Investigating the sensitivity of Gaussian processes to the choice of their correlation function and prior specifications

A Gaussian process (GP) can be thought of as an infinite collection of random variables with the property that any subset, say of dimension n, of these variables have a multivariate normal distribution of dimension n, mean vector β and covariance matrix Σ [O'Hagan, A., 1994, Kendall's Advanced Theory of Statistics, Vol. 2B, Bayesian Inference (John Wiley & Sons, Inc.)]. The elements of the covariance matrix are routinely specified through the multiplication of a common variance by a correlation function. It is important to use a correlation function that provides a valid covariance matrix (positive definite). Further, it is well known that the smoothness of a GP is directly related to the specification of its correlation function. Also, from a Bayesian point of view, a prior distribution must be assigned to the unknowns of the model. Therefore, when using a GP to model a phenomenon, the researcher faces two challenges: the need of specifying a correlation function and a prior distribution for its parameters. In the literature there are many classes of correlation functions which provide a valid covariance structure. Also, there are many suggestions of prior distributions to be used for the parameters involved in these functions. We aim to investigate how sensitive the GPs are to the (sometimes arbitrary) choices of their correlation functions. For this, we have simulated 25 sets of data each of size 64 over the square [0, 5]×[0, 5] with a specific correlation function and fixed values of the GP's parameters. We then fit different correlation structures to these data, with different prior specifications and check the performance of the adjusted models using different model comparison criteria.     

Wounds that time can’t heal: Life satisfaction and exposure to traumatic events

In this study, by employing large-scale survey data from four waves of the US Health and Retirement Study (HRS), we explore the (potentially long-lasting) effects of individuals’ exposure to psychologically traumatic life experiences on their subjective well-being. To this aim, we exploit the richness of our dataset, that contains information about occurrence and timing of a set of extreme events out of individuals’ control that may leave a “scar” extending to their current levels of life satisfaction in general as well as with regard to specific life domains. Our findings indicate that having a close relative hit by a life-threatening illness or accident and, especially, having been victim of a serious physical attack or assault are negatively related to both general and domain-specific life satisfaction, even after controlling for personality traits. Next, life satisfaction is significantly lowered by being physically abused by a parent. Overall, we provide evidence that the effects of some traumatic events are persistent over time and mostly related to women. Surprisingly, the effects of child death are negligible also in the short term.     

Expert knowledge elicitation using item response theory

In an expert knowledge elicitation exercise, experts face a carefully constructed list of questions that they answer according to their knowledge. The elicitation process concludes when a probability distribution is found that adequately captures the experts' beliefs in the light of those answers. In many situations, it is very difficult to create a set of questions that will efficiently capture the experts' knowledge, since experts might not be able to make precise probabilistic statements about the parameter of interest. We present an approach for capturing expert knowledge based on item response theory, in which a set of binary response questions is proposed to the expert, trying to capture responses directly related to the quantity of interest. As a result, the posterior distribution of the parameter of interest will represent the elicited prior distribution that does not assume any particular parametric form. The method is illustrated by a simulated example and by an application involving the elicitation of rain prophets' predictions for the rainy season in the north-east of Brazil.     

Life Satisfaction in Brazil: Testing the Psychometric Properties of the Satisfaction With Life Scale (SWLS) in Five Brazilian Samples

The aim of this paper was to validate the Brazilian-Portuguese version of the Satisfaction With Life Scale (SWLS), presenting evidence of its reliability and construct and criterion-related validity. A large Brazilian sample (2,180 participants), from five different populations (undergraduate and high school students, general population, elementary school teachers, and physicians), was considered. The results confirmed the single factorial structure and reliability (0.77 < Cronbach’s α < 0.88, mean α = 0.81) of the SWLS. Supporting its criterion-related validity, the SWLS correlated positively with positive affect and negatively with both negative affect and psychological distress across all five samples. The findings indicate that the Brazilian-Portuguese version of the SWLS is a valid instrument to use with diverse Brazilian samples.     

Attitude Toward Menopause and the Impact of the Menopausal Event on Adult Women with Diabetes Mellitus

Menopause is an event experienced universally by all women including women with chronic medical conditions such as diabetes mellitus. The purpose of this study is to examine the impact of the menopausal stage on the health and psychological adjustment to illness among women who have diabetes mellitus. The results of this study represent a beginning in the understanding of the impact of the menopausal event on chronically ill adult women.     

Evaluation of Early Adolescent Subjective Well-Being in Terms of Submissive Behavior and Self-Esteem

This research aimed to investigate the correlation between subjective well-being and submissive behavior and self-esteem in students in the early adolescent period. The research was completed with a relational design. The research group comprised sixth, seventh, and eighth class middle school students in the spring term of the 2015–2016 academic year in Trabzon province. Data collection tools included a Personal Information Form, Submissive Behavior Scale, Two-Dimensional Self-Respect Scale (Self-Liking and Self-Confidence Scale), Satisfaction with Life Scale and Positive and Negative Affect Schedule. The results of the correlation analysis found a significant positive correlation between subjective well-being and self-esteem (r?=?0.54, p?<?0.01; 95% CI [0.44, 0.61], Cohen’s d?=?1.28); however, the correlation between subjective well-being and submissive behavior was not significant (r?=?–0.02, p?>?0.05; 95% CI [–0.11, 0.09], Cohen’s d?=?0.04). There was a significant negative correlation identified between self-esteem and submissive behavior (r?=?–0.10, p < 0.05; 95% CI [–0.20, –0.01], Cohen’s d?=?–0.20). Additionally, according to our findings, self-esteem accounts for 29% of the variation in well-being (F(1, 367)?=?150.79, p?<?0.001). The contribution of self-esteem to the subjective well-being explanatory model was found to be significant (sz?=?0.54, p?<?0.001).     

Coalitional affiliation as a missing link between ethnic polarization and well-being: An empirical test from the European Social Survey

Many studies converge in suggesting (a) that ethnic and racial minorities fare worse than host populations in reported well-being and objective measures of health and (b) that ethnic/racial diversity has a negative impact on various measures of social trust and well-being, including in the host or majority population. However, there is much uncertainty about the processes that connect diversity variables with personal outcomes. In this paper, we are particularly interested in different levels of coalitional affiliation, which refers to people’s social allegiances that guide their expectations of social support, in-group strength and cohesion. We operationalize coalitional affiliation as the extent to which people rely on a homogeneous social network, and we measure it with indicators of friendships across ethnic boundaries and frequency of contact with friends. Using multi-level models and data from the European Social Survey (Round 1, 2002–2003) for 19 countries, we demonstrate that coalitional affiliation provides an empirically reliable, as well as theoretically coherent, explanation for various effects of ethnic/racial diversity.     

Measuring Multidimensional Aspiration Gaps: A Means to Understanding Cultural Aspects of Poverty

This article links primary research into the way subjective well‐being among poor people can be defined and measured to the growing literature on poverty as a failure of capacity to aspire. Data from Bangladesh, Thailand and Peru are used to illustrate a measurement strategy based on defining well‐being as a function of the gap between individuals’ diverse and multiple aspirations, and their satisfaction with achieving them. Such analysis has the potential to illuminate variation in individual and local capacity to respond to different development opportunities. It also warns against the limitations of treating aspirations as a single rather than a multidimensional concept.     

Social status and personality traits

We provide direct evidence on the relationship between social status and personality traits. Using survey data from the 2006–2012 waves of the US Health and Retirement Study, we show that self-perceived social status is associated with all the “Big Five” personality traits, after controlling for observable characteristics that arguably reflect one’s actual status. We also construct an objective status measure that in turn is associated with personality traits. Objectively measured status is positively but not highly correlated with its subjective counterpart. When incorporated in a regression specification, it still leaves room for significant correlations between personality traits and status perception: traits such as openness, conscientiousness and extraversion predict a higher self-positioning on the social ladder, while agreeableness and neuroticism predict a lower one.     

Can Business Owners Form Accurate Counterfactuals? Eliciting Treatment and Control Beliefs About Their Outcomes in the Alternative Treatment Status

A survey of participants in a large-scale business plan competition experiment, in which winners received an average of U.S. $50,000 each, is used to elicit ex-post beliefs about what the outcomes would have been in the alternative treatment status. Participants are asked the percent chance they would be operating a firm, and the number of employees and monthly sales they would have, had their treatment status been reversed. The study finds the control group to have reasonably accurate expectations of the large treatment effect they would experience on the likelihood of operating a firm, although this may reflect the treatment effect being close to an upper bound. The control group dramatically overestimates how much winning would help them grow the size of their firm. The treatment group overestimates how much winning helps their chance of their business surviving and also overestimates how much winning helps them grow their firms. In addition, these counterfactual expectations appear unable to generate accurate relative rankings of which groups of participants benefit most from treatment.