Estimation and Inference for Linear Panel Data Models Under Misspecification When Both n and T are Large

This article considers fixed effects (FE) estimation for linear panel data models under possible model misspecification when both the number of individuals, n, and the number of time periods, T, are large. We first clarify the probability limit of the FE estimator and argue that this probability limit can be regarded as a pseudo-true parameter. We then establish the asymptotic distributional properties of the FE estimator around the pseudo-true parameter when n and T jointly go to infinity. Notably, we show that the FE estimator suffers from the incidental parameters bias of which the top order is O(T^{? 1}), and even after the incidental parameters bias is completely removed, the rate of convergence of the FE estimator depends on the degree of model misspecification and is either (nT)^{? 1/2} or n^{? 1/2}. Second, we establish asymptotically valid inference on the (pseudo-true) parameter. Specifically, we derive the asymptotic properties of the clustered covariance matrix (CCM) estimator and the cross-section bootstrap, and show that they are robust to model misspecification. This establishes a rigorous theoretical ground for the use of the CCM estimator and the cross-section bootstrap when model misspecification and the incidental parameters bias (in the coefficient estimate) are present. We conduct Monte Carlo simulations to evaluate the finite sample performance of the estimators and inference methods, together with a simple application to the unemployment dynamics in the U.S.     

The Impact of Public Services Expenditure on the Spanish Income Distribution

This paper performs an assessment and imputation of the benefits produced to the individuals and households well-being by the public services provision. This analysis is very relevant in the current framework of economic crisis of the European economies. Although most of the papers in the literature compare countries, decentralization processes are included in this paper by accounting the effect of public expenditure on regional health care and education upon the levels of inequality and rates of poverty in each Spanish region. This case is relevant because of the high decentralization degree of the Spanish political structure and the persistent regional disparities. The results show a clear downward tendency in both phenomena following imputation, although education shows a greater impact. Furthermore, a decomposition, used in this context for the first time, of the effects shows the very relevant redistributive effect of this public expenditure.     

The complementarity of internal integration and product modularity: An empirical study of their interaction effect on competitive capabilities

Modular product design and internal integration are commonly adopted by manufacturers to improve operational performance. A number of studies argue that the adoption of product modularity significantly alters organization design, which affects the impact of internal integration on competitive capabilities. This paper thus aims to empirically explore the individual effects as well as interaction effects of product modularity and internal integration on competitive capabilities. The competitive capabilities studied in this paper include product innovativeness, low price, product quality, delivery, flexibility and customer services. After analysing the data from 251 Hong Kong manufacturers through moderated multiple regression analysis, the study found that better internal integration can significantly improve product innovativeness, product quality, delivery, flexibility and customer services, while a high level of product modularity enhances product innovativeness, flexibility and customer services. More importantly, the study shows that internal integration and product modularity can interact to improve product innovativeness and product quality. These results enhance our understanding of the interaction of product design and organizational coordination.     

Physical activity is inversely related to drug consumption in elderly patients with cardiovascular events

Elderly patients with cardiovascular events are characterized by high drug consumptions. Whether high drug consumptions are related to physical activity is not known. In order to examine whether physical activity is related to drug consumption in the elderly, patients older than 65 years (n?=?250) with a recent cardiovascular event were studied. Physical activity was analyzed according to the Physical Activity Scale for the Elderly (PASE) score and related to drug consumption. PASE score was 72.4?±?45.0 and drug consumption was 8.3?±?2.2. Elderly patients with greater comorbidity took more drugs (8.7?±?2.1) and are less active (PASE?=?64.4?±?50.6) than patients with Cumulative Illness Rating Scale severity score higher than 1.8 than those with a score lower than 1.8 (76.3?±?41.4, p?<?0.05, and 8.0?±?2.0, p?=?0.006, respectively). Multivariate analysis correlation confirmed that PASE score is negatively associated with drug consumption (β?=??0.149, p?=?0.031), independently of several variables including comorbidity. Thus, physical activity is inversely related to drug consumption in elderly patients with cardiovascular events. This inverse relationship may be attributable to the high degree of comorbidity observed in elderly patients in whom poor level of physical activity and high drug consumption are predominant.     

Assessing the pattern of covariance matrices via an augmentation multiple testing procedure

This paper extends the scedasticity comparison among several groups of observations, usually complying with the homoscedastic and the heteroscedastic cases, in order to deal with data sets laying in an intermediate situation. As is well known, homoscedasticity corresponds to equality in orientation, shape and size of the group scatters. Here our attention is focused on two weaker requirements: scatters with the same orientation, but with different shape and size, or scatters with the same shape and size but different orientation. We introduce a multiple testing procedure that takes into account each of the above conditions. This approach discloses a richer information on the data underlying structure than the classical method only based on homo/heteroscedasticity. At the same time, it allows a more parsimonious parametrization, whenever the patterned model is appropriate to describe the real data. The new inferential methodology is then applied to some well-known data sets, chosen in the multivariate literature, to show the real gain in using this more informative approach. Finally, a wide simulation study illustrates and compares the performance of the proposal using data sets with gradual departure from homoscedasticity.     

Breaking in a new function for casein kinase 2

DNA damage response mechanisms help ensure the fidelity of chromosomal transmission, and the failure of such mechanisms might lead to premature aging and cancer. A new report has established that casein kinase 2 (CK2), a protein that functions in diverse cellular processes, controls the activity of the DNA repair protein XRCC1. These results indicate that CK2 is a key participant in the cellular response to DNA damage.     

Framing in Legislation: The Case of Population Policy in the Philippines

This paper investigates the political framing of population in policy discourse through an analysis of legislative documents. Semantic network analysis was conducted and results were interpreted through discourse analysis of the typical arguments identified. Policy texts were classified into three sets: population management, reproductive health and family planning, and anti-abortion and anti-FP. While the “population management” frame focuses on social and economic consequences of population growth, the “reproductive health” frame defines the problem from a health perspective. Both policies propose aggressive FP programs but each frame uses distinct political rhetoric and semantic approach in its arguments. The “anti-abortion and anti-FP” frame identifies two problems: rise in incidence of abortion and existing policy that prohibit health professionals from refusing patients information on contraception. By invoking a moral argument and anchoring on rights, these policies challenge the problem and solutions identified by the first two frames.     

A comparison of classification models to identify the Fragile X Syndrome

The main models of machine learning are briefly reviewed and considered for building a classifier to identify the Fragile X Syndrome (FXS). We have analyzed 172 patients potentially affected by FXS in Andalusia (Spain) and, by means of a DNA test, each member of the data set is known to belong to one of two classes: affected, not affected. The whole predictor set, formed by 40 variables, and a reduced set with only nine predictors significantly associated with the response are considered. Four alternative base classification models have been investigated: logistic regression, classification trees, multilayer perceptron and support vector machines. For both predictor sets, the best accuracy, considering both the mean and the standard deviation of the test error rate, is achieved by the support vector machines, confirming the increasing importance of this learning algorithm. Three ensemble methods - bagging, random forests and boosting - were also considered, amongst which the bagged versions of support vector machines stand out, especially when they are constructed with the reduced set of predictor variables. The analysis of the sensitivity, the specificity and the area under the ROC curve agrees with the main conclusions extracted from the accuracy results. All of these models can be fitted by free R programs.