Search results

This survey focuses on two families of nonlinear vector time series models, the family of vector threshold regression (VTR) models and that of vector smooth transition regression (VSTR) models. These two model classes contain incomplete models in the sense that strongly exogeneous variables are allowed in the equations. The emphasis is on stationary models, but the considerations also include nonstationary VTR and VSTR models with cointegrated variables. Model specification, estimation and evaluation is considered, and the use of the models illustrated by macroeconomic examples from the literature.

A major key success factor regarding proficient Bayes threshold denoising refers to noise variance estimation. This paper focuses on assessing different noise variance estimations in three Bayes threshold models on two different characteristic brain lesions/tumor magnetic resonance imaging (MRIs).

Here, three Bayes threshold denoising models based on different noise variance estimations under the stationary wavelet transforms (SWT) domain are mainly assessed, compared to state-of-the-art non-local means (NLMs). Each of those three models, namely D1, GB and DR models, respectively, depends on the most detail wavelet subband at the first resolution level, on the entirely global detail subbands and on the detail subband in each direction/resolution. Explicit and implicit denoising performance are consecutively assessed by threshold denoising and segmentation identification results.

Implicit performance assessment points the first–second best accuracy, 0.9181 and 0.9048 Dice similarity coefficient (Dice), sequentially yielded by GB and DR; reliability is indicated by 45.66% Dice dropping of DR, compared against 53.38, 61.03 and 35.48% of D1 GB and NLMs, when increasing 0.2 to 0.9 noise level on brain lesions MRI. For brain tumor MRI under 0.2 noise level, it denotes the best accuracy of 0.9592 Dice, resulted by DR; however, 8.09% Dice dropping of DR, relative to 6.72%, 8.85 and 39.36% of D1, GB and NLMs is denoted. The lowest explicit and implicit denoising performances of NLMs are obviously pointed.

A future improvement of denoising performance possibly refers to creating a semi-supervised denoising conjunction model. Such model utilizes the denoised MRIs, resulted by DR and D1 thresholding model as uncorrupted image version along with the noisy MRIs, representing corrupted version ones during autoencoder training phase, to reconstruct the original clean image.

This paper should be of interest to readers in the areas of technologies of computing and information science, including data science and applications, computational health informatics, especially applied as a decision support tool for medical image processing.

In most cases, DR and D1 provide the first–second best implicit performances in terms of accuracy and reliability on both simulated, low-detail small-size region-of-interest (ROI) brain lesions and realistic, high-detail large-size ROI brain tumor MRIs.

This study aims to explore the relationship between the growth threshold effect on renewable energy consumption (REC) in the major oil-producing countries in sub-Saharan Africa (SSA) over the period 1990–2018.

This article used a dynamic panel threshold regression model introduced by Hansen (1996, 1999 and 2000) threshold (TR) models. The procedure is achieved using 5,000 bootstrapping replications and the grid search to obtain the asymptotic distribution and p-values. For the long-run relationship among our variables, the author followed the process in Pesaran et al. (1999) pooled mean group (PMG) for heterogeneous panels. Furthermore, for the robustness of our empirical results due to the sensitivity of the results to outliers, the author used the approach by Cook (1979) distance measure. The author applied quantile (QR) regression to explore the distribution of dependent variables following Bassett and Koenker (1982) and Koenker and Bassett (1978) approaches.

The results from the threshold effect test and threshold regression revealed a significant single threshold effect of growth level on REC. Furthermore, the result from the PMG estimation showed the growth of the variable, energy intensity, consumer prices and CO₂ emissions play a significant role in REC in major oil-producing countries in SSA. The growth threshold estimation results indicated one significant threshold value of 1.013% at one period lagged of real growth. The outlier’s sensitivity detention greatly influenced our empirical results.

The article filled the literature gap by applying a combined measure that is robustness to detect outliers in the data, which none of the studies in the literature addresses hitherto. Further, the article extends the quantile regression to growth – REC literature.

The purpose of this paper is to investigate the impact of changes in credit stock on real and financial indicators in Turkey with a focus on conditional and time-varying dynamics.

In addition to lag-augmented vector autoregression (LA-VAR) based time-varying Granger causality tests, threshold models and a research setting that identifies high/low states of credit growth based on 24-month moving averages are used to explore regime-dependent behavior. For investigating the asymmetric dynamics, the authors use a methodology that identifies good/bad news in credit growth based on 24-month moving averages and standard deviations.

Results strongly suggest that the impact of changes in credit stock induces conditional responses. Moreover, we find evidence for asymmetric responses. In the case of Turkey, efforts to spur growth through credit produce a strong negative byproduct, a depreciation in the exchange rate. The authors also find that changes in credit stock have become more relevant for uncertainties in inflation and exchange rate expectations, particularly in the era after mid-2018 in which credit growth volatility has increased noticeably.

This study provides a comprehensive analysis of time-varying and conditional responses to a change in credit stock in a major emerging economy. Using a moving threshold based only on the available information in the analysis of state-dependency represents a new approach.

Insurance companies play a significant role in every economy; hence, it is essential to investigate and understand the factors that propel their profitability. Unlike previous studies that present a linear relationship, this study provides initial evidence by exploring the non-linear impacts of the determinants of profitability amongst life insurers in South Africa.

The study uses a panel dataset of 62 life insurers in South Africa, covering 2013–2019. The generalised method of moments and the dynamic panel threshold estimation technique were used to estimate the relationship.

The empirical results from the direct relationship reveal that investment income and solvency significantly predict life insurance companies' profitability. On the other hand, underwriting risk, reinsurance and size reduce profitability. Further, the dynamic panel threshold analysis confirms non-linearities in the relationships. The results show that insurance size, investment income and solvency promote profitability beyond a threshold level, implying a propelling effect on life insurers' profitability at higher levels. Below the threshold, these factors have an adverse effect. The study further points to underwriting risk, reinsurance and leverage having a reduced effect on life insurers' profitability when they fall above the threshold level.

The findings suggest that insurers interested in boosting their profit position must commit more resources to maintain their solvency and manage their assets and returns on investment. The study further recommends that effective control of underwriting risk is critical to the profitability of the life insurance industry.

The study contributes to the literature by providing first-time evidence on the determinants of life insurance companies' profitability by way of exploring threshold effects in South Africa.

This paper investigates the main drivers of foreign direct investment (FDI) inflows for a balanced panel of 11 Middle East and North Africa (MENA) economies over the 1995–2017 annual period. The author postulates that the impacts of the main pull (growth) and push (global financial conditions, GFC) factors may not be invariant to endogenously estimated thresholds for structural domestic conditions (SDCs) including trade and capital account openness, financial development, human capital (HC) and natural resource endowments.

The author investigates whether the main SDC provide endogenous thresholds for the impacts of basic pull and push factors on FDI inflows for the MENA sample by employing panel fixed effects threshold procedure of Hansen (1999). As a robustness check, the author also present the results of the dynamic panel data two-step system generalized method of moments (GMM) estimation, which explicitly consider the potential endogeneity of SDC along with main pull factor for the evolution of FDI inflows.

Growth, GFC and SDC are important drivers of FDI inflows. The impacts of SDC tend to be higher in countries with higher financial depth, openness to international trade and finance and lower natural resource and HC endowments. The sensitivities of FDI inflows to GFC are substantially higher in the countries which are more open to international trade and capital flows and higher levels of financial depth. FDI inflows are found to be pro-cyclical and this pro-cyclicality tends to be much higher for the episodes exceeding the SDC thresholds.

Improving SDC including higher openness to international trade and finance and financial development may be effective in encouraging FDI inflows. The findings support an argument that, better SDC are crucially important not only for attracting FDI but also achieving the growth benefits of FDI inflows. Therefore, improving SDC appears to be an important growth-oriented policy agenda for emerging market and developing economies (EMDEs) including MENA.

The impacts of the main push and pull factors on FDI (and capital) inflows may be nonlinear. The literature often tackles the nonlinearity issue either by some interaction specifications or imposing exogenous thresholds. The literature, however, is yet to comprehensively investigate whether the main SDC provide endogenous thresholds for the impacts of basic pull and push factors. The author aims to contribute to the literature by estimating endogenous SDC threshold levels for the impacts of the main determinants of FDI flows for MENA.

This study examines the role of financial development (FD) in enhancing the growth effect of foreign direct investment (FDI) in emerging and developing Asia from 1996 to 2019.

The study exploits the new broad-based Financial Development Index of the International Monetary Fund (IMF) and adopts panel smooth transition regression (PSTR) to perform alternative empirical models for a multidimensional analysis of the FD threshold effect in the growth–FDI nexus.

The results show two thresholds of FD mediating the nonlinear effect of FDI on growth. FD beyond a certain level will enhance the growth effect of FDI, but very high levels of FD will not induce foreign investment to benefit economic growth in emerging and developing Asian economies. The impact of financial institutions on the FDI–growth link is stronger than that of financial markets. Besides, FDI’s effect on growth has an inverted-U shape conditional on financial depth, whereas it is positively associated with the accessibility and efficiency of the financial system.

These results suggest policy implications for emerging and developing Asian countries, emphasizing the other side of “too much finance” and the potential for improvement in the access to and efficiency of the financial system to boost the effects of FDI and FD in the growth of these economies.

The study is the first multifaceted investigation into the influence of FD on the growth effect of FDI. Beyond the previous empirical evidence showing only the impact of credit from banking sector, this study shows different mediating effects of different financial sectors and three dimensions of financing (depth, access and efficiency). The study suggests essential implications for the region in adjusting long-run policies to enhance the FDI–FD–growth link.

The purpose of this paper is to shed light on the effect of high‐level human capital investment, using tertiary education as the proxy, on the urban‐rural income gap in China.

Using a panel dataset covering 28 provinces of China over the period from 1988 to 2007, this paper employs Hansen's method and two‐step GMM‐SYS estimator to estimate the threshold regression model and the dynamic fixed‐effect panel model, respectively.

The urban‐rural income gap is found to be related to high‐level human capital investment in an inverted U‐shaped pattern with respect to economic development level. The estimated threshold turning point is around 20,000 RMB GDP per capita. This estimate is sufficiently robust to model specifications and variants of the dependent variable.

The authors forecast that high‐level human capital investment could play a role in bridging the urban‐rural income gap at the national level by 2014, when China's GDP per capita assumes an annual growth rate of 7.5 percent.

This, it is believed, is the first research to find an inverted U‐shaped pattern for high‐level human capital investment and urban‐rural income gap nexus in China.

This study examines the influence of anti-money laundering (AML) regulations on the financial development-economic growth nexus around the world.

The study uses data from 165 countries spanning continents, income levels, and regulatory regimes from 2012 to 2018. The Prais–Winsten (1954) and Hansen (2000) panel threshold estimation approaches were used to assess the study's hypothesized relationships.

Financial development, according to the research, generally stimulates economic growth. However, the authors find evidence of AML regulations' threshold effect on the finance-growth connection, with the impact of finance on growth being positive below the threshold value. Above the threshold, however, the authors observe a negative influence. Further, the authors find that AML regulations have a considerable detrimental impact on the finance-growth nexus over the threshold for developed countries. However, the authors find a positive but insignificant effect of finance on growth below the AML regulations threshold for African countries, while finance positively impacts growth above the AML regulations threshold.

The findings of the study imply that countries must make conscious efforts to combat the incidence of money laundering by establishing policies to improve financial transparency and standards, promoting public sector transparency and accountability, reducing legal and political risk, and combating bribery and corruption.

This study contributes to the literature as it is the first attempt to examine the moderating role of AML regulations in the finance-growth nexus. Also, the study examines the threshold effect of how AML regulations impact the finance-growth nexus.

The purpose of this paper is to investigate the optimal inflation targets for an appropriate exchange rate policy in 15 major oil exporting countries in Sub-Saharan African (SSA).

Dynamic heterogeneous panel threshold techniques are used via threshold-effect test and threshold regression. This procedure is achieved through a grid search and bootstrapping replications method to stimulate the asymptotic distribution of the likelihood ratio test of the null hypothesis on no-threshold as against the alternative hypothesis. The p-values validate the threshold estimates.

Findings revealed that the optimal inflation target has a turning point and its impact on the real exchange rate is up to a threshold level of 14.47 per cent. Furthermore, the inflation rate above the threshold level overwhelmingly revealed its effect on real exchange regimes.

It would have been a good idea to investigate optimal inflation targets for all African countries but due to inadequate data the selection criteria was narrowed to oil-exporting countries in Sub-Saharan Africa.

Inflation targeting beyond the threshold level would have serious implications on the monetary policy.

To the best of the knowledge, this is the first study to look at optimal inflation targets for 15 major oil exporting countries in general and SSA countries in particular. The findings provide a critical analysis of an inflation regime for a typical oil-producing country that oil exports being their source of revenue.