Analysis Of Sample Survey Data Research Articles

Viability, Government Support and the Service Function of Farmer Professional Cooperatives—Evidence from 487 Cooperatives in 13 Cities in Heilongjiang, China

As the main body that unites farmers internally and connects with markets externally, professional farmer cooperatives are playing an increasingly important role around the world. In order to investigate the significant factors influencing this subject in agricultural socialization services, 487 cooperatives in Heilongjiang Province were selected for investigation. The field survey found that many of the better-developed cooperatives have a certain degree of inadequacy in the performance of their service functions. This paper proposes that viability and government support are important factors influencing the realization of the service function of farmer professional cooperatives. Based on the empirical analysis of sample survey data and econometric models, it was demonstrated that the experience of the chairman, the number of board members, the distribution of members, the scale of land operation, profitability, and the institutional arrangement of the cooperatives are an important embodiment of the viability of the cooperatives. These factors significantly influence the service function of cooperatives in different sections, including pre-production, mid-production, and post-production. Moreover, obtaining external support from the government is necessary for cooperatives at their primary stage of development, especially regarding relevant training, which can facilitate the realization of the service functions of cooperatives in all aspects.

Positive semidefiniteness of estimated covariance matrices in linear models for sample survey data

Abstract Descriptive analysis of sample survey data estimates means, totals and their variances in a design framework. When analysis is extended to linear models, the standard design-based method for regression parameters includes inverse selection probabilities as weights, ignoring the joint selection probabilities. When joint selection probabilities are included to improve estimation, and the error covariance is not a diagonal matrix, the unbiased sample based estimator of the covariance is the Hadamard product of the population covariance, the elementwise inverse of selection probabilities and joint selection probabilities, and a sample selection matrix of rank equal to the sample size. This Hadamard product is however not always positive definite, which has implications for best linear unbiased estimation. Conditions under which a change in covariance structure leaves BLUEs and/or BLUPs are known. Interestingly, this class of “equivalent” matrices for linear models includes non-positive semi-definite matrices. The paper uses these results to explore how the estimated covariance from the sample can be modified so that it meets necessary conditions to be positive semidefinite, while retaining the property that fitting a linear model to the sampled data yields the same BLUEs and/or BLUPs as when the original Hadamard product is used.

Complex sample design effects and inference for Korea National Health and Nutrition Examination Survey data

Nutritional researchers world-wide are using large-scale sample survey methods to study nutritional health epidemiology and services utilization in general, non-clinical populations. This article provides a review of important statistical methods and software that apply to descriptive and multivariate analysis of data collected in sample surveys, such as national health and nutrition examination survey. A comparative data analysis of the Korea National Health and Nutrition Examination Survey (KNHANES) was used to illustrate analytical procedures and design effects for survey estimates of population statistics, model parameters, and test statistics. This article focused on the following points, method of approach to analyze of the sample survey data, right software tools available to perform these analyses, and correct survey analysis methods important to interpretation of survey data. It addresses the question of approaches to analysis of complex sample survey data. The latest developments in software tools for analysis of complex sample survey data are covered, and empirical examples are presented that illustrate the impact of survey sample design effects on the parameter estimates, test statistics, and significance probabilities (p values) for univariate and multivariate analyses.

Mental Health After Sexual Violence

Sequelae of sexual violence include a range of physical and emotional problems, and negative mental health outcomes are particularly severe and long lasting. To evaluate associations among sociodemographic and behavioral factors and mental health after exposure to sexual violence. Participants were 780 men and women who experienced sexual violence who participated in the 2005 South Carolina Behavioral Risk Factor Surveillance Survey. The factors analyzed were gender, age, race, income, and education; having health insurance, an identified healthcare provider, and adequate emotional support; and diet, exercise, smoking, and alcohol use. Poor mental health was defined as 5 or more poor mental health days in the past 30 days. Data were analyzed using the SAS Procedures for Analysis of Sample Survey Data. Victims of sexual violence were at greater risk of experiencing 5 or more poor mental health days than those who did not (95% confidence interval for odds ratio = 2.05-3.07, p < .0001). Poor mental health among those who experienced sexual violence was associated with younger age (p = .005), lower income (p = .02), lower educational attainment (p = .0007), lack of emotional support (p = .0001), and lack of health insurance (p = .03). Gender, race, and having an identified healthcare provider were not associated significantly with mental health. Behavioral factors significantly associated with better mental health (after controlling for socio-economic status) were healthy diet (p = .05), exercise (p = .02), and not smoking (p = .0001). Alcohol use was not associated with mental health. Treatment after sexual violence should include attention to risk factors including low income, low educational attainment, and lack of emotional support and to the protective influence of behavioral factors including a healthy diet, exercise, and not smoking. Comprehensive integrated models of care addressing mental, physical, and social sequelae of sexual violence are needed.

Private Secondary Education in Uganda: Implications for Planning

Purpose of Study A fundamental question for educational planners and policy makers is which secondary school providers are most efficient in raising student learning for the most youth, given an available level of resources. Considerable attention has been devoted in recent years to the proposition that private providers offer efficient alternatives to government-financed and administered secondary schools. This study examines the rise of private secondary schools in Uganda and calculates a unit cost estimate for representative samples of secondary schools, both private and government. Setting A unit cost analysis was conducted among 28 randomly selected secondary schools in Uganda. Research Design A national sample of secondary schools was stratified in three ways. First, schools were selected according to the type of school, allowing half of the sample to be government schools and the other half private schools. A second stratification involved urbanicity, so both urban and rural schools were included in adequate numbers to allow subsequent comparison. Finally, the school sample was stratified by the four primary geographic regions in Uganda: Central (n = 10), Eastern (n = 6), Northern (n = 6), and Western (n = 6) Regions. All findings are based on analysis of sample survey data derived from randomly selected administrators, teachers, and parents of students. Using secondary school leaving examinations as the measure of effect, the article examines the relative cost effectiveness of private and government schools. Results Private schools in Uganda appear to be attractive, low-cost alternatives to government secondary schools. Per-pupil spending is significantly related to learning achievement, regardless of whether a student attends a private or government school. Thus, if higher performance is the desired ultimate student outcome, additional spending will be required. For their per-pupil cost, this article shows that private schools produce good learning gains—better, in fact, on a dollar basis, than government schools. Conclusions/Recommendations Unit cost data, when combined with reliable and valid measures of student learning achievement, are helpful to policy analysts and policy makers in determining the most efficient use of money. Although the comparatively high unit costs of government schools in this study are affected by the inclusion of capital costs, there is strong evidence to support the contention that private schools are a cost-effective alternative to government schools in the provision of general secondary education. Recommendations for future research include extending the analysis beyond the comparison of costs and examination scores by also considering the intangible component gains of schooling experiences in both private and government schools.

Complex sample design effects and inference for mental health survey data

AbstractMental health researchers world‐wide are using large‐scale sample survey methods to study mental health epidemiology and services utilization in general, non‐clinical populations (Alegria et al. in press). This article reviews important statistical methods and software that apply to descriptive and multivariate analysis of data collected in sample surveys. A comparative analysis of mental health surveys in international locations is used to illustrate analysis procedures and ‘design effects’ for survey estimates of population statistics, model parameters and test statistics.This article addresses the following questions. How should a research analyst approach the analysis of sample survey data? Are there software tools available to perform this analysis? Is the use of ‘correct’ survey analysis methods important to interpretation of survey data? It addresses the question of approaches to the analysis of complex sample survey data. The latest developments in software tools for the analysis of complex sample survey data are covered, and empirical examples are presented that illustrate the impact of survey sample design features on the interpretation of confidence intervals and test statistics for univariate and multivariate analyses. Copyright © 1998 Whurr Publishers Ltd.

From Consumption to Savings? Interpreting Tongan and Western Samoan Sample Survey Data on Remittances

This article examines the findings of an analysis of sample survey data on the uses and determinants of remittances among Tongan and Western Samoan households. These surveys were undertaken at both the receiving and remitting ends of the process, and bring forth important evidence that remittances are not used exclusively for consumption purposes and play an important role in contributing to both savings and investment in the migrant sending countries. It also shows that remittances appear not to be driven exclusively by altruistic sentiments and the need for family support, but also, among some migrant categories, by the motivation to invest. There appears to be substantial scope for policy intervention on the part of Pacific island governments to increase the flows of remittances into their economies.

Sampling of Populations: Methods and Applications

Tables. Boxes. Figures. Getting Files from the Wiley ftp and Internet Sites. List of Data Sites Provides on Web Site. Preface to the Fourth Edition. Part 1: Basic Concepts. 1. Use of Sample Surveys. 2. The Population and the Sample. Part 2: Major Sampling Designs and Estimation Procedures. 3. Simple Random Sampling. 4. Systematic Sampling. 5. Stratification and Stratified Random Sampling. 6. Stratified Random Sampling: Further Issues. 7. Ratio Estimation. 8. Cluster Sampling: Introduction and Overview. 9. Simple One-Stage Cluster Sampling. 10. Two-Stage Cluster Sampling: Clusters Sampled with Equal Probability. 11. Cluster Sampling in Which Clusters Are Sampled with Unequal Probability: Probability Proportional to Size Sampling. 12. Variance Estimation in Complex Sample Surveys. Part 3: Selected Topics in Sample Survey Methodology. 13. Nonresponse and Missing Data in Sample Surveys. 14. Selected Topics in Sample Design and Estimation Methodology. 15. Telephone Survey Sampling (Michael W. Link and Mansour Fahimi). 16. Constructing the Survey Weights (Paul P. Biemer and Sharon L. Christ). 17. Strategies for Design-Based Analysis of Sample Survey Data. Appendix. Answers to Selected Exercises. Index.

Logistic regression analysis of sample survey data

SUMMARY Standard chi-squared, X2, or likelihood ratio, G2, test statistics for logistic regression analysis, involving a binary response variable, are adjusted to take account of the survey design. These adjustments are based on certain generalized design effects. Logistic regression diagnostics to detect any outlying cell proportions in the table and influential points in the factor space are also developed, taking account of the survey design. Finally, the results are used to analyse some data from the October 1980 Canadian Labour Force Survey.

Survey Data about Religion Available from Data Banks

T he organization of data banks which make available data from surveys has facilitated secondary analysis of sample survey data (Hyman, 1972). As part of a project about measurement in social science studies of religion, I wrote to all the major organizations which maintain files of survey data. Each of these data banks was asked for a list of studies in its collection about religion. Hundreds of studies deposited in the data banks contain one or two variables concerning religion. Religious affiliation and church attendance are very common. Carroll and Roozen (1973) have described the availability of individual questions on religion in the collection of one of the data banks-the Roper Public Opinion Research Center. Their report has been updated by Voss (1974). I only found twenty studies on file at the data banks which contain several variables concerning religion. A list of these studies is presented below. This list is intended to show researchers what is available in order that more use can be made of the data. A study available from more than one data bank is so indicated; costs will vary from one source to another. The format in which these studies are available varies. Studies may be available only on computer tape, or only on IBM cards, or either way. Some data sets have been cleaned and others remain slovenly. The quality of codebook documentation is uneven. Special permission is required to use some of the studies. Detailed information, including costs, is available directly from the data banks.

Factors Related to Farmers' Use of Credit: Least-Squares Analysis of Sample Survey Data

T HE 1960 Sample Survey of Agriculture marked the first time that farm operators in a representative national sample were asked to report all their outstanding farm debts.' Each operator was also asked about such factors as his age, tenure, and size of farm, thereby permitting study of the relationships between these characteristics and various aspects of farm indebtedness. For instance, one might examine how each factor was related to the likelihood that a farmer had debt, to how heavily indebted he was, or to the likelihood that he owed a particular kind of debt or was indebted to a particular lender group. This paper discusses the application of least-squares analysis to the first of these areas. The most direct approach to determination of the between any single factor and the presence of debt is to sort the farmers by the different values or classes of that factor and then calculate the percentage who were indebted in each class. As is well known, however, this simple approach often cannot provide the desired knowledge because other farm characteristics also affect the likelihood of indebtedness, and there are unequal proportions of farmers with these other characteristics in each of the classes of the factor being studied. We therefore wish to perform an analysis that takes account of these intercorrelations and so yields what might be termed a relationship between a factor and the probability that an operator was indebted, as contrasted to the gross relationship obtained in the initial simple calculation. The usual procedure in such investigations is cross-classification, but unfortunately this procedure has serious practical limitations. Most basically, when several correlated factors are to be studied, even a large sample may not permit cross-classification by all of them simultaneously. The analyst must settle for study of a series of two-way or three-way tables, but if more than three correlated factors are involved, the results of such study obviously may be inconclusive. Furthermore, the research report is often tedious because the analysis does not produce summary statistics that describe the nature of the net relationships, but rather