。在低价格环境下的激励可能足以促使他们尽力提供所有可能的护理，或者鉴于卫生保健知识的原始状态，他们只能提供有限的护理。奴隶价格和糖价可能不高度相关的理论原因也表明，糖价可能是奴隶价格的低效代理；例如，天气的波动可能会改变糖的供应，从而对奴隶价格影响不大。

为了调查奴隶与船员之间可能的胃肠疾病传播情况，将奴隶（或船员）在前一周内因胃肠疾病死亡的虚拟变量作为解释变量放入胃肠疾病的回归模型中。结果显示奴隶和船员死亡之间没有系统的相互作用。

## 来自你的消息:

Because individual slaves were not tagged by date of entry or exit from

the ship, it is impossible to measure accurately the length of time that the

typical slave had been on board. Since life on the ship was probably debili tating, duration aboard may have influenced the incidence and course of

disease. Experiments with measures of average duration constructed on various

assumptions about flows (such as first on, first off and last on, first off)

were unsatisfactory; the procedures sometimes produced impossible results

(negative numbers of slaves at risk on some days, for example) and in those

cases in which the measures could not be rejected out of hand, there was no

systematic association with mortality.

Differential patterns of exposure, immunity, and resistence to disease

may have affected death rates by age and sex. Children, for example, may have

acquired fewer immunities than adults Patterns in African societies of

demand for labor and ccess to food by age and sex and differential treatment

after enslavement could have led to differential mortality for males and

females. In the subset of observations providing the relevant information,

the shares of the cargo enumerated as females and children were included as

explanatory variables. Age and sex composition had no statistically signifi cant influence on fevers, but the chances of deaths from gastromtestinal

causes were systematically higher among females and children.

The chances that someone harbored or transmitted a disease may have

increased with the number of slaves or crew aboard and with the recent addi tion of slaves to the ship. Experiments with these variables failed to un cover any systematic influences. Quadratic terms in the number of slaves and

number of crew, and the number of slaves loaded within the previous week were

statistically insignificant when included in the regressions for fevers and

for gastrointestinal diseases.

Although the data employed in the paper pertain to only 5 years (1792—

1796), it is possible that captains and surgeons adjusted to the incentives of

Dolben's Act in ways that reduced mortality. A linear term in year of the

activity was included in the regressions, and the coefficient was negative and

statistically significant (t=—3.47) for gastrointestinal diseases but statistically insignificant for fevers. During the voyage the coefficient of the

year was statistically insignificant in both regressions. It is possible that

health was improved by methods that applied while loading but not during the

voyage.

## 来自ChatAI的消息:

由于船上的个别奴隶没有记录进入或离开船只的日期，因此无法准确测量典型奴隶在船上的停留时间。由于船上的生活可能具有削弱体力的效果，停留时间可能会影响疾病的发生和发展。使用基于不同假设关于流动情况的平均停留时间的实验是不令人满意的；这些方法有时会产生不可能的结果（例如某些日子奴隶的风险人数为负数），并且在那些无法完全否定这些测量值的情况下，并没有找到与死亡率有系统相关的关系。

暴露、免疫和对疾病的抵抗力的差异模式可能会影响不同年龄段和性别的死亡率。例如，儿童可能获得的免疫能力较少。非洲社会中对劳动力需求和年龄、性别以及奴役后的差别对待，可能导致男性和女性的死亡率不同。在提供相关信息的观察子集中，将货物中列举为女性和儿童的份额作为解释变量纳入考虑。年龄和性别构成对于发热没有统计上显著的影响，但是女性和儿童患胃肠疾病死亡的机率明显更高。

某人患病或传播疾病的机会可能会随着船上奴隶或船员的数量增加以及最近添加的奴隶数量的增加而增加。对这些变量的实验没有发现任何系统性的影响。在发热和胃肠疾病回归中包含的奴隶数量和船员数量的二次项以及在上一周内装载的奴隶数量在统计上都是无意义的。

尽管本文所使用的数据仅涵盖了5年（1792年至1796年），但船长和医生可能已经调整了行动以降低死亡率。在回归中，年份的线性项被纳入考虑，系数在胃肠疾病中为负且在统计上显著（t=-3.47），但在发热中统计上无意义。在航行过程中，年份的系数在两个回归中都是无意义的。可能存在在装载过程中但在航行中并不适用的方法来改善健康。

## 来自你的消息:

The regression models incorporate seasonal phenomena by including a dummy

variable for the rainy season, but in reality seasonal phenomena influencing

health and mortality were more complex than this simple dichotorr'. Patterns

of rainfall, food supply, insect vectors, and human activities varied through-.

out the year and by region in ways that make it difficult to predict the net

influence of all relevant factors.25 Empirical investigation of these phenoni—

ena among slaves is restricted by the small number of deaths that occurred

during loading. mong the crew there is sufficient information to include

dummies in month of loading as regressors in the equation for fevers on ships

that loaded north of the equator. In these data crew deaths were systemati cally lower during the dry season months of March (t=—2.33) and April

(t=-2. 58). Captai.ns were probably aware of seasonal patterns because days

spent loading peaked in March (10.7 percent of all days spent loading) and

were lowest during the summer months of the rainy season.

The Voyage

Although the variables available for study of mortality during the voyage

are similar to those employed for loading, the interpretations may differ.

Region of origin, for example, ecompasses only those aspects such as general

health or patterns of activity immediately before departure that continued to

have an influence during the voyage. Thus contrasts between regional effects

during loading and the voyage may suggest interpretations of the regional

van ables.

Table 7 shows that the chances of slave deaths from fevers were relatively high among ships departing from Sierra Leone, the Bight of Benin, and

Congo-Angola. Senegambia, Sierra Leone, Congo-Angola, and especially the

Bight of Biafra were major sources of slave deaths from gastrointestinal

diseases. The small sample size limited regional comparisons involving the

crew to the Bight of Biafra versus other regions. Companions of Tables 5-8

show that the Bight of Biafra was deadly for slaves and crew. The negative

coefficient for crew size in gastrointestinal diseases is unexpected. Errors

;n crewsize estimates may have contributed to this result, although it does

not register in this way in other regressions. Perhaps there was specialization within the crew in the case of large ships in ways that concentrated

contamination from gastrointestinal diseases.26

Crowding as measured by slaves per ton had no systematic influence on the

chances of deaths for slaves or crew during the voyage. The equations shown

in Tables 7 and 8 include only a linear term in slaves per ton on the grounds

that the range of the variable was small across ships during the voyage; however, a third degree polynomial in slaves per ton is also statistically insignificant. The lack of association contrasts with the systematic association

found for slaves during loading. Figure 1 shows that the chances of slave

deaths tended to level-off at high densities; thus if the lack of association

at high densities during loading applied to the voyage then the finding may be

an artifact of the limited range of observation during the voyage.

## 来自ChatAI的消息:

回归模型通过包括雨季的虚拟变量来考虑季节现象，但实际上影响健康和死亡的季节现象比这个简单的二元变量更为复杂。降水、食物供应、昆虫媒介和人类活动在全年和不同地区表现出不同的模式，使得很难预测所有相关因素的净影响。关于奴隶身上的这些现象的经验研究受到了装货期间死亡数量有限的限制。在船员中，有足够的信息可以将装货月份的虚拟变量纳入到北纬度以北船只上发热的方程中。在这些数据中，船员的死亡数量在三月（t=—2.33）和四月（t=-2.58）这两个旱季月份中普遍较低。船长可能意识到季节模式，因为装货日数在三月达到高峰（占所有装货日的10.7%），而在雨季夏季的月份最低。

航行旅程

尽管用于研究航行期间死亡的变量与装货期间相似，但其解释可能有所不同。例如，出发地区仅涉及到在离港前立即影响航行期间的诸如整体健康状况或活动模式等方面的特征。因此，装货期间和航行期间地区效应之间的对比可能指出了地区变量的解释。

表7显示，从塞拉利昂、贝宁湾和刚果-安哥拉出发的船只中，因发热导致奴隶死亡的几率相对较高。塞内加尔比绍、塞拉利昂、刚果-安哥拉和特别是比亚弗拉湾是奴隶死于胃肠疾病的主要来源。样本规模小限制了涉及船员与比亚弗拉湾和其他地区的地区比较。表5-8的附表显示，对奴隶和船员来说，比亚弗拉湾是致命的。在胃肠疾病中，船员规模的负系数是意外的。船员规模估计错误可能导致了这一结果，尽管这在其他回归中没有体现出来。也许在大型船只中，船员内部存在特殊化，使得胃肠疾病的污染更加集中。

航行期间，以每吨奴隶数衡量的拥挤程度对奴隶和船员的死亡几率没有系统影响。表7和8中显示的方程仅包括奴隶每吨的线性项，因为航行期间该变量的范围在船只之间非常小；然而，奴隶每吨的三次多项式也在统计上没有重要影响。与装货期间的奴隶有系统关联相反，这种缺乏关联性显著。图1显示，奴隶死亡几率在高密度时趋于稳定；因此，如果在装货期间高密度时的缺乏关联性也适用于航行期间，则这一发现可能是观察范围有限的结果。

## 来自你的消息:

Table 8 shows that crew mortality rates from fevers and gastrointestinal

diseases were negatively related to length of loading, but the coefficients

are marginally significant. If there was a systematic association involving

length of loading and these causes of death, then the interpretation may be

that the level of exposure to disease increased during loading such that those

who survived were more immune to attacks and death during the voyage.

Day of the voyage systematically influenced slave deaths from fevers and

gastrointestinial diseases and crew mortality from fevers.27 The relation ships estimated from the regressions are given in Figure 2. In each case the

estimated probabilities of deaths follow an inverted-U pattern as a function

of time. 4mong slaves the peak occurred about 25 days into the voyage for

fevers and 31 days into the voyage for gastrointestinal diseases. Crew deaths

from fevers peaked about 12 days into the voyage. The prevalent and most

deadly forn ofrnalaria in Africa was P. falciparum.28 This form usua!ly has

an incubation period of 10 to 14 days, but may be longer, and may kill up to

25 percent of nonimmune adults within 2 weeks of a primary attack.29 The days

immediately before a ship's departure usually involved considerable loading of

slaves and interaction with shore. The interaction probably increased the

crew's exposure to infective mosquitoes; this combined with the range of.in—

cubation periods and the delay from first symptoms to death is consistent with

the time profile of crew mortality from fevers. Yellow fever runs its course

within 5 to 7 days, and so it is unlikely that infections received on shore

contributed to the peak observed during the voyage. However, the putrid

fevers diagnosed by surgeons are consistent with yellow fever, and it is pos sible that infected mosquitoes taken aboard incubated the virus in ways that

led to deaths from the disease more than one week into the voyage.

Compared to the distribution for the crew, slave deaths from fevers

peaked about 2 weeks later and were more concentrated in the upper tail. The

distribution resembles that for gastrointestinal diseases. Most slaves had

probably been infected with malaria prior to capture, while traveling to the

coast, or while being held on the coast. It is doubtful that slaves with

fever symptoms were loaded. Furthermore, relapses do not occur in P. falci—

parum.30 These considerations combined with the possibilities for misdiagno—

sis and the sensitivity of deaths from Hfeversu to density during crowding

suggest that a large share of the slave deaths attributed to fevers during

the voyage may have been of gastrointestinal origin.

## 来自ChatAI的消息:

表8显示，船员因发热和胃肠疾病而死亡的率与装载时间呈负相关，但系数仅略有显著性。如果装载时间与这些死因之间存在系统性关联，则可能的解释是在装载期间，暴露于疾病的程度增加，因此那些幸存下来的人在航行期间对袭击和死亡更具免疫力。

航程的天数对奴隶死于发热和胃肠疾病以及船员死于发热的影响是有规律的。回归估计得到的关系如图2所示。在每种情况下，死亡的预计概率都随时间呈倒U形。对于奴隶，发热的高峰出现在航行约25天后，而胃肠疾病的高峰则出现在航行约31天后。船员的发热死亡在航行约12天后达到高峰。在非洲，最常见也是最致命的疟疾形式是恶性疟原虫。这种形式通常有10到14天的潜伏期，但可能更长，并且在初次感染的2周内可能导致多达25%的非免疫成年人死亡。船只出发前几天通常涉及大量奴隶的装载和与岸上的互动。这种互动可能增加了船员暴露于传染性蚊子的机会；加上潜伏期的范围和从首次出现症状到死亡的延迟，这与船员因发热而死亡的时间分布一致。黄热病的病程持续5到7天，因此不太可能是在岸上感染导致了航行期间观察到的高峰。然而，外科医生诊断的腐臭性发热与黄热病相一致，可能是由于携带进船的感染蚊子在船上潜伏导致了一周以上的病死。

与船员的分布相比，奴隶死于发热的高峰约晚2周，并且更集中在上尾部。这种分布与胃肠疾病相似。大多数奴隶在被俘前、前往海岸途中或在海岸上被感染了疟疾。怀疑被发热症状的奴隶不会装载上船。此外，恶性疟原虫不会出现复发。考虑到这些因素以及误诊可能性和在拥挤条件下死于发热的敏感性，可以推断在航行期间归因于发热的奴隶死亡中，很大一部分可能是胃肠疾病导致的。

## 来自你的消息:

The time pattern of deaths from gastrointestinal diseases shown in Figure

2 is consistent with diffusion by personal contact and with contamination from

a central source. In the case of personal contact the time pattern of deaths

on individual ships would have resembled an inverted—U, and in the latter case

the incidence of the first death across ships would have followed the

inverted-U pattern, but deaths on a particular ship should have been bunched

together, differing only by individual differences in the incubation period.

While it is impossible to measure the relative importance of these processes

from the available data, information in Tables 9 and 10 suggests that spread

by personal contact was a general tendency. Table 9 shows that the average

interval from the beginnng of the voyage to the first death was 17.1 days,

which is significantly less than the interval of roughly 30 days predicted by

the central source hypothesis. The incubation period for shigellosis ranges

from 1 to 6 days and averages 5 days.31 The fact that the average intervals

between deaths 1 and 2 and between 2 and 3 exceeded the average incubation

period casts further doubt on the central source explanation. In addition,

the size and decline of the intervals is consistent with a diffusion by contact process. Table 10 shows that one—half of the ships with 2 or more deaths

from gastrointestinal diseases had average intervals between deaths that

exceeded the upper range of the incubation period of 6 days. Because 10 out

of 26 ships had average intervals under 5 days, however, one cannot rule out

instances of contamination from a central source. Indeed, instances of more

complex processes such as spread by contact combined with contamination from a

iit.i a i uur.e ai We i I WI LII III LII SLO UI LF1e UdL.

## 来自ChatAI的消息:

图2中显示的胃肠疾病死亡的时间模式与个人接触传播和中央源污染一致。在个人接触的情况下，个别船只的死亡时间模式将呈现倒U型，而在后一种情况下，首次死亡的发生率跨越船只将遵循倒U型模式，但是同一船只的死亡应该是集中在一起，只有个体潜伏期的差异。虽然无法从现有数据中衡量这些过程的相对重要性，但表格9和10中的信息表明个人接触传播是一种普遍趋势。表格9显示，从航行开始到首次死亡的平均间隔为17.1天，明显小于中央源假设预测的大约30天的间隔。志贺菌病的潜伏期范围为1至6天，平均为5天。31并且，死亡1和2之间以及2和3之间的平均间隔超过平均潜伏期，进一步对中央源解释提出了怀疑。此外，间隔的大小和下降趋势与通过接触传播的扩散一致。表格10显示，有2人以上死于胃肠疾病的船只中，一半的船只间死亡的平均间隔超过了6天的上限范围。然而，有10艘船只的平均间隔小于5天，因此不能排除中央源污染的情况。事实上，还存在着更复杂的过程，例如通过接触传播与中央源污染相结合的情况。