Coefficients In Linear Model Research Articles

The Impact of Fiscal Deficit on Inflation Rate - Empirical Evidence Case of Eurozone

The purpose of this working paper is to investigate if determinants have an impact on inflation rate in Eurozone Countries by using times series data for 17 countries from year 1997 to 2017, in yearly basis in total 375 observations. The study used quantitative research approach and secondary data and is analyzed by using linear regression model measures: Inflation rate as a dependent variable, and five independent variables such us: GDP to growth rate, Deficit to GDP rate, Public debt to GDP rate, Government bond interest rate and Unemployment rate. Linear regression model was applied to investigate the impact of GDP to growth rate, deficit to the GDP rate, Public debt to the GDP rate, Government bond interest rate, and Unemployment rate to the dependent variable Inflation rate. From the Linear Regression Model coefficients for inflation rate as a dependent variable shows that three of five variables have a significance one with negative significance and two positive significance. The empirical result shows that the three of five ratios that we mentioned above have a strong influence on the Inflation rate.

The Impact of Fiscal Deficit on Inflation Rate - Empirical Evidence Case of Eurozone

The purpose of this working paper is to investigate if determinants have an impact on inflation rate in Eurozone Countries by using times series data for 17 countries from year 1997 to 2017, in yearly basis in total 375 observations. The study used quantitative research approach and secondary data and is analyzed by using linear regression model measures: Inflation rate as a dependent variable, and five independent variables such us: GDP to growth rate, Deficit to GDP rate, Public debt to GDP rate, Government bond interest rate and Unemployment rate. Linear regression model was applied to investigate the impact of GDP to growth rate, deficit to the GDP rate, Public debt to the GDP rate, Government bond interest rate, and Unemployment rate to the dependent variable Inflation rate. From the Linear Regression Model coefficients for inflation rate as a dependent variable shows that three of five variables have a significance one with negative significance and two positive significance. The empirical result shows that the three of five ratios that we mentioned above have a strong influence on the Inflation rate.

Exact adaptive confidence intervals for linear regression coefficients

We propose an adaptive confidence interval procedure (CIP) for the coefficients in the normal linear regression model. This procedure has a frequentist coverage rate that is constant as a function of the model parameters, yet provides smaller intervals than the usual interval procedure, on average across regression coefficients. The proposed procedure is obtained by defining a class of CIPs that all have exact $1-\alpha $ frequentist coverage, and then selecting from this class the procedure that minimizes a prior expected interval width. We describe an adaptive approach for estimating the prior distribution from the data, so that the potential risk of a poorly specified prior is reduced. The resulting adaptive confidence intervals maintain exact non-asymptotic $1-\alpha $ coverage if two conditions are met - that the design matrix is full rank (which will be known) and that the errors are normally distributed (which can be checked empirically). No assumptions on the unknown parameters are necessary to maintain exact coverage. Additionally, in a “$p$ growing with $n$” asymptotic scenario, this adaptive FAB procedure is asymptotically Bayes-optimal among $1-\alpha $ frequentist CIPs.

Калибровка коэффициентов линейной модели интегрального магнитометра за счет использования измерений трехосного гироскопа

Калибровка коэффициентов линейной модели интегрального магнитометра за счет использования измерений трехосного гироскопа

Калибровка коэффициентов линейной модели интегрального магнитометра за счет использования измерений трехосного гироскопа

Калибровка коэффициентов линейной модели интегрального магнитометра за счет использования измерений трехосного гироскопа

The effect of caffeine loading on cerebral autoregulation in preterm infants.

To evaluate cerebral autoregulation changes in preterm infants receiving a loading dose of caffeine base. In a cohort of 30 preterm infants, we extracted measures of cerebral autoregulation using time and frequency domain techniques to determine the correlation between mean arterial pressure (MAP) and tissue oxygenation index (TOI) signals. These measures included the cerebral oximetry index (COx), cross-correlation and coherence measures, and were extracted prior to caffeine loading and in the 2hours following administration of 10mg/kg caffeine base. We observed acute reductions in time domain correlation measures, including the cerebral oximetry index (linear mixed model coefficient -0.093, standard error 0.04; p=0.028) and the detrended cross-correlation coefficient (ρ5 coefficient -0.13, standard error 0.055; p=0.025). These reductions suggested an acute improvement in cerebral autoregulation. Features from detrended cross-correlation analysis also showed greater discriminative value than other methods in identifying changes prior to and following caffeine administration. We observed a reduced correlation between MAP and TOI from near-infrared spectroscopy following caffeine administration. These findings suggest an acute enhanced capacity for cerebral autoregulation following a loading dose of caffeine in preterm infants, contributing to our understanding of the physiological impact of caffeine therapy.

Short-term exposure to air pollution: Associations with lung function and inflammatory markers in non-smoking, healthy adults

IntroductionAir pollution impacts health by increasing mortality and the incidence of acute events in unhealthy individuals. In contrast, the acute effects of pollution in healthy individuals are less obvious. The present study was designed to evaluate the associations between short-term exposure to air pollution on one hand and lung function, and inflammatory markers on the other in middle-aged, non-smoking adults with no respiratory disease, in two urban areas in northern France. MethodsA sample of 1506 non-smoking adults (aged from 40 to 65) with no respiratory disease was selected from the participants in the 2011–2013 cross-sectional Enquête Littoral Souffle Air Biologie Environnement (ELISABET) survey in two urban areas in the northern France. We evaluated the associations between (i) mean levels of particulate matter with aerodynamic diameter < 10 μm (PM10), nitrogen dioxide (NO2) and ozone (O3) exposure on the day and the day before the study examination for each participant, and (ii) spirometry data and levels of inflammatory markers. Coefficients of multiple linear regression models were expressed (except for the forced expiratory volume in 1 s (FEV1)/forced vital capacity (FVC) ratio) as the percentage change [95% confidence interval] per 10 μg increment in each pollutant. ResultsLevels of PM10, NO2 and O3 exposure were below or only close to the World Health Organization's recommended limits in our two study areas. An increment in NO2 levels was significantly associated with a lower FEV1/FVC ratio (−0.38 [−0.64; −0.12]), a lower forced expiratory flow between 25% and 75% of FVC (FEF25–75%) (−1.70 [−3.15; −0.23]), and a lower forced expiratory flow measured at 75% of FVC (FEF75%) (−3.07 [−4.92; −1.18]). An increment in PM10 levels was associated with lower FEF75% (−1.41 [−2.79; −0.01]) and a non-significant elevation in serum levels of high-sensitivity C-reactive protein (+3.48 [−0.25; 7.36], p = 0.07). Lastly, an increment in O3 levels was associated with a significantly higher blood eosinophil count (+2.41 [0.10; 4.77]) and a non-significant elevation in fractional exhaled nitric oxide (+2.93 [−0.16; 6.13], p = 0.06). ConclusionA short-term exposure to air pollution was associated with a subclinical decrement in distal lung function and increment in inflammatory markers in healthy inhabitants of two urban areas in France. If these exploratory results are confirmed, this could suggest that even moderate levels of air pollution could have an impact on respiratory health on the general population, and not solely on susceptible individuals.

Feasibility and reliability of electrical, mechanical and thermal nociceptive testing and assessment of diffuse noxious inhibitory control in dogs.

PurposeQuantitative sensory testing has been used to assess the somatosensory system. This study aimed to evaluate the feasibility and reliability of electrical (ENT), mechanical (MNT) and thermal (TNT) nociceptive testing and the effect of a conditioning stimulus on MNT.Patients and methodsSixteen healthy client-owned dogs were included in this study. Stimulation was applied bilaterally to the dorsal and plantar aspect of the metacarpus and metatarsus respectively, using transcutaneous electrical stimulator, algometry and a cold nociceptive device in a randomized order until a behavior response was observed or a cut-off reached. Tests were performed twice (60 seconds apart) by two observers. Retesting was performed 5 hours later. The diffuse noxious inhibitory control was tested by comparing MNT pre- and post-conditioning stimuli. Sham-testing was performed for ENT and TNT. Statistical analysis included linear model and intra-class correlation coefficient (P<0.05).ResultsFeasibility was 99% (ENT), 93.5% (MNT) and 93.6% (TNT). Data for TNT were not analyzed due to inconsistent results. Mean ± SD were 48±22.6 mA (ENT) and 11.9±3.5 N (MNT). MNT was higher for thoracic than for pelvic limbs (P=0.002). Conditioning stimulus increased MNT (P=0.049). Inter-observer reliability was 91.4% (ENT) and 60.9% (MNT). False-positive responses were 15% (ENT) and 35.7% (TNT).ConclusionENT was feasible, repeatable and superior to MNT and TNT. The assessment of the diffuse noxious inhibitory control with a conditioning stimulus showed promising results in dogs. These tools could be used in naturally-occurring disease to provide insight on their underlying mechanisms and therapeutics.

Feature screening for multi-response varying coefficient models with ultrahigh dimensional predictors

This article investigates the feature screening procedure for multivariate response varying coefficient linear models. A new conditional canonical correlation coefficient is proposed to characterize the correlation between each predictor and the multivariate response. It is shown that the proposed method is more powerful to distinguish the informative features from the noises than the existing competitors, especially for the case of high-dimensional response. The ranking consistency and the sure screening property are established for the new method. Meanwhile, an iterative version of the feature screening procedure is also introduced. Both the numerical simulations and real data analysis are conducted to illustrate the effectiveness of our method.

Test for high-dimensional regression coefficients using refitted cross-validation variance estimation

Testing a hypothesis for high-dimensional regression coefficients is of fundamental importance in the statistical theory and applications. In this paper, we develop a new test for the overall significance of coefficients in high-dimensional linear regression models based on an estimated U-statistics of order two. With the aid of the martingale central limit theorem, we prove that the asymptotic distributions of the proposed test are normal under two different distribution assumptions. Refitted cross-validation (RCV) variance estimation is utilized to avoid the overestimation of the variance and enhance the empirical power. We examine the finite-sample performances of the proposed test via Monte Carlo simulations, which show that the new test based on the RCV estimator achieves higher powers, especially for the sparse cases. We also demonstrate an application by an empirical analysis of a microarray data set on Yorkshire gilts.

RRPP: An r package for fitting linear models to high‐dimensional data using residual randomization

Abstract Residual randomization in permutation procedures (RRPP) is an appropriate means of generating empirical sampling distributions for ANOVA statistics and linear model coefficients, using ordinary or generalized least‐squares estimation. This is an especially useful approach for high‐dimensional (multivariate) data. Here, we present an r package that provides a comprehensive suite of tools for applying RRPP to linear models. Important available features include choices for OLS or GLS coefficient estimation, data or dissimilarity matrix analysis capability, choice among types I, II, or III sums of squares and cross‐products, various effect size estimation methods, and an ability to perform mixed‐model ANOVA. The lm.rrpp function is similar to the lm function in many regards, but provides coefficient and ANOVA statistics estimates over many random permutations. The S3 generic functions commonly used with lm also work with lm.rrpp. Additionally, a pairwise function provides statistical tests for comparisons of least‐squares means or slopes, among designated groups. Users have many options for varying random permutations. Compared to similar available packages and functions, RRPP is extremely fast and yields comprehensive results for downstream analyses and graphics, following model fits with lm.rrpp. The RRPP package facilitates analysis of both univariate and multivariate response data, even when the number of variables exceeds the number of observations.

Fatigue independently predicts different work disability dimensions in etanercept-treated rheumatoid arthritis and ankylosing spondylitis patients

BackgroundWork disability remains a significant problem in ankylosing spondylitis (AS) and rheumatoid arthritis (RA), despite biological therapy. This study aimed to test the hypothesis that the prevalent symptom of fatigue longitudinally predicts work disability among RA and AS patients commencing etanercept.MethodsTwo observational studies, comprising RA and AS etanercept commencers, respectively, were analysed. Both provided data on work disability over 1 year and a comprehensive set of putative predictors, including fatigue. A series of repeated measures models were conducted, including baseline variables, visit (6/12 months), and the interaction between visit and each of the explanatory variables.ResultsA total of 1003 AS and 1747 RA patients were assessed. For AS, fatigue was significantly associated with presenteeism (linear mixed model coefficient 3.75, 95% confidence interval (CI) 2.14 to 5.36) and activity impairment (2.62, 1.26 to 3.98), but not with work productivity loss (1.81, −0.40 to 4.02) or absenteeism (generalised linear mixed model odds ratio (OR) 1.18, 95% CI 0.92 to 1.51). In RA, fatigue was associated with presenteeism (coefficient 3.44, 95% CI 2.17 to 4.70), activity impairment (1.52, 0.79 to 2.26), work productivity loss (4.16, 2.47 to 5.85), and absenteeism (OR 1.23, 95% CI 1.02 to 1.49). The lack of significant interactions between fatigue and visit supported a consistent effect of baseline fatigue over time.ConclusionsAmong patients beginning etanercept therapy, fatigue has a significant and independent effect on absenteeism, presenteeism, productivity loss, and activity impairment for RA patients and a significant but dimension-selective effect on work disability among AS patients.Trial registrationClinicalTrials.gov, NCT00544557. Registered on 16 October 2007. ClinicalTrials.gov, NCT00488475. Registered on 20 June 2006.

Theoretical personalized optimum chest compression point can be determined using posteroanterior chest radiography

AimCardiopulmonary resuscitation guidelines suggest the lower sternal half be compressed. However, stroke volume has been assumed to be maximized by compressing the ‘point’ (P_max.LV) beneath which the left ventricle (LV) is at its maximum diameter. Identifying ‘personalized’ P_max.LV on computed tomography (CT), we derived and validated rules to estimate P_max.LV using posteroanterior chest radiography (chest_PA). MethodsA retrospective, cross-sectional study was performed with non-cardiac arrest (CA) adults who underwent chest_PA and CT within 1h (derivation:validation = 3:2). On chest_PA, we defined CD (cardiac diameter), RB (distance from right cardiac border to midline) and CH (cardiac height, from carina to uppermost point of left hemi-diaphragm). Setting P_zero (0, 0) at the midpoint of xiphisternal joint and designating leftward and upward directions as positive on x and y axes, we located P_max.LV (x_max.LV, y_max.LV). Mathematically, followings were inferable: x_max.LV = α0*CD-RB; y_max.LV = ß0*CH + γ0. (α0: mean of (x_max.LV + RB)/CD; ß0, γ0: representative coefficient and constant of linear regression model, respectively). We investigated their feasibility by applying them to in-hospital (IHCA) and out-of-hospital CA (OHCA) adults. RESULTSAmong 266 (57.6 ± 16.4 years, 120 females), followings were derived: x_max.LV = 0.664*CD-RB; y_max.LV = 40 − 0.356*CH. Estimated P_max.LV was closer to the reference than other candidates and thus validated: 15 ± 9 vs 17 ± 10 (averaged P_max.LV, p = 0.025); 76 ± 13, 54 ± 11 and 63 ± 13 mm (3 equidistant points as per guidelines, all p < 0.001). Among IHCA and OHCA patients, 70.7% (106/150) and 38.0% (57/150) had previous chest_PA with measurable parameters to estimate P_max.LV. CONCLUSIONPersonalized P_max.LV, which is potentially superior to the lower sternal half and feasible in CA, is estimable with chest_PA.

Relation of Disease with Standardized Phase Angle among Older Patients.

A low phase angle (PA) has been associated with negative outcome in specific diseases. However, many patients suffer from several co-morbidities. This study aims at identifying the impact of the type and the severity of diseases on PA in a retrospective cohort study of older people. We included all people ≥65 years who underwent a PA measurement (Nutriguard®) between 1990 and 2011 at the Geneva University Hospitals. PA was standardized for gender, age and body mass index according to German reference values. Co-morbidities were reported in form of the Cumulative Illness Rating Scale which considers 14 different organs/systems (disease categories), each rated from 0 (healthy) to 4 (severe illness) (severity grades). The association between the diseases categories and standardized PA was evaluated by a multivariate linear regression. For each significant disease category, we performed univariate regression models. The adjusted R2 was used to identify the best predictors of standardized PA. We considered that the severity grade affected standardized PA if there was a progressive decrease in the regression coefficients. We included 1181 people (37% women). The multivariate regression model showed that the disease categories explain 17% of the variance of standardized PA. Many disease categories affect standardized PA and the ones best associated with standardized PA were the hematopoietic and vascular (R2 7.4%), the musculo-skeletal (R2 5.5%) and the respiratory (R2 4.0%) diseases. The regression coefficients in the univariate linear regression model decreased progressively with higher severity grades in respiratory (-0.15, -0.27, -0.55, -0.67) and musculo-skeletal diseases (-0.09, -0.46, -0.85, -0.86). Many different diseases affect standardized PA. The higher the severity grade in musculo-skeletal and respiratory diseases, the lower is the standardized PA.

A Note on the UEK Method

The paper concerns certain pitfalls of using the Moore-Penrose pseudoinverse for estimating regression coefficients in linear regression models when the matrix of explanatory variables has not full column rank. The aim of the paper is to show that in this case estimator of parameters based on the Moore-Penrose pseudoinverse is biased, and the bias leads to biased forecasts.

Empirical Likelihood Ratio Tests for Coefficients in High Dimensional Heteroscedastic Linear Models

Empirical Likelihood Ratio Tests for Coefficients in High Dimensional Heteroscedastic Linear Models

Analysis of Algorithms for Stable Estimation of Coefficients of Multiple Linear Regression Models

Computational experiments on model data were performed in order to study the effectiveness of the algorithms for realization of the least absolute deviations (LAD) method and the generalized method of the least absolute deviations (GLAD) when estimating the parameters of multiple linear regression models based on descent through the nodal straight lines. In addition, a comparative analysis of the algorithms of descent through nodal straight lines for LAD and GLAD with known exact and approximate methods to solve tasks (2) and (3) was carried out.

How to Reveal Magnitude of Gene Signals: Hierarchical Hypergeometric Complementary Cumulative Distribution Function

This article introduces a new method for genome-wide association study (GWAS), hierarchical hypergeometric complementary cumulative distribution function (HH-CCDF). Existing GWAS methods, e.g. the linear model and hierarchical association coefficient algorithm, calculate the association between a marker variable and a phenotypic variable. The ideal GWAS practice is to calculate the association between a marker variable and a gene-signal variable. If the gene-signal variable and phenotypic variable are imperfectly proportional, the existing methods do not properly reveal the magnitude of the association between the gene-signal variable and marker variable. The HH-CCDF mitigates the impact of the imperfect proportionality between the phenotypic variable and gene-signal variable and thus better reveals the magnitude of gene signals. The HH-CCDF will provide new insights into GWAS approaches from the viewpoint of revealing the magnitude of gene signals.

Posterior Means and Precisions of the Coefficients in Linear Models with Highly Collinear Regressors

When there is exact collinearity between regressors, their individual coe¢ cients are not identified, but given an informative prior their Bayesian posterior means are well defined. The case of high but not exact collinearity is more complicated but similar results follow. Just as exact collinearity causes non-identification of the parameters, high collinearity can be viewed as weak identification of the parameters, which we represent, in line with the weak instrument literature, by the correlation matrix being of full rank for a finite sample size T, but converging to a rank deficient matrix as T goes to infinity. This paper examines the asymptotic behaviour of the posterior mean and precision of the parameters of a linear regression model for both the cases of exactly and highly collinear regressors. We show that in both cases the posterior mean remains sensitive to the choice of prior means even if the sample size is su¢ ciently large, and that the precision rises at a slower rate than the sample size. In the highly collinear case, the posterior means converge to normally distributed random variables whose mean and variance depend on the priors for coe¢ cients and precision. The distribution degenerates to fixed points for either exact collinearity or strong identification. The analysis also suggests a diagnostic statistic for the highly collinear case, which is illustrated with an empirical example.

Enhancing Classification Performance of Functional Near-Infrared Spectroscopy- Brain-Computer Interface Using Adaptive Estimation of General Linear Model Coefficients.

In this paper, a novel methodology for enhanced classification of functional near-infrared spectroscopy (fNIRS) signals utilizable in a two-class [motor imagery (MI) and rest; mental rotation (MR) and rest] brain–computer interface (BCI) is presented. First, fNIRS signals corresponding to MI and MR are acquired from the motor and prefrontal cortex, respectively, afterward, filtered to remove physiological noises. Then, the signals are modeled using the general linear model, the coefficients of which are adaptively estimated using the least squares technique. Subsequently, multiple feature combinations of estimated coefficients were used for classification. The best classification accuracies achieved for five subjects, for MI versus rest are 79.5, 83.7, 82.6, 81.4, and 84.1% whereas those for MR versus rest are 85.5, 85.2, 87.8, 83.7, and 84.8%, respectively, using support vector machine. These results are compared with the best classification accuracies obtained using the conventional hemodynamic response. By means of the proposed methodology, the average classification accuracy obtained was significantly higher (p < 0.05). These results serve to demonstrate the feasibility of developing a high-classification-performance fNIRS-BCI.