Non-observable Variables Research Articles

Analysis of the effect of mammography allocation on women's health indicators

The early detection of breast cancer enables more effective forms of treatment. However, widespread access to its main screening tool, mammography, remains a challenge for the Brazilian public health system. This study aimed to analyze the effect of allocating mammography equipment on women's health indicators. In 2013, of the 4,557 municipalities that lacked the equipment, 260 received it up to 2019. The main hypothesis of this study suggests that receiving the mammography device would show a heterogeneous effect between locations and that such receival would depend on observable (propensity score matching) and non-observable variables (fixed effects model). Results indicate that the Brazilian municipalities that had mammography equipment in use from 2014 onward increased their number of exams without short-term effects to diagnoses and deaths due to malignant breast neoplasia. In addition to equipment, a more complex structure involving other factors (such as access to consultations, qualified professionals, waiting time, etc.) is important to improve women's health indicators in the analyzed municipalities.

The impact of the L'Aquila earthquake on demographic changes

AbstractThis paper analyses the consequences on demographic changes observed in the municipalities of Abruzzo region after the earthquake of L'Aquila in 2009. Relying on Italian National Institute of Statistics (Istat) data on the population in the municipalities, we aim to understand how population growth changed after the earthquake, analysing population dynamics both in the municipalities affected by the earthquake and in the other municipalities of the Abruzzo region. We apply a spatial regression model to understand the associations between population growth, the earthquake, and some demographic and economic variables, taking into account the spatial autocorrelation. Our findings confirm the importance of space and the close association of the population dynamics after the earthquake with the population age structure, both in the pre‐existing situation and in the subsequent dynamics. Population trends in the Abruzzo region were closely associated with the pre‐existing vulnerabilities. The effect of the earthquake was strong in the crater municipalities in the period immediately after the shock, while it petered out over time. A destructive earthquake implies a tremendous shock, however, in places that are already suffering from demographic, social, and economic fragility, pre‐existing factors can act equally or even more strongly on the population dynamics in the medium term. Hence, in the medium period, the characteristics of the population and socio‐economic context are stronger than in the short one, and also the effect that space and territorial contiguities have on these and other nonobservable variables is stronger than in the short period.

Asymptotic Efficiency of Point Estimators in Bayesian Predictive Inference

The point estimation problems that emerge in Bayesian predictive inference are concerned with random quantities which depend on both observable and non-observable variables. Intuition suggests splitting such problems into two phases, the former relying on estimation of the random parameter of the model, the latter concerning estimation of the original quantity from the distinguished element of the statistical model obtained by plug-in of the estimated parameter in the place of the random parameter. This paper discusses both phases within a decision theoretic framework. As a main result, a non-standard loss function on the space of parameters, given in terms of a Wasserstein distance, is proposed to carry out the first phase. Finally, the asymptotic efficiency of the entire procedure is discussed.

Data-driven Bayesian inference of turbulence model closure coefficients incorporating epistemic uncertainty

We introduce a framework for statistical inference of the closure coefficients using machine learning methods. The objective of this framework is to quantify the epistemic uncertainty associated with the closure model by using experimental data via Bayesian statistics. The framework is tailored towards cases for which a limited amount of experimental data is available. It consists of two components. First, by treating all latent variables (non-observed variables) in the model as stochastic variables, all sources of uncertainty of the probabilistic closure model are quantified by a fully Bayesian approach. The probabilistic model is defined to consist of the closure coefficients as parameters and other parameters incorporating noise. Then, the uncertainty associated with the closure coefficients is extracted from the overall uncertainty by considering the noise being zero. The overall uncertainty is rigorously evaluated by using Markov-Chain Monte Carlo sampling assisted by surrogate models. We apply the framework to the Spalart–Allmars one-equation turbulence model. Two test cases are considered, including an industrially relevant full aircraft model at transonic flow conditions, the Airbus XRF1. Eventually, we demonstrate that epistemic uncertainties in the closure coefficients result into uncertainties in flow quantities of interest which are prominent around, and downstream, of the shock occurring over the XRF1 wing. This data-driven approach could help to enhance the predictive capabilities of computational fluid dynamics (CFD) in terms of reliable turbulence modeling at extremes of the flight envelope if measured data is available, which is important in the context of robust design and towards virtual aircraft certification. The plentiful amount of information about the uncertainties could also assist when it comes to estimating the influence of the measured data on the inferred model coefficients. Finally, the developed framework is flexible and can be applied to different test cases and to various turbulence models.

The Expenditure Benchmark: Complex and Unsuitable for Independent Fiscal Institutions

The expenditure benchmark is an indicator for the evolution of public expenditure introduced in 2011 in the already complex European fiscal rules framework, being a very specific application of an expenditure rule. However, it is a quite complex indicator and not suitable for the use at national level by the Independent Fiscal Institutions—that monitor compliance with national fiscal rules—as it relies on the European Commission’s data inputs and judgement not available in real time. This paper argues for more transparency and for a simplification of this indicator to reduce the reliance on non-observable variables. Such improvements are essential as most existing proposals to reform the European Union’s fiscal rules aim to use an expenditure rule as the operational fiscal rule, a role the expenditure benchmark as is cannot fulfil.

Bayesian Modeling for Epistasis Analysis Using Data-Driven Reversible Jump.

We propose a procedure for modeling a phenotype using QTLs which estimate the additive and dominance effects of genotypes and epistasis. The estimation of the model is implemented through a Bayesian approach which uses the data-driven reversible jump (DDRJ) for multiple QTL mapping and model selection. We compare the DDRJ's performance with the usual reversible jump (RJ), QTLBim, multiple interval mapping (MIM) and LASSO using real and simulated data sets. The DDRJ outperforms the available methods to estimate the number of QTLs in epistatic models and it identifies their locations in the genome, without increasing the number of false-positive QTLs in the considered data. Since QTL mapping is a regression model involving complex non-observable variables and their interactions, the model selection procedure proposed here is also useful in other areas of research. The application for identifying main and epistatic relevant QTLs to systolic blood pressure after salt intervention is our main motivation.

Measuring Intra-Urban Inequality with Structural Equation Modeling: A Theory-Grounded Indicator

Composite indicators are almost always determined by methods that aggregate a reasonable number of manifest variables that can be weighted—or not—as new synthesis variables. A problem arises when these aggregations and weightings do not capture the possible effects that the various underlying dimensions of the phenomenon have on each other, and consequently distort the assessment of intra-urban inequality. In this paper, we explore the direct and indirect effects that the different underlying dimensions of intra-urban inequality have on indicators that represent this phenomenon. Structural equation modeling was used to build a composite indicator that captures the direct and indirect effects of the underlying dimensions of intra-urban inequality. From this modeling that combines confirmatory factor analysis with a system of simultaneous equations, the intra-urban inequality of the urban conurbation of Maringá–Sarandi–Paiçandu, Brazil was measured. The model comprises first- and second-order structures. The first-order structure is composed of non-observed variables that represent three underlying dimensions of intra-urban inequality. The second-order structure is the intra-urban inequality composite indicator that synthesizes the non-observed variables of the first-order structure. The model aims at demonstrating how to perform a theorized measurement of urban inequality so that it makes it possible to identify which dimensions most influence the others, as well as which dimensions are more relevant to this purpose.

MPE Computation in Bayesian Networks Using Mini-Bucket and Probability Trees Approximation

Given a set of uncertain discrete variables with a joint probability distribution and a set of observations for some of them, the most probable explanation is a set or configuration of values for non-observed variables maximizing the conditional probability of these variables given the observations. This is a hard problem which can be solved by a deletion algorithm with max marginalization, having a complexity similar to the one of computing conditional probabilities. When this approach is unfeasible, an alternative is to carry out an approximate deletion algorithm, which can be used to guide the search of the most probable explanation, by using A* or branch and bound (the approximate+search approach). The most common approximation procedure has been the mini-bucket approach. In this paper it is shown that the use of probability trees as representation of potentials with a pruning of branches with similar values can improve the performance of this procedure. This is corroborated with an experimental study in which computation times are compared using randomly generated and benchmark Bayesian networks from UAI competitions.

Observer Design for Estimation of Nonobservable States in Buildings

Efficient temperature control requires more than air temperature measurements. Relevant variables, such as wall, ceiling, and other construction temperature evolution are usually unmeasured. Estimation of such quantities is often difficult because they are not observable with respect to available data. Their availability however would allow efficient control design. In this paper, we propose a method for designing state observers that efficiently estimate not only observable but also nonobservable (but detectable) state variables. Our method uses contraction semigroup, to obtain observer with a monotonic error reduction. Proposed approach gives twice as fast estimation as pure simulation and avoids transitional error standard observer would have. Problem of state estimation in building control applications is an important one. Attractiveness of obtaining values of physically unmeasurable variables is easily visible, as it would allow more efficient methods of temperature control. In this paper, authors discuss the problem of such estimation using a lumped capacitance model. This type of model is usually only detectable but not observable. Methods of observer tuning for such systems are not discussed properly in the literature and require special consideration. In this paper, three approaches for estimation are compared: pure model, eigenvalue shifting, and contraction semigroup observer. Results are illustrated with numerical experiments.

Modelo de Fatores para Commodities e Cenários de Preços no Curto Prazo: o caso da soja

Resumo Este artigo analisa os cenários futuros de curto prazo para o preço da soja à vista. A abordagem é feita modelando os fatores não observáveis por processos estocásticos e inova ao incluir o componente sazonal. As variáveis de observação são os preços futuros (estrutura a termo de contratos futuros). Procede-se à estimação do modelo pelo filtro de Kalman. Os resultados mostram um cenário de curto prazo mais favorável a produtores e exportadores. Por outro lado, consumidores e importadores têm indicação de medidas de proteção necessárias para suas posições. A análise pode ser estendida a outras commodities dependentes da sazonalidade. Da mesma forma, o modelo pode ser empregado no apreçamento de derivativos, em que o ativo subjacente é o preço futuro.

Dos tradiciones en la medición del ciclo: historia general y desarrollos en Colombia

This paper analyzes two great traditions in the measurement of the economic cycle: the cyclical indicators and the calculation of aggregate non-observed variables such as potential product, natural interest rate, natural unemployment rate and equilibrium exchange rate, and their associated gaps. The first tradition, also known as the empirical vision of the cycle, owes much to the effort of the nber and developed considerably, especially in the advanced economies. In Colombia, a lot of work has been done in that direction. However, few of these survive, resulting in the country losing a valuable instrument in the analysis of the economic conjuncture. This document is the first part of the complete work and tells the story of the first tradition.

Política social y crecimiento económico en seis países Latinoamericanos, 1980-2010

Este escrito analiza la hipótesis de convergencia y el impacto de las políticas sociales en el crecimiento económico de los seis países más grandes de América Latina entre 1980 y 2010. Los resultados indican que las políticas sociales han influido en el crecimiento económico de esos países. De manera más precisa, existen variables no observables (efectos fijos) que afectaron positivamente el crecimiento de Venezuela y Chile, y factores no observables que afectaron negativamente a Brasil y México. Se encontró, además, que la velocidad de convergencia disminuye cuando aumenta el nivel de ingresos, lo que podría indicar que estos países pueden estar convergiendo a sus estados estacionarios.

Evaluation of direct and indirect effects of seasonal malaria chemoprevention in Mali

Randomized controlled trials have established that seasonal malaria chemoprevention (SMC) in children is a promising strategy to reduce malaria transmission in Sahelian West Africa. This strategy was recently introduced in a dozen countries, and about 12 million children received SMC in 2016. However, evidence on SMC effectiveness under routine programme conditions is sparse. We aim to measure the effects of the nationwide SMC programme in Mali on the prevalence of malaria and anemia in children 6–59 months. We used data from the 2015 nationally representative malaria indicator survey. A post-test only with non-randomized control group study was designed. We fitted a generalized structural equation model that controlled for potential bias on observed and non-observed variables (endogenous treatment effect model). Having received SMC reduced by 44% (95% CI [0.39–0.49]) the risk of having a positive rapid diagnostic test for malaria. In addition, the programme indirectly reduced by 18% the risk of moderate-to-severe anemia (95% CI [0.15–0.21]). SMC in Mali has substantial protective effects under routine nationwide programme conditions. Endogenous treatment effects analyses can contribute to rigorously measuring the effectiveness of health programmes and to bridging a widening gap in evaluation methods to measure progress towards achieving malaria elimination.

Impact of initial medication non-adherence to SSRIs on medical visits and sick leaves

BackgroundInitial medication non-adherence (IMNA) to antidepressants, which are commonly used to treat depression in primary care (PC), is around 6–12%. Although it is well known that post-initial non-adherence to antidepressants increases the cost of depression, the impact of IMNA on cost is unknown. The aim of this study is to assess the impact of IMNA to Selective Serotonin Reuptake Inhibitors (SSRI) on medical visits and sick leave in patients with depression treated in PC in Catalonia (Spain). MethodsThis was a four-year retrospective register-based study (2011–2014). All PC patients of working age who received a new SSRI prescription and had a diagnosis of depression were included (N = 79,642). Treatment initiation, number of visits and days on sick leave were gathered from the database. We assessed the impact of IMNA on costs with ordered logistic regressions. ResultsThe 3-year incidence of IMNA was 15%. Initially non-adherent patients made a lesser number of GP visits (OR = 0.82; 95% CI = 0.79–0.84) but had more days on sick leave (OR = 1.25; 95% CI = 1.20–1.31). There were no differences in the number of specialist visits (OR = 1.04; 95% CI = 0.99–1.08). LimitationsDifferences between adherent and non-adherent patients could be explained by non-observed variables. GP recognition and documentation of depression might be inaccurate. Costs of unpaid work and use of hospital services were not considered. ConclusionsAlthough IMNA decreases the use of medical PC services, it increases the number of days on sick leave. This could also indicate worse health status. These consequences are currently overlooked when considering post-initial medication non-adherence.

Global marine biogeochemical reanalyses assimilating two different sets of merged ocean colour products

The only observations of marine biogeochemistry with routine global coverage are satellite ocean colour, which provide measurements of ocean bio-optical properties, with coverage still incomplete and limited to the sea surface. Models are therefore required to provide full spatial coverage, and through data assimilation can be combined with observations to create a reanalysis. This can then be used to investigate both observed and non-observed variables, including those relating to the carbon cycle. As part of the Climate Modelling User Group (CMUG) within the European Space Agency's Climate Change Initiative (CCI) project, two global marine biogeochemical reanalyses have been produced by assimilating ocean colour-derived chlorophyll data into a coupled physical-biogeochemical ocean model over the period September 1997 to July 2012. One reanalysis assimilated CCI products, the other assimilated GlobColour products, with a non-assimilative hindcast run for comparison. Each has been validated against independent in situ observations of chlorophyll, nutrients and carbon cycle variables. The assimilation of either source of ocean colour data was found to improve the model's representation of chlorophyll concentration throughout the water column, including the frequency and positioning of deep chlorophyll maxima. The assimilation also resulted in a slight improvement in nutrient concentrations and surface fugacity of carbon dioxide compared with in situ observations, although the overall impact on mean fields was small. This was found to be due in part to cancelling errors within the model, with the assimilation providing information on model biases, which can be used to inform future climate model development. The reanalyses were also able to reproduce expected seasonal cycles, as well as inter-annual variability related to major climate drivers. This study concludes that both CCI and GlobColour products are suitable for assimilation purposes, and that assimilating ocean colour data is of clear benefit.

Using Horn’s Parallel Analysis Method in Exploratory Factor Analysis for Determining the Number of Factors

Psychological characteristics are of an abstract or latent nature rather than a tangible, observable one and they are called constructs or factors (Kline, 2005; Nunnaly & Bernstein, 1994). Constructs are hypothetical concepts and the existence of certain constructs is never absolutely confirmed. Therefore, observations of individual behavior mostly provide conclusions about psychological constructs. These psychological constructs such as intelligence, creativity, extrovertedness and introvertedness are not directly observable (Croker & Algina, 1986). Cronbach and Meehl (1955) define psychological construct as postulated attribute of people (as cited in Baykul, 2000). All constructs have two main features: 1. Every construct is an abstract summary of natural order; 2. Constructs are associated with observable entities or phenomena (Murphy & Davidshofer, 2001).According to Lord and Novick (1968), constructs that are not directly observable can be defined in two different ways: operational definition, which is essential to measure those constructs; and the theoretical relationship between a given construct and others and the relationship between a given construct and criteria in the outer world in addition to the operational definitions (Crocker & Algina, 1986). Operational definitions of constructs could relate to construct validity studies that discuss the development of a suitable measuring instrument for a construct and to what extent the instrument measures the related construct.Construct validity is based on the analysis of the relationships between responses to test items. To some extent, the process of establishing construct validity for a given test is the development of a scientific theory (Tekin, 2000). Construct validity is associated with the validity of implications about non-observable variables through observable variables. Construct validity shows how accurately a measuring instrument measures abstract psychological characteristics. Measuring the related abstract construct is based on transformation of the construct into a tangible, observable entity through observable behaviors. The transformation process into an observable construct includes the following stages: determining behaviors related to the measured construct, revealing constructs that are relevant or irrelevant to the measured construct and showing behavioral patterns that express others related to the measured construct (Murphy & Davidshofer, 2001).Construct validity studies could be conducted with different methods according to the quality and the form of a given construct and those of the measuring instrument used to measure the related construct, whether there are theories and scientific research on the construct and some other features (Erkus, 2003). Factor analysis is the most widely used method among these. In the literature, there is scientific consensus on the fact that factor analysis is a common statistical method used to determine construct validity (Anastasi, 1986; Atilgan, Kan, & Dogan, 2006; Crocer & Algina, 1986; Cronbach, 1990; Dancey & Reidy, 2004; Erkus, 2003; Pedhazur & Pedhazur, Schmelkin, 1991; Urbina, 2004). Because of the advantage entailed by internal dependencies in constructs by nature, factor analysis reduces the complexity of data and thus provides nearly the same amount of information as extensive data obtained by a number of original observations, with only a few factors (Cokluk, Sekercioglu, & Buyukozturk, 2010).According to Floyd and Widaman (1995), factor analysis has two approaches in the evaluation of psychological constructs: exploration and variable reduction. The exploratory aim of factor analysis defines lower dimensions of measuring instruments that represent a given construct, on the basis of the theoretical structure from which the instruments have been developed. Accordingly, the analysis focuses on the exploration of latent variables that form the basis of a scale. …

Sustainability vs credibility of fiscal consolidation

Purpose – The purpose of this paper is to explain why some countries in the eurozone between 2010 and 2012 experienced a dramatic vicious circle between hard austerity plans and rising default risk premia. Were such plans too small, and hence non-credible, or too large, and hence non-sustainable? These questions have prompted theoretical and empirical investigations in the line of the so-called “self-fulfilling beliefs”, where beliefs of unsustainability of fiscal adjustments, and hence default on debt, feed higher risk premia which indeed make fiscal adjustments less sustainable. Design/methodology/approach – Detecting the sustainability factor in the evolution of spreads is uneasy because it is largely non-observable and may be proxied by different variables. In this paper, the authors present the results of a dynamic principal components factor analysis (PCFA) applied to a panel data set of the 11 major EZ countries from 2000 to 2013, consisting of each country’s spread of long-term interest rate over Germany as dependent variable, and an array of leading fiscal and macroeconomic indicators of solvency fiscal effort and its sustainability. Findings – The authors have been able to identify the role of these indicators that combine themselves as significant latent variables in boosting spreads. Moreover, the large joint deterioration of these variables is identifiably located between 2009 and 2012 and particularly for the group of countries under most severe default risk (with Italy and France as borderline cases). The authors also find evidence that the announcement of the European Central Bank Outright Monetary Transactions program has improved the sustainability assessment of sovereign debts. Originality/value – Dynamic PCFA is a rather unusual technique with respect to standard econometric tests of models, which is particularly well-suited to reduce the number of variables in a data set by extracting meaningful linear combinations from the observed variables that may concur to explain a given phenomenon (the dependent variable). These combinations, called “common factors”, can be interpreted as latent, non-observable variables.

Latent dimensions of attitudes towards contemporary music: A structural model

Contemporary music from the Western Classical tradition, a term usually reduced to simply “contemporary music,” is widely considered as being quite under-represented on the current musical scene in comparison to the music from any other period. As a perspective from which to explore this aversion beyond the obvious likes and dislikes, our aim was to find non-observable variables or latent dimensions by means of psychological constructs modelling attitudes towards contemporary music in a relevant population, such as music teachers to-be, in order to inform thinking about how to effect a change in this aversion. In doing so, a quantitative psychometric instrument was developed, validated and applied to a sample of this population during their university training period. Retrieved data was analysed by exploratory and confirmatory factor analyses, leading to the proposal of a second-order, structural equations model comprising three constructs identified as “Perceived complexity & stridency”, “Desire to discover” and “Aesthetic respect”. Results could help in a) finding strategies to address aversion, both by the identification of its latent components and their interrelations; and b) proposing a model suitable to be compared to that of other population subgroups and to be connected to other variables for testing the effectiveness of future experimental actions in the teacher training context.

Health insurance and lifestyles

This article contributes to the discussion surrounding the existence of ex ante moral hazard and propitious selection in a voluntary private health insurance scenario. Moreover, it provides an estimation of the determinants of lifestyle choices and of private health insurance demand. A multivariate probit is estimated for health insurance demand and lifestyle decisions to take into account the potential endogeneity of these decisions. The results indicate that there is evidence of ex ante moral hazard in deciding to do sports and eating healthy snacks. Hence, no propitious selection has been found for these decisions. Another relevant result shows that there is no individual heterogeneity for the lifestyle choices, except for smoking, and private health insurance choice. Evidence from the results also supports the idea that there are nonobservable variables playing a role in the lifestyle decisions. These results provide some directions for policymakers, such as the promotion of precautionary behaviours and the use of implicit lifestyle drivers to promote healthy choices by people.

MULTISCALE TEST OF CAPM FOR THREE CENTRAL AND EASTERN EUROPEAN STOCK MARKETS

This paper examines the systematic risk and validity of the basic capital asset pricing model of Sharpe (1964), Lintner (1965) and Mossin (1966) in three Central and Eastern European stock markets (i.e. Slovenia, Hungary and Czech Republic). The CAPM is tested on a multiscale basis, building on the Fama and MacBeth (1973) methodology and applying two modern econometric techniques – wavelet analysis and generalized method of moments estimation. Empirical results indicate that the systematic risk and validity of CAPM implications are multiscale phenomena. Empirical evidence in support of CAPM implications in the investigated Central and Eastern European stock markets is found to be weak. The most commonly violated CAPM hypotheses are the zero Jensen's alpha condition, positive market premium, and the non-systematic influence of non-observable variables on the excess returns of stocks in these stock markets.