Regression Assumptions Research Articles

Determinants of Capital Structure:An Empirical Study on Ethiopian Insurance Industry

The aim of this study was to examine the firm-specific, industry-specific and macro-economic determinants of Ethiopian insurance companies’ capital structure decision with the sample size of nine insurance companies, covering the period of 2005-2016.To achieve this objective quantitative research approach and quantitative data were used. The data was obtained from the annual audited financial statement of insurance companies and from NBE. In comply with this objective the study applied panel data model with fixed effect Ordinary Least Square regression. To test the hypotheses those were formulated through the review of available literature, the collected data was organized and checked for the fulfillment of OLS linear regression assumptions and then analyzed using fixed effect linear regression. The finding of the study shows that age of the firm, firm size and growth rate of real GDP have statistically significant and positive relationship with insurance company’s capital structure decision. On the other hand, variables like business risk, tangibility of asset and liquidity have a negative and statistically significant relationship with capital structure of insurance companies However, the relationship to exchange rate, profitability, growth opportunity and non-debt tax shield appear to be statistically insignificant. Depending up on the finding the study recommends that insurance companies in Ethiopia should not focus only on firm specific factors but also on macroeconomic environment so as to make an optimal capital structure decision and also the management of those insurance companies has to be focused on reducing factors that causes earning volatility to enhance earning sustainability. Finally the regulator (NBE) need to address problem of information asymmetry through setting up of rules that will ensure effective disclosures of the insurance companies audited financial statements. Keywords: Capital structure, firm specific factors, macro-economic factors, industry specific factors DOI: 10.7176/RJFA/11-9-02 Publication date: May 31 st 2020

Factors associated with postnatal care utilization among postpartum women in Ethiopia: a multi-level analysis of the 2016 Ethiopia demographic and health survey

BackgroundMost postpartum women and newborns do not utilize postnatal care due to less emphasis given especially in developing countries. Understanding individual and community-level factors associated with postnatal care will help to design appropriate strategies and policies for improving service utilization. Therefore, this study aimed to assess individual and community-level factors associated with postnatal care utilization in Ethiopia.MethodThis study used the Ethiopian Demographic and Health Survey (EDHS) data of 2016. A total of 4489 women who gave birth 2 years before the survey were included. Two-stage stratified cluster sampling technique was used. The analysis was done using Stata version 14.0 after checking for basic assumptions of multilevel logistic regression. Multilevel mixed-effects logistic regression was used to identify determinants of postnatal care utilization. An adjusted odds ratio with a 95% confidence interval was used to show the strength and direction of the association.ResultsHusband with secondary education [AOR = 0.17, 95% CI = (0.04, 0.68)], four or more antenatal care visit [AOR = 10.77, 95% CI = (2.65, 43.70)], middle wealth quintile [AOR = 3.10, 95% CI = (1.12, 8.58)] were individual level factors. Community level education [AOR = 2.53, 95% CI = (1.06, 6.06)] and community level of health service utilization [AOR = 2.32, 95% CI = (1.14, 4.73)] were the predictors at community level.ConclusionWealth index, number of antenatal care visits, husband education, community level of education and health service utilization were significantly associated with PNC service utilization. Provision of quality antenatal care, improvement of the educational status of women and husband involvement in PNC are important strategies to increase PNC service utilization.

A Quantile-Based g-Computation Approach to Addressing the Effects of Exposure Mixtures.

Background:Exposure mixtures frequently occur in data across many domains, particularly in the fields of environmental and nutritional epidemiology. Various strategies have arisen to answer questions about exposure mixtures, including methods such as weighted quantile sum (WQS) regression that estimate a joint effect of the mixture components.Objectives:We demonstrate a new approach to estimating the joint effects of a mixture: quantile g-computation. This approach combines the inferential simplicity of WQS regression with the flexibility of g-computation, a method of causal effect estimation. We use simulations to examine whether quantile g-computation and WQS regression can accurately and precisely estimate the effects of mixtures in a variety of common scenarios.Methods:We examine the bias, confidence interval (CI) coverage, and bias–variance tradeoff of quantile g-computation and WQS regression and how these quantities are impacted by the presence of noncausal exposures, exposure correlation, unmeasured confounding, and nonlinearity of exposure effects.Results:Quantile g-computation, unlike WQS regression, allows inference on mixture effects that is unbiased with appropriate CI coverage at sample sizes typically encountered in epidemiologic studies and when the assumptions of WQS regression are not met. Further, WQS regression can magnify bias from unmeasured confounding that might occur if important components of the mixture are omitted from the analysis.Discussion:Unlike inferential approaches that examine the effects of individual exposures while holding other exposures constant, methods like quantile g-computation that can estimate the effect of a mixture are essential for understanding the effects of potential public health actions that act on exposure sources. Our approach may serve to help bridge gaps between epidemiologic analysis and interventions such as regulations on industrial emissions or mining processes, dietary changes, or consumer behavioral changes that act on multiple exposures simultaneously. https://doi.org/10.1289/EHP5838

An Information-Based Approach for Mediation Analysis on High-Dimensional Metagenomic Data.

The human microbiome plays a critical role in the development of gut-related illnesses such as inflammatory bowel disease and clinical pouchitis. A mediation model can be used to describe the interaction between host gene expression, the gut microbiome, and clinical/health situation (e.g., diseased or not, inflammation level) and may provide insights into underlying disease mechanisms. Current mediation regression methodology cannot adequately model high-dimensional exposures and mediators or mixed data types. Additionally, regression based mediation models require some assumptions for the model parameters, and the relationships are usually assumed to be linear and additive. With the microbiome being the mediators, these assumptions are violated. We propose two novel nonparametric procedures utilizing information theory to detect significant mediation effects with high-dimensional exposures and mediators and varying data types while avoiding standard regression assumptions. Compared with available methods through comprehensive simulation studies, the proposed method shows higher power and lower error. The innovative method is applied to clinical pouchitis data as well and interesting results are obtained.

Development of multiple linear regression model for biochemical oxygen demand (BOD) removal efficiency of different sewage treatment technologies in Delhi, India

Among the various modeling techniques applied to dataset, multiple linear regression (MLR) analysis is the most efficient way to figure out the relationship between the response variable and the predictive variables. This study emphasizes on establishment of multiple linear regression models to analyze Biochemical Oxygen Demand (BOD) removal efficiency for technologies, namely Densadeck, Extended Aeration and Activated Sludge Process. Assumptions of multiple linear regression like linear relationship, multivariate normality, multicollinearity and Homoscedasticity were examined. The data that verify the assumptions were analyzed with multiple linear regression. Time series plots indicate drastic decline in BOD removal efficiency in the month of Feb and March during the years 2012 and 2013. This study was significant as it gives the technology having the best-fit regression equation based upon multiple correlation coefficient (R), coefficient of determination (R2), standard error, residual and F-ratio value. Societal benefits include enhancement in the performance of sewage treatment plants.

On spline-based approaches to spatial linear regression for geostatistical data

For spatial linear regression, the traditional approach to capture spatial dependence is to use a parametric linear mixed-effects model. Spline surfaces can be used as an alternative to capture spatial variability, giving rise to a semiparametric method that does not require the specification of a parametric covariance structure. The spline component in such a semiparametric method, however, impacts the estimation of the regression coefficients. In this paper, we investigate such an impact in spatial linear regression with spline-based spatial effects. Statistical properties of the regression coefficient estimators are established under the model assumptions of the traditional spatial linear regression. Further, we examine the empirical properties of the regression coefficient estimators under spatial confounding via a simulation study. A data example in precision agriculture research regarding soybean yield in relation to field conditions is presented for illustration.

A Simulation Study of Bootstrap Approaches to Estimate Confidence Intervals in DeFries-Fulker Regression Models (with Application to the Heritability of BMI Changes in the NLSY).

The univariate bootstrap is a relatively recently developed version of the bootstrap (Lee and Rodgers in Psychol Methods 3(1): 91, 1998). DeFries-Fulker (DF) analysis is a regression model used to estimate parameters in behavioral genetic models (DeFries and Fulker in Behav Genet 15(5): 467-473, 1985). It is appealing for its simplicity; however, it violates certain regression assumptions such as homogeneity of variance and independence of errors that make calculation of standard errors and confidence intervals problematic. Methods have been developed to account for these issues (Kohler and Rodgers in Behav Genet 31(2): 179-191, 2001), however the univariate bootstrap represents a unique means of doing so that is presaged by suggestions from previous DF research (e.g., Cherny et al. in Behav Genet 22(2): 153-162, 1992). In the present study we use simulations to examine the performance of the univariate bootstrap in the context of DF analysis. We compare a number of possible bootstrap schemes as well as more traditional confidence interval methods. We follow up with an empirical demonstration, applying results of the simulation to models estimated to investigate changes in body mass index in adults from the National Longitudinal Survey of Youth 1979 data.

Detection of suspicious interactions of spiking covariates in methylation data

BackgroundIn methylation analyses like epigenome-wide association studies, a high amount of biomarkers is tested for an association between the measured continuous outcome and different covariates. In the case of a continuous covariate like smoking pack years (SPY), a measure of lifetime exposure to tobacco toxins, a spike at zero can occur. Hence, all non-smokers are generating a peak at zero, while the smoking patients are distributed over the other SPY values. Additionally, the spike might also occur on the right side of the covariate distribution, if a category “heavy smoker” is designed. Here, we will focus on methylation data with a spike at the left or the right of the distribution of a continuous covariate. After the methylation data is generated, analysis is usually performed by preprocessing, quality control, and determination of differentially methylated sites, often performed in pipeline fashion. Hence, the data is processed in a string of methods, which are available in one software package. The pipelines can distinguish between categorical covariates, i.e. for group comparisons or continuous covariates, i.e. for linear regression. The differential methylation analysis is often done internally by a linear regression without checking its inherent assumptions. A spike in the continuous covariate is ignored and can cause biased results.ResultsWe have reanalysed five data sets, four freely available from ArrayExpress, including methylation data and smoking habits reported by smoking pack years. Therefore, we generated an algorithm to check for the occurrences of suspicious interactions between the values associated with the spike position and the non-spike positions of the covariate. Our algorithm helps to decide if a suspicious interaction can be found and further investigations should be carried out. This is mostly important, because the information on the differentially methylated sites will be used for post-hoc analyses like pathway analyses.ConclusionsWe help to check for the validation of the linear regression assumptions in a methylation analysis pipeline. These assumptions should also be considered for machine learning approaches. In addition, we are able to detect outliers in the continuous covariate. Therefore, more statistical robust results should be produced in methylation analysis using our algorithm as a preprocessing step.

Estimación del carbono almacenado en una plantación de Tectona grandis L. f. mediante ecuaciones alométricas

El bióxido de carbono (CO2) es el principal gas de efecto invernadero (GEI) antropogénico de la atmósfera. El objetivo de la investigación que se describe a continuación consistió en estimar el carbono almacenado a partir de variables dasométricas y ecuaciones alométricas en una plantación de Tectona grandis en Michoacán, México. Para ello se ajustó un modelo matemático mediante procedimiento Model y algoritmo Gauss-Newton. La evaluación del modelo matemático se realizó en función de la suma de cuadrado del error (SCE), la raíz del error medio cuadrático (REMC) y R2adj además de la significancia de sus parámetros. Se verificó el cumplimiento de los supuestos de normalidad, homogeneidad de varianzas e independencia de la frecuencia de residuos. Los valores de los parámetros del modelo ajustado fueron SCE=0.0399, REMC=0.0179 y R2adj= 0.82. La prueba de Shapiro-Wilk (0.96), la de White (12.99) y la de Durbin-Watson (2.01) no violan los supuestos de la regresión y son los mejores para la estimación de la variable dependiente. La plantación de T. grandis presenta una densidad de 1 666 árboles ha-1, 220.29 m3 ha-1 de madera, densidad básica 0.59 g cm3 y almacena 77.20 ton ha-1 de carbono a los 11 años de edad. La ecuación ajustada permite estimar de manera indirecta el carbono almacenado en los árboles, puede adecuarse para plantaciones bajo condiciones bioclimáticas similares, y es factible incorporarla a los sistemas de productividad para calcular el potencial de las plantaciones forestales comerciales como proveedoras de servicios ambientales a fin de mitigar las emisiones de CO2.

PENGARUH NPL DAN BOPO TERHADAP ROE PADA PT. BANK RAKYAT INDONESIA, Tbk PERIODE 2011-2018

This research was conducted to examine the effect of Net Performing Loan (NPL) and Operational Costs on Operating Income (BOPO) on Return On Equity (ROE) in PT. Rakyat Indonesia Bank, for the period 2011-2018 period. The sampling technique in this study is 32 quarterly data obtained from the bank’s published financial statements for the period 2011-2018. The analysis technique used is multiple regression analysis. Because the data used are secondary data, then to determine the accuracy of the model it is necessary to test some basic assumptions, linear regression analysis, hypothesis testing and coefficient of determination. Testing the basic assumptions used in this study include the normality test, linearity test and homogeneity test. While the linear regression analysis includes multiple linear regression and classical assumption tests (multicollinearity, autocorrelation and heterokedastisitas) and hypothesis testing which includes t test and f test. The dependent variable in this study is ROE while the independent variables are NPL and BOPO. The results of tis study, among others, indicate that the R square is 0,519 or 51,9 %, the NPL and BOPO variables have a partial effect on ROE as well as the NPL and BOPO variables also have a simultaneous effect against ROE. Based on the results of the above research, it is suggested to be able to add knowledge about NPL and BOPO to the level of ROE so that it can be input into research that is in line with this. Keywords: NPL, BOPO dan ROE

Comparison of Cox proportional hazards regression and generalized Cox regression models applied in dementia risk prediction.

IntroductionThe frequently used Cox regression applies two critical assumptions, which might not hold for all predictors. In this study, the results from a Cox regression model (CM) and a generalized Cox regression model (GCM) are compared.MethodsData are from the Survey of Health, Ageing and Retirement in Europe (SHARE), which includes approximately 140,000 individuals aged 50 or older followed over seven waves. CMs and GCMs are used to estimate dementia risk. The results are internally and externally validated.ResultsNone of the predictors included in the analyses fulfilled the assumptions of Cox regression. Both models predict dementia moderately well (10‐year risk: 0.737; 95% confidence interval [CI]: 0.699, 0.773; CM and 0.746; 95% CI: 0.710, 0.785; GCM).DiscussionThe GCM performs significantly better than the CM when comparing pseudo‐R2 and the log‐likelihood. GCMs enable researcher to test the assumptions used by Cox regression independently and relax these assumptions if necessary.

Uncertain Box-Cox Regression Analysis With Rescaled Least Squares Estimation

Under the uncertain statistical framework by Liu [19], there is still a lack of an effective fitting method for uncertain linear models with Box-Cox transformation of response variables. For example, for the transformation parameter Λ , the uncertain least squares estimation will produce a severely low estimation result. In this paper, we propose uncertain Box-Cox regression analysis by utilizing the uncertainty theory to model the imprecise data and applying a generalized Box-Cox transformation indexed by its parameter to validate classic regression assumptions. We use rescaled least squares to estimate unknown parameters and provide an estimate for noises followed by residual analysis for these uncertain Box-Cox regression models. We also give the forecast values and confidence intervals and use a numerical example to demonstrate our methodology. Our work sets a uniformed framework for Box-Cox transformation on the uncertain regression, and extends such regression from linear to nonlinear cases, taking the Johnson-Schumacher growth model as an example.

SMEs Intention towards Use and Adoption of Digital Financial Services


 
 
 
 The purpose of this study is to analyses the SMEs owners and managers intention towards use and adoption of digital financial services in South Punjab, Pakistsan. SMEs are considered key contributors to economic activity, as a key-source of employment, growth, and invention. SMEs perform significant role in the system of national financial regulation all over the world, Jobs creation, and contributing to modernization in the financial regulation are significant exertions to achieve ecological sustainability and more growth in access to finance. Access to finance in emerging countries is one of core issue in development of SME sector as well as obstacle in economic growth. Microfinance institutions are considered a good manifesto to enhance access to inclusive finance as well as stress-free access to finance and financial literacy for SMEs to support economic growth but in Pakistan, to obtain these finances not easy for SMEs sectors. SMEs are unfortunately still struggling due to lack of inclusive finance and financial literacy. Recently financial institution introduced digital financial services at micro level that provide access to financial services to each and every citizen in the country without any restriction. To accomplish the purpose of the research, the data was acquired from the SMEs owners and mangers with a sample of 232 chosen randomly of South Punjab, Pakistan. In this research study, merged two best theories; the theory of planned behavior and technology acceptance model was used to describe their behavior. Multiple statistical tests run to check the normality by using Shapiro-Wilk test, reliability and multicollinearity of the data to test the assumptions of regression and correlation. Finally, the results of this intended study revealed that there is a moderate significant but positive relationship between the SMEs owners and managers intention towards use and adoption of digital financial services. The Government of Pakistan should create finance related awareness program, training, technical institution and make a rules and regulation. Further this study suggests to researchers that focus on internal and as well as external factors of SMEs in Pakistan.
 
 
 

PENGARUH PROFITABILITAS, LEVERAGE DAN GROWTH TERHADAP KEBIJAKAN DEVIDEN PADA PERUSAHAAN MANUFAKTUR YANG TERDAFTAR DI BURSA EFEK INDONESIA

Penelitian ini bertujuan untuk menganalisis Pengaruh Profitabilitas yang diwakili rasio return on Investment, Leverage yang diwakili rasio Debt to Equity Ratio dan Growth terhadap Kebijakan Deviden (Deviden Payout Ratio) pada perusahaan Manufaktur yang terdaftar di Bursa Efek Indonesia. Sampel yang digunakan dalam penelitian ini berjumlah 5 perusahaan dan menggunakan data tahun 2013 hingga 2018. Analisis data menggunakan regresi berganda dengan dan uji asumsi klasik yang meliputi uji normalitas uji multikolonieritas dan uji autokorelasi
 Hasil analisis parsial dengan uji t dan uji F menyimpulkan bahwa variabel Profitabilitas (ROI) berpengaruh tidak signifikan terhadap Kebijakan Deviden Leverage (DER) berpengaruh tidak signifikan terhadap kebijakan Deviden Variabel Return on investment Debt to Equity ratio dan growth dapat menjelaskan 15,9% variasi tinggi rendahnya kebijakan deviden selebihnya 84,1! Ditentukan oleh variabel lain yang tidak tercakup dalam penelitian ini.
 Implikasi hasil penelitian ini bahwa Return variabel Return on investment debt to equity ratio dan Growth tidak dapat digunakan sebagai indikator dalam menentukan kebijakan deviden suatu perusahaan

The Influence of Innovation Characteristics to Farmers’ Decision in Accepting Integrated Crop-Livestock Technology in Karanganyar Region, Central Java

Farmer’s decision in accepting integrated crop-livestock farming technology was affected by a some factors, including innovation characteristic. This research aimed to figure out the influence of innovation characteristic (relative advantage, compatibility, complexity, triability and observability) to farmer’s decision in adopting the innovation. The research was held in Ngargoyoso Subdistrict, Karanganyar Region, Central Java Province. Basic method used in this research was descriptive quantitative using purposive sampling technique to determine research location. Samples were determined using purposive sampling method with total number was 52 respondents. Data were analyzed using several analysis : data normality, validity, reliability, Oneway ANOVA, multiple linear regression and classic assumption. Oneway ANOVA test showed that farmers with different farming experience had different response in deciding to adopt the technology. Multiple linear regression test gave an equation Y = 2.379 + 0.369X1 + 0.213X2 + 0.080X3 + 0.777X4+ (-0.320X5) + e. The determination coefficient value (R2) is 0.647. The conclusion of this research was characteristic of innovation significantly influenced the farmers’ decision in accepting the integrated crop-livestock technology simultaneously, but partially only variable relative advantage and triability which significantly influenced to farmers’ decision in accepting the integrated crop-livestock technology innovation.

Normality of residuals is a continuous variable, and does seem to influence the trustworthiness of confidence intervals : A response to, and appreciation of, Williams, Grajales, and Kurkiewicz (2013)

Osborne and Waters (2002) focused on checking some of the assumptions of multiple linear regression. In a critique of that paper, Williams, Grajales, and Kurkiewicz correctly clarify that regression models estimated using ordinary least squares require the assumption of normally distributed errors, but not the assumption of normally distributed response or predictor variables. They go on to discuss estimate bias and provide a helpful summary of the assumptions of multiple regression when using ordinary least squares. While we were not as precise as we could have been when discussing assumptions of normality, the critical issue of the 2002 paper remains – researchers often do not check on or report on the assumptions of their statistical methods. This response expands on the points made by Williams, advocates a thorough examination of data prior to reporting results, and provides an example of how incremental improvements in meeting the assumption of normality of residuals incrementally improves the accuracy of confidence intervals.

Assumptions of multiple regression: Correcting two misconceptions

Permission is granted to distribute this article for nonprofit, educational purposes if it is copied in its entirety and the journal is credited. PARE has the right to authorize third party reproduction of this article in print, electronic and database forms. Volume 18, Number 11, September 2013 ISSN 1531-7714

Four Assumptions of Multiple Regression That Researchers Should Always Test.

Most statistical tests rely upon certain assumptions about the variables used in the When these assumptions are not met the results may not be trustworthy, resulting in a Type I or Type II error, or overor under-estimation of significance or effect size(s). As Pedhazur (1997, p. 33) notes, Knowledge and understanding of the situations when violations of assumptions lead to serious biases, and when they are of little consequence, are essential to meaningful data analysis. However, as Osborne, Christensen, and Gunter (2001) observe, few articles report having tested assumptions of the statistical tests they rely on for drawing their conclusions. This creates a situation where we have a rich literature in education and social science, but we are forced to call into question the validity of many of these results, conclusions, and assertions, as we have no idea whether the assumptions of the statistical tests were met. Our goal for this paper is to present a discussion of the assumptions of multiple regression tailored toward the practicing researcher. Several assumptions of multiple regression are “robust” to violation (e.g., normal distribution of errors), and others are fulfilled in the proper design of a study (e.g., independence of observations). Therefore, we will focus on the assumptions of multiple regression that are not robust to violation, and that researchers can deal with if violated. Specifically, we will discuss the assumptions of linearity, reliability of measurement, homoscedasticity, and normality.

Monetary Policy and the Real Economy: A Study of the Manufacturing and Services Sectors in Nigeria

This study examined the effect of monetary policy on the real sector of the Nigerian economy. A model was specified for each of the manufacturing and services sectors to interrogate the effect of monetary policy on the real sector. Annual data were sourced from the World Development Indicators for 1981 to 2017. Preliminary tests of the time series properties suggested the autoregressive distributed lag (ARDL) regression as the most appropriate framework for the achievement of our objectives. Diagnostic tests of the distribution of regression errors confirmed the satisfaction of all necessary regression assumptions. The models were also found stable over the study period. Thus, the models adequately represented the problems formulated for investigation and good for valid inference. While all the four channels of monetary transmission considered were found significant for value-added expansion in manufacturing, the exchange rate channel was not a significant factor in value-added change in the services sector. Our findings suggested that domestic credit is the dominant channel for the transmission of monetary impulses to the real sector. The study concluded that monetary policy will benefit the real economy more with export expansion in both the manufacturing and services sectors.

A Machine Learning Approach to Predict Human Judgments in Compensatory and Noncompensatory Judgment Tasks

Traditionally, in judgment analysis, multiple linear regression based lens model, which assumes decision makers assess every cue, weigh, and combine them to make overall judgments, has been used to model and analyze human judgments. However, linear regression assumptions are limited in situations where logical rules for making decisions are not consistent with a weighting and summing formula. In this study, we sought to extend the body of knowledge in the judgment analysis research by adopting the rule-based lens model and using machine learning models to predict human judgments in compensatory and noncompensatory judgment tasks. Overall, the selected machine learning models outperformed the linear logistic regression (LgR) model in both compensatory and noncompensatory tasks. Our own results suggest that, at least for the present application, machine learning models may be better at predicting human judgments in compensatory and noncompensatory judgment tasks than linear multiple LgR models. We conclude that machine learning algorithms can yield useful models for training and decision support applications.