Search results

This paper introduces more advanced panel data specifications that would exploit heterogeneity and allow for arbitrary forms of autocorrelation and heteroskedasticity in the error terms.

In line with Assaf and Tsionas (2019a, 2019b), this paper builds on the Mundlak device to propose panel data models to allow for random slope coefficients, as well as time slope coefficients. This paper allows for arbitrary heteroskedasticity and autocorrelation, thus mitigating possible model misspecification. This paper develops and estimates the model in a Bayesian framework. This paper’s methods can be generalized to many nonlinear models including limited dependent variable models.

This paper compares several competing models such as a classical panel data model, which has only firm effects. This paper also examines the role of standard deviations in the formation of firm effects and time effects in the Mundlak device. This paper clearly shows that our framework introduces the best flexibility and model fit.

This paper illustrates the importance of using more flexible models (i.e. unit-specific and time-varying coefficients) for future estimation of panel data in the field.

This paper discusses techniques that will improve panel data estimation in the hospitality and tourism literature.

This paper aims to serve as an important guide for more rigorous quantitative research in tourism and hospitality.

This paper relies on comments from several methodological experts in the field, as well as the authors’ main observation of the literature.

This paper identifies ten important areas of concern. In each of these areas, the authors provide recommendations for best practices.

There are certainly other issues and concerns that are not covered in this paper. However, the issues addressed can be applied or generalized to most methodological contexts.

This paper does not present results from original research but provides interesting and comprehensive recommendations for more rigorous quantitative research.

The purpose of this note is to describe the concept of regression trees (RTs) for hospitality data analysis.

RT is an effective non-parametric predicting modelling approach that would free researchers from the need to force a certain functional form. The method does not require normalization or scaling of data.

The authors illustrate how RTs can be used to find a model that would result in the best prediction.

A common challenge facing hospitality researchers is to estimate a regression model with the correct specification. RTs can help researchers identify the best explanatory model for prediction.

This paper describes the concept of RTs for the modelling of hospitality data.

This paper aims to focus on addressing endogeneity using instrument-free methods. The authors discuss some extensions to well-known techniques.

This paper discusses some attractive methods to address endogeneity without the need for instruments. The methods are labeled are “harmless” in the sense that instruments are not needed and the distributional assumptions are kept to a minimum or they are replaced by more flexible semi-parametric assumptions.

Using a hospitality application, the authors provide evidence about the effectiveness of these techniques and provide directions for their implementation.

Finding valid instruments has always been a key challenge for researchers in the field. This paper discusses and introduces methods that free researchers from the need to find instruments.

The paper discusses techniques that are introduced from the first time in the tourism literature.

This paper aims to present several Bayesian specification tests for both in- and out-of-sample situations.

The authors focus on the Bayesian equivalents of the frequentist approach for testing heteroskedasticity, autocorrelation and functional form specification. For out-of-sample diagnostics, the authors consider several tests to evaluate the predictive ability of the model.

The authors demonstrate the performance of these tests using an application on the relationship between price and occupancy rate from the hotel industry. For purposes of comparison, the authors also provide evidence from traditional frequentist tests.

There certainly exist other issues and diagnostic tests that are not covered in this paper. The issues that are addressed, however, are critically important and can be applied to most modeling situations.

With the increased use of the Bayesian approach in various modeling contexts, this paper serves as an important guide for diagnostic testing in Bayesian analysis. Diagnostic analysis is essential and should always accompany the estimation of regression models.

This paper aims to foster a new discussion on endogeneity in hospitality and tourism research.

This paper elaborates on some of the common sources of endogeneity and the methods available to address them.

The authors present a variety of methods that can be used to mitigate the endogeneity problem. The authors provide simulation evidence regarding the risk of incorrectly selecting instrumental variables. The authors also provide several important practical recommendations for future research.

There are other issues and methods of correcting for endogeneity, that is not covered in this paper. However, the paper focuses on issues and methods that can be generalized to most contexts.

The paper provides practical recommendations for more rigorous regression estimation.

In this paper, the authors investigate whether coronavirus disease 2019 (COVID-19) impacts household finances, like household debt repayments in the UK.

This paper employs a vector autoregressive (VAR) model that nests neural networks and uses Mixed Data Sampling (MIDAS) techniques. The authors use data information related to COVID-19, financial markets and household finances.

The authors' results show that household debt repayments' response to the first principal component of COVID-19 shocks is negative, albeit of low magnitude. However, when the authors employ specific COVID-19-related data like vaccines and tests the responses are positive, insinuating the underlying dynamic complexities. Overall, confirmed deaths and hospitalisations negatively affect household debt repayments. The authors also report low persistence in household debt repayments. Generalised impulse response functions (IRFs) confirm the main results. As draconian measures, the lockdowns are eased and the COVID-19 shocks are diminishing, and household financial data converge to the levels prior to the pandemic albeit with some lags.

To the best of the authors' knowledge, this is the first study that examines the impact of the pandemic on household debt repayments. The authors' findings show that policy response in the future should prioritise innovation of new vaccines and testing.

The purpose of this paper is to analyze the bank efficiency in three developing countries, namely Angola, Brazil and Mozambique, aiming to infer differences given that they belong to the same cultural tradition. The underlying idea is to control for the cultural background, thus allowing the discussion on how different socio-economic and historical variables maybe impacting different levels of banking efficiency and returns to scale results within the ambit of these three countries.

Due to the presence of latent inefficiency, the authors have to modify the technique to accommodate simulation by importance sampling; therefore, in effect, the authors use a local maximum simulated likelihood approach.

The results reveal that Brazil has the highest level of output-oriented efficiency, followed by Angola and then Mozambique. The same ranking is observed in returns to scale, except that vis-à-vis technical change, Brazil and Angola rank first. Finally, inefficiency derived from technical change is highest in Mozambique, followed by Angola and then Brazil. Therefore, these results reveal that the countries with the highest degree of development are higher in efficiency.

Previous studies have identified factors such as legal tradition, accounting conventions, regulatory structures, property rights, culture and religion as possible explanations for cross-border variations in financial development and economic growth. This is the first time banking efficiency is assessed in light of a common cultural background by selecting a group of countries that share the same language and colonial past. Since results are controlled for the same background, it is possible to affirm that the findings are purely related to scale size and economic/political background issues of each country.

This study proposes a new model to measure unexpected core earnings, using Bayesian dynamic latent method.

The Bayesian dynamic latent modelling approach identifies the effects that stem from complex, multidimensional variables related to culture and legal framework, on unexpected core earnings. It also allows testing whether there is persistence over time in unexpected core earnings. We use sequential Bayesian Monte Carlo methods, also known as particle filtering, that simplify estimations.

In an international empirical application, we find evidence of persistence in unexpected core earnings as well as classification shifting. The impact of the legal framework on classification shifting shows variability across samples. Religion reduces classification shifting, whereas the cultural variables of power distance, masculinity, and uncertainty avoidance enhances it. Interestingly, the persistence in unexpected core earnings is strong and moderates the ability of legal framework and religion in abating classification shifting.

In terms of policy implications, we show that strengthening legal framework would improve financial reporting and reduce the scope for manipulation. This could involve stricter enforcement mechanisms, increased penalties for non-compliance, and regular audits to detect and deter classification shifting practices. Given that religion plays a role in moderating classification shifting, policymakers may explore partnerships or collaborations with religious institutions to promote ethical financial practices. Engaging religious leaders and organizations can help emphasize the importance of integrity and ethical behaviour in financial reporting, potentially influencing the behaviour of individuals and organizations.

To the best of our knowledge this is the first study that opts for Bayesian dynamic latent model for an international sample.