Non-nested Tests Research Articles

Pengujian dan Pemilihan Model Neraca Pembayaran Indonesia Dengan Uji Non-Nested

This research has the purpose of analyzing the Indonesian Balance of Payments by tracing international reserves based on Keynesian and Monetary theory. This research uses using ECM data analysis technique to see short run and long-run relation of macroeconomic variables to international reserve changes and a nested test to see the causality inter variables. The result of data analysis using the ECM technique on Keynesian and Monetary models shows a significant ECT value. This value means that according to the Keynesian model, it will take around a quarter for the adjusting process to attain a new equilibrium on the international reserve, while according to the Monetary model, it will take around six quarters or one and a half years. Based on the non-nested test, it is found that the Monetary model is fitter than the Keynesian model in analyzing Indonesian Balance of Payments behavior

Application of a count regression model to identify the risk factors of under-five child morbidity in Bangladesh.

Bangladesh has seen a significant decline in child mortality in recent decades, but morbidity among children <5y of age remains high. The aim of this analysis was to examine trends and identify risk factors related to child morbidity in Bangladesh. This analysis is based on data from four successive cross-sectional Bangladesh Demographic and Health Surveys for the years 2007, 2011, 2014 and 2017-18. Several count regression models were fitted and the best model was used to identify risk factors associated with morbidity in children <5y of age. According to the results of the trend analysis, the prevalence of non-symptomatic children increased and the prevalence of fever, diarrhoea and acute respiratory infections (ARIs) decreased over the years. The Vuong's non-nested test indicated that Poisson regression could be used as the best model. From the results of the Poisson regression model, child age, sex, underweight, wasted, stunting, maternal education, wealth status, religion and region were the important determinants associated with the risk of child morbidity. The risk was considerably higher among women with a primary education compared with women with a secondary or greater education in Bangladesh. This analysis concluded that child morbidity is still a major public health problem for Bangladesh. Thus it is important to take the necessary measures to reduce child morbidity (particularly fever, diarrhoea and ARI) by improving significant influencing factors.

Selecting correct functional form in consumption function: Analysis of energy demand at household level.

In the estimation of demand functions for energy resources, parametric econometric models of energy demand are commonly used to predict future energy needs. The functional forms commonly assumed in parametric energy demand models include linear functional forms, log-linear forms, trans-log models, and an almost ideal demand system. It is frequently debated which is the "best" functional form to employ in order to accurately represent the underlying relationships between the demand for various energy resources and explanatory variables such as energy prices, income, and other demographic factors. The study has focused on developing proper non-nested tests to compare the two demand systems, the double log model and the LA-AIDS model. C-test is used to test the validity of using the two parametric functional forms in models of residential energy demand. Cross-sectional household-level data of the Pakistan Social and Living Standards Measurement (PSLM) 2013-14 and Asian Development Bank (ADB) Asia and Pacific 2018 are used. Results indicate that the LA-AIDS model is better than the double log model. The estimated elasticity of own prices, cross-prices, and income in terms of spending, family size, and equipment are particularly important to producers and policymakers in making investment and incentive choices. A significant part of the budget for families is for electricity, natural gas, firewood, and other fuels; smaller budget shares are set down to other items such as kerosene oil, cylinder gas, and diesel. Household per capita demand for energy resources will rise over the next decade; therefore, the government needs to make progress on developing energy-saving strategies. If not addressed the issue properly, we may face energy shortages and high energy import bills.

A comparison between mixed logit model and latent class logit model for multi-profile best-worst scaling: evidence from mobile payment choice dataset

ABSTRACT This paper uses a multi-profile best-worst scaling dataset to compare the mixed logit model and the latent class logit model for mobile payment choice. Three non-nested tests are applied to show the comparison results. The results indicate that the mixed logit model is superior to the latent class logit model in all three tests.

Influence diagnostics and model validation for the generalized extreme-value nonlinear regression model

ABSTRACTExtreme-value theory is useful for modelling extremal events. The behaviour of such extremal events may be impacted by other variables and such dependence is captured using a regression framework. In this paper, we develop residual based diagnostic analysis, generalized leverage, generalized Cook's distance and also global and local influence analysis for the generalized extreme-value nonlinear regression model. Two residuals for use with the model are proposed: the standardized and deviance residuals. Additionally, we present a model misspecification test that can be used to determine whether the fitted model is incorrectly specified. We also show how to perform nonnested testing inferences. Empirical applications based on simulated and observed data are presented and discussed.

The Small Sample Behaviour of some Non-Nested Tests

The Small Sample Behaviour of some Non-Nested Tests

Evolution of embryo selection for IVF from subjective morphology assessment to objective time-lapse algorithms improves chance of live birth.

Does using an objective time-lapse imaging algorithm (TLIA) after IVF relate to conventional morphological assessment of human blastocysts as a prognosticator for live birth? Prospective use of a TLIA to select embryos in multicentre IVF clinics all using the same strictly controlled laboratory protocols. Each blastocyst was given a ranking from A to D, with the highest rank preferred for fresh transfer. This ranking was retrospectively compared with a given morphological score, which was blinded to the TLIA rank; all embryos were cultured under the same conditions. Using multiple variable logistic regression models, TLIA embryo rank enabled greater discrimination between cycles with and without live births than the conventional morphology grade, even when considered in isolation, and when adjusting for covariates related to treatment and patient criteria. Of the 1810 cycles of single blastocyst transfer, 894 (49.4%) resulted in a live birth. A Vuong non-nested test including covariates showed strong evidence of the superiority of the embryo rank model compared with the transfer grade model (P=0.0008 [raw], P=0.0003 [Akaike information criterion - corrected]). From the receiver operating characteristic (ROC) curves across all possible thresholds the TLIA rank showed better true positive and true negative rates and had a higher area under the curve [AUC] of 67.43% compared with 61.74% for the blastocyst morphology grade. The same analysis but excluding covariates demonstrated an AUC of 62.86% versus 54.02%, respectively. Objective TLIA is superior for selecting embryos for their propensity to generate a live birth over a conventional, subjective blastocyst morphology scoring system.

Relative performance and systemic risk contributions of small and large banks during the financial crisis

During the financial crisis of 2007-2009, large banks (BHCs with assets exceeding $1 billion) suffered a sharper decline in performance and a greater increase in systemic risk, than small banks (BHCs with assets less than $1 billion). Performance is measured by return on assets (ROA) and EBIT/TA. Systemic risk (SRISK) is measured by the capital shortfall indicator proposed by Brownless and Engle (2017) and total risk is standard deviation of monthly returns. We test four hypotheses associated with the dissimilarity in behavioral patterns of large and small banks during the crisis: (1) the nontraditional banking activity hypothesis, (2) the organizational structure hypothesis, (3) the accounting risk hypotheses, and (4) the accounting conservatism hypothesis. We find that behavioral dissimilarities between large and small banks can be, at least, partially related to the first three hypotheses. Non-nested test procedures show that factors associated with nontraditional activity hypothesis fit the data for performance (ROA and EBIT/TA) and total risk the best. Organizational complexity factors are the most relevant set of variables related to systemic risk of banks (SRISK). The implications of our findings are that regulators should focus on factors related these two hypotheses to optimally alter bank performance and bank contribution to systemic risk, rather than limiting bank size and bank acquisitions as proposed by Section 622 of the Dodd-Frank Act (effective January 1, 2015). Our recommendation is in accord with attempts by the Trump administration to relax the Dodd-Frank Act.

Housing Market Microstructure: What is a Competing House?

Housing market microstructure focuses on how neighborhood market conditions affect prices and liquidity. In this paper, we test alternative empirical microstructure models in which substitute houses are determined by similar price or size. Specification tests reveal that price-based measures of substitute or competing houses introduce endogeneity bias into the hedonic price function estimates. Non-nested specification tests do not provide strong support for living area-based or number-of-bedrooms-based models. But the results do support using microstructure measures that allow for asymmetric competition and shopping externalities from larger and smaller neighboring houses, a set of measures not yet employed in the literature.

Environmental considerations and the financing of healthcare: Evidence from sixteen European countries

The results of empirical work on the relation between health expenditure and environmental quality invariably show that environmental degradation has a positive effect on health expenditure, in the sense that more resources are allocated to healthcare to combat the effect of environmental degradation on health. In this paper, the relation between environmental degradation and health expenditure is examined by using data on 16 European countries. The analysis is conducted by using simulation, mathematical derivation and empirical testing using ARDL, FMOLS and non-nested model selection tests. The results reveal that in all cases the relation between per capita health expenditure and CO2 emissions is significantly negative and that in some cases the addition of income per capita as an explanatory variable does not make much difference. Negative correlation between health expenditure and environmental degradation is explained in terms of the environmental Kuznets curve and expenditure on environmental protection.

A GENERAL CLASS OF NON-NESTED TEST STATISTICS FOR MODELS DEFINED THROUGH MOMENT RESTRICTIONS

In this article, we introduce a new class of Cox’s non-nested test statistics for models defined through overidentifying moment restrictions that depend on a finite dimensional parameter vector. In addition to showing that the GEL test statistics proposed in Smith (1997,Economic Journal107, 503–519) and Ramalho and Smith (2002,Journal of Econometrics107, 99–125) are members of this class, we reveal that further members can be constructed using the artificial compound model approach, which was originally applied by Atkinson (1970,Journal of the Royal Statistical Society, Series B32, 323–335) in the parametric setting. We investigate the asymptotic properties of the statistics and propose tests based on modified versions of these statistics that have correct asymptotic size in a uniform sense, a requirement not satisfied by existing Cox’s non-nested tests. A Monte Carlo study examines the performance of the proposed tests.

A Comparison of Three Psychometric Values Measures for Modeling Ecologically Conscious Consumption Behavior

We model environmentally conscious consumption behavior (ECCB) with three psychometric values constructs: Schwartz’s Self-Transcendence Values, Kahle’s List of Values, and Richins and Dawson’s Materialism. Comparison of competing models and non-nested specification tests lead to a statistically significant model of ECCB which reasonably fits our author-designed and collected survey data. In addition, benevolence and universalism (elements of Schwartz’s construct), and acquisition centrality (an element of Materialism) exhibit statistical significance and conform to expectations.

Non-nested hypothesis testing inference for GAMLSS models

Two or more regression models are said to be non-nested if neither can be obtained from the remaining models when parametric restrictions are imposed. Tests for choosing between linear non-nested regression models are found in literature, such as J and MJ tests. In this paper we propose variants of these two tests for the GAMLSS (Generalized Additive Models for Location, Scale and Shape) class of models. We report Monte Carlo evidence on finite sample behaviour of the proposed tests. Bootstrap-based testing inference is also considered. Overall, bootstrap MJ test had the best performance. An empirical application is presented and discussed.

Structuralist Vs. Post-Keynesian Theory: Industrial Pricing in India

How is industrial price determined in India? Using 40 years data spanning from 1970-71 through 2009-10 we provide fresh evidence to this question. We ask whether industrial pricing responds more to wage cost that rises with exogenous factors such as food prices (Structuralist theory) or to the endogenous need to finance new investment (i.e., Post-Keynesian theory). Though both the theories argue that industrial price is cost-determined, yet they differ in their methodology and thus, policy implication differs. We use Engel-Granger cointegration test and ARDL bounds test to answer the question. Since data support both the theories, a non-nested test is conducted where we find that the Structuralist theory outperforms its rival. This points out to the important role of agricultural goods in general, and food prices in particular in industrial price. The policy implication of this finding is that since agricultural prices play an important role in industrial price inflation, then monetary policy cannot control core inflation. Rather, the solution may lie in improving agricultural productivity through raising greater public investment.

Dynamic Conditional Beta

Dynamic conditional beta is an approach to estimating regressions with time varying parameters. The conditional covariance matrices of the exogenous and dependent variable for each time period are used to formulate the dynamic beta. Joint estimation of the covariance matrices and other regression parameters is developed. Tests of the hypothesis that betas are constant are non-nested tests and several approaches are developed including a novel nested model. The methodology is applied to industry multifactor asset pricing and to global systemic risk estimation with non-synchronous prices.

Non-nested testing of spatial correlation

We develop non-nested tests in a general spatial, spatio-temporal or panel data context. The spatial aspect can be interpreted quite generally, in either a geographical sense, or employing notions of economic distance, or when parametric modelling arises in part from a common factor or other structure. In the former case, observations may be regularly-spaced across one or more dimensions, as is typical with much spatio-temporal data, or irregularly-spaced across all dimensions; both isotropic models and non-isotropic models can be considered, and a wide variety of correlation structures. In the second case, models involving spatial weight matrices are covered, such as “spatial autoregressive models”. The setting is sufficiently general to potentially cover other parametric structures such as certain factor models, and vector-valued observations, and here our preliminary asymptotic theory for parameter estimates is of some independent value. The test statistic is based on a Gaussian pseudo-likelihood ratio, and is shown to have an asymptotic standard normal distribution under the null hypothesis that one of the two models is correct; this limit theory rests strongly on a central limit theorem for the Gaussian pseudo-maximum likelihood parameter estimates. A small Monte Carlo study of finite-sample performance is included.

Comparison of Rotterdam Model versus almost ideal demand system for fish and red meat

ABSTRACTThe Rotterdam and the almost ideal demand systems (AIDS) are often used to model consumer demand system. The present study determined which model performed better in recovering the true elasticities of consumer demand for red meat and fish. For the linearised AIDS model, Stone, Paasche, Laspeyres, and Turnquist price indexes were used. This study also compared the results of the linearised AIDS and the full nonlinear AIDS (NLAIDS) models. According to Lutkepohl, normality test for joint residuals, the linearised AIDS model that used Turnquist price index, was the best system and, based on the Akaike criteria, the linear approximate (LA) AIDS outperformed NLAIDS. The results of the non-nested test for LAAIDS versus Rotterdam showed that LAAIDS is more appropriate for red meat and fish demand in Iran. Price elasticity for fish and red meat showed that they are elastic. Cross elasticity from LAAIDS and NLAIDS showed that fish and red meat are substitutes. Allen-Uzawa elasticity results indicate that the two goods are strong substitutes. Income elasticity indicated that red meat and fish are considered to be luxury goods.

M Tests with a New Normalization Matrix

This paper proposes a new family of M tests building on the work of Kuan and Lee (2006) and Kiefer et al. (2000). The idea is to replace the asymptotic covariance matrix in conventional M tests with an alternative normalization matrix, constructed using moment functions estimated from (K + 1) recursive subsamples. The new tests are simple to implement. They automatically account for the effect of parameter estimation and allow for conditional heteroskedasticity and serial correlation of general forms. They converge to central F distributions under the fixed-K asymptotics and to chi-square distributions if K is allowed to approach infinity. We illustrate their applications using three simulation examples: (1) specification testing for conditional heteroskedastic models, (2) non-nested testing with serially correlated errors, and (3) testing for serial correlation with unknown heteroskedasticity. The results show that the new tests exhibit good size properties with power often comparable to the conventional M tests while being substantially higher than that of Kuan and Lee (2006).

Two Spatial Non-Nested Tests for Weight Structure in the Spatial Autoregressive Model

The spatial J-test (SJ-test) and the spatial JA-test (SJA-test) are outlined to determine the appropriate spatial weight structure for the spatial autoregressive model against a single, or a set of, non-nested alternatives. These two non-nested tests are based on the maximum likelihood framework and can be applied to both the simple spatial autoregressive model and the general spatial autoregressive model. The Monte Carlo simulation results showed that the SJ-test and the SJA-test had clearly distinct performance in determining the appropriate spatial weight structure for a spatial autoregressive model against a single alternative and against two alternatives. The SJ-test performed better than the SJA-test in failing to reject a true null hypothesis when compared against a single alternative, whereas the SJA-test performed better than the SJ-test in failing to reject a true hypothesis when compared against two alternatives. Therefore, the SJ-test should be applied to determine the spatial weight structure against a single alternative, and the SJA-test should be applied to determine the spatial weight structure against a set of alternatives. Performance improved with a larger sample size and with a larger magnitude of spatial autocorrelation. The power of the tests depended on the degree of similarity between the alternatives and the underling true structure. The power of the tests was likely to be lower with two alternatives rather than a single alternative. This is due to the introduction of a false spatial weight matrix into the alternative with the true spatial weight matrix. El articulo describe la prueba J espacial (J-test o SJ-test) y la prueba JA espacial prueba espacial (SJA-test), las cuales son utilizadas para determinar la estructura de ponderacion espacial apropiada para el modelo autorregresivo espacial frente a una alternativa nonestad unica o frente a un conjunto de alternativas nonnested. Estas dos pruebas nonnested se basan en el marco de maxima verosimilitud (maximum likelihood-ML) y se pueden aplicar tanto al modelo autorregresivo espacial simple como al modelo autorregresivo espacial general. Los resultados de la simulacion Monte Carlo presentados aqui muestran que SJ-test y SJA-test tienen una performance claramente distintiva en cuanto a la determinacion de la estructura espacial de ponderacion apropiada para un modelo autorregresivo espacial versus una alternativa unica y versus dos alternativas. El SJ-test funciono mejor que el SJA-test al no rechazar una hipotesis nula verdadera cuando se compara con una alternativa unica, mientras que el SJA-test funciono mejor que el SJ-test al no rechazar una hipotesis verdadera cuando se le compara con dos alternativas. Por lo tanto, los autores concluyen que el SJ-test se debe aplicar para determinar la estructura espacial de peso versus una alternativa unica, mientras que la SJA-test se debe aplicar para determinar la estructura espacial de ponderacion versus un conjunto de alternativas. Los resultados de performance mejoraron con un tamano de muestra mas grande y con una magnitud mayor de autocorrelacion espacial. El poder estadistico de las pruebas depende del grado de similitud entre las alternativas y la estructura espacial verdadera subyacente (la matriz). El poder estadistico de las pruebas analizadas tiende a ser inferior cuando las dos alternativas nonestad son utilizadas en lugar de la alternativa unica. Esto se debe a la introduccion de una matriz falsa de ponderacion espacial en la alternativa que contiene la matriz verdadera de ponderacion espacial. 本文阐述了空间J检验(SJ-test)和JA检验(SJA-test)，以确定在单个或者一系列非嵌套备择空间自回归模型中恰当的空间权重结构。两种非嵌套检验方法均基于最大似然框架，并可用于简单的和广义的空间自回归模型。蒙特卡洛模拟结果显示，在单个和两种备择方案下，SJ检验和SJA检验对空间自回归模型的空间权重结构的确定效果明显不同。与在单个备择方案比较时，SJ在未能拒绝真实零假设方面检验效果优于SJA检验；反之，在与两个备择方案比较时，SJA检验在未能拒绝真假设方面的效果则优于SJ检验。因此，SJ检验应该应用于单备择的空间权重结构确定，而SJA检验则应用于多备择的空间权重结构确定。当进行更大样本量和更大量级的空间自相关分析时，模型的性能和效果会得到提升。检验方法的能力取决于备择方案与下属真实结构的相似度，在具有两种（或多种）备择方案情况下，模型的检验能力会降低，并可能导致将错误的空间权重矩阵引入真实的空间权重结构矩阵构建中。

Non-nested tests of a GDP-augmented Fama–French model versus a conditional Fama–French model in the Australian stock market

We extend Vassalou (2003) by conditioning the Fama–French model with the same macroeconomic variables used to construct a GDP factor. The motivation for doing so is to ascertain whether the ability of the GDP-augmented model to explain equity returns is actually due to news about future GDP growth or whether it is due to the macroeconomic conditioning variables used to construct the GDP factor. We compare the performance of a GDP-enhanced Fama–French model with the conditional Fama–French model using non-nested testing techniques. We find that the GDP-augmented model considerably underperforms the conditional version of the model.