Demographic and Health Survey 1987 - Trinidad and Tobago

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

The Trinidad and Tobago DHS survey--a national-level self-weighting random sample survey--was funded by the United States Agency for International Development (US/AID) and executed by the Family Planning Association of Trinidad and Tobago (FPATT). Technical assisstance was provided by the Demographic and Health Surveys Program at the Institute for Resource Development (IRD), a subsidiary of Westinghouse located in Columbia, Maryland.

The sampling frame for the TTDHS was the Continuous Sample Survey of Population (CSSP), an ongoing survey conducted by the Central Statistical Office based on the 1980 Population and Housing Census.

The TTDHS used a household schedule to collect information on residents of selected households, and to identify women eligible for the individual questionnaire. The individual questionnaire was based on DHS's Model "A" Questionnaire for High Contraceptive Prevalence countries, which was modified for use in Trinidad and Tobago. It covered four main areas: (1) background information on the respondent, her partner and marital status, (2) fertility and fertility preferences, (3) contraception, and (4) the health of children.

The short term objective of the Trinidad and Tobago Demographic and Health Survey (TTDHS) is to collect and analyse data on the demographic characteristics of women in the reproductive years, and the health status of their young children. Policymakers and programme managers in public and private agencies will be able to utilize the data in designing and administering programmes.

The long term objective of the project is to enhance the ability of organisations involved in the TTDHS to undertake surveys of excellent technical quality.

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

National

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

- Household
- Women age 15-49

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

The population covered by the 1988 TTDHS is defined as the universe of all women age 15­-49.

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

Sample survey data

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

The sample for the TTDHS was based on the Continuous Sample Survey of Population (CSSP), used by the Central Statistical Office since 1968, and redesigned on the basis of the 1980 Population and Housing Census.
The country is divided into 14 domains of study, comprising a total of 1,638 enumeration districts (EDs). Results from the 1980 Census indicated that some EDs were too large (more than 300 households) and some too small (fewer than 30 households) to be appropriate primary sampling units (PSUs) for the TFDHS. Therefore, the largest units were further subdivided, and the smaller units combined with contiguous ones for the CSSP sample.

The CSSP sample is selected in two stages. In the first, PSUs are systematically selected, with probability proportional to size (size equals the number of households in the PSU). Following an operation to list all households in each selected PSU, individual households are selected, with probability of selection inversely proportional to the PSU's size.

The CSSP grand sample, which provides an overall sampling fraction of one household in forty (1/40) has been divided into 9 sub-samples, each with an overall sampling fraction of one in three-hundred sixty (1/360). Each CSSP survey round, conducted quarterly, uses three of the nine sub-samples, with an overall sampling fraction of one in one-hundred twenty (1/120).

The DHS sample was taken from the CSSP sample selected for the January-March 1987 quarter. The main objectives of the DHS sample were:
- a self-weighting sample of households,
- a sample take in each selected PSU of about 25 women aged 15-49, and
- a total of 4,000 completed interviews with women aged 15-49.

To achieve this sample size, 5,000 households were selected. This figure assumes an average of one eligible woman per household, and 294,400 eligible women nationwide, giving an overall sampling fraction of one in sixty (1/60). It also allows for 10 percent non-response at both the household and the individual interview level, commensurate with CSO experience in similar recent surveys. In total, 178 PSUs were selected throughout Trinidad and Tobago.

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

Face-to-face

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

The individual questionnaire was based on DHS's Model "A" Questionnaire for High Contraceptive Prevalence countries, which was modified for use in Trinidad and Tobago. It covered four main areas: (1) background information on the respondent, her partner and marital status, (2) fertility and fertility preferences, (3) contraception, and (4) the health of children.

The DHS model "A" questionnaire was adapted for use in Trinidad and Tobago, and pretested during February 1987. Thirteen pretest interviewers were trained for two weeks by FPATI', CSO, and IRD staff, and carded out two days of interviews. The questionnaire was further modified based on pretest results and interviewer comments.

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

The data processing staff consisted of a chief editor, 3 data entry clerks, and a control clerk who logged in questionnaires when they reached the office. All data entry staff completed the main interviewer training, in addition to data processing instruction by IRD staff. Data entry, editing, and tabulations were performed on microcomputers using the Integrated System for Survey Analysis (ISSA) programme, developed by IRD. The system performed range, skip, and consistency checks upon data entry, so that relatively little machine or manual editing was required. The chief editor was responsible for supervising data entry, and for resolving inconsistencies in the questionnaires detected during secondary machine editing.

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

4,122 households were successfully interviewed, out of the 4,799 selected for the sample. The household response rate was 94 percent. This represents households for which the interview was successfully completed out of 4,371 households for which an interview could have been conducted. This latter group includes households not interviewed due to the absence of a competent respondent, refusal, or the interviewer not finding the selected household. Among the 677 selected households which were not interviewed, 604 were missed because of contact difficulties: addresses not found, houses vacant, or those in which the occupants were not at home during repeated visits. Fewer than one percent of households refused to be interviewed.

The household questionnaires identified 4,196 women eligible for the individual questionnaire. This figure represents a yield of one eligible woman per household, which was the average expected. Questionnaires were completed for 3,806 women. The response rate at the individual level was 92 percent, which represents the proportion of interviews successfully completed out of the total number of women identified by the household schedule. The overall response rate, the product of response rates at the household and individual levels is 87 percent.

Contact was not made with 199 eligible women, either because the respondent was not at home during any of three visits by the interviewer, or was temporarily away from the household. Sixty-eight cases were missed due to "Other" reasons, and 83 women refused to be interviewed.

The response rates for the urban and rural areas were similar. In the urban areas, the overall response rate was 86 percent, compared with 88 percent for the rural areas.

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

Sampling errors, on the other hand, can be evaluated statistically. The sample of women selected in the 'IIDHS is only one of many samples of the same size that could have been drawn from the population using the same design. Each sample would have yielded slightly different results from the sample actually selected. The variability observed among all possible samples constitutes sampling error, which can be estimated from survey results (though not measured exact/y).

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

If simple random sampling had been used to select women for the TTDHS, it would have been possible to use straightforward formulas for calculating sampling errors. However, the TTDHS sample design used two stages and clusters of households, and it was necessary to use more complex formulas. Therefore, the computer package CLUSTERS, developed for the World Fertility Survey, was used to compute sampling errors.

In addition to the standard errors, CLUSTERS 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 indicates that the sample design is as efficient as a simple random sample; a value greater than 1 indicates that the increase in the sampling error is due to the use of a more complex and less statistically efficient design.

Sampling errors are presented in Table B.1 of the Final Report for 35 variables considered to be of primary interest. Results are presented for the whole country, for urban and rural areas, and for three age groups. For each variable, the type of statistic (mean, proportion) and the base population (e.g., all women, women in union) are given in Table B.1. Table B.2 presents the value of the statistac, R; its standard error, SE; the actual number of cases, N; the DEFT value; and the relative standard error, SE/R for each variable. In addition to these indicators, the 95 percent confidence limits for the statistic, R-2SD and R+2SD, are presented.

In general, the sampling errors for the country as a whole are small, which means that the TTDHS results are reliable. For example, in the whole sample, the survey found that women average 2.059 children ever born; the standard error of this estimate is .037. Therefore, to obtain the 95 percent confidence limit, one adds and subtracts twice the standard error to the sample estimate, i.e., 2.05 + .074. There is a 95 percent chance that the true average number of children ever born to all women 15-49 in Trinidad and Tobago is between 1.985 and 2.134. This same calculation can be performed for all other variables listed.

摘要
---------------------------

特立尼达和多巴哥人口与家庭健康调查——一项国家级的自加权随机抽样调查——由美国国际开发署（US/AID）资助，并由特立尼达和多巴哥家庭规划协会（FPATT）执行。技术支持由位于马里兰州哥伦比亚的西屋电气公司子公司资源开发研究所（IRD）下属的人口与家庭健康调查项目提供。

TTDHS的调查框架是持续人口抽样调查（CSSP），这是一项基于1980年人口和住房普查的持续进行的调查，由中央统计局执行。

TTDHS采用家庭日程收集关于选定家庭居民的信息，并确定符合个人问卷资格的女性。个人问卷基于DHS为高避孕率国家制定的“模型A”问卷，针对特立尼达和多巴哥进行了修改。它涵盖了四个主要领域：（1）受访者、其伴侣及婚姻状况的背景信息，（2）生育和生育偏好，（3）避孕，（4）儿童的保健。

特立尼达和多巴哥人口与家庭健康调查（TTDHS）的短期目标是收集和分析育龄妇女的 demographic 特征及其年轻子女的健康状况数据。公共和私营机构的政策制定者和项目管理人员将能够利用这些数据来设计和实施项目。

项目的长期目标是提高参与TTDHS的组织进行高质量技术调查的能力。

地理覆盖范围
---------------------------

全国

分析单元
---------------------------

- 家庭
- 15-49岁女性

总体
---------------------------

1988年TTDHS涵盖的总体定义为所有15-49岁女性的总体。

数据类型
---------------------------

抽样调查数据

抽样程序
---------------------------

TTDHS的样本基于自1968年以来中央统计局使用的持续人口抽样调查（CSSP），并根据1980年人口和住房普查重新设计。
国家被划分为14个研究区域，共有1,638个计数区（ED）。1980年普查的结果表明，一些计数区（超过300户家庭）太大，而一些计数区（少于30户家庭）太小，不适合作为TFDHS的初级抽样单位（PSU）。
...