Classical Linear Regression Model Research Articles

Analysis of ICT, Power Supply and Human Capital Development in Nigeria as an Emerging Market Economy

Abstract This paper analyzed the impact of information and communication technology (ICT) and power supply on human capital development in Nigeria as an emerging market economy. The study adopted the Classical Linear Regression Model for the empirical analysis. The result showed that ICT, power supply (proxied by electricity consumption) and population impact positively on human capital development, while infant mortality has a negative impact on human capital development in Nigeria. The impact of ICT on school enrolment suggests that technology is fast evolving and new technologies are preferred to old ones. The study, therefore, recommended that Nigeria should follow in the trend of ICT globally in harnessing her human capital endowments. In conclusion, the Nigerian government should harness her ICT and electric power potentials and develop the human capital available to her to prevent the emigration of her human resource endowment to more resilient and promising economies.

Cementing the Asymmetric Confluence of Exchange Rate and Stock Prices: NARDL Modeling for Kuwait

The efficiency of the stock market is tested by linear and non-linear methods benefiting from variables such as exchange rate, interest rate, money supply, and commodity prices. This paper specifically focuses on the exchange rate variable for an oil producer country, Kuwait, and tries to estimate parameters using the Classical Linear Regression Model, Autoregressive Distributed Lag Model and Nonlinear Autoregressive Distributed Lag Model. According to nonlinear results, we explore that macroeconomic and financial variables are inextricably interwined with stock prices. In this respect, exchange rate substantial harbinger considering magnitude and asymmetry. The results put forward in this study indicate a cointegration relationship, a short-run and long-run asymmetry between exchange rate and stock prices. Although the linear model indicates that an appreciation of the local currency increases stock prices in the short-run, the nonlinear model reveals a drop in stock prices significantly in the long-run.

Managing slow-moving item: a zero-inflated truncated normal approach for modeling demand.

This paper proposes a slow-moving management method for a system using of intermittent demand per unit time and lead time demand of items in service enterprise inventory models. Our method uses zero-inflated truncated normal statistical distribution, which makes it possible to model intermittent demand per unit time using mixed statistical distribution. We conducted numerical experiments based on an algorithm used to forecast intermittent demand over fixed lead time to show that our proposed distributions improved the performance of the continuous review inventory model with shortages. We evaluated multi-criteria elements (total cost, fill-rate, shortage of quantity per cycle, and the adequacy of the statistical distribution of the lead time demand) for decision analysis using the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). We confirmed that our method improved the performance of the inventory model in comparison to other commonly used approaches such as simple exponential smoothing and Croston’s method. We found an interesting association between the intermittency of demand per unit of time, the square root of this same parameter and reorder point decisions, that could be explained using classical multiple linear regression model. We confirmed that the parameter of variability of the zero-inflated truncated normal statistical distribution used to model intermittent demand was positively related to the decision of reorder points. Our study examined a decision analysis using illustrative example. Our suggested approach is original, valuable, and, in the case of slow-moving item management for service companies, allows for the verification of decision-making using multiple criteria.

Robust Function-on-Function Regression

ABSTRACT Functional linear regression is a widely used approach to model functional responses with respect to functional inputs. However, classical functional linear regression models can be severely affected by outliers. We therefore introduce a Fisher-consistent robust functional linear regression model that is able to effectively fit data in the presence of outliers. The model is built using robust functional principal component and least squares regression estimators. The performance of the functional linear regression model depends on the number of principal components used. We therefore introduce a consistent robust model selection procedure to choose the number of principal components. Our robust functional linear regression model can be used alongside an outlier detection procedure to effectively identify abnormal functional responses. A simulation study shows our method is able to effectively capture the regression behavior in the presence of outliers, and is able to find the outliers with high accuracy. We demonstrate the usefulness of our method on jet engine sensor data. We identify outliers that would not be found if the functional responses were modeled independently of the functional input, or using nonrobust methods.

K-NEAREST NEIGHBOR AND LINEAR REGRESSION IN THE PREDICTION OF THE ARTIFICIAL FORM FACTOR

k-nearest neighbor and linear regression in the prediction of the artificial form factor . T he proposal of this study was to test whether the performance of the non parametric approach k -Nearest Neighbor ( k -NN), would improve estimates of individual artificial form factor ( f 1.3 ) of trees of the hybrid Eucalyptus urophylla x Eucalyptus grandis compared to the O rdinary L east S quares method. A total of 149 sample-trees were selected , felled , and diameter was measured along the trunk at 10% (d 0. 1 ), 30% (d 0. 3 ), 50% (d 0. 5 ) and 70% (d 0. 7 ) of commercial height and posteriorly at 2m intervals . Mathematical models recognized in the literature for predicting the form factor were adjusted for comparison . The hyperparameter k of optimum adjust ment for the k -NN estimator was obtained by repeated cross-validation. The training data of the k -NN regression model were identical to those used in the adjustment of the linear regression models since m ost multiple linear regression models present problems of collinearity or multicollinearity. The use of the covaria te (d0.3.d0.7)/d1.32 and k = 15 made it possible to construct k -NN models with better generalization capacity. The potential of the k -NN estimator to predict the artificial form factor and thus to obtain less biased estimates of individual tree volumes was demonstrated and considered to be superior to the use of linear regression and average form factors. The k -NN approach can be considered more generic for predicti on of the tree form factor , and its use is recommended when classical linear regression models or other simpler methods do not yield good results.

Modelling approaches for predicting moisture transfer during baking of chhana podo (milk cake) incorporated with tikhur (Curcuma angustifolia) starch

Chhana podo, a popular dairy product of India, is prepared by baking the dough of chhana (heat-acid coagulated milk solids), semolina and sugar. Heat induced moisture loss during baking influences the chain of physico-chemical changes, which in turn determine the quality of the final product. Thus, in this work, modelling approaches for predicting moisture transfer during baking of chhana podo prepared by replacing semolina with tikhur (Curcuma angustifolia) starch were developed. Moisture loss, moisture ratio, specific volume, oven spring, volumetric expansion and other physico-chemical quality changes of the dough were determined during baking, and were used in the development of moisture transfer models. The effective moisture diffusivity of chhana podo increased from 8.10 × 10–9 to 37.05 × 10–9 m2/s as baking temperature increased from 110 to 150 °C. The artificial neural networks (ANN) model based on multilayer feed-forward (MLFF) algorithm and radial basis function (RBF) and adaptive neuro-fuzzy inference system (ANFIS) models based on Sugeno-type fuzzy inference system were developed to predict moisture ratio, and their predictive performance was compared with classical multiple linear regression and empirical models. Amongst the four prediction approaches, the MLFF neural network with baking temperature and time as input factors, and with 12 neurons in the hidden layer, produced the best performance in predicting moisture ratio with R2 as high as 0.9946 (99.46% accuracy) and RMSE of 0.0188 for the entire range of baking temperature studied. Sensitivity analysis showed that baking temperature was the most influential parameter (strength ratio was 0.89) deciding moisture transfer. MLFF neural network was observed to be a simple and efficient technique for predicting the complex moisture transfer phenomenon during baking, which could be used by the industry to optimize the baking conditions.

IDENTIFICATION OF LINEAR REGRESSIONS WITH ERRORS IN ALL VARIABLES

This paper analyzes the classical linear regression model with measurement errors in all the variables. First, we provide necessary and sufficient conditions for identification of the coefficients. We show that the coefficients are not identified if and only if an independent normally distributed linear combination of regressors can be transferred from the regressors to the errors. Second, we introduce a new estimator for the coefficients using a continuum of moments that are based on second derivatives of the log characteristic function of the observables. In Monte Carlo simulations, the estimator performs well and is robust to the amount of measurement error and number of mismeasured regressors. In an application to firm investment decisions, the estimates are similar to those produced by a generalized method of moments estimator based on third to fifth moments.

Bootstrapping regression models with locally stationary disturbances

A linear regression model with errors following a time-varying process is considered. In this class of models, the smoothness condition both in the trend function and in the correlation structure of the error term ensures that these models can be locally approximated by stationary processes, leading to a general class of linear regression models with locally stationary errors. We focus here on the bootstrap approximation to the distribution of the least-squares estimator for such class of regression models. We compare and discuss the results on both the classical and bootstrap confidence intervals through an intensive simulation study. The trend is also discussed through a real data analysis on time series of monthly inflation in US with locally stationary errors.

Examining the spatiotemporal variations and inequality of China's provincial CO2 emissions.

Tremendous energy consumption appears as rapid economic development, leading to large amount of CO2 emissions. Although plentiful studies have been made into the driving factors of CO2 emissions, the existing literatures that take the spatial differences and temporal changes into consideration are few. Therefore, this study first analyzes the variations of total CO2 emissions' spatial distribution from 2008 to 2017 and present the changes of driving factors, finding significant spatial autocorrelation in CO2 emissions at the province level, and that urbanization rate, per capita GDP and per capita CO2 emissions increased significantly, but energy consumption structure and trade openness decreased. We then compared the effects of different factors affecting CO2 emissions, using classic linear regression model, panel data model, and the geographically weighted regression (GWR) model, and the three models roughly agree on the effects of factors. The GWR model considering spatial heterogeneity provides more detailed results. Population, urbanization rate, per capita carbon emissions, energy consumption structure, and trade openness all have positive effects, while per capita GDP has a two-way impact on CO2 emissions. The influence of urbanization rate and energy consumption structure in the central and western regions increased even faster than in eastern regions, and the impacts of trade openness in lower and higher opening areas are more significant. The population and per capita CO2 emission have declining influences, among which the influence of population in coastal areas declined more slowly, while the rate of decline of per capita CO2 emission was positively correlated with the local total CO2 emissions. The Lorenz curve and the Gini coefficient reveal the inequality distribution of CO2 emissions in various regions, with the highest CO2 emissions growth in the medium-economic-level areas, where the key area of carbon mitigation is. Finally, per capita GDP reveals that China as a whole has the trend of inverted N-shape Kuznets curve, and the underdeveloped regions are in the rising stage between the two inflection points, while developed regions are at the end of the rising stage and about to reach the second inflection point.

Промените във валутния курс и експортният сектор: нови емпирични доказателства от Нигерия

The impact of exchange rate movements on the export sector in Nigeria is examined in this study through the use of time series data and the classical linear regression model (CLRM) estimation technique. The variables employed in this study are exchange rate, agric. output, manufacturing output, total export earnings, government capital expenditure, foreign direct investment and broad money supply (M2). From the result, it becomes apparent that exchange rate movements play a significant role in the performance of the export sector in Nigeria. More specifically, the findings show that exchange rate, manufacturing output, agric. output, government capital expenditure and foreign direct investment are positively related to export earnings while the broad money supply (M2) is negatively related. It is therefore recommended that the apex bank should keep a close watch on exchange rate developments in order to enhance exchange rate stability, which will in turn contribute to the development of the export sector in Nigeria.

A Machine Learning Approach to Forecast Economic Recessions—An Italian Case Study

In economic activity, recessions represent a period of failure in Gross Domestic Product (GDP) and usually are presented as episodic and non-linear. For this reason, they are difficult to predict and appear as one of the main problems in macroeconomics forecasts. A classic example turns out to be the great recession that occurred between 2008 and 2009 that was not predicted. In this paper, the goal is to give a different, although complementary, approach concerning the classical econometric techniques, and to show how Machine Learning (ML) techniques may improve short-term forecasting accuracy. As a case study, we use Italian data on GDP and a few related variables. In particular, we evaluate the goodness of fit of the forecasting proposed model in a case study of the Italian GDP. The algorithm is trained on Italian macroeconomic variables over the period 1995:Q1-2019:Q2. We also compare the results using the same dataset through Classic Linear Regression Model. As a result, both statistical and ML approaches are able to predict economic downturns but higher accuracy is obtained using Nonlinear Autoregressive with exogenous variables (NARX) model.

Quantum tomography by regularized linear regressions

In this paper, we study extended linear regression approaches for quantum state tomography based on regularization techniques. For unknown quantum states represented by density matrices, performing measurements under certain basis yields random outcomes, from which a classical linear regression model can be established. First of all, for complete or over-complete measurement bases, we show that the empirical data can be utilized for the construction of a weighted least squares estimate (LSE) for quantum tomography. Taking into consideration the trace-one condition, a constrained weighted LSE can be explicitly computed, being the optimal unbiased estimation among all linear estimators. Next, for general measurement bases, we show that ℓ2-regularization with proper regularization gain provides even a lower mean-square error under a cost in bias. The optimal regularization parameter is defined in terms of a risk characterization for any finite sample size and a resulting implementable estimator is proposed. Finally, a concise and unified formula is established for the regularization parameter with complete measurement basis under an equivalent regression model, which proves that the proposed implementable tuning estimator is asymptotically optimal as the number of copies grows to infinity. Additionally, several numerical examples are provided to validate the established results.

FINANCIAL DISTRESS DI BUMN INDONESIA DAN FAKTOR-FAKTOR YANG MEMPENGARUHI INVESTASI, LEVERAGE DAN CASH FLOW OPERATION TERHADAP FINANCIAL DISTRESS PADA PERUSAHAAN BUMN

This study aims to analyze the effect of managerial compensation, working capital, investment growth, and cash flow operations on financial distress in state-owned companies. This study uses several independent variables that empirically affect operating cash flow that has an impact on SOE financial distress. This study also uses financial indicators as control variables to limit the influence of factors or other variables outside the independent variable. The control variable used in this study is leverage. The researcher selected secondary data from 2014-2017 from a sample of 19 State-owned enterprises that received subsidies or equity participation from the government. The analytical method used is a statistical approach through the classical assumption test and linear regression model. The results of this study indicate that Working Capital and leverage have an influence on Financial Distress. Management Compensation, Investment Growth, and Cash Flow Operations have no influence on Financial Distress.

Impact of Leadership Style and Demographic Profile on Accounting Student Performance – The Case of Academic Administrators and Faculty Members in the Philippines

Manuscript type: Research paper Research aims: This study aims to investigate how leadership styles and the demographic profiles of academic administrators and faculty members can influence the university students’ performance in the Board Licensure Examination for Certified Public Accountants (BLECPA). Design/Methodology/Approach: The leadership styles of the academic administrators and faculty members are measured through the Bass model. Data are collected from 94 academic administrators and faculty members attached to 35 top performing colleges/universities in the 2017’s BLECPA. Research findings: The results suggest that the leadership styles and the demographic profiles of the academic administrators affect the students’ performance in the BLECPA. Theoretical contribution/Originality: This study extends on the existing literature by providing empirical evidence which highlight the relationship between academic leadership styles and universities’ performance in the BLECPA. This outcome focusses on universities in and outside of Manila. This study uses a more sophisticated estimation technique to address the limitations of the classical linear regression model (CLRM). Moreover, this study evaluates leadership by incorporating both the administrators and the faculty members’ leadership styles. In that regard, this study differs from existing studies which had focused on a single source of leadership. Practitioner/Policy implications: The findings of this study inform universities on how leadership style and the characteristics of academic administrators, and faculty members may influence universities’ performance. Policies can be formulated based on the findings of this paper, particularly those offering accountancy education for both the Philippines and the ASEAN region. Research limitation: This study does not take into account the differences of the organisational structure and the number of staff and students of the universities. Keywords: Bass Leadership Model, Demographic Profile, Student Performance, Higher Institution Education JEL Classification: M49

CREDIT RISK AND BANK PROFITABILITY OF COMMERCIAL BANKS IN GHANA

This study attempted to explore the connection between credit risk management and the profitability of the Ghana Stock Exchange (GSE) listed commercial banks. The study specifically sought to examine the relationship between credit risk and the profitability of the firms as measured by ROA. The study adopted these variables to measure credit risk (non-performing loan ratio, cost per loan asset, capital reserved 0.1ratio and asset growth ratio) and return on asset (ROA) as a profitability estimator. Following some diagnostic and specification studies to address the fundamental assumptions of the Classical Linear Regression Model (CLRM). The study uncovered that NPLR had a significantly negative effect on the firms’ profitability as measured by ROA [β=-0.1671, (p=0.1360)>0.05]. Also, the cost per loan asset (CPLA) had a positive influence on the firms’ profitability as measured by ROA [β= 0.0249, (p=0.8252)>0.05]. For the other variables of credit risk measurements, capital reserved ratio, and assets growth ratio. The capital reserve ratio had a significant positive association with ROA [β=0.2867, (p=0.0095) <0.05. Similarly, asset growth ratio had a statistically significant negative connection with firm’s profitability measured by ROA [β=-0.3835, (p=0.0004) <0.05. Based on the results, the study suggested that since credit risk had a negative association with the firm’s profitability, the companies should adopt efficient credit risk management methods to assist guide their profitability. This point is raised because, as demonstrated by the results of the study, an increase in credit risk led to a decrease in the profitability of the companies. KEYWORDS: Credit risk, Commercial banks, Loans, Profitability, Ghana Stock Exchange.

Monte Carlo power comparison of seven most commonly used heteroscedasticity tests

Assumption of the classical linear regression model states that the disturbances should have a constant (equal) variance. When this requirement is not met, the loss in efficiency in using ordinary least squares may be substantial and the biases in estimated standard errors may lead to invalid inferences. This problem is known as heteroscedasticity. There are many tests for heteroscedasticity, we want to know which test is more powerful. We use Monte Carlo simulation to compare the power of seven most commonly used tests for detecting heteroscedasticity, namely, Breusch–Pagan test, Glejser test, Goldfeld–Quandt test, Harvey–Godfrey test, Harrison–McCabe test, Park test, and White test for six common types of heteroscedasticity. Simulation results show that the Harrison–McCabe test has generally the most power in all of the six common types of heteroscedasticity and the White test has generally the least power in all of the six common types of heteroscedasticity.

Some remarks on a pair of seemingly unrelated regression models

Abstract Linear regression models are foundation of current statistical theory and have been a prominent object of study in statistical data analysis and inference. A special class of linear regression models is called the seemingly unrelated regression models (SURMs) which allow correlated observations between different regression equations. In this article, we present a general approach to SURMs under some general assumptions, including establishing closed-form expressions of the best linear unbiased predictors (BLUPs) and the best linear unbiased estimators (BLUEs) of all unknown parameters in the models, establishing necessary and sufficient conditions for a family of equalities of the predictors and estimators under the single models and the combined model to hold. Some fundamental and valuable properties of the BLUPs and BLUEs under the SURM are also presented.

Hydrodynamic object identification with artificial neural models

The lateral-line system that has evolved in many aquatic animals enables them to navigate murky fluid environments, locate and discriminate obstacles. Here, we present a data-driven model that uses artificial neural networks to process flow data originating from a stationary sensor array located away from an obstacle placed in a potential flow. The ability of neural networks to estimate complex underlying relationships between parameters, in the absence of any explicit mathematical description, is first assessed with two basic potential flow problems: single source/sink identification and doublet detection. Subsequently, we address the inverse problem of identifying an obstacle shape from distant measures of the pressure or velocity field. Using the analytical solution to the forward problem, very large training data sets are generated, allowing us to obtain the synaptic weights by means of a gradient-descent based optimization. The resulting neural network exhibits remarkable effectiveness in predicting unknown obstacle shapes, especially at relatively large distances for which classical linear regression models are completely ineffectual. These results have far-reaching implications for the design and development of artificial passive hydrodynamic sensing technology.

Does oil price volatility influence real sector growth? Empirical evidence from Pakistan

The study investigates the short-run and long-run relationship between oil price fluctuation and real sector growth in Pakistan. Four major sectors of the economy (Manufacturing, electricity, transport and communication, and livestock) were analyzed to find any relation. Similar studies can be found in the existing literate, however, the distinguish feature of present study is that it investigates each individual sector’s linkage to oil price changes. Annual time series data of selected sectors ranging from 1976 to 2017 is selected for the study. Classical normal linear regression models under auto regressive distributed lag (ARDL) were employed to study the relationship between economic sectors and oil price fluctuation. Empirical results indicate that changes in oil price adversely affect manufacturing, livestock and electricity sectors in short-run and long-run, while significant positive impact was found on transportation and communication. Consequently, the sectors prone to oil price changes require special attention of policy makers. An expansionary monetary policy can be a short-run solution to reduce the impact of increasing oil price, whereas the government can introduce a policy framework to counter this effect in long-run.

A generalized model for combining dependent SNP-level summary statistics and its extensions to statistics of other levels

Here I propose a fundamentally new flexible model to reveal the association between a trait and a set of genetic variants in a genomic region/gene. This model was developed for the situation when original individual-level phenotype and genotype data are not available, but the researcher possesses the results of statistical analyses conducted on these data (namely, SNP-level summary Z score statistics and SNP-by-SNP correlations). The new model was analytically derived from the classical multiple linear regression model applied for the region-based association analysis of individual-level phenotype and genotype data by using the linear compression of data, where the SNP-by-SNP correlations are among the explanatory variables, and the summary Z score statistics are categorized as the response variables. I analytically show that the regional association analysis methods developed within the framework of the classical multiple linear regression model with additive effects of genetic variants can be reformulated in terms of the new model without the loss of information. The results obtained from the regional association analysis utilizing the classical model and those derived using the proposed model are identical when SNP-by-SNP correlations and SNP-level statistics are estimated from the same genetic data.