Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “sampling design”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 433 records · Page 24Linked to original sources
PubMed1990

Experimental design and efficient parameter estimation in population pharmacokinetics.

A computer simulation technique used to evaluate the influence of several aspects of sampling designs on the efficiency of population pharmacokinetic parameter estimation is described. Although the simulations are restricted to the one-compartment one-exponential model, they provide the basis for a discussion of the structural aspects involved in designing a population study. These aspects include number of subjects required, number of samples per subject, and timing of these samples. Parameter estimates obtained from different sampling schedules based on two- and three-point designs are evaluated in terms of accuracy and precision. These simulated data sets include noise terms for both inter- and intraindividual variability. The results show that the population fixed-effect parameters (mean clearance and mean volume of distribution) for this simple pharmacokinetic model are efficiently estimated for most of the sampling schedules when two or three points are used, but the random-effect parameters (describing inter- and intraindividual variability) are inaccurate and imprecise for most of the sampling schedules when only two points are used. This drawback was remedied by increasing the number of data points per individual to three.

Computer Simulation↗
PubMed2000

Sampling for evaluation. Issues and strategies for community-based HIV prevention programs.

Sampling methods are an important issue in the evaluation of community-based HIV prevention initiatives because it is through responsible sampling procedures that a valid model of the population is produced and reliable estimates of behavior change determined. This article provides an overview on sampling with particular focus on the needs of community-based organizations (CBOs). As these organizations continue to improve their capacity for sampling and program evaluation activities, comparisons across CBOs can become more rigorous, resulting in valuable information collectively regarding the effectiveness of particular HIV prevention initiatives. The author reviews several probability and non-probability sampling designs; discusses bias, cost, and feasibility factors in design selection; and presents six guidelines designed to encourage community organizations to consider these important sampling issues as they plan their program evaluations.

Community Health Services↗
PubMed2005

WAIS III UK: an extension of the UK comparability study.

OBJECTIVES: To correct and augment the sample on which a previous study, assessing the applicability of USA WAIS III norms to the UK population, was based. To repeat this study using the modified sample. DESIGN: The WAIS III UK was administered to a supplementary sample, which was used to enhance and correct the original sample, allowing a better match to UK population demographics. METHOD: WAIS III UK scores were processed using USA norms. RESULTS: Distributions of UK IQ, Index, and subtest scores were consistent with USA norms. Means were significantly above USA values and did not show a flat profile. Correlational analysis suggested the presence of an age-related sampling bias, which was then statistically controlled for using analysis of covariance, with age as covariate, to give corrected means. These means, with the exception of two subtests (block design and picture arrangement), did not differ significantly from USA values. CONCLUSION: With a minor proviso concerning the above subtests, it is probable that USA norms can be safely used with the UK population. Future UK samples need to ensure random sampling within demographic categories if sampling bias is to be avoided.

Adolescent↗
PubMedDate not supplied

Tobacco use among students in Bihar (India).

UNLABELLED: Determination of the prevalence and attitudes toward tobacco use was assessed among 13-15 years school students in Bihar (India). SETTINGS AND DESIGN: Schools having grade 8-10 in Bihar. A two stage cluster sample design was used. SUDAAN and the C-sample procedure in Epi-Info was used for statistical analysis. Of the 2636 respondents, 71.8% (76.5% boys, 57.2% girls) were ever tobacco users; of them 48.9% had used tobacco before 10 years of age. Current use was reported by 58.9% (Boys 61.4%, Girls 51.2%); smokeless tobacco by 55.6% (Boys 57.6%, Girls 49.2%); and smoking by 19.4% (23.0% boys, 7.8% girls). Nearly one third (29%) students were exposed to ETS inside their homes and nearly half (48%) outside their homes. Almost all students reported watching cigarette and gutka advertisements in almost all kinds of media and events. Tobacco use by parents and friends, knowledge on harmful effects of chewing tobacco, smoking and environmental smoke, and attitudes on tobacco use by others were strongly associated with student tobacco use. Current tobacco use was reported significantly more by students who received pocket money/or were earning than by students who did not receive any pocket money/or did not earn (p value for trend <0.0001). Over half of current users (56%) bought their tobacco products from stores; of these, over 3/4th (77.2%) of them despite their age, had no difficulty in procuring these products. Teaching in schools regarding harmful effects of tobacco use was non-existent (3%). This urgently requires a comprehensive prevention program in schools and the community especially targeted towards girls.

Adolescent↗
PubMed2005

The Epworth Sleepiness Scale: influence of age, ethnicity, and socioeconomic deprivation. Epworth Sleepiness scores of adults in New Zealand.

STUDY OBJECTIVES: To examine possible relationships between excessive sleepiness (Epworth Sleepiness Scale score >10), and age, sex, ethnicity, socioeconomic deprivation, usual sleep, and self-reported symptoms of obstructive sleep apnea. DESIGN: Mail-out survey to a stratified random sample of 10,000 people aged 30 to 60 years, selected from the electoral roll. SETTING: Nationwide survey of adults in New Zealand (71% response rate). PARTICIPANTS: The sample design aimed for equal numbers of Măori and non-Măori participants, men and women, and participants in each age decade. INTERVENTIONS: N/A. MEASUREMENTS AND RESULTS: Two-page questionnaire. Măori participants had higher mean Epworth Sleepiness Scale scores than non-Măori (7.5 versus 6.0) and were more likely to have an Epworth Sleepiness Scale score of more than 10. Logistic multiple regression modeling identified the following significant independent risk factors for having an Epworth Sleepiness Scale score >10: being Măori, male, older, reporting more or less than 7.5 to 8.0 hours usual sleep, never or rarely getting enough sleep, never or rarely waking refreshed, larger neck circumference, observed apneas, and not drinking alcohol (compared with moderate alcohol consumption). CONCLUSIONS: The relationships between an Epworth Sleepiness Scale score >10 and sleep habits and risk factors for obstructive sleep apnea are as expected. The relationships between an ESS score > 10 and being Măori, a man, older, or more socioeconomically deprived could be related to a higher prevalence of sleep disorders in these groups. However, more research is needed to understand possible differences not only in pathophysiologic processes, but also in the wider societal trends and pressures that may impact differentially on sleep and sleepiness.

Adult↗
PubMed2005

Robust ascertainment-adjusted parameter estimation.

Nonrandom ascertainment is commonly used in genetic studies of rare diseases, since this design is often more convenient than the random-sampling design. When there is an underlying latent heterogeneity, Epstein et al. ([2002] Am. J. Hum. Genet. 70:886-895) showed that it is possible to get unbiased or consistent estimation of population parameters under ascertainment adjustment, but Glidden and Liang ([2002] Genet. Epidemiol. 23:201-208) showed in a simulation study that the resulting estimates are highly sensitive to misspecification of the latent components. To overcome this difficulty, we consider a heavy-tailed model for latent variables that allows a robust estimation of the parameters. We describe a hierarchical-likelihood approach that avoids the integration used in the standard marginal likelihood approach. We revisit and extend the previous simulation, and show that the resulting estimator is efficient and robust against misspecification of the distribution of latent variables.

Genetic Diseases, Inborn↗
PubMed1997

Quality of life outcomes after intensive care. Comparison with a community group.

OBJECTIVE: Compare the health related quality of life of intensive care patients with a community sample. DESIGN: Self-completed questionnaire posted to a consecutive sample of 238 patients 16 months after discharge from an intensive care unit (ICU) and to a random community sample (n = 242). SETTING: The Liverpool Hospital is the main referral and teaching hospital in a community of 620,000 people. It has a ten-bed general ICU. PATIENTS AND PARTICIPANTS: All patients admitted to the ICU over 8 months with a length of stay > or = 24 h and a sample drawn from the community telephone directory. MEASUREMENTS AND MAIN RESULTS: The self completed questionnaire contained physical and psychosocial health and quality of life (QOL) scales. Analysis of variance indicated that ICU patients were more physically ill and anxiously depressed than the community sample. Sixty-three per cent of patients had not attained full health, were functionally impaired and had a poorer QOL than those patients who had returned to full health and the community. Psychosocial health (apart from anxious depression) was related to the level of perceived physical health rather than to whether or not they had been admitted to the ICU. Those subjects not in full health had poorer interpersonal relationships, less positive attitudes about life, more anxious depression and more suicidal depression. CONCLUSIONS: ICU patients following discharge have worse perceived health and more anxiety than others in the community. Sixty-three per cent of patients had a poorer QOL and functional health than those who returned to full health and those in the community.

Analysis of Variance↗
PubMed2001

The health and well-being of adolescents: a school-based population study of the self-report Child Health Questionnaire.

PURPOSE: To evaluate a new generic measure of adolescent health status, the self-report version of the Child Health Questionnaire (CHQ), and provide population-based data. Furthermore, we aimed to examine the impact of common adolescent illness and health concerns on their health and well-being. METHODS: A stratified, two-stage, random cluster sampling design was used to obtain a cross-sectional sample of subjects through schools. A written questionnaire included the 80-item 12-scale self-report CHQ and items measuring health concerns, illnesses/health conditions, and sociodemographics. RESULTS: A total of 2361 adolescents participated (response rate of 70%). Reliability was high: Tests of internal consistency and discriminant validity reported 90% of item-scale correlations >.4; all scales had Cronbach alpha coefficients >.7. Adolescents with illnesses/conditions or health concerns reported lower scores and larger differences for content-related scales, supporting content and construct validity. Statistically significant age and gender trends were observed for Mental Health, Self-Esteem, General Health, and Family Cohesion scales. Health status worsened as health concerns increased (X(2) linear trend, p =.00) with deterioration in health of 5-20% on all scales for emotional health concerns (40% of sample). CONCLUSIONS: The self-report CHQ is a reliable and seemingly valid measure of health and well-being for adolescent health research, although additional measures may be required where scales have high ceiling values. The significantly lower scores reported by adolescents with illness and/or health concerns lend support to the use of standardized health measures and longitudinal research to further examine the impact of adolescent comorbidities and their causal determinants.

Adolescent↗
PubMed2001

Determinants of glycated haemoglobin in the general population: associations with diet, alcohol and cigarette smoking.

OBJECTIVE: We evaluated cigarette smoking, alcohol intake and consumption of different foods as determinants of glycated haemoglobin in a general population sample. DESIGN: Cross-sectional survey. SETTING: England. SUBJECTS: Representative sample of 15 809 adults aged 16 y and older. Data analysed for 9772 non-diabetic, white European subjects. MAIN OUTCOME MEASURES: Glycated haemoglobin (GHb). Analyses were adjusted for age, sex, body mass index (BMI), waist-hip circumference ratio, activity level, and educational attainment. RESULTS: After adjusting for confounding, GHb was 0.277% (95% confidence interval 0.218 to 0.336) higher in current smokers of 20 or more per day, compared with non-smokers. GHb was 0.189% (0.101 to 0.277) lower in those drinking 42 or more units of alcohol per week than in non-drinkers. GHb was not associated with frequency of consumption of pulses, fruit, vegetables and salads, cakes, bread or confectionery. GHb was higher in subjects who took sugar in tea (0.051%, 0.015 to 0.087%) or in coffee (0.069%, 0.034 to 0.105%). GHb was higher in subjects who used solid fat for cooking (0.082%, 0.022 to 0.142%), or who drank whole rather than reduced-fat milk (0.088%, 0.036 to 0.140%), or used butter or hard margarine rather than low-fat spreads (0.075%, 0.029 to 0.121%). CONCLUSIONS: In the general population, higher GHb may be associated with cigarette smoking, or frequent consumption of fat-containing foods. Consumption of alcohol may be associated with lower GHb. SPONSORSHIP: None.

Adolescent↗
PubMed2003

Salt iodisation and public health campaigns to eradicate iodine deficiency disorders in Armenia.

BACKGROUND: Iodine deficiency disorders (IDD) are endemic in the mountain regions of Armenia. Universal salt iodisation has been chosen as the control measure. OBJECTIVES: (1). To measure the prevalence of iodine deficiency in the Armenian population; (2). to evaluate household use of iodised salt; and (3). to monitor iodised salt promotion strategies. DESIGN: Cross-sectional study on a nationally representative sample of 2627 households, including 3390 children under five and 2649 women of fertile age. Cluster sampling design on four population strata: residents, refugees, rural and urban. RESULTS: Thyroid was palpable in one-third of the women, 6% of them having a visible goitre. Median of urinary iodine excretion in children was 139.5 microg l-1. One-third of the children showed low urinary iodine concentration. Iodised salt was consumed in 66% of the households. The national IDD control programme included modernisation of the Yerevan Salt Factory, legislative regulation of the iodine content of the salt, and public information by the media. CONCLUSIONS: Armenia was still an endemic zone for goitre in 1997. The iodine status of children under five in 1997 was not considered alarming even though 33% of them had low values of urinary iodine. After four years of intervention strategies, the use of iodised salt has increased by 17%. Further efforts should be made to control salt imports and to monitor IDD indicators in vulnerable groups.

Adolescent↗
PubMed2004

Who reports insomnia? Relationships with age, sex, ethnicity, and socioeconomic deprivation.

STUDY OBJECTIVES: To investigate the prevalence of self-reported insomnia symptoms among Mâori (indigenous people) and non-Mâori adults in the general population of New Zealand. To explore the possible links between insomnia symptoms and ethnicity, gender, age, employment status and socio-economic deprivation. DESIGN: Mail-out survey to a stratified random sample of 4,000 people aged 20 to 59 years, selected from the electoral roll. SETTING: Nationwide survey of New Zealand adults (72.5% response rate). PARTICIPANTS: The sample design aimed for equal numbers of Mâori and non-Mâori participants, men and women, and participants in each decade of age. INTERVENTIONS: N/A. MEASUREMENTS AND RESULTS: Population prevalence estimates indicated that self-reported insomnia symptoms and sleeping problems were higher among Mâori than non-Mâori. Multiple logistic regression analyses identified unemployment and socioeconomic deprivation as being strongly associated to all insomnia symptoms and to reporting a sleeping problem lasting more than 6 months. CONCLUSIONS: Socioeconomic factors and ethnicity are significant independent predictors of reported insomnia symptoms. This finding has important implications for the provision of treatment services to those most in need.

Adult↗
PubMed1979

Geochemical surveys in the United States in relation to health.

Geochemical surveys in relation to health may be classified as having one, two or three dimensions. One-dimensional surveys examine relations between concentrations of elements such as Pb in soils and other media and burdens of the same elements in humans, at a given time. The spatial distributions of element concentrations are not investigated. The primary objective of two-dimensional surveys is to map the distributions of element concentrations, commonly according to stratified random sampling designs based on either conceptual landscape units or artificial sampling strata, but systematic sampling intervals have also been used. Political units have defined sample areas that coincide with the units used to accumulate epidemiological data. Element concentrations affected by point sources have also been mapped. Background values, location of natural or technological anomalies and the geographic scale of variation for several elements often are determined. Three-dimensional surveys result when two-dimensional surveys are repeated to detect environmental changes.

Air Pollutants↗
PubMed2002

Prevalence of blindness and low vision in Malaysian population: results from the National Eye Survey 1996.

BACKGROUND: A national eye survey was conducted in 1996 to determine the prevalence of blindness and low vision and their major causes among the Malaysian population of all ages. METHODS: A stratified two stage cluster sampling design was used to randomly select primary and secondary sampling units. Interviews, visual acuity tests, and eye examinations on all individuals in the sampled households were performed. Estimates were weighted by factors adjusting for selection probability, non-response, and sampling coverage. RESULTS: The overall response rate was 69% (that is, living quarters response rate was 72.8% and household response rate was 95.1%). The age adjusted prevalence of bilateral blindness and low vision was 0.29% (95% CI 0.19 to 0.39%), and 2.44% (95% CI 2.18 to 2.69%) respectively. Females had a higher age adjusted prevalence of low vision compared to males. There was no significant difference in the prevalence of bilateral low vision and blindness among the four ethnic groups, and urban and rural residents. Cataract was the leading cause of blindness (39%) followed by retinal diseases (24%). Uncorrected refractive errors (48%) and cataract (36%) were the major causes of low vision. CONCLUSION: Malaysia has blindness and visual impairment rates that are comparable with other countries in the South East Asia region. However, cataract and uncorrected refractive errors, though readily treatable, are still the leading causes of blindness, suggesting the need for an evaluation on accessibility and availability of eye care services and barriers to eye care utilisation in the country.

Adolescent↗
PubMed1977

[Determination of a small amount of acrylamide in air (author's transl)].

According to the recently published "Guidebook of Measuring Method for Environmental Atmosphere" edited by the Department of Safety and Health Labour Administration of Japan, it is recommended to determine acrylamide (AAM) in air by sampling with glass fiber filter, extracting into methanol and injecting in the FID gaschromatograph (GC). Although acrylamide particle may be measured by this method, it is questionable whether a small amount of gaseous acrylamide could be determined together. We have investigated the determination of a small amount of acrylamide monomer in air by sampling it on solid adsorbent packed in a specially designed sampling tube. We concluded that it is capable to determine a small amount of acrylamide in air, by using the above mentioned sampling tube packed with Flusin-F (treated with phosphoric acid; 30--60 mesh) as the solid adsorbent, at the concentration range from 1.0 to 0.01 ppm (v/v), and the recovery rate of 82--83%.

Acrylamides↗
PubMed1995

The Jamaican Diabetes Survey. A protocol for the Caribbean.

OBJECTIVE: This study was designed to investigate the point prevalence of diabetes in Jamaica. RESEARCH DESIGN AND METHODS: A two-stage stratified random sampling design was used, and individuals aged 15 years and over were interviewed. Nonresponse was documented and factored into the final analysis of the survey data. The overall response rate obtained was 57.9%. All subjects with fasting blood glucose (FBG) greater than 6.1 mmol/1 (110 mg/dl) were brought back for an abbreviated glucose tolerance test. The data was analyzed using Epi 5, an advanced statistical program designed specifically for use with epidemiological data. RESULTS: The 2,109 subjects who participated were the basis for estimates of diabetes and IGT prevalence. Among those with previously diagnosed diabetes, diet therapy alone, oral hypoglycemic agents plus diet therapy, insulin therapy, and lack of treatment were reported. CONCLUSIONS: By the World Health Organization (WHO) criteria, Jamaica has a point prevalence of diabetes of 17.9% in the 15-and-over age-group.

Adolescent↗
PubMed2005

Peer and parental influences on adolescent smoking.

PURPOSE: The purpose of this study was to determine the relationship between peer and parental factors and smoking behavior of adolescents in urban cities and to investigate whether there are gender differences. METHODS: A stratified and random cluster sampling design was used to obtain a cross-sectional sample of high school students in two urban cities. The sample consisted of 512 Korean adolescents (256 boys and 256 girls) aged 15 to 18 (mean age 16.7+/-.58). Self-reported questionnaire consisted of adolescent smoking behavior, peer smoking and alcohol use, parental smoking and alcohol use, father-mother-peer relationships and perceived social support from peers and parents. Multiple logistic regression analysis was used to examine the hypothesized model. RESULTS: The findings showed that peer and parental factors accounted for 30.3% of the variance in adolescent smoking and peer smoking was most strongly associated with adolescent smoking behavior (OR=10.18). In addition, peer smoking (OR=4.71), peer alcohol use (OR=4.21), and peer relationships (OR=1.03) were significantly associated with boys' smoking behavior. In girls, peer smoking (OR=26.50) and parent smoking (OR=5.48) were significantly associated with smoking behavior. CONCLUSIONS: Consistent with previous findings, peer smoking is a significant factor on adolescent smoking. Specifically, boys would be more influenced from peers than girls. Therefore, smoking prevention programs for adolescents might be focused on the social context such as, resisting to peer pressure and enhancing the self-efficacy to control.

Adolescent↗
PubMed2002

[Spanish pediatric publications in PubMed between 1996 and 2001].

OBJECTIVES: To assess and compare the scientific pediatric production of Spanish authors in Pubmed and Journal Citation Reports (JCR) between 1996 and 2001. MATERIAL AND METHODS: We reviewed the first 200 articles that appeared in PubMed between 1996 and 2001 on childhood ("newborn OR neonate OR children OR child OR infant") by Spanish authors (Spain [affiliation]). We compared the quality of study design, sample sizes, subject of the article, impact factor and the authors' specialty, using the chi-squared and/or Student's t-test. The factors related to publication in journals with an impact factor of more than 2 were analyzed using logistic regression analysis. RESULTS: Only 35 % of the articles selected were performed exclusively in children. Between 1996 and 2001, Spanish pediatric publications included in the Journal Impact Factor increased by 37.5 %. The impact factor between these two years was similar (1.776 vs 1.823; p: NS). An impact factor of more than 2 was related to articles published in non-pediatric journals (OR: 3, 95 % CI: 1.17-7.69, p 0.018), publications including multiple regression analysis in the statistical analysis (OR: 3.27; 95 % CI: 1.12-9.56; p 0.028), multicenter studies (OR: 4.2, 95 % CI: 1.1-22.4, p 0.048) and articles on immunology or molecular biology (OR: 2.45; 95 % CI: 1.01-5.92; p 0.044). CONCLUSIONS: In the last 5 years Spanish pediatric publications in journals included in the JCR increased by 37.5 %. We should promote publications with larger sample sizes, multicentric studies and those with high quality design (clinical trials and cohort studies).

Bibliometrics↗
PubMed2003

[Drugs use among adolescents: results from the National Survey on Addictions, 1998].

OBJECTIVE: The aim of this paper is to describe drug and associated factors use among adolescents (12 to 17 years of age). MATERIAL AND METHODS: Data come from the recent Encuesta Nacional de Adicciones, 1998 (National Survey on Addictions) undertaken in urban areas of Mexico. A probabilistic, multi-stage, stratified cluster sampling design was used to select the study population. The sampling unit was the individual in each household. Statistical analysis consisted of the estimation of prevalences of drug use, with 95% confidence intervals. Associations were analyzed using logistic regressions models. RESULTS: Excluding tobacco and alcohol, 3.57% of males and 0.6% of females have used one or more drugs; 2.14% and 0.45% used them in the 12 months previous to the survey, and 1.4% and 0.3% in the previous 30 days, respectively. Marihuana was the drug more often used by males (2.4%) and females (0.45%), followed by inhaled solvents (1.08% and 0.20%), and cocaine (0.99% and 0.22%), respectively. The risk of using illicit drugs was associated to being male, having dropped out from school, perceiving availability, drug use by family and friends, social tolerance among friends, and symptoms of depression. CONCLUSIONS: Adolescents between 12 to 17 years of age are exposed to increasing drug use. The rates of drug use have risen, especially in the northern region of Mexico and in the big urban areas (Tijuana, Mexico City and Guadalajara). These findings emphasize the need to develop campaigns to detect emotional problems. Preventive measures should provide appropriate care to prevent drug use as a mechanism to cope with such emotional conflicts. Also, more intense preventive interventions should be targeted to adolescents with a high probability of developing drug abuse.

Adolescent↗