Ordinary Least Squares Approach Research Articles

Machine learning models applied to altimetry era tide gauge and grid altimetry data for comparative long-term trend estimation: A study from Shikoku Island, Japan

Estimation of sea level trends is essential for understanding sea level rise dynamics. In this study, the performance of traditional Ordinary Least Squares (OLS) linear trend forecasting is compared with modern machine learning techniques, specifically Random Forests (RF) and Least Squares Support Vector Machines (LS-SVM).These methods are applied to 50 years of long-term tide gauge (TG) data from six tide gauge stations off the coast of Shikoku Island, Japan, and CMEMS Grid Altimetry data from 1993 to the present. The analysis uses OLS, RF, and LS-SVM to estimate trends from both data sets and compares the results. The objective is to determine the consistency and accuracy of RF and LS-SVM methods compared to the OLS method. The results indicate that machine learning algorithms (LS-SVM) effectively estimate sea level trends, offering potential improvements in precision for both long-term and medium-term analyses. Shikoku Island's coastal sea level trend is determined as 2.91±1.44 mm/yr using TG data and 3.00±1.52 mm/yr using CMEMS Grid Altimeter data with the OLS approach. Using the LS-SVM approach, the trend is found as 2.96±1.58 mm/yr with TG data and 3.02±1.60 mm/yr with CMEMS Grid Altimetry data. The novelty of this study lies in its thorough comparison of traditional and machine learning approaches for sea level trend estimation, providing valuable insights for future predictions of the sea level rise.

Evaluation of the Impact of Regional Trade Agreements on Indian Exports

This article scrutinises the repercussion of the regional trade agreements on Indian exports. The gravity model has been used for the analysis of two decades of panel data from 30 countries, spanning from 2001 to 2019. The gravity equation is estimated by the Ordinary Least Square (OLS) and Poisson pseudo-maximum likelihood (PPML) techniques using panel data regression. The PPML approach addresses the heteroskedasticity bias that is typically present in the OLS method. The study has revealed that the PPML results are more encouraging than those obtained based on the traditional OLS approach. According to the empirical findings, India’s trading partners in South Asia benefit more from its economic integration than India does. However, the measurement of country-specific degrees of globalisation has a negligible effect on fostering trade across select nations. JEL Codes: C1, F1, F2, F6

A Novel Inversion Approach for the Kernel-Driven BRDF Model for Heterogeneous Pixels

The bidirectional reflectance distribution function (BRDF) of the land surface contains information relating to its physical structure and composition. Accurate BRDF modeling for heterogeneous pixels is important for global ecosystem monitoring and radiation balance studies. However, the original kernel-driven models, which many operational BRDF/Albedo algorithms have adopted, do not explicitly consider the heterogeneity within heterogeneous pixels, which may result in large fitting residuals. In this paper, we attempted to improve the fitting ability of the kernel-driven models over heterogeneous pixels by changing the inversion approach and proposed a dynamic weighted least squares (DWLS) inversion approach. The performance of DWLS and the traditional ordinary least squares (OLS) inversion approach were compared using simulated data. We also evaluated its ability to reconstruct multiangle satellite observations and provide accurate BRDF using unmanned aerial vehicle observations. The results show that the developed DWLS approach improves the accuracy of modeled BRDF of heterogeneous pixels. The DWLS approach applied to satellite observations shows better performance than the OLS method in study regions and exhibits smaller mean fitting residuals both in the red and near-infrared bands. The DWLS approach also shows higher BRDF modeling accuracy than the OLS approach with unmanned aerial vehicle observations. These results indicate that the DWLS inversion approach can be a better choice when kernel-driven models are used for heterogeneous pixels.

Forecasting the real prices of crude oil: A robust weighted least squares approach

The ordinary least squares (OLS) estimator inflates the estimation variance of parameters in the presence of outliers, thus providing poor out-of-sample forecasts. We forecast the real price of crude oil using a robust weighted least squares (RWLS) approach that has the potential to improve forecasting performance by dealing with outliers. This approach down-weights extreme observations using a class of kernel functions. Our results show that the RWLS improves forecasting accuracy relative to the standard OLS approach. Furthermore, the predictability of oil prices revealed by the RWLS is statistically significant for longer horizons. The predictive ability of the RWLS comes from more efficient estimates and the trade-off between forecast bias and variance. Sensitivity analyses indicate that the findings are robust to alternative validation samples, kernel functions, and combination strategies.

A New Approach to Improving Hedging Performance in the OLS Model

The sensitivity of VIX futures to market movements changes over time with changes in market risk. Accordingly, in the case of using the OLS (ordinary least squares) model to hedge S&P 500 exposure with VIX futures, hedge ratios are affected by changes in risk appetite, which in turn contributes to the overall hedging performance as well as the asymmetry of the performance distribution. The conventional OLS approach does not effectively reflect this phenomenon in the model. In this study, the authors explore a new approach to improving hedging performance in the OLS model. They introduce an interaction term between the VIX and VIX futures returns into the OLS model. They find that the hedge ratios derived by the new approach provide better hedging results compared to the univariate OLS model in terms of mean return and downside risk protection, and also improve the asymmetry of the performance distribution. They extend their research to compare it with the performance of the dynamic conditional correlation (DCC)-generalized autoregressive conditional heteroskedasticity (GARCH) model. The new approach also shows better results than the DCC-GARCH approach. They obtain the same results in case studies of the Global Financial Crisis and the COVID-19 pandemic, and also in applying a trading strategy to each hedging methodology.

Harmonic Analysis of Non-Phase-Locked Tides with Red Noise Using the red_tide Package

Abstract A novel tidal analysis package (red_tide) has been developed to characterize low-amplitude non-phase-locked tidal energy and dominant tidal peaks in noisy, irregularly sampled, or gap-prone time series. We recover tidal information by expanding conventional harmonic analysis to include prior information and assumptions about the statistics of a process, such as the assumption of a spectrally colored background, treated as nontidal noise. This is implemented using Bayesian maximum posterior estimation and assuming Gaussian prior distributions. We utilize a hierarchy of test cases, including synthetic data and observations, to evaluate this method and its relevance to analysis of data with a tidal component and an energetic nontidal background. Analysis of synthetic test cases shows that the methodology provides robust tidal estimates. When the background energy spectrum is nearly spectrally white, red_tide results replicate results from ordinary least squares (OLS) commonly used in other tidal packages. When background spectra are red (a spectral slope of −2 or steeper), red_tide’s estimates represent a measurable improvement over OLS. The approach highlights the presence of tidal variability and low-amplitude constituents in observations by allowing arbitrarily configurable fitted frequencies and prior statistics that constrain solutions. These techniques have been implemented in MATLAB in order to analyze tidal data with non-phase-locked components and an energetic background that pose challenges to the commonly used OLS approach.

A modelling approach with geographically weighted regression methods for determining geographic variation and influencing factors in housing price: A case in Istanbul

Determining real estate market dynamics has become an important issue in the city economy for achieving sustainable urban land management and investment planning. This study aims to determine the potential influencing factors of housing prices through applying global regression models including Ordinary Least Squares (OLS), Spatial Lag Model (SLM), and Spatial Error Model (SEM) and to examine their geographic variation by local regression approaches such as Geographically Weighted Regression (GWR) and Multiscale Geographically Weighted Regression (MGWR). Pendik district of Istanbul (Turkey) was selected as study area. For these purposes, a case geodatabase was created with twenty-eight attributes: structural, geographic, and neighbourhood variables. Initially, nine significant variables used as input in the other models were selected with a stepwise OLS approach. The modelling results suggested that local models achieve better performance in comparison to global models. Furthermore, local model factor coefficients and local R2 values were mapped for nine variables. Geographic variations of these variables with regards to housing price were analysed for GWR and MGWR models. This study provides a comprehensive methodology for the real estate market and city authorities to understand the geographic variations of factors affecting the real estate market in urban geography.

Forecasting the Chinese stock market volatility: A regression approach with a t-distributed error

ABSTRACT In this paper, we improve the ordinary least squares (OLS) estimation approach by replacing a normally distributed error with a t-distributed error. Empirically, we investigate the predictability of the Chinese stock market volatility based on this modified approach. Results show that the modified OLS method with a t-distributed error has a significantly stronger forecasting power than its counterpart with a normally distributed error. From an asset allocation perspective, the modified OLS approach can help a mean-variance investor obtain sizeable utility gains. We also conduct two extended empirical analyses and further verify the superiority of the regression approach with a t-distributed error. Our results are robust to a series of settings. Finally, we find that the regression approach with a t-distributed error shows greater tolerance for outliers by assigning smaller weights to them, thereby highlighting its superior performance.

Tradeoffs between economies of scale and specialization in efficiency for the global semiconductor industry

ABSTRACT This paper combines the semiparametric modified ordinary least-squares approach by Simar et al. (2017) with the nonparametric shape constraint regression approach by Du et al. (2013) to evaluate the performance in the semiconductor industry. Using panel data on 470 companies in the global semiconductor industry over 1999–2018, we compare technical eficiencies between the integrated device manufacturer business model and the fabless-foundry business model. The performance differences between the vertically integrated device manufacturers and the vertically specialized fabless and foundry firms are disentangled by the intensity of labour and capital in a very flexible form. The estimation results indicate that the capital-intensive integrated device manufacturers taking advantage of the economies of scale are operating more efficiently than the niche fabless companies in the global semiconductor industry.

Spatial Analysis of Distribution of Inmates in Nigeria Prisons

The number of prison facilities available in Nigeria differs from state to state as well as across the regions. Hence the distribution of the inmates across these correctional facilities differs. This study investigates the distribution of the inmates across Nigeria correctional facilities (prisons) and the likely factors that may influence the distribution considering the spatial effect of the distribution. The considered factors are; year, month, state, region, gender and state population. Ordinary Least Square (OLS) was used to obtain the multiple regression model and Moran’s I test of spatial autocorrelation showed that there is presence of spatial autocorrelation in the distribution of inmates across Nigeria prisons. The Spatial Autocorrelation Regression Model (SARM) was therefore adopted to fit the regression model. While OLS approach indicated that all factors are significant except state, the SARM approach found both state and region not to be significant among the factors considered in the model. The SARM did not only give good compact spatial distribution of the inmates across Nigeria prisons it also gave a better predicted (forecast) values of inmates’ distribution than the OLS approach.

Model to Predict Wartime Equipment Waste Based on Multiple Regression Analysis

Predicting wartime equipment waste has not only been a research topic at home and abroad but is also difficult. Traditional research methods emphasize the trend of wartime equipment waste but ignore the effects of influencing variables. This paper discusses the influencing factors of wartime equipment waste and proposes a model to predict wartime equipment waste based on multiple regression analysis. An ordinary least-squares approach is used to estimate the parameters of the model. The significance of the model and regression coefficient is evaluated by the complex correlation coefficient and the t-test, respectively. Ways to optimize and improve the model in future studies are discussed. Expressions to calculate the prediction value and prediction interval are given. This paper establishes three main factors that can be quantified and have a certain sample size: combat time, failure rate, and military input. First, a conventional multiple linear regression model is established. Based on the results of the significance test, the model is iteratively analyzed and optimized. Second, a stepwise regression method is used to screen the independent variables, and a weighted least- square estimation is used to evaluate the influence of changes in the automatic variables on the residual. Finally, a multivariate nonlinear regression approach using a weighted ternary quadratic polynomial model for statistical data is discussed and established. Results from testing indicate that the proposed model has good significance, feasibility, and practical application.

Does Financial Development Enhance Foreign Trade in Selected Transitional Economies?

The study investigates the influence of financial development on foreign trade in transitional economies using panel data (1994–2014). Although empirical studies on the impact of financial development on foreign trade are available, none of them that the authors are aware of attempted to explore the subject matter in the context of transitional economies. None attempted to investigate if human capital development is a channel through which financial development influences foreign trade or international trade. Under fixed effects, financial development was found to have a non‑significant positive influence on foreign trade, while the random effects approach shows a significant positive relationship running from financial development towards foreign trade. The findings resonate with the majority of the literature on the subject. However, pooled ordinary least squares (OLS) shows that financial development had a significant negative influence on foreign trade.
 Under both fixed and random effects, human capital development was found to be a channel through which financial development had a significant positive effect on foreign trade. The results are in line with Patrick’s (1966) argument that foreign trade is quickened by high levels of human capital and financial development. The implication of the study is that transitional authorities should develop and implement human capital development enhancement policies in order to enable financial development to have a significant positive effect on foreign trade. In contrast to the available literature, human capital development was found to have had a significant negative impact on foreign trade under the OLS approach. Future studies on the subject matter should address the endogeneity concerns and the dynamic characteristics of the foreign trade data.

1042P Objective response rate as an intermediate surrogate endpoint to predict overall survival at 12 months

Immune checkpoint inhibitors (ICI) have a unique mechanism of action that differs from chemotherapy. Despite the poor correlation between ORR and overall survival (OS), 12-month OS (OS12) ratio is a good intermediate surrogate for OS at trial level. We aimed to develop and validate a model using ORR as a predictor for OS12 in ICI trials. We performed an electronic search to identify eligible studies. Randomized controlled trials (RCTs) reported between January 2020-June 2019 formed the model development dataset. Correlation between ORR and OS12 were examined both at trial and ICI arm levels. Using the ICI arm data, a linear regression model was fitted using the ordinary least-squares approach, adjusting for tumour types, with ORR as a predictor for OS12. We then extracted data from an independent dataset of RCTs and single-arm ICI studies, reported from June 2019 to Jan 2020, to validate the performance of our prediction model. We identified 63 eligible trials, with 78 ICI treatment arms (58 RCTs, 20 single-arm). Thirteen trials were doublet ICI studies. The tumours types were predominantly non-small cell lung cancer (30%) and melanoma (13%). Other main tumours types included gastric/oesophageal (10%), renal cell (9%), head and neck squamous cell (8%), urothelial carcinoma (8%) and others (17%). Fifty ICI arms (from 43 RCTs) formed the model development dataset. The validation dataset comprised of 28 ICI arms (8 RCTs, 20 single arm studies). At arm level, the correlation between ORR and OS12 within ICI arms was strong, r=0.80. Complete response rate correlates poorly with OS12 (r= 0.50). The ORR-OS12 prediction model was OS12 = (1.012324 x ORR) + 0.3006825 + (0 x melanoma) + (0.0021079 x NSCLC) – (0.038521 x other tumors). When this model was applied in the validation dataset, the fitted line of scatterplot of ORR-predicted OS12 revealed close calibration with the observed OS12, r= 0.63. At trial level, the correlation between ORR risk ratio and OS HR was poor, r=0.58. Our prediction model using ORR can be used to predict for OS12 in early phase ICI trials, regardless of tumour type, overcoming the issue of poor correlation between ORR and OS. This may help support decisions for phase III testing based on ORR in phase II trials of ICI.

Probabilistic estimation of variogram parameters of geotechnical properties with a trend based on Bayesian inference using Markov chain Monte Carlo simulation

ABSTRACT When geotechnical properties show a trend with spatial coordinates, estimation of a variogram model is a challenging task. In the previous studies, the trend-removal method based on ordinary least-squares approach has been commonly used. However, the obtained variogram is biased because the residuals are assumed to be statistically independent. In this study, the ability of Bayesian inference using Markov chain Monte Carlo (MCMC) simulation to estimate the variogram of geotechnical properties with a trend is explored using cone penetration resistance (q c) data of piezocone penetration tests (CPTU). The results show that the Bayesian inference method can estimate variogram parameters and the coefficients of trend function accurately. Based on the posterior variogram models, the predictive uncertainty and total uncertainty bounds are presented using kriging and sequential Gaussian simulation (SGS) methods. 96% validation points lie within the 95% confidence intervals of the total uncertainty based on 200 measurements of q c at NS31. The median and mean SSD of the prediction are 0.34 and 0.87, which is closer to the SSD criterion than the trend-removal method. The model uncertainty of the variograms, the predictive and total uncertainty of prediction all decrease as the sampling density increases at NS31 and NS12.

Examining the factors that influence firm performance in Ghana: a GMM and OLS approach

This research aims to establish the determinants of firm performance in 15 non-financial Ghanaian companies listed on the Ghana Stock Exchange, over a period of 10 years (2008–2017). The analysis is based on two methods of estimation; two-step system generalized method of moments (GMM) and ordinary least square (OLS) method. The new empirical evidence derived from the results of the analysis reveals that firm size (SIZE), growth (GR) and cash flow ratio (CFR), significantly and positively determines firm's performance whereas debt to equity (DE) exerted negative influence on firm performance. Robustness test conducted using the three-stage least-squares regression, indicates similar results with the main findings of the study. These results imply that, firms that rely on debt to execute its operations run at a higher risk of insolvency.

Updating urban design floods for changes in central tendency and variability using regression

Ordinary least squares (OLS) regression offers a decision-oriented approach for modeling trends in annual peak flows. We introduce a two-stage OLS approach for nonstationary flood frequency analysis that (i) models changes in their central tendency (median) in response to environmental perturbations with one regression and then (ii) examines changes in the coefficient of variation (Cv) by running a second regression on Anscombe-transformed residuals from the first regression. Monte Carlo simulations show that this approach yields 100-year flood estimates with mean squared errors comparable to estimates made with an advanced generalized linear model-based method. Also, this second-stage regression often produces approximately normal residuals, which permits statistical inferences on Cv trends. Case studies illustrate the dramatic impact that decreasing and increasing Cv trends can have on 100-year floods. Findings motivate the incorporation of trends in variability in infrastructure design along with further research examining asymmetric changes in urban flood variability.

On the estimation of Okun’s coefficient in some countries in Latin America: a comparison between OLS and GME estimators

We explore Okun’s coefficient in several Latin American countries for the period from 1995 to 2017 and compare the results obtained using ordinary least squares (OLS) and generalised maximum entropy (GME) estimators. There are several advantages in considering the GME estimator over traditional regression approaches. First, it can estimate the parameters of an equation without imposing constraints on the probability distribution of the errors. Second, empirical and simulation studies available in the literature showed that GME worked well for ill-posed problems (e.g. when a model estimate is performed using a small sample of data). Among the main findings, we confirm the inverted relationship between changes in the unemployment rate and real gross domestic product growth in the explored countries except for Peru. Okun’s coefficient and the associated confidence intervals obtained by applying GME were very close to those obtained from OLS. Therefore, we did not observe a gain when using the GME estimator rather than the classic OLS approach.

Does Financial Inclusion Improve the Financial Performance of Commercial Banks in Egypt?: Pooled OLS Approach

Financial inclusion is gaining acceptance in Egypt as a prominent policy toward the economic reform during the last few years. However, there is relative dearth of em1 pirical studies examining the impact of financial inclusion on the performance of banks in Egypt. This paper fills this gap. Using Pooled Ordinary Least Square (OLS) of six commercial banks listed in the Egyptian stock market over the period from 2013 to 2018, this study empirically investigate the impact of financial inclusion on the performance of Egyptian banks measured in terms of Return on Assets (ROA) and Return on Equity (ROE). Financial inclusion is measured subject to two main dimensions- the access to financial services and utilization of bank account and its related financial services. Due to the difficulty of getting data, the usage dimension is taken for the side of individuals only and ignores SMEs such as credit card; loan; deposit for SMEs. Results showed that financial inclusion positively contribute to banks’ ROA and ROE.

How Does Remittance Impact on Economic Development in South Asia? A Dynamic Ordinary Least-Square Approach

This paper aims to examine the impacts of remittances on the economic development of four South Asian countries: Bangladesh, India, Pakistan and Sri Lanka. The study considers the World Bank’s balanced panel data (1977–2017). The dynamic ordinary least-square approach finds mixed results, which explain the realisation of the pluralistic approach. Evidence shows that remittances directly increase gross domestic product, household consumption and expenditure and decreases government consumption expenditure, inflation and population growth. However, the flow of remittances is not promoting private bank credit; rather it increases import-dominated trade. Besides, remittances are yet to be significant at gross capital formation. Therefore, we recommend that policymakers should find a way to bring remittance through formal channels for capital formation and investment. Fortunately, remittance inflows indirectly cause population control and sustainability. Decision-makers should also formulate policies that will modify remittance-induced current production and consumption patterns to promote the process of sustainable development further.

THE IMPACT OF FINANCIAL DEVELOPMENT ON CARBON EMISSIONS IN AFRICA

The paper explored the influence of financial development on carbon emissions in West African countries using pooled ordinary least squares (OLS), fixed and random effects with data spanning from 2003 to 2014. On the theoretical front, arguments for both financial development led positive impact on carbon emissions and financial development led negative impact on carbon emissions are quite compelling. Empirical studies on the role played by financial development on carbon emissions produced quite divergent and conflicting findings. It is clear from both theoretical and empirical sides that the influence of financial development on carbon emissions is still a contentious issue which is yet to be resolved in literature. Overally, pooled OLS approach (both lagged and non-lagged variable) shows that only domestic credit provided by financial sector resulted in the significant increase in carbon emissions in Western African countries.