A generalized estimating equations approach for analysis of the impact of new technology on a trawl fishery

The article describes a generalized estimating equations approach that was used to investigate the impact of technology on vessel performance in a trawl fishery during 1988-96, while accounting for spatial and temporal correlations in the catch-effort data. Robust estimation of parameters in the presence of several levels of clustering depended more on the choice of cluster definition than on the choice of correlation structure within the cluster. Models with smaller cluster sizes produced stable results, while models with larger cluster sizes, that may have had complex within-cluster correlation structures and that had within-cluster covariates, produced estimates sensitive to the correlation structure. The preferred model arising from this dataset assumed that catches from a vessel were correlated in the same years and the same areas, but independent in different years and areas. The model that assumed catches from a vessel were correlated in all years and areas, equivalent to a random effects term for vessel, produced spurious results. This was an unexpected finding that highlighted the need to adopt a systematic strategy for modelling. The article proposes a modelling strategy of selecting the best cluster definition first, and the working correlation structure (within clusters) second. The article discusses the selection and interpretation of the model in the light of background knowledge of the data and utility of the model, and the potential for this modelling approach to apply in similar statistical situations.

Systematic analysis of changes in cannabis use among participants in control conditions of randomised controlled trials

Introduction Cannabis remains the most used illegal substance across the globe, and negative outcomes and disorders are common. A spotlight therefore falls on reductions in cannabis use in people with cannabis use disorder. Current estimates of unassisted cessation or reduction in cannabis use rely on community surveys, and few studies focus on individuals with disorder. A key interest of services and researchers is to estimate effect size of reductions in consumption among treatment seekers who do not obtain treatment. Effects within waiting list or information-only control conditions of randomised controlled trials offer an opportunity to study this question. Method This paper examines the extent of reductions in days of cannabis use in the control groups of randomised controlled trials on treatment of cannabis use disorders. A systematic literature search was performed to identify trials that reported days of cannabis use in the previous 30 (or equivalent). Results Since all but one of the eight identified studies had delayed treatment controls, results could only be summarised across 2–4 months. Average weighted days of use in the previous 30 days fell from 24.5 to 19.9, and a meta-analysis using a random effects model showed an average reduction of 0.442 SD. However, every study had at least one significant methodological issue. Conclusions While further high-quality data is needed to confirm the observed effects, these results provide a baseline from which researchers and practitioners can estimate the extent of change required to detect effects of cannabis treatments in services or treatment trials.

Occupational determinants of pancreatic cancer

Objective and background. Tobacco smoking, pancreatitis and diabetes mellitus are the only known causes of pancreatic cancer, leaving ample room for yet unidentified determinants. This is an empirical study on a Finnish data on occupational exposures and pancreatic cancer risk, and a non-Bayesian and a hierarchical Bayesian meta-analysis of data on occupational factors and pancreatic cancer. Methods. The case-control study analyzed 595 incident cases of pancreatic cancer and 1,622 controls of stomach, colon, and rectum cancer, diagnosed 1984-1987 and known to be dead by 1990 in Finland. The next-of-kin responded to a mail questionnaire on job and medical histories and lifestyles. Meta-analysis of occupational risk factors of pancreatic cancer started off with 1,903 identified studies. The analyses were based on different subsets of that database. Five epidemiologists examined the reports and extracted the pertinent data using a standardized extraction form that covered 20 study descriptors and the relevant relative risk estimates. Random effects meta-analyses were applied for 23 chemical agents. In addition, hierarchical Bayesian models for meta-analysis were applied to the occupational data of 27 job titles using job exposure matrix as a link matrix and estimating the relative risks of pancreatic cancer associated with nine occupational agents. Results. In the case-control study, logistic regressions revealed excess risks of pancreatic cancer associated with occupational exposures to ionizing radiation, nonchlorinated solvents, and pesticides. Chlorinated hydrocarbon solvents and related compounds, used mainly in metal degreasing and dry cleaning, are emerging as likely risk factors of pancreatic cancer in the non-Bayesian and the hierarchical Bayesian meta-analysis. Consistent excess risk was found for insecticides, and a high excess for nickel and nickel compounds in the random effects meta-analysis but not in the hierarchical Bayesian meta-analysis. Conclusions. In this study occupational exposure to chlorinated hydrocarbon solvents and related compounds and insecticides increase risk of pancreatic cancer. Hierarchical Bayesian meta-analysis is applicable when studies addressing the agent(s) under study are lacking or very few, but several studies address job titles with potential exposure to these agents. A job-exposure matrix or a formal expert assessment system is necessary in this situation.

WinBUGS code to run a network meta-analysis

WinBUGS code and data to reproduce our network meta-analysis from "Control strategies to prevent total hip replacement-related infections: a systematic review and mixed treatment comparison" published in BMJ Open.

Fishing power increases continue in Queensland's east coast trawl fishery, Australia

The Queensland east coast trawl fishery is by far the largest prawn and scallop otter trawl fleet in Australia in terms of number of vessels, with 504 vessels licensed to fish for species including tiger prawns, endeavour prawns, red spot king prawns, eastern king prawns and saucer scallops by the end of 2004. The vessel fleet has gradually upgraded characteristics such as engine power and use of propeller nozzles, quad nets, global positioning systems (GPS) and computer mapping software. These changes, together with the ever-changing profile of the fleet, were analysed by linear mixed models to quantify annual efficiency increases of an average vessel at catching prawns or scallops. The analyses included vessel characteristics (treated as fixed effects) and vessel identifier codes (treated as random effects). For the period from 1989 to 2004 the models estimated overall fishing power increases of 6% in the northern tiger, 6% in the northern endeavour, 12% in the southern tiger, 18% in the red spot king, 46% in the eastern king prawn and 15% in the saucer scallop sector. The results illustrate the importance of ongoing monitoring of vessel and fleet characteristics and the need to use this information to standardise catch rate indices used in stock assessment and management.

Bayesian estimation of the dynamics of pandemic (H1N1) 2009 influenza transmission in Queensland: A space–time SIR-based model

Background A pandemic strain of influenza A spread rapidly around the world in 2009, now referred to as pandemic (H1N1) 2009. This study aimed to examine the spatiotemporal variation in the transmission rate of pandemic (H1N1) 2009 associated with changes in local socio-environmental conditions from May 7–December 31, 2009, at a postal area level in Queensland, Australia. Method We used the data on laboratory-confirmed H1N1 cases to examine the spatiotemporal dynamics of transmission using a flexible Bayesian, space–time, Susceptible-Infected-Recovered (SIR) modelling approach. The model incorporated parameters describing spatiotemporal variation in H1N1 infection and local socio-environmental factors. Results The weekly transmission rate of pandemic (H1N1) 2009 was negatively associated with the weekly area-mean maximum temperature at a lag of 1 week (LMXT) (posterior mean: −0.341; 95% credible interval (CI): −0.370–−0.311) and the socio-economic index for area (SEIFA) (posterior mean: −0.003; 95% CI: −0.004–−0.001), and was positively associated with the product of LMXT and the weekly area-mean vapour pressure at a lag of 1 week (LVAP) (posterior mean: 0.008; 95% CI: 0.007–0.009). There was substantial spatiotemporal variation in transmission rate of pandemic (H1N1) 2009 across Queensland over the epidemic period. High random effects of estimated transmission rates were apparent in remote areas and some postal areas with higher proportion of indigenous populations and smaller overall populations. Conclusions Local SEIFA and local atmospheric conditions were associated with the transmission rate of pandemic (H1N1) 2009. The more populated regions displayed consistent and synchronized epidemics with low average transmission rates. The less populated regions had high average transmission rates with more variations during the H1N1 epidemic period.

Ambient temperature and risk of cardiovascular hospitalization: An updated systematic review and meta-analysis

The association between temperatures and risk of cardiovascular mortality has been recognized but the association drawn from previous meta-analysis was weak due to the lack of sufficient studies. This paper presented a review with updated reports in the literature about the risk of cardiovascular hospitalization in relation to different temperature exposures and examined the dose–response relationship of temperature-cardiovascular hospitalization by change in units of temperature, latitudes, and lag days. The pooled effect sizes were calculated for cold, heat, heatwave, and diurnal variation using random-effects meta-analysis, and the dose–response relationship of temperature-cardiovascular admission was modelled using random-effect meta-regression. The Cochrane Q-test and index of heterogeneity (I2) were used to evaluate heterogeneity, and Egger's test was used to evaluate publication bias. Sixty-four studies were included in meta-analysis. The pooled results suggest that for a change in temperature condition, the risk of cardiovascular hospitalization increased 2.8% (RR, 1.028; 95% CI, 1.021–1.035) for cold exposure, 2.2% (RR, 1.022; 95% CI, 1.006–1.039) for heatwave exposure, and 0.7% (RR, 1.007; 95% CI, 1.002–1.012) for an increase in diurnal temperature. However no association was observed for heat exposure. The significant dose–response relationship of temperature — cardiovascular admission was found with cold exposure and diurnal temperature. Increase in one-day lag caused a marginal reduction in risk of cardiovascular hospitalizations for cold exposure and diurnal variation, and increase in latitude was associated with a decrease in risk of cardiovascular hospitalizations for diurnal temperature only. There is a significant short-term effect of cold exposure, heatwave and diurnal variation on cardiovascular hospitalizations. Further research is needed to understand the temperature-cardiovascular relationship for different climate areas.

Prevalence of foot disease and risk factors in general inpatient populations: A systematic review and meta-analysis

Objective: To systematically review studies reporting the prevalence in general adult inpatient populations of foot disease disorders (foot wounds, foot infections, collective ‘foot disease’) and risk factors (peripheral arterial disease (PAD), peripheral neuropathy (PN), foot deformity). Methods: A systematic review of studies published between 1980 and 2013 was undertaken using electronic databases (MEDLINE, EMBASE and CINAHL). Keywords and synonyms relating to prevalence, inpatients, foot disease disorders and risk factors were used. Studies reporting foot disease or risk factor prevalence data in general inpatient populations were included. Included study's reference lists and citations were searched and experts consulted to identify additional relevant studies. 2 authors, blinded to each other, assessed the methodological quality of included studies. Applicable data were extracted by 1 author and checked by a second author. Prevalence proportions and SEs were calculated for all included studies. Pooled prevalence estimates were calculated using random-effects models where 3 eligible studies were available. Results: Of the 4972 studies initially identified, 78 studies reporting 84 different cohorts (total 60 231 517 participants) were included. Foot disease prevalence included: foot wounds 0.01–13.5% (70 cohorts), foot infections 0.05–6.4% (7 cohorts), collective foot disease 0.2–11.9% (12 cohorts). Risk factor prevalence included: PAD 0.01–36.0% (10 cohorts), PN 0.003–2.8% (6 cohorts), foot deformity was not reported. Pooled prevalence estimates were only able to be calculated for pressure ulcer-related foot wounds 4.6% (95% CI 3.7% to 5.4%)), diabetes-related foot wounds 2.4% (1.5% to 3.4%), diabetes-related foot infections 3.4% (0.2% to 6.5%), diabetes-related foot disease 4.7% (0.3% to 9.2%). Heterogeneity was high in all pooled estimates (I2=94.2–97.8%, p<0.001). Conclusions: This review found high heterogeneity, yet suggests foot disease was present in 1 in every 20 inpatients and a major risk factor in 1 in 3 inpatients. These findings are likely an underestimate and more robust studies are required to provide more precise estimates.

Decomposing the Gender Wage Gap: The effect of firms, occupations and Job Stratification

This paper presents new evidence on the role of segregation into firms, occupations within a firm and stratification into professional categories within firm-occupations in explaining the gender wage gap. I use a generalized earnings model that allows observed and unobserved group characteristics to have different impact on wages of men and women within the same group. The database is a large sample of individual wage data from the 1995 Spanish Wage Structure Survey. Results indicate that firm segregation in our sample accounts for around one-fifth of the raw gender wage gap. Occupational segregation within firms accounts for about one-third of the raw wage gap, and stratification into different professional categories within firms and occupations explains another one-third of it. The remaining one-fifth of the overall gap arises from better outcomes of men relative to women within professional categories. It is also found that rewards to both observable and unobservable skills, particularly those related to education, are higher for males than for females within the same group. Finally, mean wages in occupations or job categories with a higher fraction of female co-workers are lower, but the negative impact of femaleness in higher for women.

Impactos da abertura comercial na margem de lucro da indústria brasileira de transformação entre 1990 e 1996: uma análise em dados de painel

O objetivo principal desta dissertação é analisar os impactos da abertura comercial vista no Brasil no início da década de 1990 entre 1990 a 1996 na margem de lucro das indústrias de transformação passando por três padrões monetários diferentes (cruzeiro, cruzeiro real e real). A especificação e metodologia adotadas no trabalho são as de Goldar e Aggawal (2004), que fazem uma análise de dados em painel para efeitos fixos e randômicos para as indústrias de transformação indianas como um todo e, posteriormente, aplicando os mesmos testes separando os vinte e oito setores da indústria brasileira de transformação em setores de bens de capital e intermediários no primeiro grupo e bens de capital no segundo. Este trabalho ainda inclui esta metodologia aplicando, além das duas já citadas, o teste de mínimos quadrados ordinários (MQO) para permitir uma melhor análise com três testes diferentes antes e depois de separar os setores por meio de variáveis explicativas como barreiras à importação, concentração industrial, participação salarial, produtividade do trabalho, representatividade setorial e variação na taxa de crescimento da produção do setor entre os anos. Conclui-se que o aumento observado na margem de lucro foi impactado significativamente pelas variáveis expostas acima e estes resultados são importantes para que possamos auferir de que forma impactaram positivamente ou contribuíram negativamente na margem de lucro auferida pela indústria brasileira de transformação entre 1990 e 1996.

Transtorno do Estresse Pós-Traumático e alterações lipídicas

O transtorno do estresse pós-traumático (TEPT) e alterações lipídicas são as temáticas principais dessa Dissertação. Seu objetivo principal foi investigar a associação entre o TEPT e as concentrações séricas de colesterol total (CT), lipoproteína de baixa densidade (LDL), lipoproteína de alta densidade (HDL) e triglicerídeos (TG) através de uma revisão sistemática da literatura seguida de metanálise. Adicionalmente, a relação entre essas variáveis lipídicas e os grupos de sintomas do TEPT revivescência, esquiva/entorpecimento emocional e hiperestimulação autonômica foi avaliada em um segundo estudo com dados primários. A metanálise incluiu 18 artigos, totalizando 2.110 indivíduos com TEPT e 17.550 indivíduos sem TEPT. As diferenças de médias ponderadas (DMP) mg/dL dos parâmetros lipídicos foram calculadas por modelos de efeitos aleatórios e modelos de meta-regressão foram ajustados para investigar possíveis fontes de heterogeneidade. O estudo encontrou que o TEPT foi associado a um pior perfil lipídico quando comparados a controles sem o transtorno (DMPCT= 20,57, IC 95% 12,21 28,93; DMPLDL= 12,11, IC 95% 5,89 18,32; DMPHDL= -3,73, IC 95% -5,97 -1,49; DMPTG= 35,87, IC 95% 21,12 50,61). A heterogeneidade estatística entre os resultados dos estudos foi alta para todos os parâmetros lipídicos e a variável que mais pareceu explicar essas inconsistências foi idade. O segundo artigo faz parte de um estudo maior conduzido em 2004 com 157 policiais do sexo masculino do Batalhão de Choque da Polícia Militar do Estado de Goiás (BPMCHOQUE). Somente oficiais de férias ou em dispensa inclusive dispensa médica não foram avaliados. O instrumento utilizado para o rastreio do TEPT foi a versão em português para civis da Post-Traumatic Stress Disorder Checklist (PCL-C). Trinta e nove participantes (25%) foram excluídos do estudo: dois porque falharam no preenchimento dos questionários e 37 cujas amostras de sangue não foram coletadas por vários motivos. Neste trabalho, encontrou-se uma forte correlação positiva entre as concentrações séricas de CT e LDL com o grupo de sintomas de hiperestimulação autonômica, somente no grupo TEPT: ρ= 0,89 (p<0,01) e ρ =0,92 (p<0,01), respectivamente. Em suma, espera-se que os resultados dessa Dissertação possam colaborar para o estabelecimento de um melhor acompanhamento clínico de pacientes com TEPT, particularmente porque estes parecem estar sob um maior risco de doenças cardiovasculares devido a um pior perfil lipídico.

Associação entre bebidas adoçadas e consumo calórico em refeições na população brasileira.

Nas últimas décadas, tem sido observado o aumento da oferta de bebidas com elevado conteúdo calórico e com grandes quantidades de açúcar de rápida absorção. Essas bebidas adoçadas, cujo consumo tem aumentado no Brasil assim como em outras partes do mundo, são consideradas fatores de risco para obesidade e diabetes. O consumo de bebidas adoçadas pode levar ao balanço energético positivo e consequentemente ao ganho de peso. Essa associação pode ser explicada pelo mecanismo regulatório de compensação de calorias líquidas. Compensação calórica ocorre quando há redução no consumo de calorias provenientes de alimentos sólidos para compensar as calorias líquidas adicionadas à refeição ou dieta. No entanto, não há consenso em relação a evidências da compensação calórica, dificultando a elaboração de recomendações sobre essas bebidas em saúde pública. Razões para a falta de consenso incluem a diversidade de desenhos de estudos, experimentos realizados em ambientes controlados e não reais em relação ao consumo de alimentos e bebidas, e estudos com amostras pequenas ou de conveniência. Esta dissertação estudou a associação entre bebidas adoçadas e consumo calórico, verificando se calorias de bebidas adoçadas são compensadas em refeições realizadas em um ambiente pragmático. Os dados de consumo calórico de 34.003 indivíduos, com idade igual ou superior a dez anos, foram obtidos pelo Inquérito Nacional de Alimentação 2008-2009, em todo território nacional. Os participantes completaram dois registros alimentares, em dias não consecutivos da mesma semana. Foram selecionadas as refeições dos períodos café da manhã, almoço e jantar de cada indivíduo em cada um dos dias. Para cada refeição, foi calculado o valor calórico de alimentos e de bebidas adoçadas consumidos. Para testar a compensação calórica, um modelo de regressão linear multinível com efeitos mistos foi ajustado para analisar cada período. A variável reposta utilizada foi consumo calórico proveniente de alimentos e a variável explicativa foi consumo calórico de bebida adoçada na refeição. Os efeitos intra-indivíduo da bebida adoçada no consumo calórico foram estimados e interpretados. Esses efeitos são considerados não-enviesados pois são controlados pelas características constantes dos indivíduos, tendo assim o indivíduo atuando como seu próprio controle na análise. Covariadas incluídas no modelo foram variáveis da refeição: local, dia da semana, horário, consumo calórico na refeição anterior e intervalo de tempo desde a última refeição; e do indivíduo: sexo, faixa etária, categoria de Índice de Massa Corpórea e quartos de renda per capita. Efeitos aleatórios dos indivíduos e dos domicílios foram incluídos no modelo para melhor estimar a estrutura de erros de dados correlacionados. A compensação calórica foi de 42% para o café da manhã, não houve compensação no almoço e para o jantar, compensação variou de 0 a 22%, tendo interação com quartos de renda per capita. A conclusão desta dissertação é que as bebidas adoçadas não são completamente compensadas em refeições realizadas em ambiente pragmático. Assim, a redução do consumo de bebidas adoçadas em refeições pode ajudar a diminuir o consumo calórico excessivo e levar a um melhor controle do peso em indivíduos.

Pressure support versus T-tube for weaning from mechanical ventilation in adults

BackgroundMechanical ventilation is important in caring for patients with critical illness. Clinical complications, increased mortality, and high costs of health care are associated with prolonged ventilatory support or premature discontinuation of mechanical ventilation. Weaning refers to the process of gradually or abruptly withdrawing mechanical ventilation. the weaning process begins after partial or complete resolution of the underlying pathophysiology precipitating respiratory failure and ends with weaning success (successful extubation in intubated patients or permanent withdrawal of ventilatory support in tracheostomized patients).ObjectivesTo evaluate the effectiveness and safety of two strategies, a T-tube and pressure support ventilation, for weaning adult patients with respiratory failure that required invasive mechanical ventilation for at least 24 hours, measuring weaning success and other clinically important outcomes.Search methodsWe searched the following electronic databases: Cochrane Central Register of Controlled Trials (CENTRAL) (The Cochrane Library 2012, Issue 6); MEDLINE (via PubMed) (1966 to June 2012); EMBASE (January 1980 to June 2012); LILACS (1986 to June 2012); CINAHL (1982 to June 2012); SciELO (from 1997 to August 2012); thesis repository of CAPES (Coordenacao de Aperfeicoamento de Pessoal de Nivel Superior) (http://capesdw.capes.gov.br/capesdw/) (August 2012); and Current Controlled Trials (August 2012).We reran the search in December 2013. We will deal with any studies of interest when we update the review.Selection criteriaWe included randomized controlled trials (RCTs) that compared a T-tube with pressure support (PS) for the conduct of spontaneous breathing trials and as methods of gradual weaning of adult patients with respiratory failure of various aetiologies who received invasive mechanical ventilation for at least 24 hours.Data collection and analysisTwo authors extracted data and assessed the methodological quality of the included studies. Meta-analyses using the random-effects model were conducted for nine outcomes. Relative risk (RR) and mean difference (MD) or standardized mean difference (SMD) were used to estimate the treatment effect, with 95% confidence intervals (CI).Main resultsWe included nine RCTs with 1208 patients; 622 patients were randomized to a PS spontaneous breathing trial (SBT) and 586 to a T-tube SBT. the studies were classified into three categories of weaning: simple, difficult, and prolonged. Four studies placed patients in two categories of weaning. Pressure support ventilation (PSV) and a T-tube were used directly as SBTs in four studies (844 patients, 69.9% of the sample). in 186 patients (15.4%) both interventions were used along with gradual weaning from mechanical ventilation; the PS was gradually decreased, twice a day, until it was minimal and periods with a T-tube were gradually increased to two and eight hours for patients with difficult and prolonged weaning. in two studies (14.7% of patients) the PS was lowered to 2 to 4 cm H2O and 3 to 5 cm H2O based on ventilatory parameters until the minimal PS levels were reached. PS was then compared to the trial with the T-tube (TT).We identified 33 different reported outcomes in the included studies; we took 14 of them into consideration and performed meta-analyses on nine. With regard to the sequence of allocation generation, allocation concealment, selective reporting and attrition bias, no study presented a high risk of bias. We found no clear evidence of a difference between PS and TT for weaning success (RR 1.07, 95% CI 0.97 to 1.17, 9 studies, low quality of evidence), intensive care unit (ICU) mortality (RR 0.81, 95% CI 0.53 to 1.23, 5 studies, low quality of evidence), reintubation (RR 0.92, 95% CI 0.66 to 1.26, 7 studies, low quality evidence), ICU and long-term weaning unit (LWU) length of stay (MD -7.08 days, 95% CI -16.26 to 2.1, 2 studies, low quality of evidence) and pneumonia (RR 0.67, 95% CI 0.08 to 5.85, 2 studies, low quality of evidence). PS was significantly superior to the TT for successful SBTs (RR 1.09, 95% CI 1.02 to 1.17, 4 studies, moderate quality of evidence). Four studies reported on weaning duration, however we were unable to combined the study data because of differences in how the studies presented their data. One study was at high risk of other bias and four studies were at high risk for detection bias. Three studies reported that the weaning duration was shorter with PS, and in one study the duration was shorter in patients with a TT.Authors' conclusionsTo date, we have found evidence of generally low quality from studies comparing pressure support ventilation (PSV) and with a T-tube. the effects on weaning success, ICU mortality, reintubation, ICU and LWU length of stay, and pneumonia were imprecise. However, PSV was more effective than a T-tube for successful spontaneous breathing trials (SBTs) among patients with simple weaning. Based on the findings of single trials, three studies presented a shorter weaning duration in the group undergoing PS SBT, however a fourth study found a shorter weaning duration with a T-tube.

The impact of structured support groups for pregnant South African women recently diagnosed HIV positive.

The authors of this study evaluated a structured 10-session psychosocial support group intervention for newly HIV-diagnosed pregnant South African women. Participants were expected to display increases in HIV disclosure, self-esteem, active coping and positive social support, and decreases in depression, avoidant coping, and negative social support. Three hundred sixty-one pregnant HIV-infected women were recruited from four antenatal clinics in Tshwane townships from April 2005 to September 2006. Using a quasi-experimental design, assessments were conducted at baseline and two and eight months post-intervention. A series of random effects regression analyses were conducted, with the three assessment points treated as a random effect of time. At both follow-ups, the rate of disclosure in the intervention group was significantly higher than that of the comparison group (p<0.001). Compared to the comparison group at the first follow-up, the intervention group displayed higher levels of active coping (t=2.68, p<0.05) and lower levels of avoidant coping (t=-2.02, p<0.05), and those who attended at least half of the intervention sessions exhibited improved self-esteem (t=2.11, p<0.05). Group interventions tailored for newly HIV positive pregnant women, implemented in resource-limited settings, may accelerate the process of adjusting to one's HIV status, but may not have sustainable benefits over time.

Lognormal and gamma mixed negative binomial regression

In regression analysis of counts, a lack of simple and efficient algorithms for posterior computation has made Bayesian approaches appear unattractive and thus underdeveloped. We propose a lognormal and gamma mixed negative binomial (NB) regression model for counts, and present efficient closed-form Bayesian inference; unlike conventional Poisson models, the proposed approach has two free parameters to include two different kinds of random effects, and allows the incorporation of prior information, such as sparsity in the regression coefficients. By placing a gamma distribution prior on the NB dispersion parameter r, and connecting a log-normal distribution prior with the logit of the NB probability parameter p, efficient Gibbs sampling and variational Bayes inference are both developed. The closed-form updates are obtained by exploiting conditional conjugacy via both a compound Poisson representation and a Polya-Gamma distribution based data augmentation approach. The proposed Bayesian inference can be implemented routinely, while being easily generalizable to more complex settings involving multivariate dependence structures. The algorithms are illustrated using real examples. Copyright 2012 by the author(s)/owner(s).