Cambodia Demographic Health Survey in 2005
Cambodia, 2005 - 2006
Get MicrodataIdentification
KHM-NIS-CDHS-2005-v01
Cambodia Demographic Health Survey in 2005
Angket Sokpheap Neng Brocheasas Ney Kampuchea Chhnam 2005
| Name | Country code |
|---|---|
| Cambodia | KHM |
Demographic and Health Survey [hh/dhs]
Cambodia Demographic Health Survey in 2005 (CDHS) was conducted by the National Instutute of Statistics (NIS) in 2005. MEASURE DHS is a five-year project to assist institutions in collecting and analyzing data needed to plan, monitor, and evaluate population, health, and nutrition programs. and that is the second survey of this type conducted successfully in Cambodia.
The 2005 Cambodia Demographic and Health Survey (CDHS) is the second nationally representative survey conducted in Cambodia on population and health issues. It uses the same methodology as its predecessor, the 2000 Cambodia Demographic and Health Survey, allowing policymakers to use the two surveys to assess trends over time. The primary objective of the CDHS is to provide the Ministry of Health, Ministry of Planning (MOP), and other relevant institutions and users with updated and reliable data on infant and child mortality, fertility preferences, family planning behavior, maternal mortality, utilization of maternal and child health services, health expenditures, women’s status, domestic violence, and knowledge and behavior regarding HIV/AIDS and other sexually transmitted infections. This information contributes to policy decisions, planning, monitoring, and program evaluation for the development of Cambodia at both national- and local-government levels.The long-term objectives of the survey are to technically strengthen the capacity of the National Institute of Public Health (NIPH), Ministry of Health, and the National Institute of Statistics (NIS) of MOP for planning, conducting, and analyzing the results of further surveys.
Sample survey data [ssd]
Household, individual (including women and men between the ages of 15 and 49 and children aged 5 and below)
Version
Version 1.1 - Edited data for internal use only.
2006-12
Scope
CDHS 2005 covers 20 main areas of social concern:
-
Household Population and Housing Characteristics
-
Utilization of Health Services for Accident, Illness or Injury
-
Respondent Characteristics
-
Fertility
-
Practice of Abortion
-
Family Planning
-
Other Proximate Determinants of Fertility
-
Fertility Preferences
-
Adult and Maternal Mortality
-
Infant and Child Mortality
-
Causes of Death Among Infants and Young Children
-
Maternal Health
-
Child Health
-
Nutrition of Children and Women
-
Malaria
-
HIV/AIDS-Related Knowledge, Attitudes and Behavior
-
HIV Prevalence and Associated Factors
-
Children at Risk
-
Women's Status and Empowerment
-
Domestic Violence
| Topic | Vocabulary | URI |
|---|---|---|
| health policy [8.6] | CESSDA | http://www.nesstar.org/rdf/common |
| nutrition [8.7] | CESSDA | http://www.nesstar.org/rdf/common |
| accidents and injuries [8.1] | CESSDA | http://www.nesstar.org/rdf/common |
| childbearing, family planning and abortion [8.2] | CESSDA | http://www.nesstar.org/rdf/common |
| fertility [14.2] | CESSDA | http://www.nesstar.org/rdf/common |
| migration [14.3] | CESSDA | http://www.nesstar.org/rdf/common |
| morbidity and mortality [14.4] | CESSDA | http://www.nesstar.org/rdf/common |
Coverage
The sample was designed to provide estimates of the indicators at the national level, for urban and rural areas, and for 19 domains: 1.Banteay Mean Chey, 2.Kampong Cham, 3.Kampong Chhnang, 4.Kampong Speu, 5.Kampong Thom, 6.Kandal, 7.Phnom Penh, 8.Prey Veng, 9.Pursat, 10.Svay Rieng, 11.Takeo, 12.Kratie, 13.Siem Reap, 14.Otdar Mean Chey, 15. Battambang and Krong Pailin, 16. Kampot and Krong Kep, 17.Krong Preah Sihanouk and Kaoh Kong, 18.Preah Vihear and Steng Treng; and 19.Mondol Kiri and Rattanak Kiri.
Village level (by commune, district and province)
The survey covered the whole resident population (regular household) , with the exception of homeless in Cambodia
Producers and sponsors
| Name | Affiliation |
|---|---|
| National Institute of Statistics | Ministry of Planning |
| National Institute of Public Health | Ministry of Health |
| ORC Macro | Calverton, Maryland, USA |
| Name | Affiliation | Role |
|---|---|---|
| National Institute of Public Health | MOH | Technical assistance in field work and data processing in office. |
| World Bank | Technical and financial assistance | |
| World Health Organization | Financial assistance | |
| Deutsche Gesellschaft für Technische Zusammenarbeit | Financial assistance | |
| ORC Macro | Teachnical assitance |
| Name | Role |
|---|---|
| US Agency for International Development | Technical support |
| United Nations Population Fund | Financial support |
| United Nations Children's Fund | Financial support |
| Asian Development Bank | Financial support |
| Cambodia Development Council | Financial support |
| DFID | Financial support |
| Name | Affiliation | Role |
|---|---|---|
| Darith Hor | NIS/MoP | SURVEY COORDINATORS |
| Sovanratnak Sao | DGH/MoH | SURVEY COORDINATORS |
| Vonthanak Saphonn | NIPH/MoH | TECHNICAL COMMITTEE |
| Kia Reinis | ORC Macro | Survey Specialist |
| Keith Purvis | ORC Macro | Senior Data Processing Specialist |
| Kaye Mitchell | ORC Macro | Sampling Specialist |
| Bernard Barrère | ORC Macro | Coordinator |
| John Chang | ORC Macro | Analysis and preparation of CDHS report |
| Sidney Moore | ORC Macro | Analysis and preparation of CDHS report |
| Andrew Inglis | ORC Macro | Analysis and preparation of CDHS report |
| John Chang | ORC Macro | Analysis and preparation of CDHS report |
| Erica Nybro | ORC Macro | Analysis and preparation of CDHS report |
| Monica Kothari | ORC Macro | Analysis and preparation of CDHS report |
| Sri Poedjastoeti | ORC Macro | Analysis and preparation of CDHS report |
| Joy Fishel | ORC Macro | Analysis and preparation of CDHS report |
| Kiersten Johnson | ORC Macro | Analysis and preparation of CDHS report |
| Noah Bartlett | ORC Macro | Analysis and preparation of CDHS report |
| Rathavuth Hong | ORC Macro | Analysis and preparation of CDHS report |
| Ruilin Ren | ORC Macro | Sampling Specialist |
Sampling
TThe 2005 CDHS sample is a stratified sample selected in two stages. Stratification is achieved by separating every study domain into urban and rural areas. Areas are defined as urban or rural based on the classification in the 1998 GPC, provided by NIS. Therefore the 19 domains are stratified into 38 sampling strata in total. Samples are selected independently in every stratum, by a two-stage selection. This means that 38 independent samples were selected, one from each sampling stratum. Implicit stratifications were achieved at each of the lower geographical or administrative levels by sorting the sampling frame according to the geographical/administrative order and by using a probability proportional to the size selection in the first stage of sampling. The explicit and implicit stratifications together guarantee a better scattering of the sampled points. In the first stage of selection, 557 villages were selected with a probability proportional to the village size. The village size is the number of households in the village. After this selection and before the data collection, an updating operation was conducted over all of the 557 selected villages. The updating operation consisted of visits to every selected village. During the visits, records were made of every structure found on the ground; structures were identified by type (residential or not); number of households in each residential structure were identified; location map and a sketch map were drawn showing the boundaries of the village and the location of each structure. This important operation guaranteed the quality of the fieldwork and prevented nonsampling errors. A household list was set up for each selected village. The resulting lists of households served as the sampling frame for the selection of households in the second stage. Some of the selected villages were big. To minimize the task of household listing, villages with more than 300 households were segmented. A segment corresponds to an enumeration area (EA) that was created for the GPC 1998. Size and boundaries were well-defined and maps were available. Among segmented villages, only one EA was selected from the village with a selection probability proportional to the EA size. Household listing was conducted only in the selected EA. Therefore, a CDHS cluster is either a village or an EA. Detailed information on the sampling methodology is available in Appendix A to the Survey Report.
In the second stage of selection, a fixed number of 24 households were selected in every urban cluster, and 28 households were selected in every rural cluster. They were selected by an equal probability systematic sampling. The decision on number of households selected per cluster is a tradeoff between fieldwork efficiency and precision. All women ages 15-49 in the selected households were eligible for the interview. The advantages of this two-stage selection procedure are: 1. It is simple to implement and reduces possible nonsampling errors. 2. It is easy to locate the selected households, reducing nonsampling errors and nonresponse. 3. The interviewers interview only the households in the preselected dwellings. No allowance for replacement of dwellings prevents survey bias.
Creation of the 2005 CDHS sample was based on the objective of collecting a nationally representative sample of completed interviews with women and men between the ages of 15 and 49. To achieve a balance between the ability to provide estimates for all 24 provinces in the country and limiting the sample size, 19 sampling domains were defined, 14 of which correspond to individual
provinces and 5 of which correspond to grouped provinces.
• Fourteen individual provinces: Banteay Mean Chey, Kampong Cham, Kampong Chhnang, Kampong Speu, Kampong Thom, Kandal, Kratie, Phnom Penh, Prey Veng, Pursat, Siem Reap, Svay Rieng, Takeo, and Otdar Mean Chey;
• Five groups of provinces: Battambang and Krong Pailin, Kampot and Krong Kep, Krong Preah Sihanouk and Kaoh Kong, Preah Vihear and Steung Treng, Mondol Kiri, and Rattanak Kiri.
The sample of households was allocated to the sampling domains in such a way that estimates of indicators can be produced with known precision for each of the 19 sampling domains, for all of Cambodia combined, and separately for urban and rural areas of the country.
The sampling frame used for 2005 CDHS is the complete list of all villages enumerated in the 1998 Cambodia General Population Census (GPC) plus 166 villages which were not enumerated during the 1998 GPC, provided by the National Institute of Statistics (NIS). It includes the entire country and consists of 13,505 villages. The GPC also created maps that delimited the boundaries of every village. Of the total villages, 1,312 villages are designated as urban and 12,193 villages are designated as rural, with an average household size of 161 households per village. The survey is based on a stratified sample selected in two stages. Stratification was achieved by separating every reporting domain into urban and rural areas. Thus the 19 domains were stratified into a total of 38 sampling strata. Samples were selected independently in every stratum, by a two
stage selection. Implicit stratifications were achieved at each of the lower geographical or administrative levels by sorting the sampling frame according to the geographical/administrative order and by using a probability proportional to size selection at the first stage of selection.
(Please see the report of external resources)
Response rate:
Households: 98 per cent
Women ages 15-49: 98 per cent
Men ages 15-49: 93 per cent
See Table 1.1 of Section 1.8 (Sample Coverage of external resources) of the Report for details.
Several sets of weight are calculated for CDHS 2005 in order to satisfy different users of the dataset:
Household weights: the inverse of the probability of selection, adjusted for nonresponse and normalized at the national level to make the number of weighted cases equal to the number of unweighted cases for all household indicators based on the whole national sample. The resulting weights are called standard weights. Variable hv005 in the household data files (RECH0 - RECHML) is the household weight.
Weights for Women and men ages 15-49: women/men individual standard weights were calculated based on the household standard weights. Similarly, the women/men weights were adjusted for non-response and normalization. The reason for normalization is the same as for the normalization of the household weights. In the women data files (REC01 - REC99), the weight variable is v005. In the men data files (MREC01 - MREC91), the weight variable is mv005. In the household data files (RECH0 - RECHML), the men weight variable is hv028.
Weights for domestic violence module: Weights were calculated in the same manner and the women and men individual weights. The weight was adjusted for the selection of only one woman in the household for the module and is thus related to the number of eligible women in the household.
HIV weights: Due to budgetary considerations, HIV samples which include both men and women were taken from the men's subsample and a special weight was given to this individuals for the calculaton of HIV prevalence. The women's and men's indiviual weights were calculated from the household standard weights for the men's subsample and standardized. Variable ha69 is the HIV weight in data file RECH5.
Details of the weighting procedure are provided in Appendix A (A.7 Weighting and The Representativeness) of the CDHS 2005 Final Report.
Survey instrument
There are three types of questionnaires used in the CDHS: the Household Questionnaire, the Individual Woman's Questionnaire, and the Individual Man's Questionnaire.
The households that have been scientifically selected to be included in the CDHS sample were visited and interviewed using a Household Questionnaire. The Household Questionnaire consisted of a cover sheet to identify the household and a form on which all members of the household and visitors were listed. Data collected about each household member were name, sex, age, education, and survival of parents for children under age 18 years, etc. The Household Questionnaire was used to collect information on housing characteristics such as type of water, sanitation facilities, quality of flooring, and ownership of durable goods.
The Household Questionnaire permitted the interviewer to identify women and men who were eligible for the Individual Questionnaire. Women ages 15-49 years in every selected household who are members of the household (those that usually live in the household) and visitors (those who do not usually live in the household but who slept there the previous night) were eligible to be interviewed with the individual Woman's Questionnaire.
After all of the eligible women in a household have been identified, female interviewers used the Woman's Questionnaire to interview the women. The Woman's Questionnaire collected information on the following topics:
· socio-demographic characteristics
· reproduction
· birth spacing
· maternal health care and breastfeeding
· immunization and health of children
· cause of death of children
· marriage and sexual activity
· fertility preferences
· characteristics of the husband and employment activity of the woman
· HIV/AIDS and other sexually transmitted infections
· maternal mortality
· women's status
· household relationsIn one-half of the households, men were identified as eligible for individual interview, and the male interviewer of each team used the Man's Questionnaire to interview the eligible men. Team leaders informed their teams which households in the sample have been selected for including interviews with men. The Man's Questionnaire collected information on the following topics:
· socio-demographic characteristics
· reproduction
· birth spacing
· marriage and sexual activity
· HIV/AIDS and other sexually transmitted infectionsBiomarker data collection were conducted in the same one-half of the households which were selected to include men for interview. The biomarker data collection included: measuring the height and weight of women and children (under age 6 years), anemia testing of women and children, and drawing blood samples from women and men for laboratory testing of HIV. Biomarker data collection were recorded in the Household Questionnaire.
Data collection
| Start | End |
|---|---|
| 2005-09-09 | 2006-03-07 |
| Name | Affiliation |
|---|---|
| National Institute of Statistics | Ministry of Planning |
| National Institute of Public Health | Ministry of Health |
Supervision of Interviewers
The team supervisor was tasked to:
· Oversee the work of the team.
· Assign households to interviewers.
· Help interviewers locate households.
· Spot-check some of the addresses selected for interviewing to be sure that you interviewed the correct households and the correct women and men.
· Review all non-interviews.
· Observe some of your interviews to ensure that you are asking the questions in the right manner and recording the answers correctly.
· Handle funds and manage equipment.
· Supervise anthropometric measurement, anemia testing, and blood sample collection.
· Meet with you on a daily basis to discuss performance and give out future work assignments.
· Help you resolve any problems that you might have with finding the assigned households, understanding the questionnaire, or dealing with difficult respondents.The field editor was tasked to:
· Oversee the work of the team.
· Assign households to interviewers.
· Help interviewers locate households.
· Review all non-interviews.
· Review all questionnaires before the team leaves the cluster.
· Review completed questionnaires with interviewers and observe interviews.Full details of the responsibilities of the Supervisors and Field Editors are discussed in the Interviewer's Manual.
Training were conducted to form 19 field teams to be responsible for data collection in one of the 19 survey domains (comprised of the 24 provinces). Field teams were each composed of 6 people: team leader, field editor, three female interviewers, and one male interviewer.
The field teams were subjected to 6 weeks of training which included:
-
1 week on the Household Questionnaire
-
2 weeks on 13 sections of the Woman Questionnaire, review of the Household Questionnaire, including the selection of women for the Household Relations Module, Consent Statements for blood collection, and conversion of ages and dates of birth between the Khmer and Gregorian calendar
-
1 week on the Man Questionnaire, measuring height and weight of women and children, sample implementation and household selection, collection of Geographic Positioning System data, testing of household salt for iodine, organization of documents and materials for return to the head office
-
1 week on collection of blood samples (all interviewers wer designated to collect blood samples in the field)
-
1 week of full field practice
A total of 122 field personnel attended the 6 weeks training. The first 3 weeks were also attended by data entry staff.
The progression of fieldwork by geographic location had to take into account weather conditions during rainy season. A fieldwork supervision plan was created for the six CDHS survey coordinators from NIS and NIPH and ORC Macro to conduct regular field supervision visits. Supervision visits were conducted throughout the six months of data collection and included the retrieval of questionnaires and blood samples from the field. In addition, a quality control program was run by the data processing team to detect key data collections errors for each team. Based on these data checks, regular feedback was given to each team based on their specific performance.
Data processing
Data editing was done in the following data processing stages:
a. Office editing and coding - minimal since CSPro has been designed to be an intelligent data entry program
b. Data entry
c. Completeness of data file
d. Verification of Data - prior to this stage, data are again entered and tagged as V to indicate that the dataset is a verification data
e. Secondary editing
Data appraisal
The computer software used to calculate sampling errors for the 2005 CDHS is a Macro SAS procedure. This procedure used the Taylor linearization method for variance estimation for survey estimates that are means or proportions. The Jackknife repeated replication method is used for variance estimation of more complex statistics such as fertility and mortality rates. ISSA also computes ISSA computes the design effect (DEFT) for each estimate.
Sampling errors for the 2005 CDHS are calculated for selected variables considered to be of primary interest for woman’s survey and for man’s surveys, respectively for the country as a whole, for urban and rural areas, and for each of the 19 study domains. Sampling errors along with other statistics and the DEFT are presented in Tables B.1 to B.23 of Appendix B of the CDHS 2005 Final Report.
Appendix C of the CDHS 2005 final report contains all data quality tables generation for the dataset. These tables include
-
Table C.1 Household age distribution
-
Table C.2.1 Age distribution of eligible and interviewed women
-
Table C.2.2 Age distribution of eligible and interviewed men
-
Table C.3 Completeness of reporting
-
Table C.4 Births by calendar year
-
Table C.5 Reporting of age at death in days
-
Table C.6 Reporting of age at death in months
Data Access
| Name | Affiliation | URL | |
|---|---|---|---|
| Measure DHS | ORC Macro | www.measuredhs.com | |
| Director General | National Institute of Statistics | www.nis.gov.kh | sythan@forum.ore.kh |
| Director, ICT Department | National Institute of Statistics | www.nis.gov.kh | saintlundy@yahoo.com |
| Is signing of a confidentiality declaration required? | Confidentiality declaration text |
|---|---|
| yes | Data has been anonymized and is available for public use. |
Datasets are made available with the following conditions:
-
Survey data files are distributed by MEASURE DHS for academic research/statistical analysis. Researchers need to provide a description of any research/analysis that will be using the data, before access is granted to the datasets.
-
Once downloaded, the datasets must not be passed on to other researchers without the written consent of MEASURE DHS.
-
All reports and publications based on the requested data must be sent to the MEASURE DHS Data Archive as a Portable Format Document (pdf) or a hard copy, for us to forward to the country(ies) whose data have been used.
National Institute of Public Health, National Institute of Statistics [Cambodia] and ORC Macro. 2006. Cambodia Demographic and Health Survey 2005. Phnom Penh, Cambodia and Calverton, Maryland, USA: National Institute of Public Health, National Institute of Statistics and ORC Macro.
Disclaimer and copyrights
For the National Institute of Statistics:
The user of the data acknowledges that the National Institute of Statistics, Cambodia bears no responsibility for use of the data or for interpretations or inferences based upon such uses.
For Measure DHS:
Every effort is made to provide accurate and complete information. However, with the thousands of documents available, often uploaded within short deadlines, we cannot guarantee that there will be no errors. We make no claims, promises or guarantees about the accuracy, completeness, or adequacy of the contents of this Web site and expressly disclaim liability for errors and omissions in the contents of this Web site.
With respect to the content of this site, neither the United States Government, nor USAID, nor MEASUREDHS, nor their employees and contractors make any warranty, expressed or implied or statutory, including but not limited to the warranties of non-infringement of third party rights, title, and the warranties of merchantability and fitness for a particular purpose with respect to content available from this Web site or other Internet resources linked from it. Additionally, neither the U.S. Government, nor USAID, nor MEASUREDHS assume any legal liability for the accuracy, completeness, or usefulness of any information, product, or process disclosed herein nor freedom from computer virus, and do not represent that use of such information, product, or process would not infringe on privately owned rights.
(c) 2006, National Institute of Statistics, National Institute of Public Health [Cambodia], and ORC Macro [USA]
Contacts
| Name | Affiliation | URL | |
|---|---|---|---|
| Director, Demographic Statistics Census and Survey Department | National Institute of Statistics | census@camnet.com.kh | www.nis.gov.kh |
| Data User Service Center | National Institute of Statistics | dusc@nis.gov.kh | www.nis.gov.kh |
| National Institute of Public Health | Ministry of Health | usa@camnet.com.kh | www.niph.org.kh |
| ORC Macro | reports@orcmacro.com | www.measuredhs.com |
Metadata production
DDI-KHM-NIS-CDHS-2005-v013
| Name | Affiliation | Role |
|---|---|---|
| Nguon Sovann | NIS | Archivist |
| Fe Vida Dy-Liacco | ADP Asia | Reviewer |
| Shine Cagas | ADP Asia | Reviewer |
| Nguon Sovann | NIS | Archivist |
| Khieu Khemarin | NIS | Archivist |
| Shine Cagas | ADP Asia | Reviewer |
| Saint Lundy | NIS | Archivist |
2009-09-28
Metadata version
Version 1.3 (July 2010). This version contains edits on version 1.2 of the DDI document.
Version 1.2 (February 2010). This version contains edits on version 1.1 of the DDI document.
Version 1.1 (October 2009). This version contains edits on the original DDI document.