Missing data mechanisms and their implications on the analysis of categorical data

We review some issues related to the implications of different missing data mechanisms on statistical inference for contingency tables and consider simulation studies to compare the results obtained under such models to those where the units with missing data are disregarded. We confirm that although, in general, analyses under the correct missing at random and missing completely at random models are more efficient even for small sample sizes, there are exceptions where they may not improve the results obtained by ignoring the partially classified data. We show that under the missing not at random (MNAR) model, estimates on the boundary of the parameter space as well as lack of identifiability of the parameters of saturated models may be associated with undesirable asymptotic properties of maximum likelihood estimators and likelihood ratio tests; even in standard cases the bias of the estimators may be low only for very large samples. We also show that the probability of a boundary solution obtained under the correct MNAR model may be large even for large samples and that, consequently, we may not always conclude that a MNAR model is misspecified because the estimate is on the boundary of the parameter space.

Estimate of Dementia Prevalence in a Community Sample from Sao Paulo, Brazil

Aims: To estimate dementia prevalence and describe the etiology of dementia in a community sample from the city of Sao Paulo, Brazil. Methods: A sample of subjects older than 60 years was screened for dementia in the first phase. During the second phase, the diagnostic workup included a structured interview, physical and neurological examination, laboratory exams, a brain scan, and DSM-IV criteria diagnosis. Results: Mean age was 71.5 years (n = 1,563) and 58.3% had up to 4 years of schooling (68.7% female). Dementia was diagnosed in 107 subjects with an observed prevalence of 6.8%. The estimate of dementia prevalence was 12.9%, considering design effect, nonresponse during the community phase, and positive and negative predictive values. Alzheimer`s disease was the most frequent cause of dementia (59.8%), followed by vascular dementia (15.9%). Older age and illiteracy were significantly associated with dementia. Conclusions: The estimate of dementia prevalence was higher than previously reported in Brazil, with Alzheimer`s disease and vascular dementia being the most frequent causes of dementia. Dementia prevalence in Brazil and in other Latin American countries should be addressed by additional studies to confirm these higher dementia rates which might have a sizable impact on countries` health services. Copyright (C) 2008 S. Karger AG, Basel

Adult-onset Still`s Disease with Pulmonary and Cardiac Involvement and Response to Intravenous Immunoglobulin

Cardiopulmonary manifestations of adult-onset Still`s disease (AOSD) include pericarditis, pleural effusion, transient pulmonary infiltrates, pulmonary interstitial disease and myocarditis. Serositis are common but pneumonitis and myocarditis are not and bring elevated risk of mortality. They may manifest on disease onset or flares. Previously reported cases were treated with high-dose glucocorticoids and immunosupressants and, when refractory, intravenous immunoglobulin (IVIG). We report an AOSD patient whose flare presented with severe pleupneumonitis and myopericarditis and, following nonresponse to a methylprednisolone pulse, high dose of prednisone and cyclosporine A, recovered after a 2-day 1g/kg/day IVIG infusion.

Very early prediction of response to HCV treatment with PEG-IFN-alfa-2a and ribavirin in HIV/HCV-coinfected patients

The objective of this study was to find very early viral kinetic markers to predict nonresponse to hepatitis C virus (HCV) therapy in a group of human immunodeficiency virus (HIV)/HCV-coinfected patients. Twenty-six patients (15 HCV genotype-1 and 11 genotype-3) were treated with a 48-week regimen of peginterferon-alfa-2a (PEG-IFN) (180 mu g/week) and weight-based ribavirin (11 mg/kg/day). Samples were collected at baseline; 4, 8, 12, 18, 24, 30, 36 and 42 h; days 2, 3, 4, 7, 8, 15, 22, 29, 43 and 57 then weekly and monthly. Five patients discontinued treatment. Seven patients (27%) achieved a sustained virological response (SVR). Nadir HCV RNA levels were observed 1.6 +/- 0.3 days after initiation of therapy, followed by a 0.3- to 12.9-fold viral rebound until the administration of the second dose of PEG-IFN, which were not associated with SVR or HCV genotype. A viral decline < 1.19 log for genotype-1 and < 0.97 log for genotype-3, 2 days after starting therapy, had a negative predictive value (NPV) of 100% for SVR. The day 2 virological response had a similar positive predictive value for SVR as a rapid virological response at week 4. In addition, a second-phase viral decline slope (i.e., measured from day 2 to 29) < 0.3 log/week had a NPV = 100% for SVR. We conclude that first-phase viral decline at day 2 and second-phase viral decline slope (< 0.3 log/week) are excellent predictors of nonresponse. Further studies are needed to validate these viral kinetic parameters as early on-treatment prognosticators of nonresponse in patients with HCV and HIV.

The H63D genetic variant of the HFE gene is independently associated with the virological response to interferon and ribavirin therapy in chronic hepatitis C

Background Conflicting results have been reported in studies evaluating the relationship between serum markers of iron overload, liver iron deposits, and HFE mutations (C282Y and H63D) in chronic hepatitis C patients, and also their impact on the response to therapy in these patients. Aim To evaluate the role of HFE mutations in the severity of liver disease and in the response to therapy in chronic hepatitis C. Methods Two hundred and sixty-four hepatitis C patients treated with standard interferon and ribavirin were divided into two groups according to type of antiviral response: sustained virological response (SVR) and nonresponse or relapse. We evaluated the relationship between HFE mutation and the type of antiviral response, clinical data, biochemical tests, liver histopathology, virological data, and HFE mutations. Results Of the 264 patients, 88 (32.1%) had SVR whereas 67.9% had nonresponse or relapse. Liver iron deposits were observed in 49.2% of the patients. The factors associated with SVR were hepatitis C virus genotype 2 or 3, transferrin saturation value of 45% or less, and detection of the H63D mutation. HFE mutation was more frequent in patients with iron deposits, but without association with serum iron biochemistry or severity of liver disease. Steatosis was more frequent in patients with liver iron deposits. Conclusion The H63D mutation was an independent factor associated with SVR in chronic hepatitis C patients, as also were hepatitis C virus genotype 2 or 3 and transferrin saturation value of 45% or less. Moreover, the H63D mutation was associated with liver iron deposits. Eur J Gastroenterol Hepatol 22: 1204-1210 (C) 2010 Wolters Kluwer Health | Lippincott Williams & Wilkins.

Inferential Implications of Over-Parametrization: A Case Study in Incomplete Categorical Data

P>In the context of either Bayesian or classical sensitivity analyses of over-parametrized models for incomplete categorical data, it is well known that prior-dependence on posterior inferences of nonidentifiable parameters or that too parsimonious over-parametrized models may lead to erroneous conclusions. Nevertheless, some authors either pay no attention to which parameters are nonidentifiable or do not appropriately account for possible prior-dependence. We review the literature on this topic and consider simple examples to emphasize that in both inferential frameworks, the subjective components can influence results in nontrivial ways, irrespectively of the sample size. Specifically, we show that prior distributions commonly regarded as slightly informative or noninformative may actually be too informative for nonidentifiable parameters, and that the choice of over-parametrized models may drastically impact the results, suggesting that a careful examination of their effects should be considered before drawing conclusions.Resume Que ce soit dans un cadre Bayesien ou classique, il est bien connu que la surparametrisation, dans les modeles pour donnees categorielles incompletes, peut conduire a des conclusions erronees. Cependant, certains auteurs persistent a negliger les problemes lies a la presence de parametres non identifies. Nous passons en revue la litterature dans ce domaine, et considerons quelques exemples surparametres simples dans lesquels les elements subjectifs influencent de facon non negligeable les resultats, independamment de la taille des echantillons. Plus precisement, nous montrons comment des a priori consideres comme peu ou non-informatifs peuvent se reveler extremement informatifs en ce qui concerne les parametres non identifies, et que le recours a des modeles surparametres peut avoir sur les conclusions finales un impact considerable. Ceci suggere un examen tres attentif de l`impact potentiel des a priori.