Demographic and Health Survey 2005
Moldova, 2005
Get MicrodataIdentification
MDA_2005_DHS_v01_M
Demographic and Health Survey 2005
Studiul Demografic si de Sanatate din Republica Moldova 2005
| Name | Country code |
|---|---|
| Moldova | MDA |
Demographic and Health Survey (standard) - DHS V
The Moldova Demographic and Health Survey 2005 is the first survey of its kind to be conducted in Moldava.
The survey obtained detailed information on fertility levels, abortion levels, marriage, sexual activity, fertility preferences, awareness and use of family planning methods, breastfeeding practices, nutritional status of women and young children, childhood mortality, maternal and child health, adult health, and awareness and behavior regarding HIV infection and other sexually transmitted diseases. Hemoglobin testing was conducted on women and children to detect the presence of anemia. Additional features of the 2005 MDHS include the collection of information on international emigration, language preference for reading printed media, and domestic violence.
The 2005 MDHS was carried out by the National Scientific and Applied Center for Preventive Medicine, hereafter called the National Center for Preventive Medicine (NCPM), of the Ministry of Health and Social Protection. ORC Macro provided technical assistance for the MDHS through the USAID-funded MEASURE DHS project. Local costs of the survey were also supported by USAID, with additional funds from the United Nations Children's Fund (UNICEF), the United Nations Population Fund (UNFPA), and in-kind contributions from the NCPM.
MAIN RESULTS
CHARACTERISTICS OF RESPONDENTS
Ethnicity and Religion. Most women and men in Moldova are of Moldovan ethnicity (77 percent and 76 percent, respectively), followed by Ukrainian (8-9 percent of women and men), Russian (6 percent of women and men), and Gagauzan (4-5 percent of women and men). Romanian and Bulgarian ethnicities account for 2 to 3 percent of women and men. The overwhelming majority of Moldovans, about 95 percent, report Orthodox Christianity as their religion.
Residence and Age. The majority of respondents, about 58 percent, live in rural areas. For both sexes, there are proportionally more respondents in age groups 15-19 and 45-49 (and also 45-54 for men), whereas the proportion of respondents in age groups 25-44 is relatively lower. This U-shaped age distribution reflects the aging baby boom cohort following World War II (the youngest of the baby boomers are now in their mid-40s), and their children who are now mostly in their teens and 20s. The smaller proportion of men and women in the middle age groups reflects the smaller cohorts following the baby boom generation and those preceding the generation of baby boomers' children. To some degree, it also reflects the disproportionately higher emigration of the working-age population.
Education. Women and men in Moldova are universally well educated, with virtually 100 percent having at least some secondary or higher education; 79 percent of women and 83 percent of men have only a secondary or secondary special education, and the remainder pursues a higher education. More women (21 percent) than men (16 percent) pursue higher education.
Language Preference. Among women, preferences for language of reading material are about equal for Moldovan (37 percent) and Russian (35 percent) languages. Among men, preference for Russian (39 percent) is higher than for Moldovan (25 percent). A substantial percentage of women and men prefer Moldovan and Russian equally (27 percent of women and 32 percent of men).
Living Conditions. Access to electricity is almost universal for households in Moldova. Ninety percent of the population has access to safe drinking water, with 86 percent in rural areas and 96 percent in urban areas. Seventy-seven percent of households in Moldova have adequate means of sanitary disposal, with 91 percent of households in urban areas and only 67 percent in rural areas.
Children's Living Arrangements. Compared with other countries in the region, Moldova has the highest proportion of children who do not live with their mother and/or father. Only about two-thirds (69 percent) of children under age 15 live with both parents. Fifteen percent live with just their mother although their father is alive, 5 percent live with just their father although their mother is alive, and 7 percent live with neither parent although they are both alive. Compared with living arrangements of children in 2000, the situation appears to have worsened.
FERTILITY
Fertility Levels and Trends. The total fertility rate (TFR) in Moldova is 1.7 births. This means that, on average, a woman in Moldova will give birth to 1.7 children by the end of her reproductive period. Overall, fertility rates have declined since independence in 1991. However, data indicate that fertility rates may have increased in recent years. For example, women of childbearing age have given birth to, on average, 1.4 children at the end of their childbearing years. This is slightly less than the total fertility rate (1.7), with the difference indicating that fertility in the past three years is slightly higher than the accumulation of births over the past 30 years.
Fertility Differentials. The TFR for rural areas (1.8 births) is higher than that for urban areas (1.5 births). Results show that this urban-rural difference in childbearing rates can be attributed almost exclusively to younger age groups.
CONTRACEPTION
Knowledge of Contraception. Knowledge of family planning is nearly universal, with 99 percent of all women age 15-49 knowing at least one modern method of family planning. Among all women, the male condom, IUD, pills, and withdrawal are the most widely known methods of family planning, with over 80 percent of all women saying they have heard of these methods. Female sterilization is known by two-thirds of women, while periodic abstinence (rhythm method) is recognized by almost six in ten women. Just over half of women have heard of the lactational amenorrhea method (LAM), while 40-50 percent of all women have heard of injectables, male sterilization, and foam/jelly. The least widely known methods are emergency contraception, diaphragm, and implants.
Use of Contraception. Sixty-eight percent of currently married women are using a family planning method to delay or stop childbearing. Most are using a modern method (44 percent of married women), while 24 percent use a traditional method of contraception. The IUD is the most widely used of the modern methods, being used by 25 percent of married women. The next most widely used method is withdrawal, used by 20 percent of married women. Male condoms are used by about 7 percent of women, especially younger women. Five percent of married women have been sterilized and 4 percent each are using the pill and periodic abstinence (rhythm method).
The results show that Moldovan women are adopting family planning at lower parities (i.e., when they have fewer children) than in the past. Among younger women (age 20-24), almost half (49 percent) used contraception before having any children, compared with only 12 percent of women age 45-49.
MATERNAL HEALTH
Antenatal Care and Delivery Care. Among women with a birth in the five years preceding the survey, almost all reported seeing a health professional at least once for antenatal care during their last pregnancy; nine in ten reported 4 or more antenatal care visits. Seven in ten women had their first antenatal care visit in the first trimester. In addition, virtually all births were delivered by a health professional, in a health facility. Results also show that the vast majority of women have timely checkups after delivering; 89 percent of all women received a medical checkup within two days of the birth, and another 6 percent within six weeks.
CHILD HEALTH
Childhood Mortality. The infant mortality rate for the 5-year period preceding the survey is 13 deaths per 1,000 live births, meaning that about 1 in 76 infants dies before the first birthday. The under-five mortality rate is almost the same with 14 deaths per 1,000 births. The near parity of these rates indicates that most all early childhood deaths take place during the first year of life. Comparison with official estimates of IMRs suggests that this rate has been improving over the past decade.
NUTRITION
Breastfeeding Practices. Breastfeeding is nearly universal in Moldova: 97 percent of children are breastfed. However the duration of breast-feeding is not long, exclusive breastfeeding is not widely practiced, and bottle-feeding is not uncommon. In terms of the duration of breastfeeding, data show that by age 12-15 months, well over half of children (59 percent) are no longer being breastfed. By age 20-23 months, almost all children have been weaned.
Exclusive breastfeeding is not widely practiced and supplementary feeding begins early: 57 percent of breastfed children less than 4 months are exclusively breastfed, and 46 percent under six months are exclusively breastfeed. The remaining breastfed children also consume plain water, water-based liquids or juice, other milk in addition to breast milk, and complimentary foods.
Bottle-feeding is fairly widespread in Moldova; almost one-third (29 percent) of infants under 4 months old are fed with a bottle with a nipple.
Nutritional Status of Children. At the national level, about 8 percent of children under age five are stunted (low height-for-age), while about 4 percent of children are wasted (low weight-forheight), and 4 percent are underweight (low weight-for-age).
HIV/AIDS KNOWLEDGE
Awareness of HIV/AIDS. Awareness of HIV/AIDS is almost universal among persons of reproductive age. Ninety-seven percent of men and women age 15-49 have heard of HIV/AIDS, but men are slightly better informed than women about specific ways to avoid contracting the disease: 81 percent of women and 89 percent of men indicate that the chances of getting the AIDS virus can be reduced by limiting sex to one faithful partner; 78 percent of women and 87 percent of men are aware that condoms can reduce the risk of contracting HIV during sexual intercourse; and 63 percent of women and 85 percent of men know that abstaining from sex reduces the chances of getting the disease. Seventy-six percent of women and 78 percent of men know that a healthy-looking person can have the AIDS virus.
Knowledge patterns between men and women are reversed for mother-to-child transmission of HIV: 68 percent of women compared with 53 percent of men know that HIV can be transmitted by breastfeeding; 86 percent of women and 79 percent of men know the disease can be transmitted from the mother to the child during pregnancy; and 82 percent of women and 76 percent of men know it can be transmitted during delivery.
HIV Testing. Thirty-six percent of women in Moldova have been tested for HIV at some time, compared with 30 percent of men. Thirty-four percent of women and 27 percent of men were tested and also received the results of their HIV test.
DOMESTIC VIOLENCE
Violence Since Age 15. MDHS data show that one-quarter of all women (27 percent) have experienced violence since they were age 15 and 13 percent experienced violence in the 12 months preceding the survey. The main perpetrators of violence against women are husbands (69 percent) and, to a lesser extent, fathers/stepfathers (14 percent), and mothers/stepmothers (7 percent).
Marital Violence. Twenty-three percent of ever-married women report having experienced emotional violence by husbands, 24 percent report physical violence, and 4 percent report sexual violence. Almost one-third (32 percent) of ever-married women report suffering emotional, physical, or sexual violence, while 3 percent have experienced all three forms of violence by their current or most recent husband.
The data further show that divorced or separated women are more than twice as likely as married women to have been abused emotionally, physically, and sexually, suggesting that the violence might have been a factor in the termination of their marriages.
EMIGRATION
In Moldova, and in post-Soviet states in general, large-scale labor emigration is an important demographic phenomenon that has a substantial negative impact on the population growth as well as on the social and economic structure of society.
Emigrant Households. Seventeen percent of households in Moldova have at least one former member who emigrated. This percentage is about the same in urban and rural households. The highest percentage of households with at least one emigrant is in the South region (21 percent) and the lowest is in Chisinau (13 percent).
Emigrant Characteristics. A slightly higher proportion of emigrants are males (52 percent, compared with 48 percent for women). However, in Chisinau and the South region, a slightly higher proportion of emigrants are females. The distribution of emigrants by age at emigration is similar for males and females. The most common age group for emigration is age 20-24 for both sexes. This age group accounts for roughly one-quarter of all emigrants (22 percent of females and 27 percent of males). Approximately three-quarters of all emigrants leave the country between age 15 and 39 (73 percent of females and 79 percent of males).
Sample survey data
- Household
- Women age 15-49
- Men age 15-49
Scope
The Moldova Demographic and Health Survey 2005 covers the following topics:
- Abortion
- Anemia Questions–Questions or testing assessing prevalence/severity of iron-def. anemia among women or children
- Anemia Testing
- Anthropometry
- Domestic Violence
- Full Pregnancy History–All surveys with the calendar and surveys that use DHS+ core questionnaire include a five-year calendar. Purpose to calculate abortion rates and neonatal rates if the calendar is not available.
- GPS/Georeferenced–Global Positioning System or Georeferenced Data
- HIV Behavior
- HIV Knowledge–Questions assess knowledge/sources of knowledge/ways to avoid HIV
- Iodine salt test
- Men's Survey
- Reproductive Calendar
- TB Questions
- Tobacco Use
- Women's Status–Questions: women's autonomy (household decisionmaking/free movement/access money) & Dom. violence
Coverage
National
The population covered by the 2007 UDHS is defined as the universe of all women age 15-49 in the total sample of households, and all men age 15-59 in a subsample of one-third of households, who were either usual residents of the households in the MDHS sample or visitors present in the household on the night before the survey were eligible to be interviewed in the survey.
Producers and sponsors
| Name | Affiliation |
|---|---|
| National Scientific and Applied Center for Preventive Medicine (NCPM) | Ministry of Health and Social Protection |
| Name | Role |
|---|---|
| ORC Macro | Technical assistance |
| Name | Role |
|---|---|
| United States Agency for International development | Main Funding |
| United Nations Children’s Fund | Additional Funding |
| United Nations Population Fund | Additional Funding |
| Name | Affiliation | Role |
|---|---|---|
| Moldovan National Scientific and Applied Centre for Preventive Medicine | NSACPM | In-Kind contribution |
Sampling
The 2005 Moldova Demographic and Health Survey is based on a representative probability sample of over 11,000 households. This sample was designed in such a manner as to allow separate urban and rural estimates for key population and health indicators, e.g., fertility, contraceptive prevalence, and infant mortality for children under five. Transnistria, the semiautonomous region in the eastern part of the country accounting for approximately 15 percent of Moldova's population, is not included in the sample.
The 2005 MDHS utilized a two-stage sample design. The first stage involved selecting a sample of cluster sectors from an updated master sampling frame constructed from the 2004 Moldova Population and Housing Census. A total of 400 clusters in Moldova were selected from the master sampling frame. Clusters for urban and rural domains (233 urban and 167 rural) were selected using systematic sampling with probabilities proportional to their size. The distribution of clusters between urban and rural domains is not proportional to the 2004 census distribution, and consequently neither is the final household distribution. The 2005 MDHS is, therefore, not a self-weighted household sample. A final weighting adjustment procedure was carried out to provide estimates at the national level.
A complete household listing operation was carried out from early April to late May 2005 in all of the selected clusters in order to provide a sampling frame for the second stage selection of households. The second stage selection involved the systematic selection of households from a complete listing of all households in each of the 400 clusters. The sample "take" in both urban and rural clusters was 30 households.
SAMPLE FRAME
Administratively, Moldova (West) is divided into three major geographical regions including North, Center, South regions and Chisinau municipality. For the purposes of conducting the 2004 Population and Housing Census, each geographical region was further subdivided into administrative areas called census sectors (CS). Each CS is classified as urban or rural. The population size of each CS, made available from the 2004 census, coupled with detailed cartographic information for each CS, comprise the master sample frame for the 2005 MDHS survey.
CHARACTERISTICS OF THE SAMPLE
The primary sampling unit (PSU), referred to as a "cluster" in the 2005 MDHS, is defined based on the list of CSs as demarcated in the 2004 census. The CS was a unit originally constructed to ensure a convenient census workload, and it also serves as a practical primary sampling unit for the 2005 MDHS.
The 2005 MDHS utilized a two-stage sample design. The primary sampling stage involved selecting a sample of 400 clusters from an updated master sampling frame from the 2004 census. The pre-classified urban and rural CSs were used to define the explicit strata for the purpose of cluster selection i.e., for Moldova (West) as a whole, a specified number of urban and rural CSs was selected independently. The second stage of sampling involved the systematic selection of households from an updated listing of all households in each of the selected clusters. A sample take of 30 households in each cluster was selected prior to data collection.
SAMPLE ALLOCATION AND SAMPLE SIZE
The target household sample size needed for the 2005 MDHS survey was estimated to be 12,000 selected households in the whole of Moldova (West). This number of households was expected to yield an adequate number of women of eligible age (approximately 8,100) to compute survey indicators, and an adequate number of children under five years (approximately 1,800) whose information would be collected from the women (or, in some cases, the child's caretaker). The estimated sample sizes are based on the levels of response resulting from the 2000 Moldova MICS, where both urban and rural households provided, on average, 0.7 women of eligible age. The average number of children under age five was approximately 0.1-0.2 per household.
The final recommended sample is one adjusted to collect information on an approximately equal number of children in each domain (see Table A.3 in the survey Final Report). A total of 400 clusters in Moldova (West) were selected from the sampling frame, including 233 urban and 167 rural clusters selected using systematic sampling with probabilities proportional to their size. Table A.3 shows the final distribution of selected households for the 2005 MDHS.
A total of 12,206 households were selected for the sample, of which 11,649 were occupied at the time of fieldwork. The main reason for the difference is that some of the dwelling units that were occupied during the household listing operation were either vacant or the household was away for an extended period at the time of interviewing. Of the occupied households, 95 percent were successfully interviewed.
In the households interviewed in the survey, a total of 7,826 eligible women age 15-49 were identified; interviews were completed with 7,440 of these women, yielding a response rate of 95 percent. In a subsample of one-third of households in the MDHS sample, a total of 2,897 eligible men were identified and interviews were completed with 2,508 of these men, yielding a male response rate of 87 percent. As is typically found in other surveys, the response rates are lower for the urban than for the rural sample, and lower among men than women.
The principal reason for nonresponse among both eligible women and men was the failure to find individuals at home despite repeated visits to the household.
Survey instrument
Three questionnaires were used for the 2005 MDHS: the Household Questionnaire, the Women's Questionnaire and the Men's Questionnaire. The contents of these questionnaires were based on model questionnaires developed by the MEASURE DHS program. Consultations with partners were held in Chisinau to obtain input from various national and international experts on a broad array of issues. Based on these consultations, the DHS model questionnaires were modified to reflect issues relevant in Moldova concerning population, women and children's health, family planning, and other health issues. After approval of the final content by the steering committee, these questionnaires were translated from English into Romanian and Russian.
a) The Household Questionnaire was used to list all the usual members and visitors in the selected households and to identify women and men who were eligible for the individual interview. Basic information was collected on the characteristics of each person listed, including their age, sex, education, and relationship to the head of the household. In addition, a separate listing and basic information on former household members who had emigrated abroad was collected. The Household Questionnaire was also designed to collect information on characteristics of the household's dwelling unit, such as the source of water, type of toilet facilities, materials used for the floor and roof of the house, ownership of various durable goods, etc. Finally, height and weight measurements, and the results of hemoglobin measurements for consenting women age 15-49 years and children age 6-59 months were recorded in the Household Questionnaire.
b) The Women's Questionnaire was used to collect information from all women age 15-49. These women were asked questions on the following topics:
- background characteristics (education, residential history, media exposure, etc.);
- reproductive history;
- knowledge and use of family planning methods;
- fertility preferences;
- antenatal and delivery care;
- breastfeeding and infant feeding practices;
- vaccinations and childhood illnesses;
- marriage and sexual activity;
- woman's work and husband's background characteristics;
- infant and child feeding practices;
- childhood mortality; and
- awareness and behavior about AIDS and other sexually transmitted infections (STIs).
The Women's Questionnaire had a number of important additions to the DHS model questionnaire. First, a series of questions were incorporated to obtain information on women's experience of domestic violence. These questions were administered to one woman per household. In households with two or more eligible women, special procedures were followed in order to ensure that there was random selection of the women to be interviewed with these questions. Another addition to the Women's Questionnaire was a vaccination module for each child under the age of five years to be completed at the local health clinic. According to child health experts, immunization information is more frequently kept at the health clinic than on a health card in the mother's possession. The purpose of this module was, therefore, to collect information on immunizations from the local health clinic in addition to that collected during the woman's interview. The vaccination module provides better quality immunization indicators because information gathered during the interview is augmented with information from the local health clinic.
Closely related to the Women's Questionnaire is the caretaker module. This separate module contains the same set of child health questions as those in the Women's Questionnaire regarding immunizations, childhood illnesses such as fever and diarrhea, and nutrition. The purpose of this module is to gather information on children under age 5 years whose mother does not live in the selected household or is not available to be interviewed. This is important because of the large number of young women emigrating and leaving behind a significant number of children to be cared for by another caretaker.
c) The Men's Questionnaire was administered to all men age 15-59 living in every third household in the MDHS sample. The Men's Questionnaire collected much of the same information found in the Women's Questionnaire, but was shorter because it did not contain questions on reproductive history, maternal and child health, nutrition, and domestic violence.
All aspects of the MDHS data collection were pretested in April 2005. Twenty-six people with medical backgrounds and other specialties were trained for two weeks and then dispatched to conduct interviews in Romanian and Russian, carry out hemoglobin testing, and take height and weight measurements. Over 200 households in urban and rural areas were interviewed in the pretest. The lessons learned from the pretest were used to finalize the survey instruments and logistical arrangements. The major changes as a result of the pretest were incorporation of the caretaker module described above and soliciting the assistance of local medical personnel in each cluster to introduce field personnel to selected households. The latter served to improve household response rates, especially in urban areas.
Data collection
| Start | End |
|---|---|
| 2005-06 | 2005-08 |
| Name | Affiliation |
|---|---|
| National Scientific and Applied Center for Preventive Medicine | MOH |
The most experienced participants, namely those who had participated in the pretest and those who did very well in the main survey training, were selected to be supervisors and editors. Senior staff from the NCPM coordinated and supervised all aspects of fieldwork activities. ORC Macro followed fieldwork progress by receiving approximately every two weeks a standard set of quality control tables generated from the most recent accumulation of data.
Training of fieldwork staff began on May 16, 2005 in Chisinau and lasted three weeks. A total of 96 training participants were trained as field staff supervisors, editors, and interviewers. In addition, 12 data entry operators and two office editors attended the training. All field staff were also trained as technicians to conduct hemoglobin testing. Most of the participants had a medical background and several had prior experience as interviewers for the UNICEF Multiple Indicator Survey (MICS 2000). Interviewer training was conducted mostly in Romanian by senior staff from NCPM with technical input from ORC Macro. In addition, resource persons from other agencies made presentations on Moldova's program for family planning, maternal and child health, HIV/AIDS, and gender issues including domestic violence. All participants were trained on interviewing techniques and the contents of the MDHS questionnaires. The training was conducted following the standard DHS training procedures, including class presentations, mock interviews, and written tests. All of the participants were trained on how to complete the Household Questionnaire, the Women's Questionnaire, and the Men's Questionnaire. In addition to in-class training, participants practiced taking anthropometric measures and conducting anemia testing on consenting women and children at local health clinics. They also spent several days in practice field sites interviewing in both languages and carrying out all fieldwork activities. While both female and male interviewers interviewed respondents for the Household Questionnaire, only female interviewers interviewed respondents eligible for the Women's Questionnaire and only male interviewers for the Men's Questionnaire. Participants selected as field supervisors and editors were given an additional two days of training on how to supervise fieldwork and edit questionnaires.
Fifteen teams were organized for fieldwork. Each team was made up of a field supervisor, an editor, three female interviewers, and one male interviewer. The field staff was selected on the basis of assessments of in-class participation, field practice, fluency in languages, and capacity to conduct interviews as well as anemia testing. The most experienced participants, namely those who had participated in the pretest and those who did very well in the main survey training, were selected to be supervisors and editors.
Senior staff from the NCPM coordinated and supervised all aspects of fieldwork activities. ORC Macro followed fieldwork progress by receiving approximately every two weeks a standard set of quality control tables generated from the most recent accumulation of data. Data collection took place for just over two months, from June 13 to August 18, 2005. On average, each team completed one cluster over two full days, taking advantage of early mornings and late evenings to find respondents at home.
Data processing
The processing of the MDHS results began shortly after the fieldwork commenced. Completed questionnaires were returned weekly from the field to the NCPM headquarters in Chisinau, where they were entered and edited by data processing personnel who were specially trained for this task. Data were entered using CSPro, a program specially developed for use in DHS surveys. All data were entered twice (100 percent verification). The concurrent processing of the data with ongoing data collection was a distinct advantage for data quality since NCPM had the opportunity to advise field teams of problems detected during the data entry. The data entry and editing phase of the survey was completed in late August 2005.
Data appraisal
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 MDHS sample is the result of a multistage stratified design, and, consequently, it was necessary to use more complex formulae. The computer software used to calculate sampling errors for the 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 MDHS, there were 400 non-empty clusters (PSUs). Hence, 400 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 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 the three regions (North, Center, and South) and for Chisanau. 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.7 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 subpopulations. For example, for the variable contraceptive use for 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 1.1 percent, 1.5 percent, and 1.5 percent, respectively.
The confidence interval (e.g., as calculated for contraceptive use for currently married women age 15-49) can be interpreted as follows: the overall national sample proportion is .678 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. .678±2(0.007). There is a high probability (95 percent) that the true average proportion of contraceptive use for currently married women age 15 to 49 is between .663 and .692.
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 MDHS to minimize this type of error, non-sampling errors are impossible to avoid and difficult to evaluate statistically.
Data Access
| Name | Affiliation | URL | |
|---|---|---|---|
| MEASURE DHS | ICF International | www.measuredhs.com | archive@measuredhs.com |
National Scientific and Applied Center for Preventive Medicine (NCPM) [Moldova] and ORC Macro. 2006. Moldova Demographic and Health Survey 2005. Calverton, Maryland: National Scientific and Applied Center for Preventive Medicine of the Ministry of Health and Social Protection and ORC Macro.
Disclaimer and copyrights
The user of the data acknowledges that the original collector of the data, the authorized distributor of the data, and the relevant funding agency bear no responsibility for use of the data or for interpretations or inferences based upon such uses.
Contacts
| Name | URL | |
|---|---|---|
| General Inquiries | info@measuredhs.com | www.measuredhs.com |
| Data and Data Related Resources | archive@measuredhs.com | www.measuredhs.com |
Metadata production
DDI_MDA_2005_DHS_v01_M
| Name | Role |
|---|---|
| World Bank, Development Economics Data Group | Generation of DDI documentation |
2012-05-15