Pedro Luis do Nascimento Silva

Análise estatística de dados da PNAD: incorporando a estrutura do plano amostral

Este artigo descreve como podem ser considerados na analise dos dados da Pesquisa Nacional por Amostra de Domicilios (PNAD) do IBGE os diversos aspectos de seu plano amostral complexo: estratificacao, conglomeracao, probabilidades desiguais de selecao e ajustes dos pesos para calibracao. Para isso, inclui: uma descricao resumida porem completa do plano amostral dessa pesquisa; indicacao de como seus dados podem ser usados para estimar totais; e tambem uma descricao resumida dos metodos essenciais para ajustar modelos parametricos regulares com os dados da pesquisa levando em conta os aspectos de amostragem complexa. Apresenta ainda os resultados de algumas estimativas para caracteristicas de pessoas e domicilios calculadas com base nos dados da PNAD/1998, para as quais sao apresentadas estimativas dos respectivos desvios padrao e dos efeitos do plano amostral. Conclui com uma indicacao dos cuidados que os usuarios devem ter ao analisar tais dados em sua pratica de pesquisa.

Sampling design for the World Health Survey in Brazil

This paper describes the sample design used in the Brazilian application of the World Health Survey. The sample was selected in three stages. First, the census tracts were allocated in six strata defined by their urban/rural situation and population groups of the municipalities (counties). The tracts were selected using probabilities proportional to the respective number of households. In the second stage, households were selected with equiprobability using an inverse sample design to ensure 20 households interviewed per tract. In the last stage, one adult (18 years or older) per household was selected with equiprobability to answer the majority of the questionnaire. Sample weights were based on the inverse of the inclusion probabilities in the sample. To reduce bias in regional estimates, a household weighting calibration procedure was used to reduce sample bias in relation to income, sex, and age group.

Desenho da amostra Nascer no Brasil: Pesquisa Nacional sobre Parto e Nascimento

Este artigo descreve a amostra da Pesquisa Nacional sobre Parto e Nascimento no Brasil. Os hospitais com 500 ou mais nascidos vivos em 2007 foram estratificados por macrorregiao, capital de estado ou nao, e tipo, e selecionados com probabilidade proporcional ao numero de nascidos-vivos em 2007. Amostragem inversa foi usada para selecionar tantos dias de pesquisa (minimo de 7) quantos fossem necessarios para alcancar 90 entrevistas realizadas com puerperas no hospital. As puerperas foram amostradas com igual probabilidade entre as elegiveis que entraram no hospital no dia. Os pesos amostrais basicos sao o inverso do produto das probabilidades de inclusao em cada estagio e foram calibrados para assegurar que estimativas dos totais de nascidos vivos dos estratos correspondessem aos totais de nascidos vivos obtidos no SINASC. Para os dois seguimentos telefonicos (6 e 12 meses depois), a probabilidade de resposta das puerperas foi modelada pelas variaveis disponiveis na pesquisa de base, a fim de corrigir, para a nao resposta, os pesos amostrais em cada onda de seguimento.This paper describes the sample design for the National Survey into Labor and Birth in Brazil. The hospitals with 500 or more live births in 2007 were stratified into: the five Brazilian regions; state capital or not; and type of governance. They were then selected with probability proportional to the number of live births in 2007. An inverse sampling method was used to select as many days (minimum of 7) as necessary to reach 90 interviews in the hospital. Postnatal women were sampled with equal probability from the set of eligible women, who had entered the hospital in the sampled days. Initial sample weights were computed as the reciprocals of the sample inclusion probabilities and were calibrated to ensure that total estimates of the number of live births from the survey matched the known figures obtained from the Brazilian System of Information on Live Births. For the two telephone follow-up waves (6 and 12 months later), the postnatal womans response probability was modelled using baseline covariate information in order to adjust the sample weights for nonresponse in each follow-up wave.

Sampling design for the Study of Cardiovascular Risks in Adolescents (ERICA)

O Estudo de Riscos Cardiovasculares em Adoles-centes (ERICA) objetiva estimar prevalencia de fatores de risco cardiovascular e da sindrome metabolica em adolescentes (12 a 17 anos) matriculados em escolas publicas e privadas dos 273 municipios com mais de 100 mil habitantes no Brasil. A populacao de pesquisa foi estratificada em 32 estratos geograficos (27 capitais e cinco conjuntos com os demais municipios de cada macrorregiao do pais) e uma amostra de 1.251 escolas foi selecionada com probabilidade proporcional ao tamanho. Em cada escola foram selecionadas tres combinacoes de turno (manha e da tarde) e ano (serie), e em cada uma destas combinacoes foi selecionada uma turma. Todos os alunos elegiveis das turmas selecionadas foram objeto de pesquisa. Os pesos amostrais do desenho foram calculados pelo produto dos inversos das probabilidades de inclusao em cada estagio da amostra e foram depois calibrados considerando as projecoes do numero de adolescentes matriculados em escolas localizadas nos estratos geograficos considerados por sexo e idade.The Study of Cardiovascular Risk in Adolescents (ERICA) aims to estimate the prevalence of cardiovascular risk factors and metabolic syndrome in adolescents (12-17 years) enrolled in public and private schools of the 273 municipalities with over 100,000 inhabitants in Brazil. The study population was stratified into 32 geographical strata (27 capitals and five sets with other municipalities in each macro-region of the country) and a sample of 1,251 schools was selected with probability proportional to size. In each school three combinations of shift (morning and afternoon) and grade were selected, and within each of these combinations, one class was selected. All eligible students in the selected classes were included in the study. The design sampling weights were calculated by the product of the reciprocals of the inclusion probabilities in each sampling stage, and were later calibrated considering the projections of the numbers of adolescents enrolled in schools located in the geographical strata by sex and age.

Sampling design for the Birth in Brazil: National Survey into Labor and Birth

Este artigo descreve a amostra da Pesquisa Nacional sobre Parto e Nascimento no Brasil. Os hospitais com 500 ou mais nascidos vivos em 2007 foram estratificados por macrorregiao, capital de estado ou nao, e tipo, e selecionados com probabilidade proporcional ao numero de nascidos-vivos em 2007. Amostragem inversa foi usada para selecionar tantos dias de pesquisa (minimo de 7) quantos fossem necessarios para alcancar 90 entrevistas realizadas com puerperas no hospital. As puerperas foram amostradas com igual probabilidade entre as elegiveis que entraram no hospital no dia. Os pesos amostrais basicos sao o inverso do produto das probabilidades de inclusao em cada estagio e foram calibrados para assegurar que estimativas dos totais de nascidos vivos dos estratos correspondessem aos totais de nascidos vivos obtidos no SINASC. Para os dois seguimentos telefonicos (6 e 12 meses depois), a probabilidade de resposta das puerperas foi modelada pelas variaveis disponiveis na pesquisa de base, a fim de corrigir, para a nao resposta, os pesos amostrais em cada onda de seguimento.This paper describes the sample design for the National Survey into Labor and Birth in Brazil. The hospitals with 500 or more live births in 2007 were stratified into: the five Brazilian regions; state capital or not; and type of governance. They were then selected with probability proportional to the number of live births in 2007. An inverse sampling method was used to select as many days (minimum of 7) as necessary to reach 90 interviews in the hospital. Postnatal women were sampled with equal probability from the set of eligible women, who had entered the hospital in the sampled days. Initial sample weights were computed as the reciprocals of the sample inclusion probabilities and were calibrated to ensure that total estimates of the number of live births from the survey matched the known figures obtained from the Brazilian System of Information on Live Births. For the two telephone follow-up waves (6 and 12 months later), the postnatal womans response probability was modelled using baseline covariate information in order to adjust the sample weights for nonresponse in each follow-up wave.

Desenho da amostra do Estudo do Risco Cardiovascular em Adolescentes (ERICA)

O Estudo de Riscos Cardiovasculares em Adoles-centes (ERICA) objetiva estimar prevalencia de fatores de risco cardiovascular e da sindrome metabolica em adolescentes (12 a 17 anos) matriculados em escolas publicas e privadas dos 273 municipios com mais de 100 mil habitantes no Brasil. A populacao de pesquisa foi estratificada em 32 estratos geograficos (27 capitais e cinco conjuntos com os demais municipios de cada macrorregiao do pais) e uma amostra de 1.251 escolas foi selecionada com probabilidade proporcional ao tamanho. Em cada escola foram selecionadas tres combinacoes de turno (manha e da tarde) e ano (serie), e em cada uma destas combinacoes foi selecionada uma turma. Todos os alunos elegiveis das turmas selecionadas foram objeto de pesquisa. Os pesos amostrais do desenho foram calculados pelo produto dos inversos das probabilidades de inclusao em cada estagio da amostra e foram depois calibrados considerando as projecoes do numero de adolescentes matriculados em escolas localizadas nos estratos geograficos considerados por sexo e idade.The Study of Cardiovascular Risk in Adolescents (ERICA) aims to estimate the prevalence of cardiovascular risk factors and metabolic syndrome in adolescents (12-17 years) enrolled in public and private schools of the 273 municipalities with over 100,000 inhabitants in Brazil. The study population was stratified into 32 geographical strata (27 capitals and five sets with other municipalities in each macro-region of the country) and a sample of 1,251 schools was selected with probability proportional to size. In each school three combinations of shift (morning and afternoon) and grade were selected, and within each of these combinations, one class was selected. All eligible students in the selected classes were included in the study. The design sampling weights were calculated by the product of the reciprocals of the inclusion probabilities in each sampling stage, and were later calibrated considering the projections of the numbers of adolescents enrolled in schools located in the geographical strata by sex and age.

Comparison of different degrees of variability in tidal volume to prevent deterioration of respiratory system elastance in experimental acute lung inflammation

BACKGROUND Variable ventilation improves respiratory function, but it is not known whether the amount of variability in tidal volume (VT) can be reduced in recruited lungs without a deterioration of respiratory system elastance. METHODS Acute lung inflammation was induced by intratracheal instillation of lipopolysaccharide in 35 Wistar rats. Twenty-eight animals were anaesthetized and ventilated in volume-controlled mode. Lungs were recruited by random variation of VT (mean 6 ml kg(-1), coefficient of variation 30%, normal distribution) for 30 min. Animals were randomly assigned to different amounts of VT variability (n=7 for 90 min per group): 30, 15, 7.5, or 0%. Lung function, diffuse alveolar damage, and gene expression of biological markers associated with cell mechanical stress, inflammation, and fibrogenesis were assessed. Seven animals were not ventilated and served as controls for post-mortem analyses. RESULTS A VT variability of 30%, but not 15, 7.5, or 0%, prevented deterioration of respiratory system elastance [Mean (SD) -7.5 (8.7%), P<0.05; 21.1 (9.6%), P<0.05; 43.3 (25.9), P<0.05; and 41.2 (16.4), P<0.05, respectively]. Diffuse alveolar damage was lower with a VT variability of 30% than with 0% and without ventilation, because of reduced oedema and haemorrhage. A VT variability of 30, 15, or 7.5% reduced the gene expression of amphiregulin, cytokine-induced neutrophil chemoattractant-1, and tumour necrosis factor α compared with a VT variability of 0%. CONCLUSIONS In this model of acute lung inflammation, a VT variability of 30%, compared with 15 and 7.5%, was necessary to avoid deterioration of respiratory system elastance and was not associated with lung histological damage.

Reaching the hard-to-reach: a probability sampling method for assessing prevalence of driving under the influence after drinking in alcohol outlets.

Drinking alcoholic beverages in places such as bars and clubs may be associated with harmful consequences such as violence and impaired driving. However, methods for obtaining probabilistic samples of drivers who drink at these places remain a challenge – since there is no a priori information on this mobile population – and must be continually improved. This paper describes the procedures adopted in the selection of a population-based sample of drivers who drank at alcohol selling outlets in Porto Alegre, Brazil, which we used to estimate the prevalence of intention to drive under the influence of alcohol. The sampling strategy comprises a stratified three-stage cluster sampling: 1) census enumeration areas (CEA) were stratified by alcohol outlets (AO) density and sampled with probability proportional to the number of AOs in each CEA; 2) combinations of outlets and shifts (COS) were stratified by prevalence of alcohol-related traffic crashes and sampled with probability proportional to their squared duration in hours; and, 3) drivers who drank at the selected COS were stratified by their intention to drive and sampled using inverse sampling. Sample weights were calibrated using a post-stratification estimator. 3,118 individuals were approached and 683 drivers interviewed, leading to an estimate that 56.3% (SE = 3,5%) of the drivers intended to drive after drinking in less than one hour after the interview. Prevalence was also estimated by sex and broad age groups. The combined use of stratification and inverse sampling enabled a good trade-off between resource and time allocation, while preserving the ability to generalize the findings. The current strategy can be viewed as a step forward in the efforts to improve surveys and estimation for hard-to-reach, mobile populations.

Effects of acute hypercapnia with and without acidosis on lung inflammation and apoptosis in experimental acute lung injury

We investigated the effects of acute hypercapnic acidosis and buffered hypercapnia on lung inflammation and apoptosis in experimental acute lung injury (ALI). Twenty-four hours after paraquat injection, 28 Wistar rats were randomized into four groups (n=7/group): (1) normocapnia (NC, PaCO2=35-45 mmHg), ventilated with 0.03%CO2+21%O2+balancedN2; (2) hypercapnic acidosis (HC, PaCO2=60-70 mmHg), ventilated with 5%CO2+21%O2+balancedN2; and (3) buffered hypercapnic acidosis (BHC), ventilated with 5%CO2+21%O2+balancedN2 and treated with sodium bicarbonate (8.4%). The remaining seven animals were not mechanically ventilated (NV). The mRNA expression of interleukin (IL)-6 (p=0.003), IL-1β (p<0.001), and type III procollagen (PCIII) (p=0.001) in lung tissue was more reduced in the HC group in comparison with NC, with no significant differences between HC and BHC. Lung and kidney cell apoptosis was reduced in HC and BHC in comparison with NC and NV. In conclusion, in this experimental ALI model, hypercapnia, regardless of acidosis, reduced lung inflammation and lung and kidney cell apoptosis.

Sampling and Estimation in Household Surveys

Publisher Summary A household survey is a particular type of social survey. Household surveys focus on the characteristics of all or some members of the household. These characteristics include a subset of variables, such as health, education, income, expenditure, employment status, and use of various types of services. Because they became common in the 1940s, a number of major trends in household surveys have been evident. Many of these trends are closely linked to technological advances both in statistical agencies and in society and have accelerated following the spread of personal computers in the early 1980s. A good example of simplification is the Canadian Labour Force Survey (LFS), which went from four stages of sampling to two stages and for which the feasibility of using a single-stage design, with an address register as a frame, is being studied. In the United States, the American Community Survey (ACS) also adopted a stratified unclustered design.