Variance Of Coefficients Research Articles

IT Parkinson’s Disease Diagnostics Based on the Freezing of Gait Analysis Using Long Short Term Memory Neural Network

An analysis of methods for processing data from gait deceleration sensors for detecting Parkinson’s disease and a description of the development of a Parkinson’s recognition system based on neural networks with long short term memory (LSTM) are performed. The data used was a publicly available dataset of gait deceleration scores of patients with Parkinson’s disease, obtained using three wearable sensors to collect data from different parts of the body. The research was carried out using machine learning using an LSTM neural network. First, the DAPHNet datasets were segmented using a fixed sliding window algorithm. The wavelet algorithm was then used to extract features from the data set: wavelet entropy and energy, wavelet waveform length, variance and standard deviation of wavelet coefficient. Next, a data enhancement algorithm was used to balance the number of samples in the data sets. To train the model, an LSTM neural network was built with a six-layer network structure: input layer, LSTM layer, reLU layer, fully connected layer, Softmax layer and output layer. After training the model for 1000 iterations, the LSTM neural network algorithm achieved 96.3 % accuracy, 96.05 % precision, 96.5 % sensitivity, and 96.24 % average F1 score for recognizing Parkinson’s disease based on test datasets. Similar studies conducted by other scientific organizations achieved a maximum accuracy of 91.9 % for the same data sets.

Myocardial Injury in Peritoneal Dialysis Patients Assessed by Multiparametric MRI: Relationship With Left Ventricular Phenotypes.

Myocardial injury is common in end-stage renal disease (ESRD) patients, but the presence and severity of myocardial injury in different left ventricular (LV) phenotypes were still not fully explored. To evaluate myocardial tissue characteristics and deformation in ESRD patients on peritoneal dialysis separated into normal geometry, concentric remodeling, concentric left ventricular hypertrophy (LVH) and eccentric LVH patterns by multiparametric cardiac MRI. Prospective. A total of 142 subjects, including 102 on peritoneal dialysis (69 males) and 40 healthy controls (27 males). At 3.0 T, cine sequence, T1 mapping and T2 mapping. LV mass index and LV remodeling index were used to create four subgroups with normal geometry, concentric remodeling, concentric LVH, and eccentric LVH. LV function, strain and strain rate, myocardial native T1 and T2 were measured. Descriptive statistics, analysis of variance and analysis of covariance, Pearson/Spearman correlation, stepwise regression, and intraclass correlation coefficient. P-value <0.05 was considered statistically significant. Even in normal geometry, LV strain parameters still diminished compared with the controls (global radial strain: 30.5 ± 7.7% vs. 37.1 ± 7.9%; global circumferential strain: -18.2 ± 2.6% vs. -20.6 ± 2.2%; global longitudinal strain: -13.3 ± 2.5% vs. -16.0 ± 2.8%). Eccentric LVH had significantly lower global circumferential systolic strain rate than concentric LVH (-0.82 ± 0.21%/-second vs. -0.96 ± 0.20%/-second). Compared with the controls, the four subgroups all revealed elevated native T1 and T2, especially in eccentric LVH, while concentric remodeling had the least changes including native T1, T2, and LV ejection fraction. After adjusting for covariates, there was no statistically significant difference in T2 between the four subgroups (P = 0.359). Eccentric LVH is associated with the most pronounced evidence of myocardial tissue characteristics and function impairment, while as a benign remodeling, the concentric remodeling subgroup had the least increase in native T1. This study further confirms that native T1 and strain indicators can reflect the severity of myocardial injury in ESRD, providing better histological and functional basis for future grouping treatments. 1 TECHNICAL EFFICACY: Stage 3.

Development of sensitivity calculation capability of Legendre moments of scattering angular distributions in NECP-MCX

The capability of sensitivity coefficients calculation of keff and reaction rate ratios to Legendre moment of scattering angular distributions based on a fully continuous method has been developed in the Monte Caro code NECP-MCX. The sensitivity calculation was based on Iterated Fission Probability (IFP) and Contributon-Linked eigenvalue sensitivity/Uncertainty estimation via Track-length importance Characterization (CLUTCH) method for k-eigenvalue sensitivity analysis and Generalized Adjoint Responses in Monte Carlo (GEAR-MC) method for generalized sensitivity analysis. The Jezebel and Flattop problems are analyzed and the sensitivity results calculated by NECP-MCX are compared with those by Serpent and ERANOS to demonstrate the accuracy of NECPMCX. In addition, the CLUTCH-FC (CLUTCH coupled with forced collisions) method is implemented to reduce the variance of sensitivity coefficients of Legendre moment of scattering angular distributions with relatively small scattering cross sections. The numerical results indicate that 1) the sensitivity coefficients calculated by NECP-MCX agree well with those by Serpent and ERANOS, and 2) the CLUTCH-FC method is efficient in reducing the variance of sensitivity coefficients of Legendre moment of scattering angular distributions with relatively small scattering cross sections. The Figure of Merit (FOM) values of sensitivity coefficients calculated by the CLUTCH-FC method have increased by 1.9~306.0 times for Jezebel and Flattop problems compared to those calculated by the CLUTCH method.

Visually assessing work performance using a smartwatch via day-to-day fluctuations in heart rate variability.

To optimize workplace health promotion, a simple method for quantifying allostatic load response is needed. This study examines the feasibility of optimizing objective anxiety and presenteeism monitoring using daily smartwatch-measured ultra-short heart rate variability (HRV). Office workers without diagnosed disease prospectively performed 30 s HRV self-measurement each morning for two months and responded to the State-Trait Anxiety Inventory (STAI) and Work Limitation Questionnaire (WLQ). Logistic regression analysis examined daily HRV parameters in the high-trait anxiety group (HTA, STAI ≥ 40) using mean and variance HRV, age, self-reported gender, and body mass index (BMI). The ideal cutoff value enabled comparison of WLQ using the Mann-Whitney U test. Heart rate variability data were collected for 279 participants (male ratio, 83.9%; age, 42 ± 10 years) who completed questionnaires and monitored HRV for 30+ days. Compared to the low-trait anxiety group, HTA exhibited higher variance of the log-transformed coefficient of component variance of high-frequency component (LnccvHF) and low-frequency per HF (Lnccv L/H), in addition to differences in the means of these HRV parameters. In addition to BMI (odds ratio [OR] = 0.92, p = 0.02) and mean LnccvL/H (OR = 10.75, p < 0.01), the variance of Lnccv L/H was an independent predictor of HTA (OR = 2.39E + 8, p = 0.011). The daily Lnccv L/H dispersion group had a lower WLQ productivity loss score (p = 0.02, r = 0.17). By focusing on HRV dispersion status, this simple and instantly applicable daily HRV monitoring system enables optimized quantitative monitoring of anxiety and productivity.

Dimension reduction for uncertainty propagation and global sensitivity analyses of a cesium adsorption model

This paper presents an efficient method to perform uncertainty and sensitivity analyses in a cesium adsorption model upstream chained with a pore water composition model. As the number of uncertain input parameters is about twenty for each of the two models, a dimension reduction technique is implemented to build a polynomial approximation of the cesium distribution coefficient in a reduced subspace. Two approaches are tested depending on the water composition and adsorption models are treated as a single block or two separate blocks. In view of assessing the robustness of the approaches, three initial cesium concentrations are considered to explore different regimes of the adsorption model. The interpretation of the linear transformations projecting the original inputs to the reduced coordinates is broadly consistent with the geochemical features of the model. Validation results show that the relative error levels of the surrogate models are around a few percent for both approaches with only one thousand realizations of the chained model. Global sensitivity analysis highlights that the variance of the cesium distribution coefficient is overwhelmingly governed by the adsorption model. Still, this conclusion is nuanced when considering the whole cumulative distribution function for which the interaction effects between the two models account for a fifth.

Krylov complexity and chaos in quantum mechanics

Recently, Krylov complexity was proposed as a measure of complexity and chaoticity of quantum systems. We consider the stadium billiard as a typical example of the quantum mechanical system obtained by quantizing a classically chaotic system, and numerically evaluate Krylov complexity for operators and states. Despite no exponential growth of the Krylov complexity, we find a clear correlation between variances of Lanczos coefficients and classical Lyapunov exponents, and also a correlation with the statistical distribution of adjacent spacings of the quantum energy levels. This shows that the variances of Lanczos coefficients can be a measure of quantum chaos. The universality of the result is supported by our similar analysis of Sinai billiards. Our work provides a firm bridge between Krylov complexity and classical/quantum chaos.

Disentangling the dynamics of energy allocation to develop a proxy for robustness of fattening pigs

BackgroundThere is a growing need to improve robustness of fattening pigs, but this trait is difficult to phenotype. Our first objective was to develop a proxy for robustness of fattening pigs by modelling the longitudinal energy allocation coefficient to growth, with the resulting environmental variance of this allocation coefficient considered as a proxy for robustness. The second objective was to estimate its genetic parameters and correlations with traits under selection and with phenotypes that are routinely collected. In total, 5848 pigs from a Pietrain NN paternal line were tested at the AXIOM boar testing station (Azay-sur-Indre, France) from 2015 to 2022. This farm is equipped with an automatic feeding system that records individual weight and feed intake at each visit. We used a dynamic linear regression model to characterize the evolution of the allocation coefficient between the available cumulative net energy, which was estimated from feed intake, and cumulative weight gain during the fattening period. Longitudinal energy allocation coefficients were analysed using a two-step approach to estimate both the genetic variance of the coefficients and the genetic variance in their residual variance, which will be referred to as the log-transformed squared residual (LSR).ResultsThe LSR trait, which could be interpreted as an indicator of the response of the animal to perturbations/stress, showed a low heritability (0.05 ± 0.01), a high favourable genetic correlation with average daily growth (− 0.71 ± 0.06), and unfavourable genetic correlations with feed conversion ratio (− 0.76 ± 0.06) and residual feed intake (− 0.83 ± 0.06). Segmentation of the population in four classes using estimated breeding values for LSR showed that animals with the lowest estimated breeding values were those with the worst values for phenotypic proxies of robustness, which were assessed using records routinely collected on farm.ConclusionsResults of this study show that selection for robustness, based on estimated breeding values for environmental variance of the allocation coefficients to growth, can be considered in breeding programs for fattening pigs.

Data-driven stochastic spectral modeling for coarsening of the two-dimensional Euler equations on the sphere

A resolution-independent data-driven subgrid-scale model in coarsened fluid descriptions is proposed. The method enables the inclusion of high-fidelity data into the coarsened flow model, thereby enabling accurate simulations also with the coarser representation. The small-scale model is introduced at the level of the Fourier coefficients of the coarsened numerical solution. It is designed to reproduce the kinetic energy spectra observed in high-fidelity data of the same system. The approach is based on a control feedback term reminiscent of continuous data assimilation implemented using nudging (Newtonian relaxation). The method relies solely on the availability of high-fidelity data from a statistically steady state. No assumptions are made regarding the adopted discretization method or the selected coarser resolution. The performance of the method is assessed for the two-dimensional Euler equations on the sphere for coarsening factors of 8 and 16 times. Applying the method at these significantly coarser resolutions yields good results for the mean and variance of the Fourier coefficients and leads to improvements in the empirical probability density functions of the attained vorticity values. Stable and accurate large-scale dynamics can be simulated over long integration times and are illustrated by capturing long-time vortex trajectories.

A Study of Drought and Flood Cycles in Xinyang, China, Using the Wavelet Transform and M-K Test

Accurately identifying and predicting droughts can provide local managers with a basis for decision-making. The Xinyang region is prone to droughts and floods, which have a large impact on local agriculture and socio-economics. This paper employs precipitation data from the Xinyang region to provide a scientific basis for drought and flood control measures in this region. The data are first treated with standardized precipitation indices (SPIs) on three-month, six-month, and nine-month time scales. Subsequently, a Morlet wavelet analysis is performed for each of the three time scales analyzed for the SPI. The results show multiple time scales of drought and flood disasters in the Xinyang region. The cycles of drought and flood disasters in the Xinyang region show different fluctuations on different SPI scales. The SPI time series reflect a strong fluctuation period of 17a for drought and flood disasters in the Xinyang region. An analysis of the variance of the wavelet coefficients showed that the first main cycle of drought and flood disasters in the Xinyang region is 7a, and the second and third sub-cycles are 4a and 13a, respectively. We conclude that floods are more frequent than droughts in Xinyang and are more likely to occur from 2017 to 2021, with a subsequent shift to droughts. Local managers should put drought prevention measures in place to deal with droughts after 2021.

Tests of symmetry based on the bootstrap estimation of the asymptotic variance of a skewness coefficient

Testing for symmetry about an unknown median is a problem that has attracted the attention of statisticians for decades. Many of the existing tests of symmetry are based on the asymptotic distribution of a skewness coefficient, which typically is asymptotically normal and centered around zero for symmetric distributions. Unfortunately, the asymptotic variance depends on the underlying distribution and differs from one symmetric distribution to another one. A possible way out is to estimate this asymptotic variance from the sample by means of the bootstrap. In this paper, we explore this approach for six different skewness coefficients existing in the literature. Extensive experiments are performed for comparing the performance of the six associated tests of symmetry to that of two state-of-the-art symmetry tests in terms of preservation of the significance level under several symmetric distributions, power under asymmetric distributions and robustness in the presence of outliers. Even though the results show no clear best test, we conclude by providing some guidelines for choosing a test of symmetry based on the needs of the user.

Dynamic variation of groundwater level and its influencing factors in typical oasis irrigated areas in Northwest China

Abstract It is essential to analyze the dynamic characteristics of regional groundwater levels and their driving factors for the rational development of groundwater in irrigated areas. This article explores the spatial distribution characteristics of the amplitude of groundwater level change in the Shihezi irrigated area by using the ArcGIS interpolation method and contrast coefficient variance method and analyzes the influence factors of dynamic change of groundwater levels by integrating the grey relational degree and path analysis methods and obtaining the sensitivity of each influencing factor to changes in groundwater levels and the relative importance of the influencing factors. The following results are obtained: (1) the groundwater level of the Shihezi irrigated area showed an overall increasing trend from 2012 to 2019, with a fluctuation range of 12.26–14.14 m. The groundwater level in the southeast of the irrigated area showed an upward trend, while the groundwater level in the northwest area showed a downward trend. (2) The groundwater level in the irrigated area first increased, then decreased, and then increased again. The variance of the contrast coefficient in the irrigated area ranged from 0.04 to 11.31, and the fluctuation range of the groundwater level in the central area was higher than that in the northern and southern areas. (3) The irrigated area of cultivated land and evaporation are the main factors affecting groundwater level change in the Shihezi irrigated area. The grey relation analysis shows that the irrigated area of cultivated land has the highest grey correlation degree with the evolution of the groundwater level, which is 0.947, and the average grey correlation index is between 0.74 and 0.95. Path analysis showed that the irrigated area of cultivated land, surface water usage, and evaporation were the main factors affecting groundwater levels. Human activities are one of the main driving forces of groundwater level change, and the research results provide a theoretical basis for the rational utilization and sustainable development of groundwater resources in the Shihezi irrigation area.

Cash flow management and its effect on firm performance: Empirical evidence on non-financial firms of China.

The main purpose of this research is to investigate the impact of changes in cash flow measures and metrics on firm financial performance. The study uses generalized estimating equations (GEEs) methodology to analyze longitudinal data for sample of 20288 listed Chinese non-financial firms from the period 2018:q2-2020:q1. The main advantage of GEEs method over other estimation techniques is its ability to robustly estimate the variances of regression coefficients for data samples that display high correlation between repeated measurements. The findings of study show that the decline in cash flow measures and metrics bring significant positive improvements in the financial performance of firms. The empirical evidence suggests that performance improvement levers (i.e. cash flow measures and metrics) are more pronounced in low leverage firms, suggesting that changes in cash flow measures and metrics bring more positive changes in low leverage firms' financial performance relatively to high leveraged firms. The results hold after mitigating endogeneity based on dynamic panel system generalized method of moments (GMM) and sensitivity analysis considering the robustness of main findings. The paper makes significant contribution to the literature related to cash flow management and working capital management. Since, this paper is among few to empirically study, how cash flow measures and metrics are related to firm performance from dynamic stand point especially from the context of Chinese non-financial firms.

Alternative covariance structures in mixed-effects models: Addressing intra- and inter-individual heterogeneity

Mixed-effects models for repeated measures and longitudinal data include random coefficients that are unique to the individual, and thus permit subject-specific growth trajectories, as well as direct study of how the coefficients of a growth function vary as a function of covariates. Although applications of these models often assume homogeneity of the within-subject residual variance that characterizes within-person variation after accounting for systematic change and the variances of the random coefficients of a growth model that quantify individual differences in aspects of change, alternative covariance structures can be considered. These include allowing for serial correlations between the within-subject residuals to account for dependencies in data that remain after fitting a particular growth model or specifying the within-subject residual variance to be a function of covariates or a random subject effect to address between-subject heterogeneity due to unmeasured influences. Further, the variances of the random coefficients can be functions of covariates to relax the assumption that these variances are constant across subjects and to allow for the study of determinants of these sources of variation. In this paper, we consider combinations of these structures that permit flexibility in how mixed-effects models are specified to understand within- and between-subject variation in repeated measures and longitudinal data. Data from three learning studies are analyzed using these different specifications of mixed-effects models.

Multiple imputation of more than one environmental exposure with nondifferential measurement error.

Measurement error is common in environmental epidemiologic studies, but methods for correcting measurement error in regression models with multiple environmental exposures as covariates have not been well investigated. We consider a multiple imputation approach, combining external or internal calibration samples that contain information on both true and error-prone exposures with the main study data of multiple exposures measured with error. We propose a constrained chained equations multiple imputation (CEMI) algorithm that places constraints on the imputation model parameters in the chained equations imputation based on the assumptions of strong nondifferential measurement error. We also extend the constrained CEMI method to accommodate nondetects in the error-prone exposures in the main study data. We estimate the variance of the regression coefficients using the bootstrap with two imputations of each bootstrapped sample. The constrained CEMI method is shown by simulations to outperform existing methods, namely the method that ignores measurement error, classical calibration, and regression prediction, yielding estimated regression coefficients with smaller bias and confidence intervals with coverage close to the nominal level. We apply the proposed method to the Neighborhood Asthma and Allergy Study to investigate the associations between the concentrations of multiple indoor allergens and the fractional exhaled nitric oxide level among asthmatic children in New York City. The constrained CEMI method can be implemented by imposing constraints on the imputation matrix using the mice and bootImpute packages in R.

Local heat transfer characteristics of circular multiple air jet impinging on a semicircular concave surface

ABSTRACT The local heat transfer characteristics of circular multiple air jet impingement on semicircular concave surface were studied experimentally. For constant Reynolds number (Re = 9,000), the effect of jet to concave surface spacing (z/d = 1, 4.2, 6), ratio of curvature (D/d = 4.28, 6, 8.6), jet-to-jet spacing (s/d = 2.4, 4, 5.6), and number of jets were considered. The local heat transfer characteristics were determined by using infrared thermal camera and thin foil method. Lower curvature value ratio (D/d = 4.28) resulted higher average heat transfer coefficient due to broader spread of heat transfer distribution, whereas higher curvature ratio (D/d = 8.6) resulted in lower average heat transfer coefficient due to steeper heat transfer distribution in the stagnation area. At lower D/d, z/d, and s/d with seven jet configuration, the heat transfer coefficients were found effective as compared to other configurations due to broad heat transfer distribution and less interaction between the jets. At given D/d and s/d configuration, the stagnation Nu at θ = 0° do not coincide with jet hole center axis and this shift is more pronounced at higher z/d value. This could be due to additional push before jet impinging on concave surface. The secondary peaks were observed between two neighboring stagnation regions in Nu distribution along the center longitudinal line for lower z/d and higher s/d values. This resulted due to upwash that was obtained from jet interactions related to collisions with the wall jets. The correlations of stagnation line average Nu and overall average Nu were obtained. The coefficient of variance of local heat transfer coefficient for each configuration was determined, and correlation was proposed to analyze the degree of non-uniformity.

Displacement Monitoring of a Bridge Based on BDS Measurement by CEEMDAN-Adaptive Threshold Wavelet Method.

From the viewpoint of BDS bridge displacement monitoring, which is easily affected by background noise and the calculation of a fixed threshold value in the wavelet filtering algorithm, which is often related to the data length. In this paper, a data processing method of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), combined with adaptive threshold wavelet de-noising is proposed. The adaptive threshold wavelet filtering method composed of the mean and variance of wavelet coefficients of each layer is used to de-noise the BDS displacement monitoring data. CEEMDAN was used to decompose the displacement response data of the bridge to obtain the intrinsic mode function (IMF). Correlation coefficients were used to distinguish the noisy component from the effective component, and the adaptive threshold wavelet de-noising occurred on the noisy component. Finally, all IMF were restructured. The simulation experiment and the BDS displacement monitoring data of Nanmao Bridge were verified. The results demonstrated that the proposed method could effectively suppress random noise and multipath noise, and effectively obtain the real response of bridge displacement.

Improvement of the CLUTCH method for sensitivity analysis of k-eigenvalue to continuous-energy nuclear data in NECP-MCX

The Iterated Fission Probability (IFP) method and Contributon-Linked eigenvalue sensitivity/Uncertainty estimation via Track-length importance Characterization (CLUTCH) method are commonly implemented in Monte-Carlo codes to calculate the sensitivity coefficients of keff to continuous-energy nuclear data. However, these methods are plagued by the problem of large variance of sensitivity coefficients of the scattering reactions with relatively small cross sections. This problem means that more particles are needed to accurately calculate these sensitivity coefficients. To address this problem, a novel technique called CLUTCH coupled with forced collisions (CLUTCH-FC) method is proposed to reduce the variance of sensitivity coefficients of those reactions. The forced collision method is performed with specified reactions rather than specified cells in tradition to increase the sampling of specified reactions and a new rule for the setting of cutoff weight of neutrons is also proposed to make the best use of forced collisions. Three methods, viz. IFP, CLUTCH and CLUTCH-FC methods, are implemented in the Monte-Carlo code NECP-MCX. The verification is conducted in Godiva, Jezebel and TMI-1 problems by comparing the sensitivity coefficients calculated by IFP and CLUTCH methods with those calculated by the direct numerical perturbation (DNP) method. The numerical results indicate that 1) the sensitivity coefficients calculated by the IFP and CLUTCH methods corroborate well with those calculated by the DNP method, and 2) the CLUTCH-FC method is efficient in improving the tally efficiency of sensitivity coefficients of scattering reactions with relatively small cross sections by comparing results of CLUTCH-FC and CLUTCH methods.

An Ultra-Short-Term PV Power Forecasting Method for Changeable Weather Based on Clustering and Signal Decomposition

Photovoltaic (PV) power shows different fluctuation characteristics under different weather types as well as strong randomness and uncertainty in changeable weather such as sunny to cloudy, cloudy to rain, and so on, resulting in low forecasting accuracy. For the changeable type of weather, an ultra-short-term photovoltaic power forecasting method is proposed based on affinity propagation (AP) clustering, complete ensemble empirical mode decomposition with an adaptive noise algorithm (CEEMDAN), and bi-directional long and short-term memory network (BiLSTM). First, the PV power output curve of the standard clear-sky day was extracted monthly from the historical data, and the photovoltaic power was normalized according to it. Second, the changeable days were extracted from various weather types based on the AP clustering algorithm and the Euclidean distance by considering the mean and variance of the clear-sky power coefficient (CSPC). Third, the CEEMDAN algorithm was further used to decompose the data of changeable days to reduce its overall non-stationarity, and each component was forecasted based on the BiLSTM network, so as to obtain the PV forecasting value in changeable weather. Using the PV dataset obtained from Alice Springs, Australia, the presented method was verified by comparative experiments with the BP, BiLSTM, and CEEMDAN-BiLSTM models, and the MAPE of the proposed method was 2.771%, which was better than the other methods.

A critical reflection on computing the sampling variance of the partial correlation coefficient.

The partial correlation coefficient quantifies the relationship between two variables while taking into account the effect of one or multiple control variables. Researchers often want to synthesize partial correlation coefficients in a meta-analysis since these can be readily computed based on the reported results of a linear regression analysis. The default inverse variance weights in standard meta-analysis models require researchers to compute not only the partial correlation coefficients of each study but also its corresponding sampling variance. The existing literature is diffuse on how to estimate this sampling variance, because two estimators exist that are both widely used. We critically reflect on both estimators, study their statistical properties, and provide recommendations for applied researchers. We also compute the sampling variances of studies using both estimators in a meta-analysis on the partial correlation between self-confidence and sports performance.

Olsavs: A New Algorithm For Model Selection

The shrinkage methods such as Lasso and Relaxed Lasso introduce some bias in order to reduce the variance of the regression coefficients in multiple linear regression models. One way to reduce bias after shrinkage of the coefficients would be to apply ordinary least squares to the subset of predictors selected by the shrinkage method used. This work extensively investigated this idea and developed a new variable selection algorithm. The authors named this technique OLSAVS (Ordinary Least Squares After Variable Selection). The OLSAVS algorithm was implemented in R. Simulations were used to illustrate that the new method is able to produce better predictions with less bias for various error distributions. The OLSAVS method was compared with a few widely used shrinkage methods in terms of their achieved test root mean square error and bias.