Pseudo Maximum Likelihood Estimation Research Articles

Assessing the impact of non-tariff measures on Sri Lankan mango exports: insights, challenges, and recommendations

IntroductionWith the increase in non-tariff measures (NTMs) in recent years, understanding their impact on trade policies and agricultural exports is of utmost importance for countries like Sri Lanka, where the proliferation of NTMs has posed substantial impediments to its mango export industry. However, studying NTMs can be challenging due to their complex nature, diverse range, and limited information availability.MethodsThis research aims to investigate the significant effect of NTMs on Sri Lankan mango exports, identify the pivotal drivers influencing mango exports, and analyze the performance of mango exports in Sri Lanka. This study utilized a panel dataset of 16 importing countries spanning the period from 2000 to 2021. The primary focus was on examining NTM-related challenges and obstacles faced by the mango export industry in Sri Lanka. The identification and quantification of these obstacles were achieved through a multifaceted approach in which assessment of NTM-related rejections, both domestic and overseas, evaluation of NTM incidences using frequency and coverage ratio measures, and the deployment of various gravity model equations to quantify the effect of NTMs were taken into consideration. Probit, Ordinary Least Square, Random Effects, and Poisson Pseudo Maximum Likelihood estimation techniques were utilized for data analysis.ResultsThe findings indicate a significant inverse correlation between the increase in the total count of NTMs and Sri Lankan mango exports if the country aims to export more mangoes to relevant markets, while Sanitary and Phytosanitary Measures (SPS), Technical Barriers to Trade (TBT), and Pre-shipment Inspection (PSI) contributed to increased mango exports. Among other explanatory variables, the GDP of both importing and exporting countries had a positive influence on Sri Lankan mango exports. Surprisingly, the distance to the importing country had no significant effect, though it shows a negative sign.DiscussionThis study provides valuable insights into the impact of NTMs on Sri Lankan mango exports. It highlights the considerable influence of NTMs on the overall fresh fruit export sector. We recommend proactively aligning internal quality testing regulations with the standards required by destination countries to promote future expansion.

The more the better? How degree programs’ variety affects university students’ churn risk

Students’ intra- and, especially, inter-degree relocation poses significant challenges that tertiary education systems and universities must address to identify the best possible solutions for its reduction. Indeed, this phenomenon has a major impact on several aspects, from the reallocation of financial resources to factors related to the organization of spaces and activities, as well as in terms of human and social capital. Moreover, it is much more challenging when involving different universities in different geographical areas. This paper addresses the issue of churn risk among students and its relationship with the institutions’ educational offerings, in terms of degree programs, by accounting for the impact of the characteristics of both universities and hosting areas. In particular, the analysis relies on Italian administrative data regarding students who decide to change university or field of study when enrolling in their second year of career. The results obtained performing the Poisson Pseudo Maximum Likelihood estimation show that the variety and the dimension of universities’ services supply contribute to reducing students’ churn risks and are positively associated with universities’ retention rates.

Semiparametric Probit Regression Model with General Interval-Censored Failure Time Data

Interval-censored data frequently arise in various biomedical areas involving periodical follow-ups where the failure or event time of interest cannot be observed exactly but is only known to fall into a time interval. This article considers a semiparametric probit regression model, a valuable alternative to other commonly used semiparametric models in survival analysis, to investigate potential risk factors for the interval-censored failure time of interest. We develop an expectation-maximization (EM) algorithm to conduct the pseudo maximum likelihood estimation (MLE) using the working independence strategy for general or mixed-case interval-censored data. The resulting estimators of regression parameters are shown to be consistent and asymptotically normal with the empirical process techniques. In addition, we propose a novel penalized EM algorithm for simultaneously achieving variable selection and parameter estimation in the case of high-dimensional covariates. The proposed variable selection method can be readily implemented with some existing software and considerably reduces the estimation error of the proposed pseudo-MLE approach. Simulation studies demonstrate the satisfactory performance of the proposed methods. An application to a set of interval-censored data on prostate cancer further confirms the utility of the methodology. Supplementary materials for this article are available online.

Economic geography of talent migration and agglomeration in China: A dual-driver framework

The long-standing debate on the role of economic factors and amenities on talent migration and redistribution foreshadows the importance of spatial economic theoretical thinking in resolving the effects of duality, a point yet to be conclusively addressed in the existing literature. Situated within the framework of new economic geography (NEG), this article introduces an innovative theoretical model – the Dual-Driver (DD) framework– aiming at comprehending the nuanced dual impact of economic and amenity factors on talent movements between regions. While the DD framework retains the mechanisms of increasing returns to scale, iceberg transportation cost, and talent agglomeration presented in the NEG models, it depicts, for the first time, the self-reinforcing mechanisms between non-traded goods (i.e., amenities) and talent agglomeration. The model describes a logic of talent movements influenced by the dual drivers of regional economic factors (nominal wage, the diversity of local manufacturing products) and amenities (the diversity and quality of amenities, transfer payment for talent), among which the economic effects play a predominant role versus the amenity effects. Empirical evidence has been given by the geographical analysis of China's internal talent migration between 2000 and 2015 and the corresponding econometric analysis using the Poisson pseudo-maximum likelihood (PPML) estimation. Our findings furnish a theoretical perspective for comprehending talent geography and offer policy insights into China's logic of talent migration.

Unravelling open innovation determinants and firm performance relationships in CEE and SEE countries

Purpose Open innovation (OI), by now one of the major concepts for the analysis of innovation, is seen as a methodology for collaboratively designing and implementing solutions by engaging stakeholders in an iterative and inclusive service design process. This paper aims to empirically investigate OI capacities, defined as a cooperative, knowledge-sharing innovation ecosystem, and to explore how it can lead to improved performance of firms in Central and Eastern European (CEE) and Southeastern European (SEE) countries.Design/methodology/approach The study builds on the World Bank/European Bank for Reconstruction and Development (EBRD’s) Business Environment Enterprise Performance Survey (BEEPS) dataset for 2009, 2013 and 2019. Primarily, the research model was estimated using log-transformed ordinary least squares (OLS). Taking into consideration that this method might produce substantial bias, yielding misleading inferences, this study is fitting Poisson pseudo maximum likelihood estimators with robust standard errors and instrumental variable/generalized method of moments estimation (IV/GMM) approach for comparative results. Secondarily, the research model was tested using structural equation modelling (SEM) to investigate the relationship between five OI capacities and firm performance.Findings The findings indicate that there is a significant positive relationship between most OI capacities and firm performance, except for innovation, which did not show a statistically significant relationship with firm performance. Specifically, research and development (R&D), knowledge and coopetition are statistically significant and positively associated with firm performance, whereas transformation is statistically significant but negatively associated with firm performance. The IV/GMM estimations’ findings support the view that the firm performance is significantly affected by OI capacities, together with some control variables such as size, age, foreign ownership and year dummy to have a significant impact on firm performance.Originality/value This paper fills an identified gap in the literature by investigating the impact of OI on firm performance executed in the specific CEE and SEE country context.

How Social Networks Shape Refugee Movements in Wartime: Evidence from the Russian Attack on Ukraine

This article analyzes the key factors guiding the destination choice of Ukrainian refugees in the EU between March and December 2022 in the framework of the activation of the Temporary Protection Directive. To this end, it specifies a migration model, computed for the whole period and two subperiods (March–May and June–December), that captures the influence of social networks. Furthermore, our migration model makes a distinction for the first time between prewar migrant communities and the new social networks that are emerging in wartime circumstances. The estimation of the model, using the Poisson Pseudo-Maximum Likelihood estimator by Santos Silva and Tenreyro (2006), confirmed the importance of both types of social networks in explaining refugees’ choice of destination. The results also revealed that some economic variables (expected earnings and the size of the informal sector) influenced the location choice of refugees since the outbreak of the war, while other socioeconomic and political factors (risk of social exclusion, anti-immigration sentiment, and rule of law) only did so after a few months, when it became increasingly self-evident that the war was going on for a long time.

Misspecified Exponential Regressions: Estimation, Interpretation, and Average Marginal Effects

Abstract Exponential regressions are frequently used when outcomes are non-negative. They are attractive because they are easy to interpret and to estimate, using pseudo maximum likelihood (PML). However, the validity of these methods depends on the correct specification of the conditional expectation, and little is known regarding their properties when the conditional expectation is misspecified. We show that PML estimators of misspecified exponential models provide optimal approximations to the conditional expectation, in a weighted mean squared error sense, and we give conditions under which their Poisson PML estimator identifies average marginal effects.

Does financial development and institutional quality matter in South-South Trade? Evidence from Sub-Saharan Africa

This study re-evaluates the determinants of international trade in the global south, focusing on intra- and extra-SSA trade while considering financial development and institutional quality as additional predictors. It also examines whether these factors differ for south-south and north–south trade ties. We used a 22-years (ranging from 2000 to 2021) panel of 98 countries (41 from the SSA and the remaining from the ROW). A panel gravity model with Poisson pseudo-maximum likelihood (PPML) estimation is used for the analysis. The results show that financial development in origin and destination countries boosts intra-trade in SSA countries, and the developed financial sector of the destination countries contributes to both intra-bloc and international trade. Financial development of exporting countries also spurs intra-bloc trade in SSA countries and the global south. In addition, apart from common expectations, the institutional quality of exporting countries plays a deterrent role, while the institutional quality of destination countries plays a positive and significant role in trade in the global south. We identified the interaction term for financial development and institutional quality of the exporting countries with a significant and positive coefficient for the global south and the global north, and null for intra-SSA trade. For destination countries, it becomes significantly positive with SSA and the global south but negative with the global north. The findings suggest that as part of the policy measures to boost intra-bloc trade in SSA and the global south, ensuring financial development needs better emphasis.

Analysing the Nexus between the Financial Sector and Economic Growth in Nigeria: A Comparative Investigation using, BVAR, Linear Regression (OLS), and PPML Models

Aims: This study aims to analyze the complex relationship between the financial sector and economic growth in Nigeria. The study aims to provide comprehensive insights into this nexus by employing a comparative investigation using three distinct models: Linear Regression, Poisson Pseudo Maximum Likelihood (PPML), and Bayesian Vector Autoregression (BVAR).
 Methodology: The study then applied three different models, with a specific focus on the BVAR(2) model, supported by various diagnostic tests and stability assessments. The inclusion of Linear regression analysis and Poisson Pseudo Maximum Likelihood Estimator (PPML) enhances the depth of the study, providing nuanced insights into the impact of specific financial sector variables on economic growth.
 Results: The BVAR (2) model emerges as the optimal choice, demonstrating its reliability in capturing dynamic interactions and offering a powerful tool for policymakers. Specific results, such as the significant negative impact of D(CPS) in the regression analysis and the high R-squared in PPML, provide actionable insights into areas requiring policy interventions and underscore the substantial contribution of the financial sector to economic growth.
 Conclusion: The comparative assessment of model performances, favoring the BVAR model, guides future research and policy considerations, providing a reliable framework for further investigations. The study's insights are positioned as valuable for policymakers seeking to enhance economic growth through strategic interventions in the financial sector. Overall, the abstract succinctly encapsulates the aims, methodology, results, and concluding implications of the study on the nexus between the financial sector and economic growth in Nigeria.

Proportional rates models for multivariate panel count data.

Multivariate panel count data arise when there are multiple types of recurrent events, and the observation for each study subject consists of the number of recurrent events of each type between two successive examinations. We formulate the effects of potentially time-dependent covariates on multiple types of recurrent events through proportional rates models, while leaving the dependence structures of the related recurrent events completely unspecified. We employ nonparametric maximum pseudo-likelihood estimation under the working assumptions that all types of events are independent and each type of event is a nonhomogeneous Poisson process, and we develop a simple and stable EM-type algorithm. We show that the resulting estimators of the regression parameters are consistent and asymptotically normal, with a covariance matrix that can be estimated consistently by a sandwich estimator. In addition, we develop a class of graphical and numerical methods for checking the adequacy of the fitted model. Finally, we evaluate the performance of the proposed methods through simulation studies and analysis of a skin cancer clinical trial.

Maximum Pseudo-Likelihood Estimation of Copula Models and Moments of Order Statistics

It has been shown that, despite being consistent and in some cases efficient, maximum pseudo-likelihood (MPL) estimation for copula models overestimates the level of dependence, especially for small samples with a low level of dependence. This is especially relevant in finance and insurance applications when data are scarce. We show that the canonical MPL method uses the mean of order statistics, and we propose to use the median or the mode instead. We show that the MPL estimators proposed are consistent and asymptotically normal. In a simulation study, we compare the finite sample performance of the proposed estimators with that of the original MPL and the inversion method estimators based on Kendall’s tau and Spearman’s rho. In our results, the modified MPL estimators, especially the one based on the mode of the order statistics, have a better finite sample performance both in terms of bias and mean square error. An application to general insurance data shows that the level of dependence estimated between different products can vary substantially with the estimation method used.

Deploying Machine Learning Methods to Predict Global Trade Patterns: The Case of Beef

Highlights Machine Learning (ML) methods are offered as an alternative to conventional techniques for understanding global commodity trade. A formal comparison is made between ML results with those from the Poisson Pseudo Maximum Likelihood (PPML) Estimator, which is the most commonly used statistical technique for bilateral trade analysis. PPML takes into account fixed effects and the dynamic nature of panel data to provide a better fit and higher prediction accuracy than ML in the context of in-sample forecasts. ML methods have strengths in feature selection, better validation statistics, and stronger predictive power than PPML, especially with out-of-sample forecasts. Abstract. In international economics, there has been a steady stream of innovations to explain patterns of trade between and among countries with emerging techniques. The most recent - Poisson Pseudo Maximum Likelihood (PPML) estimator – corrects for a potential bias caused by the large proportion of zero observations in bilateral trade data. Alternatively, this study offers Machine Learning (ML) as an option, especially in the presence of finer data on bilateral trade patterns. Using monthly and HS-6-digit (product) level data, the study finds that the main advantage of PPML is its accuracy of forecasts in-sample, but feature selection is somewhat rigid due to the inclusion of a large number of pair-wise fixed effects. ML models have the advantage in selecting features when a long list of explanatory variables is to be considered. Model validation statistics such as MAE and RMSE favor ML methods, but PPML tends to yield higher goodness of fit. In the out-of-sample context, ML has better accuracy than PPML, and a one-step walk-forward ML approach further improves the accuracy of ML forecasts. While PPML has a rich research and application history, emerging ML techniques have sufficient room for improvement in their adaptation to economic analysis. Keywords: Beef, Bilateral Trade, Boosting, Machine learning, ML for Policy

Comparing maximum likelihood and maximum pseudolikelihood estimators for the Ising model

The Ising model is one of the most popular models in network psychometrics. However, statistical analysis of the Ising model is difficult due to the presence of its intractable normalizing constant in the probability function. As a result, maximum likelihood estimation using the exact likelihood is only possible for small graphs, and approximation methods are needed for larger graphs. Two popular approximations of the exact likelihood are the joint pseudolikelihood (JPL) and the disjoint pseudolikelihood (DPL). These approximations yield consistent estimators, but we do not know how well they perform for finite data. In this paper, we investigate the relative performance of parameter estimation methods based on the two approximations and compare them to maximum likelihood estimation using the exact likelihood. We perform an extensive simulation study comparing the estimators in terms of bias and variance. We show that maximum pseudolikelihood estimation based on the JPL is a stable estimation method that is able to accurately approximate the maximum likelihood estimates, but that maximum pseudolikelihood estimation based on the DPL only works well for large sample sizes.

DETERMINANTS OF VIETNAM’S AGRICULTUAL EXPORTS, FOCUSING ON ITS TRADING PARTNERS’ CHARACTERISTICS

This study investigates the determinants of Vietnam’s agricultural exports, focusing on its trading partners’ characteristics. The author adopts Poisson Pseudo-Maximum Likelihood estimators to estimate a gravity model covering bilateral agricultural exports from Vietnam to 187 of its trading partners during 1996-2021. The empirical results reveal that exchange rate volatility and geographical distance hamper exports, while regional trade agreements (RTAs), shared borders, and dependent relationships in the past boost exports. When considering the features of importing countries, I find that population, GDP per capita, policy stability, and financial development are crucial in promoting Vietnam's agricultural exports. The findings of this study imply that it is necessary to maintain stable exchange rates and actively join RTAs to increase the agricultural exports of Vietnam. Moreover, to enhance agricultural exports, exporting firms should target trading partners in countries with large economic size, high per capita income, good governance quality, developed financial markets, or those who share a common border or have ever in dependent relationship with Vietnam.

Energy security, governance quality, and economic performance in sub-Saharan Africa

This study investigates the role of energy security and governance quality in economic performance using 22 sub-Saharan African countries between 2000 and 2020. It explores Poisson Pseudo-maximum Likelihood Estimator. More so, five measures of energy security (accessibility, affordability, acceptability, availability, and developability) and four measures of governance quality (political, economic, institutional, and aggregate) are considered. The results show that only the availability and developability of energy security significantly and positively enhance economic performance. Other measures have little or no effect on economic performance. Additionally, measures of governance quality largely and positively facilitate economic performance. On interaction terms, governance quality was found to significantly enhance the effectiveness of the availability aspects of energy security on economic performance. However, the governance structure is still very weak to foster the effectiveness of other aspects of energy security in the growth process. Thus, countries need to be proactive in strengthening their governance structures to harness the benefits associated with energy security for sustainable economic growth. Specifically, policymakers need to prioritize policies that will enhance energy availability and developability, promote energy sustainability and equality, disincentivize high-emission energy sources, strengthen governance roles in energy security, and mitigate oil price volatility.

THE EFFECTS OF INTERNATIONAL LOGISTICS IN GLOBAL VALUE CHAIN TRADE

The current empirical literature shows that logistics plays a vital role in increasing the total volume of international trade. However, there is scarce literature on the impact of logistics performance on global value chain trade. Therefore, the objective of this paper is to investigate the effect of logistics performance on global value chain trade, measured by the value-added exports. The empirical specification of this paper is based on the structural gravity model of international trade. The analysis is based on biennial panel data on bilateral trade flows for the EU-15, CEE, and the Western Balkans and covers the period from 2010 to 2018. The model is estimated with a Poisson Pseudo Maximum Likelihood Estimator. The results show that logistics performance appears to have significant positive effects on global value chain trade and that the logistics performance of the partner country plays a more critical role than the logistics performance of the reporting country. Institutional quality matters greatly for global value chain trade. Individual differences in the observed variables were found between selected groups of countries. The need to improve logistics performance and invest in knowledge and technology will help countries improve in value chains, along with adequate institutional support.

Export of Travel Services in Western Balkans: A Gravity Model Approach

ABSTRACT This paper investigates the importance of travel service exports in Western Balkans countries. It identifies the key drivers and barriers in exporting travel services for five Western Balkan economies, in their intraregional trade and in trade in travel services with the EU. We use a gravity model, estimated over 2013–2019, applying the Poisson pseudo-maximum likelihood estimator. The results of the trade gravity model reveal that GDP, geographical distance, and cultural characteristics such as language and historical similarities and cultural heritage influence travel services.

Trade potential in European Union manufacturing

PurposeThis study deals with changes in European Union's (EU's) trade potential in Machinery (HS 84–85) and Transportation (HS86-89) products.Design/methodology/approachThe study uses a Structural Gravity model, Poisson Pseudo Maximum Likelihood (PPML) estimation together with panel data for the years 2002–2018 and a two-step procedure that employs predicted values of bilateral trade to compare potential to actual trade.FindingsResults for Machinery products suggest a potential to expand trade with existing Regional Trade Agreements (RTAs) in the American continent, and countries of the IGAD region in Africa. In Transportation, a high trade potential with RTAs is found in the Americas, Africa and the Middle East. Policy suggestions concentrate on opportunities for enhancing trade relations through trade liberalization and agreement proliferation.Originality/valueThere are no studies to date, that examine “collective” measure of EU trade potential, that treats the EU as a single country. Changes in existing opportunities to expand trade, common for EU members, are of special interest for policy formulation, especially after the recent turmoil presented by the Global Financial Crisis (GFC) and the Greek Economic Crisis (GEC). Treating the EU as a single entity, is necessary for the formulation of an effective, common, EU trade policy. This study concentrates on the manufacturing sector to examine existing opportunities for the EU to expand trade, after the GFC and the GEC. This article deals with Machinery (HS 84 and 85) and Transportation (HS 86 through 89) products as they comprise a significant part of total EU exports, reaching 41% of total exports in 2016. Finally, this study offers a unique illustration of results through trade potential heat maps.

Improving ERGM starting values using simulated annealing

Much of the theory of estimation for exponential family models, which include exponential-family random graph models (ERGMs) as a special case, is well-established and maximum likelihood estimates (MLEs) in particular enjoy many desirable properties. However, in the case of many ERGMs, direct calculation of MLEs is impossible and therefore methods for approximating MLEs and/or alternative estimation methods must be employed. Many MLE approximation algorithms require an alternative estimate as a starting point. The maximum pseudo-likelihood estimator (MPLE) is frequently taken as this starting point. Here, we discuss a potentially large class of such alternatives based on the fact that, unlike the MLE, the MPLE fails to satisfy the so-called “likelihood principle”. This means that different networks may have different MPLEs even if they have the same sufficient statistics. We exploit this fact here to search for improved starting values for approximation-based MLE methods. The method we propose has shown its merit in producing an MLE for a network dataset and model that had defied estimation using all other known methods.

The Determinants of Trade in Services With the Focus on Tourism

This paper estimates the gravity of bilateral trade in services at an aggregate level. The aim of the paper is to assess the effects of social and economic factors on the export of services. A large part of the trade-in services is directly or indirectly related to the tourism industry; therefore, the results of this research are mainly discussed from the perspective of the tourism industry. To achieve the paper's aim, we estimate the augmented gravity model on a sample of 5,359 trading partners from 2000 to 2018. We evaluate our model using the Poisson Pseudo Maximum Likelihood estimator. We include various fixed-effect dummies in our model to address the endogeneity issues. Our results show that standard gravity variables such as economic size and distance are significant for service trade. From the tourism industry perspective, it can be concluded that trade in tourism services is determined by the similarity in economic size, proximity, and common socio-economic factors such as common first language and shared religious beliefs. In contrast, common colonial history has no significant effects on service trade.