Demographic and Health Survey 2000 - Malawi

Abstract
---------------------------

The 2000 Malawi Demographic and Health Survey (MDHS) is a nationally represen­tative sample survey covering 14,213 house­holds, 13,220 women age 15-49, and 3,092 men age 15-54. The 2000 MDHS is similar, but much expanded in size and scope, to the 1992 MDHS. The survey was designed to provide information on fertility trends, family planning knowledge and use, early childhood mortality, various indicators of maternal and child health and nutrition, HIV/AIDS, adult and maternal mortality, and malaria control programme indicators. Unlike earlier surveys in Malawi, the 2000 MDHS sample was sufficiently large to allow for estimates of certain indicators to be produced for 11 districts in addition to esti­mates for national, regional, and urban-rural domains. Twenty-two mobile survey teams, trained and supervised by the National Statisti­cal Office, conducted the survey from July to November 2000.

The principal aim of the 2000 MDHS project is to provide up-to-date information on fertility and childhood mortality levels, nuptiality, fertility preferences, awareness and use of family planning methods, use of maternal and child health services, and knowledge and behaviours related to HIV/AIDS and other sexually transmitted infections. It was designed as a follow-on to the 1992 MDHS survey, a national-level survey of similar scope. The 2000 MDHS survey also strived to collect data that would be comparable to those collected under the international Multiple Indicator Cluster Survey (MICS), sponsored by UNICEF.

In broad terms, the 2000 MDHS survey aimed to :
- Assess trends in Malawi's demographic indicators-principally, fertility and mortality
- Assist in the evaluation of Malawi's health, population, and nutrition programmes
- Advance survey methodology in Malawi and contribute to national and international databases. In more specific terms, the 2000 MDHS survey was designed to provide data on the family planning and fertility behaviour of the Malawian population and to thereby enable policymakers to evaluate and enhance family planning initiatives in the country.
- Measure changes in fertility and contraceptive prevalence and at the same time, study the factors that affect these changes, such as marriage patterns, desire for children, availability of contraception, breastfeeding habits, and important social and economic factors.
- Examine basic indicators of maternal and child health and welfare in Malawi, including nutritional status, use of antenatal and maternity services, treatment of recent episodes of childhood illness, and use of immunisation services. A particular emphasis was placed on the area of malaria programmes, including prevention activities and treatment of episodes of fever.
- Describe levels and patterns of knowledge and behaviour related to the prevention of HIV/AIDS and other sexually transmitted infections.
- Measure the level of adult and maternal mortality at the national level.
- Assess the status of women in the country.

SUMMARY OF FINDINGS

- FERTILITY Fertility Decline. The 2000 MDHS data indicate that there has been a modest decline in fertility since the 1992 MDHS. Large Fertility Differentials. Fertility levels remain high in Malawi, especially in rural parts of the country. The total fertility rate among rural women is 6.7 births per woman compared with 4.5 births in urban areas. Childbearing at Young Ages. One-third of adolescent females (age 15-19) have either already had a child or are currently pregnant.

- FAMILY PLANNING Increasing Use of Contraception. A principle cause of the fertility decline in Malawi is the steady increase in contraceptive use over the last decade.
Changing Method Mix. Currently, the most widely used methods among married women are injectable contraceptives (16 per­cent), female sterilisation (5 percent), and the pill (3 percent). Source of Family Planning Methods. The survey results show that government-run facilities remain the major source for contra­ceptives in Malawi-providing family planning methods to 68 percent of the current users.

- CHILD HEALTH AND SURVIVAL Progress in Reducing Early Childhood Mortality. The 2000 MDHS data indicate that mortality of children under age 5 has declined since the early 1990s.
Childhood Vaccination Coverage Declines. The 2000 MDHS results show that 70 percent of children age 12-23 months are fully vaccinated.
Improved Breastfeeding Practices. The 2000 MDHS results show that exclusive breast-feeding of children under 4 months of age has increased to 63 percent from only 3 percent in the 1992 MDHS. Nutritional Status of Children. The results show no appreciable change in the nutritional status of children in Malawi since 1992; still, nearly half (49 percent) of the children under age five are chronically mal­nourished or stunted in their growth.

- MALARIA CONTROL PROGRAMME INDICATORS Bednets. The use of insecticide-treated bednets (mosquito nets) is a primary health intervention proven to reduce malaria transmission.
Treatment of Fever in Children Under Age Five. The survey found that 42 percent of children under age five had a fever in the two weeks preceding the survey.

- WOMEN'S HEALTH Maternal Health Care. The survey findings indicate that use of antenatal services remains high in Malawi. Constraints to Use of Health Services. Women in the 2000 MDHS were asked whether certain circumstances constrain their access to and use of health services for themselves.
Rising Maternal Mortality. The survey collected data allowing measurement of maternal mortality. For the period 1994-2000, the maternal mortality ratio was estimated at 1,120 maternal deaths per 100,000 live births. This represents a rise from 620 maternal deaths per 100,000 estimated from the 1992 MDHS for the period 1986-1992.

- HIV/AIDS Impact of the Epidemic on Adult Mortality. All-cause mortality has risen by 76 percent among men and 74 percent among women age 15-49 during the 1990s. The age patterns of the increase are consistent with causes related to HIV/AIDS.
Improved Knowledge of AIDS Preven­tion Methods. The 2000 MDHS results indi­cate that practical AIDS prevention knowledge has improved since the 1996 MKAPH survey.
Condom Use. One of the main objectives of the National AIDS Control Programme is to encourage consistent and correct use of con­doms, especially in high-risk sexual encounters. The
HIV-testing Experience. The 2000 MDHS data show that 9 percent of women and 15 percent of men have been tested for HIV. However, more than 70 percent of both men and women, while not yet tested, said that they would like to be tested.

Geographic coverage
---------------------------

National

Analysis unit
---------------------------

- Household
- Women age 15-49
- Men age 15-54

Universe
---------------------------

The population covered by the 2000 MDHS is defined as the universe of all women age 15­-49 in malawi and all men age 15-54 living in the household.

Kind of data
---------------------------

Sample survey data

Sampling procedure
---------------------------

A major objective of the 2000 MDHS sample design was to provide independent estimates with acceptable precision for important population and health indicators. The sample was designed to provide these estimates for different domains, including estimates for the country, for urban and rural areas, for each of the three regions, and for eleven selected districts (each as a separate domain). The selected districts were chosen based on the size of the district (the five largest) and for programmatic importance.

The population covered by the 2000 MDHS was all women age 15-49 living in the selected households. The initial target sample was 14,000 completed eligible women interviews, and the final sample was 13,220 completed interviews. Information on sampling errors for five selected variables from the MDHS 1992 was used to help determine the most efficient allocation of the target number of interviews by domain with a minimum allocation of 900 for each of the 11 district domain. Based on this objective and some adjustments to ensure that the sample size requirements for each domain were met, the target number of completed interviews was distributed by districts.

SAMPLE FRAME

Based on the 1998 census frame, the National Statistical Office developed an updated preliminary master sample to use during the intercensal period. In order to maintain an integrated household survey approach for future household surveys, it was decided that the 2000 MDHS sample should use the preliminary master sample as the sample frame. The 2000 MDHS sample of enumeration areas (EAs) is thus a sub-sample of NSO's preliminary master sample. NSO's preliminary master sample of EAs is stratified according to district designation and, within districts, by urban-rural designation.1 Since one objective of the master sample is to permit estimation at the district level, the total number of EAs per district was not allocated proportional to population size of the district. Instead, a minimum of 24 EAs were allocated to each district, with certain districts being allocated more EAs based on size and programmatic interest. For instance, Lilongwe and Blantyre districts were each allocated 48 EAs in the master sample. The master sample includes a total of 816 EAs out of the 9,213 EAs established in the 1998 census. A small number of EAs located in national parks and forest areas (representing less than 1 percent of the population of Malawi) were excluded from the master sample.

The design features and stratification of the master sample are implicit in the 2000 MDHS and all other subsamples.

SAMPLE SELECTION

Based on the 2000 MDHS sample design objectives of 36 EAs per "emphasis" district and adequate urban and rural representation, a total of 560 EAs were selected from the master sample: 489 in rural and 71 in urban areas. All districts are represented in the sample, but the sample is specifically designed to allow for estimation of certain parameters for the following "oversampled" districts: Lilongwe, Blantyre, Karonga, Mzimba, Kasungu, Salima, Mangochi, Machinga, Zomba, Thyolo, and Mulanje. A simple systematic sample of EAs was implemented district by district; Before the final household selection, a complete household listing operation was completed for each selected EA. Based on these household lists, the household selection was then implemented to maintain a self-weighted sample in each domain but the sampling rates differ between districts. Therefore, the total 2000 MDHS sample is weighted, and a final weighting adjustment is required to provide national estimates.

All women age 15-49 were targeted for interview in the selected households. Every fourth household was identified for inclusion in the male survey; in those households, all men age 15-54 were identified and considered eligible for individual interview.

Mode of data collection
---------------------------

Face-to-face

Research instrument
---------------------------

Three types of questionnaires were used in the 2000 MDHS survey: a) the Household Questionnaire, b) the Women's Questionnaire, and c) the Men's Questionnaire. The contents of the questionnaires were based on the MEASURE DHS+ model. A series of meetings were held with policy experts, programme managers, and other professionals in Malawi to review, adapt, and revise the questionnaires. This process culminated in English-version questionnaires that were then translated into Chichewa and Tumbuka.

a) The Household Questionnaire was used to list all of the usual members and visitors in the selected households1. Basic information on each person listed was collected, including age, sex, education, and relationship to the head of the household. The main purpose of the Household Questionnaire was to identify all of the eligible women (age 15-49) and men (age 15-54) for individual interviews. In addition, information was collected about characteristics of the household, such as the source of water, type of toilet facilities, materials used to construct the household's dwelling, and ownership of various consumer goods. Data on child labour practises, use of bednets (mosquito nets), and nutritional status of children and women were also collected in the Household Questionnaire.

b) The Women's Questionnaire was used to collect information from women age 15-49 and included questions on the following topics:
- Background characteristics (age, education, religion, etc.)
- Reproductive history (to arrive at fertility and childhood mortality rates)
- Knowledge and use of family planning methods
- Antenatal and delivery care
- Infant feeding practises, including patterns of breastfeeding
- Childhood vaccinations
- Recent episodes of childhood illness and responses to illness, especially recent fevers
- Marriage and sexual activity
- Fertility preferences
- Woman's status and decisionmaking
- Mortality of adults, including maternal mortality
- AIDS-related knowledge, attitudes, and behaviour

c) The Men's Questionnaire covered many of the same topics but excluded the detailed reproductive history and sections dealing with maternal and child health and adult and maternal mortality. The Men's questionnaire is consequently much shorter than the Women's Questionnaire.

The questionnaires were pretested in February 2000 in Mzimba, Ntcheu, and Blantyre City. More than 200 interviews were conducted over a one-week period. The questionnaires were produced in three language versions: Chichewa, Tumbuka, and English. However, interviews could be conducted in any of the languages spoken in Malawi if the respondent was not fluent in one of these three languages. Adjustments in language and content were made to the questionnaires based on the lessons drawn from the pretest interviews.

Cleaning operations
---------------------------

Complete, field-edited questionnaires were brought to the NSO headquarters in Zomba after collection during supervisory visits by NSO senior staff. Data entry began one week after data collection started and was completed in December 2000. Office editing, coding of open-ended questions, and editing based on computer identified inconsistencies in the data continued into January 2001. The questionnaires were entered, verified, and edited using a new version of ISSA (Integrated System for Survey Analysis) adapted by ORC Macro and the U.S. Bureau of Census for integrated use in censuses and surveys.

Response rate
---------------------------

A total of 15,421 households were selected in the MDHS sample, of which 14,352 were occupied. Of the occupied households, 14,213 were interviewed, yielding a household response rate of 99 percent. The household response rate was slightly higher in rural areas.

Within the interviewed households, 13,538 eligible women age 15-49 were identified, of which 13,220 were interviewed. The individual women's response rate to the 2000 MDHS survey was 98 percent. In the one-in-four subsample of households, 3,377 men age 15-54 were identified, of which 3,092 men were interviewed, giving a response rate of 92 percent. The main reason for nonresponse among both eligible men and women was the failure to find them at home despite repeated visits to the household. It is typical for male response rates to be lower than female response rates because men are more frequently absent from the household. Response rates for women were not influenced by urban-rural residence, but men's response rates were significantly better in rural areas than in urban areas.

In comparing response rates from the 1992 MDHS survey and the 2000 MDHS survey, the more recent survey performed slightly better. The women's response rate rose from 97 to 98 percent, and the men's response rate increased from 89 to 92 percent.

Sampling error estimates
---------------------------

Sampling errors, on the other hand, can be evaluated statistically. The sample of respondents selected in the 2000 MDHS is only one of many samples that could have been selected from the same population, using the same design and expected size. Each of these samples would yield results that differ somewhat from the results of the actual sample selected. Sampling errors are a measure of the variability between all possible samples. Although the degree of variability is not known exactly, it can be estimated from the survey results.

A sampling error is usually measured in terms of the standard error for a particular statistic (mean, percentage, etc.), which is the square root of the variance. The standard error can be used to calculate confidence intervals within which the true value for the population can reasonably be assumed to fall. For example, for any given statistic calculated from a sample survey, the value of that statistic will fall within a range of plus or minus two times the standard error of that statistic in 95 percent of all possible samples of identical size and design.

If the sample of respondents had been selected as a simple random sample, it would have been possible to use straightforward formulas for calculating sampling errors. However, the 2000 MDHS sample is the result of a multi-stage stratified design, and, consequently, it was necessary to use more complex formulae. The computer software used to calculate sampling errors for the 2000 MDHS is the ISSA Sampling Error Module (ISSAS). This module used the Taylor linearization method of variance estimation for survey estimates that are means or proportions. The Jacknife repeated replication method is used for variance estimation of more complex statistics such as fertility and mortality rates.

The Jacknife repeated replication method derives estimates of complex rates from each of several replications of the parent sample, and calculates standard errors for these estimates using simple formulae. Each replication considers all but one clusters in the calculation of the estimates. Pseudo-independent replications are thus created. In the 2000 MDHS, there were 559 non-empty clusters (one cluster contained no eligible women). Hence, 559 replications were created.

In addition to the standard error, ISSAS computes the design effect (DEFT) for each estimate, which is defined as the ratio between the standard error using the given sample design and the standard error that would result if a simple random sample had been used. A DEFT value of 1.0 indicates that the sample design is as efficient as a simple random sample, while a value greater than 1.0 indicates the increase in the sampling error due to the use of a more complex and less statistically efficient design. ISSAS also computes the relative error and confidence limits for the estimates.

Sampling errors for the 2000 MDHS are calculated for selected variables considered to be of primary interest. The results are presented in an appendix of the Final Report for the country as a whole, for urban and rural areas, for north, central and south regions, and for each of 11 over-sampled district plus the rest of the country. For each variable, the type of statistic (mean, proportion, or rate) and the base population are given in Table B.1 of the Final Report. Tables B.2 to B.18 present the value of the statistic (R), its standard error (SE), the number of unweighted (N) and weighted (WN) cases, the design effect (DEFT), the relative standard error (SE/R), and the 95 percent confidence limits (R±2SE), for each variable. The DEFT is considered undefined when the standard error considering simple random sample is zero (when the estimate is close to 0 or 1).

In general, the relative standard error for most estimates for the country as a whole is small, except for estimates of very small proportions. There are some differentials in the relative standard error for the estimates of sub-populations. For example, for the variable contraceptive use among currently married women age 15-49, the relative standard errors as a percent of the estimated mean for the whole country, for urban areas, and for rural areas are 2.2 percent, 4.7 percent, and 2.3 percent, respectively.

The confidence interval (e.g., as calculated for contraceptive use among currently married women age 15-49) can be interpreted as follows: the overall national sample proportion is 0.306 and its standard error is 0.007. Therefore, to obtain the 95 percent confidence limits, one adds and subtracts twice the standard error to the sample estimate, i.e. 0.306±2(0.007). There is a high probability (95 percent) that the true average proportion of contraceptive use among currently married women age 15 to 49 is between 0.293 and 0.320.

Data appraisal
---------------------------

Nonsampling errors are the results of mistakes made in implementing data collection and data processing, such as failure to locate and interview the correct household, misunderstanding of the questions on the part of either the interviewer or the respondent, and data entry errors. Although numerous efforts were made during the implementation of the 2000 MDHS to minimize this type of error, nonsampling errors are impossible to avoid and difficult to evaluate statistically.

摘要
---------------------------
2000年马拉维人口与健康状况调查（MDHS）是一项全国代表性样本调查，涵盖了14,213户家庭，13,220名15-49岁的女性，以及3,092名15-54岁的男性。2000年MDHS在规模和范围上与1992年MDHS相似，但规模更大。该调查旨在提供有关生育趋势、计划生育知识及使用情况、婴幼儿死亡率、母婴健康与营养的各种指标、HIV/AIDS、成人及孕产妇死亡率以及疟疾控制项目指标的信息。与马拉维早期调查不同，2000年MDHS样本量足够大，除了提供全国、区域及城乡领域的估计值外，还可为11个地区提供某些指标的估计值。22个移动调查团队由国家统计局培训并监督，于2000年7月至11月进行调查。

2000年MDHS项目的主要目标是提供有关生育和儿童死亡率水平、婚姻状况、生育偏好、计划生育方法的认识和使用、母婴健康服务的使用、与HIV/AIDS及其他性传播感染相关的知识和行为等方面的最新信息。该调查被设计为1992年MDHS调查的后续调查，MDHS是一项类似范围的国家级调查。2000年MDHS调查还力求收集与国际联合国儿童基金会（UNICEF）赞助的多个指标集群调查（MICS）可比的数据。

总体而言，2000年MDHS调查旨在：
- 评估马拉维人口指标（主要是生育和死亡率）的趋势
- 协助评估马拉维的健康、人口和营养计划
- 推进马拉维的调查方法，并为国家和国际数据库做出贡献。
- 提供有关马拉维人口计划生育和生育行为的数据，从而使政策制定者能够评估和加强国家的计划生育倡议。
- 衡量生育和避孕普及率的变化，同时研究影响这些变化的因素，如婚姻模式、生育愿望、避孕药的可用性、母乳喂养习惯以及重要的社会经济因素。
- 检查马拉维母婴健康和福利的基本指标，包括营养状况、产前和分娩服务的使用、近期儿童疾病的治疗以及疫苗接种服务的使用。特别强调疟疾项目领域，包括预防活动和发热病例的治疗。
- 描述与HIV/AIDS及其他性传播感染的预防相关的知识和行为水平。
- 衡量全国成人及孕产妇死亡率水平。
- 评估该国妇女的地位。

结果摘要
---------------------------
- 生育率：生育率有所下降。2000年MDHS数据显示，自1992年MDHS以来，生育率有所下降。生育率差异很大。马拉维的生育率水平仍然很高，尤其是在农村地区。农村女性的总和生育率为每名女性6.7个出生，而城市地区为每名女性4.5个出生。
- 计划生育：避孕药使用率有所增加。马拉维生育率下降的主要原因是过去十年避孕药使用率的稳步上升。
- 儿童健康和存活率：降低婴幼儿死亡率方面取得进展。2000年MDHS数据显示，自20世纪90年代初以来，5岁以下儿童的死亡率有所下降。
- 疟疾控制项目指标：蚊帐的使用。使用经杀虫剂处理的蚊帐（蚊帐）是一种经过证实的公共卫生干预措施，可减少疟疾的传播。
- 妇女健康：孕产妇保健。调查结果指出，马拉维孕产妇保健服务的使用率仍然很高。
- HIV/AIDS：流行对成人死亡率的影响。20世纪90年代，15-49岁男性和女性的全因死亡率分别上升了76%和74%，其年龄模式与HIV/AIDS相关的原因一致。

地理覆盖范围
---------------------------
全国
分析单位
---------------------------
- 家庭
- 15-49岁的女性
- 15-54岁的男性

总体
---------------------------
2000年MDHS的覆盖人口定义为马拉维所有15-49岁的女性和所有居住在选定家庭中的15-54岁的男性。
数据类型
---------------------------
样本调查数据
抽样程序
---------------------------
2000年MDHS样本设计的主要目标是提供独立估计值，以可接受的精度提供重要的人口和健康指标。样本设计旨在为不同的领域提供这些估计值，包括为国家、城市和农村地区、三个地区中的每一个以及11个选定地区（每个作为一个单独的领域）提供估计值。

人口覆盖范围
---------------------------
2000年MDHS的人口覆盖范围为所有15-49岁的女性和所有居住在选定家庭中的15-54岁的男性。
数据类型
---------------------------
样本调查数据
抽样程序
---------------------------
2000年MDHS样本设计的主要目标是提供独立估计值，以可接受的精度提供重要的人口和健康指标。样本设计旨在为不同的领域提供这些估计值，包括为国家、城市和农村地区、三个地区中的每一个以及11个选定地区（每个作为一个单独的领域）提供估计值。

抽样框架
---------------------------
基于1998年人口普查框架，国家统计局开发了在人口普查期间使用的更新的初步主样本。为了保持未来家庭调查的综合家庭调查方法，决定2000年MDHS样本应使用初步主样本作为抽样框架。因此，2000年MDHS的抽样区域（EA）是国家统计局初步主样本的子样本。

抽样选择
---------------------------
基于2000年MDHS样本设计的目标，为每个“重点”地区提供36个EA，并确保城市和农村地区有足够的代表性，从主样本中选择了560个EA：489个在农村地区，71个在城市地区。

数据收集方式
---------------------------
面对面
研究工具
---------------------------
2000年MDHS调查中使用了三种类型的问卷：a）家庭问卷，b）女性问卷，c）男性问卷。问卷的内容基于MEASURE DHS+模型。与政策专家、项目经理和其他专业人士在马拉维举行了多次会议，以审查、调整和修改问卷。这一过程最终导致了英文版本的问卷，然后被翻译成奇切瓦语和图姆布卡语。

数据清洗操作
---------------------------
在数据收集期间，通过国家统计局高级人员的监督访问，将收集到的完整、现场编辑的问卷带到索莫巴的国家统计局总部。数据录入在数据收集开始后一周开始，并于2000年12月完成。办公室编辑、开放式问题的编码以及基于计算机识别的数据不一致的编辑一直持续到2001年1月。使用ORC Macro和美国人口普查局为综合用于人口普查和调查而改编的新版本ISSA（综合调查分析系统）输入、验证和编辑问卷。

响应率
---------------------------
在MDHS样本中选择了15,421个家庭，其中14,352个被占用。在被占用的家庭中，有14,213个被访问，家庭响应率为99%。农村地区的家庭响应率略高。

在访问的家庭中，确定了13,538名符合条件的15-49岁女性，其中13,220名被访问。2000年MDHS调查的女性个人响应率为98%。在四分之一子样本的家庭中，确定了3,377名15-54岁的男性，其中3,092名男性被访问，响应率为92%。合格男性和女性未响应的主要原因是在多次访问家庭后未能找到他们。男性响应率通常低于女性响应率，因为男性更频繁地不在家庭中。女性的响应率不受城乡居住的影响，而男性的响应率在乡村地区明显优于城市地区。

在比较1992年MDHS调查和2000年MDHS调查的响应率时，较近的调查表现略好。女性的响应率从97%上升到98%，男性的响应率从89%上升到92%。

抽样误差估计
---------------------------
抽样误差可以从统计上进行评估。2000年MDHS的受访者样本只是从同一人口中、使用相同的设计和预期规模可能选出的许多样本之一。每个这些样本都会产生与实际选出的样本的结果略有不同的结果。抽样误差是衡量所有可能样本之间差异的一个指标。尽管这种差异的程度无法确切知道，但它可以从调查结果中估计出来。

抽样误差通常用特定统计量（平均值、百分比等）的标准误差来衡量，这是方差的平方根。标准误差可用于计算置信区间，其中可以合理地假设人口的真实值将落在该区间内。例如，对于从样本调查中计算出的任何给定统计量，该统计量的值将在95%的所有可能样本的相同大小和设计中，落在加减两倍标准误差的范围内。

如果受访者样本被选为简单随机样本，则可以使用简单的公式来计算抽样误差。然而，2000年MDHS样本是多层分层设计的结果，因此有必要使用更复杂的公式。用于计算2000年MDHS抽样误差的计算机软件是ISSA抽样误差模块（ISSAS）。该模块使用泰勒线性化方法进行方差估计，用于调查估计的均值或比例。使用Jackknife重复复制方法对更复杂的统计量（如生育率和死亡率）进行方差估计。

除了标准误差之外，ISSAS还计算每个估计值的设计效应（DEFT），该值定义为使用给定样本设计计算的标准误差与使用简单随机样本将产生标准误差之间的比率。DEFT值为1.0表示样本设计与简单随机样本一样有效，而大于1.0的值表示由于使用更复杂且统计效率较低的样本设计而增加的抽样误差。

ISSAS还计算估计的相对误差和置信限。

2000年MDHS的抽样误差是为选定的一些变量计算的，这些变量被认为是最重要的。结果在最终报告的附录中呈现，涵盖整个国家、城市和农村地区、北部、中部和南部地区以及每个11个超抽样地区加上该国其余地区。对于每个变量，统计量的类型（平均值、比例或比率）和基数人口在最终报告的表B.1中给出。表B.2至B.18呈现了统计量的值（R）、其标准误差（SE）、未加权（N）和加权（WN）案例的数量、设计效应（DEFT）、相对标准误差（SE/R）以及每个变量的95%置信限（R±2SE）。当考虑简单随机样本的标准误差为零时（当估计值接近0或1时），DEFT被视为未定义。

一般来说，大多数国家整体估计的相对标准误差都很小，除了非常小比例的估计值。对于子人口估计值的相对标准误差存在一些差异。例如，对于目前已婚15-49岁女性的避孕药使用这一变量，整个国家、城市地区和农村地区的相对标准误差分别占估计平均值的2.2%、4.7%和2.3%。

置信区间（例如，对于目前已婚15-49岁女性的避孕药使用计算）可以这样解释：整体国家样本比例是0.306，其标准误差是0.007。因此，要获得95%的置信限，需要将样本估计值加减两倍的标准误差，即0.306±2(0.007)。有很高的概率（95%）认为，目前15至49岁已婚女性的真实避孕药使用平均比例在0.293和0.320之间。

数据评估
---------------------------
非抽样误差是由于在数据收集和处理过程中出现的错误而产生的结果，例如未能找到并采访正确的家庭、采访者或受访者对问题的误解以及数据录入错误。尽管在实施2000年MDHS期间做出了许多努力以最大限度地减少此类错误，但非抽样误差无法避免且难以进行统计分析。