Parameter recovery for a skew-normal IRT model under a Bayesian approach: hierarchical framework, prior and kernel sensitivity and sample size

Item response theory (IRT) comprises a set of statistical models which are useful in many fields, especially when there is an interest in studying latent variables (or latent traits). Usually such latent traits are assumed to be random variables and a convenient distribution is assigned to them. A very common choice for such a distribution has been the standard normal. Recently, Azevedo et al. [Bayesian inference for a skew-normal IRT model under the centred parameterization, Comput. Stat. Data Anal. 55 (2011), pp. 353-365] proposed a skew-normal distribution under the centred parameterization (SNCP) as had been studied in [R. B. Arellano-Valle and A. Azzalini, The centred parametrization for the multivariate skew-normal distribution, J. Multivariate Anal. 99(7) (2008), pp. 1362-1382], to model the latent trait distribution. This approach allows one to represent any asymmetric behaviour concerning the latent trait distribution. Also, they developed a Metropolis-Hastings within the Gibbs sampling (MHWGS) algorithm based on the density of the SNCP. They showed that the algorithm recovers all parameters properly. Their results indicated that, in the presence of asymmetry, the proposed model and the estimation algorithm perform better than the usual model and estimation methods. Our main goal in this paper is to propose another type of MHWGS algorithm based on a stochastic representation (hierarchical structure) of the SNCP studied in [N. Henze, A probabilistic representation of the skew-normal distribution, Scand. J. Statist. 13 (1986), pp. 271-275]. Our algorithm has only one Metropolis-Hastings step, in opposition to the algorithm developed by Azevedo et al., which has two such steps. This not only makes the implementation easier but also reduces the number of proposal densities to be used, which can be a problem in the implementation of MHWGS algorithms, as can be seen in [R.J. Patz and B.W. Junker, A straightforward approach to Markov Chain Monte Carlo methods for item response models, J. Educ. Behav. Stat. 24(2) (1999), pp. 146-178; R. J. Patz and B. W. Junker, The applications and extensions of MCMC in IRT: Multiple item types, missing data, and rated responses, J. Educ. Behav. Stat. 24(4) (1999), pp. 342-366; A. Gelman, G.O. Roberts, and W.R. Gilks, Efficient Metropolis jumping rules, Bayesian Stat. 5 (1996), pp. 599-607]. Moreover, we consider a modified beta prior (which generalizes the one considered in [3]) and a Jeffreys prior for the asymmetry parameter. Furthermore, we study the sensitivity of such priors as well as the use of different kernel densities for this parameter. Finally, we assess the impact of the number of examinees, number of items and the asymmetry level on the parameter recovery. Results of the simulation study indicated that our approach performed equally as well as that in [3], in terms of parameter recovery, mainly using the Jeffreys prior. Also, they indicated that the asymmetry level has the highest impact on parameter recovery, even though it is relatively small. A real data analysis is considered jointly with the development of model fitting assessment tools. The results are compared with the ones obtained by Azevedo et al. The results indicate that using the hierarchical approach allows us to implement MCMC algorithms more easily, it facilitates diagnosis of the convergence and also it can be very useful to fit more complex skew IRT models.

The CUPID (Cultural and Psychosocial Influences on Disability) Study: Methods of Data Collection and Characteristics of Study Sample

Background: The CUPID (Cultural and Psychosocial Influences on Disability) study was established to explore the hypothesis that common musculoskeletal disorders (MSDs) and associated disability are importantly influenced by culturally determined health beliefs and expectations. This paper describes the methods of data collection and various characteristics of the study sample. Methods/Principal Findings: A standardised questionnaire covering musculoskeletal symptoms, disability and potential risk factors, was used to collect information from 47 samples of nurses, office workers, and other (mostly manual) workers in 18 countries from six continents. In addition, local investigators provided data on economic aspects of employment for each occupational group. Participation exceeded 80% in 33 of the 47 occupational groups, and after pre-specified exclusions, analysis was based on 12,426 subjects (92 to 1018 per occupational group). As expected, there was high usage of computer keyboards by office workers, while nurses had the highest prevalence of heavy manual lifting in all but one country. There was substantial heterogeneity between occupational groups in economic and psychosocial aspects of work; three-to fivefold variation in awareness of someone outside work with musculoskeletal pain; and more than ten-fold variation in the prevalence of adverse health beliefs about back and arm pain, and in awareness of terms such as "repetitive strain injury" (RSI). Conclusions/Significance: The large differences in psychosocial risk factors (including knowledge and beliefs about MSDs) between occupational groups should allow the study hypothesis to be addressed effectively.

Birth weight, current body mass index, and insulin sensitivity and secretion in young adults in two Latin American populations

Background and aims: Although studies have shown association of birth weight (BW) and adult body mass index (BMI) with insulin sensitivity in adults, there is limited evidence that BW is associated with insulin secretion. We assessed the associations between BW and current BMI with insulin sensitivity and secretion in young Latin American adults. Methods and results: Two birth cohorts, one from Ribeirao Preto, Brazil, based on 1984 participants aged 23-25 years, and another from Limache, Chile, based on 965 participants aged 22-28 years were studied. Weight and height at birth, and current fasting plasma glucose and insulin levels were measured. Insulin sensitivity (HOMA%S) and secretion (HOMA%beta) were estimated using the Homeostatic Model Assessment (HOMA2). Multiple linear regression analyses were carried out to test the associations between BW and adult BMI z-scores on log HOMA%S and log HOMA%beta. BW z-score was associated with HOMA%S in the two populations and HOMA%beta in Ribeirao Preto when adult BMI z-score was included in the model. BW z-score was associated with decreasing insulin secretion even without adjusting for adult BMI, but only in Ribeirao Preto. BMI z-score was associated with low HOMA%S and high HOMA%beta. No interactions between BW and BMI z-scores on insulin sensitivity were shown. Conclusions: This study supports the finding that BW may affect insulin sensitivity and secretion in young adults. The effect size of BW on insulin status is small in comparison to current BMI. (C) 2010 Elsevier B.V. All rights reserved.

Psychology and psychoanalysis in Brazil - From cultural syncretism to the collapse of liberal individualism

This paper focuses first on cultural syncretism, used to characterize Brazilian culture. The other aspect of this socially and racially blended culture is the unfinished assimilation of liberalism in politics and the economy, which defines Brazilian society. The increased assimilation and dissemination of psychology may be linked with these in cultural and social aspects. During the military period (1964-1974) the major expansion in university-level studies in psychology contributed ideologically to the dissemination of psychology throughout Brazilian society. This introduced a type of psychology that was related primarily to clinical practice and developed in opposition to social work practice. This paper examines the ideological bases for this conflict between clinical and social work. Criteria for understanding the cultural dissemination of psychoanalysis are then discussed, and it is argued that cultural incorporation of psychoanalysis involves the development of discourse complexes to reflect particular aspects of Brazilian society. The criteria (a non-totalitarian society and the displacement of a magical and religious interpretation of mental disturbance by psychiatric interpretation) are evaluated in relation to the peculiarities of Brazilian syncretism. The paper argues that cultural syncretism and the incomplete assimilation of liberal ideology must be included as criteria in understanding the particular cultural incorporation of psychoanalysis in Brazil.

Metabolism of plasma cholesterol and lipoprotein parameters are related to a higher degree of insulin sensitivity in high HDL-C healthy normal weight subjects

Abstract Background We have searched if plasma high density lipoprotein-cholesterol (HDL-C) concentration interferes simultaneously with whole-body cholesterol metabolism and insulin sensitivity in normal weight healthy adult subjects. Methods We have measured the activities of several plasma components that are critically influenced by insulin and that control lipoprotein metabolism in subjects with low and high HDL-C concentrations. These parameters included cholesteryl ester transfer protein (CETP), phospholipid transfer protein (PLTP), lecithin cholesterol acyl transferase (LCAT), post-heparin lipoprotein lipase (LPL), hepatic lipase (HL), pre-beta-1HDL, and plasma sterol markers of cholesterol synthesis and intestinal absorption. Results In the high-HDL-C group, we found lower plasma concentrations of triglycerides, alanine aminotransferase, insulin, HOMA-IR index, activities of LCAT and HL compared with the low HDL-C group; additionally, we found higher activity of LPL and pre-beta-1HDL concentration in the high-HDL-C group. There were no differences in the plasma CETP and PLTP activities. Conclusions These findings indicate that in healthy hyperalphalipoproteinemia subjects, several parameters that control the metabolism of plasma cholesterol and lipoproteins are related to a higher degree of insulin sensitivity.