Ordinary Least-squares Method Research Articles

Estimating Weibull Parameters Using Least Squares and Multilayer Perceptron vs. Bayes Estimation

The Weibull distribution is regarded as among the finest in the family of failure distributions. One of the most commonly used parameters of the Weibull distribution (WD) is the ordinary least squares (OLS) technique, which is useful in reliability and lifetime modeling. In this study, we propose an approach based on the ordinary least squares and the multilayer perceptron (MLP) neural network called the OLSMLP that is based on the resilience of the OLS method. The MLP solves the problem of heteroscedasticity that distorts the estimation of the parameters of the WD due to the presence of outliers, and eases the difficulty of determining weights in case of the weighted least square (WLS). Another method is proposed by incorporating a weight into the general entropy (GE) loss function to estimate the parameters of the WD to obtain a modified loss function (WGE). Furthermore, a Monte Carlo simulation is performed to examine the performance of the proposed OLSMLP method in comparison with approximate Bayesian estimation (BLWGE) by using a weighted GE loss function. The results of the simulation showed that the two proposed methods produced good estimates even for small sample sizes. In addition, the techniques proposed here are typically the preferred options when estimating parameters compared with other available methods, in terms of the mean squared error and requirements related to time.

Finite Sample Identification of Low-Order LTI Systems via Nuclear Norm Regularization

This paper studies the problem of identifying low-order linear time-invariant systems via Hankel nuclear norm (HNN) regularization. This regularization encourages the Hankel matrix to be low-rank, which corresponds to the dynamical system being of low order. We provide novel statistical analysis for this regularization, and contrast it with the unregularized ordinary least-squares (OLS) estimator. Our analysis leads to new finite-sample error bounds on estimating the impulse response and the Hankel matrix associated with the linear system using HNN regularization. We design a suitable input excitation, and show that we can recover the system using a number of observations that scales optimally with the true system order and achieves strong statistical estimation rates. Complementing these, we also demonstrate that the input design indeed matters by proving that intuitive choices, such as i.i.d. Gaussian input, lead to sub-optimal sample complexity. To better understand the benefits of regularization, we also revisit the OLS estimator. Besides refining existing bounds, we experimentally identify when HNN regularization improves over OLS: (1) For loworder systems with slow impulse-response decay, OLS method performs poorly in terms of sample complexity, (2) the Hankel matrix returned by regularization has a more clear singular value gap that makes determining the system order easier, (3) HNN regularization is less sensitive to hyperparameter choice. To choose the regularization parameter, we also outline a simple joint train-validation procedure

ESTIMASI PARAMETER MODEL REGRESI LINIER DENGAN PENDEKATAN METODE BAYESIAN

The method used to estimate the regression parameters in this study is the Bayes method. The steps in estimating the parameters of the linear regression model using the Bayes method are to determine the Likelihood function from the normal distribution density function, determine the Prior Non-Informative distribution from a normal distribution, then look for the Posterior distribution by switching the Prior distribution with the Likelihood function.Writing this thesis aims to determine the estimation of the parameters of the linear regression model with the Bayesian method approach. From the regression model generated by the OLS method, it was identified that there was one Outlier data. Outlier is a factor that influences parameter estimation in linear regression model. A model will be shown in an example data case by comparing the results of the Ordinary Least Square (OLS) method using R and the results of the Bayesian method using WinBUGS. It can be seen that the MSE value obtained from the Bayesian Method estimation is smaller than the MSE value obtained from the OLS Method estimate. The Mean Square Error (MSE) value obtained from the estimation of the OLS Method is 0.8469 while the Mean Square Error (MSE) value obtained from the estimation of the Bayesian MCMC Method is 0.3723. This shows that the Bayesian MCMC method is much better than the OLS method.
 

A Parallel Pandemic: Increased Firearm Injuries at Five Northern California Trauma Centers During the COVID-19 Pandemic: An Interrupted Time-series Analysis.

Objective:This study aimed to characterize changes in firearm injuries at 5 level 1 trauma centers in Northern California in the 12 months following the start of the COVID-19 pandemic compared with the preceding 4 years, accounting for regional variations and seasonal trends.Summary and Background Data:Increased firearm injuries have been reported during the early peaks of the COVID-19 pandemic despite shelter-in-place restrictions. However, these data are overwhelmingly from singlecenter studies, during the initial phase of the pandemic prior to lifting of shelter-in-place restrictions, or do not account for seasonal trends.Methods:An interrupted time-series analysis (ITSA) of all firearm injuries presenting to 5 adult level 1 trauma centers in Northern California was performed (January 2016to February 2021). ITSA modeled the association of the onset of the COVID-19 pandemic (March 2020) with monthly firearm injuries using the ordinary least-squares method, included month indicators to adjust for seasonality, and specified lags of up to 12 months to account for autocorrelation.Results:Prior to the start of COVID-19, firearm injuries averaged (±SD) of 86 (±16) and were decreasing by 0.5/month (P < 0.01). The start of COVID- 19 (March 2020) was associated with an alarming increase of 39 firearm injuries/month (P < 0.01) followed by an ongoing rise of 3.5/mo (P < 0.01). This resulted in an average of 130 (±26) firearm injuries/month during the COVID-19 period and included 8 of the 10 highest monthly firearm injury rates in the past 5 years.Conclusions:These data highlight an alarming escalation in firearm injuries in the 12 months following the onset of the COVID-19 pandemic in Northern California. Additional studies and resources are needed to better understand and address this parallel public health crisis.

Analytical Intervention of Remote Working Correlates on Risk Culture and Entrepreneurial Adaptability in South-South Geopolitical Zone, Nigeria: Covid-19 Perspective

This study explored the analytical intervention of remote-working correlates on risk culture and entrepreneurial adaptability in South-South geopolitical zone, Nigeria. The study adopted ex-post facto design and exploratory research design. Data were generated from entrepreneurs’ with specialty on self-development training program for hand craft skills by quantitative and qualitative methods. The study used multi-stage cluster sampling and proportionate stratified random sampling techniques. A total population of 200 and a sample size of 133 were determined using Krejcie and Morgan Table. Also, 133 copies of questionnaire were distributed to the respondents and 127 copies were completed and retrieved. The instrument was validated with reliability above 0.7 co-efficient, using Cronbach Alpha technique. The reliability coefficient analysis was attitude (α =0.912), behaviour (α=0.893), competence (α =0.894), adaptability (α=0.911) and remote working (α=0.901). Four research questions and four hypotheses were raised which were tested with KMO for the sampling adequacy and Barllet’s test for data appropriateness sphericity. The Ordinary Least Square Method (OLSM) and Partial Correlation Co-efficient were used to analyze the hypotheses of the explanatory, response and intervening variables via SPSS 25 version. From the findings, remote working correlates risk culture and entrepreneurial adaptability positively. In conclusion, attitude, behavior and competence have significant influence on entrepreneurial adaptability of self-development training program enterprise. Based on the findings and conclusion, this study contributes to the knowledge that to adapt with the storm of the covid-19 variant and working from home, risk culture measures should be streamline with the enterprise vision and mission pursuit. It could be recommended that to encourage remote working, the risk culture ABC model must be adopted and practice that will enable the enterprise to have competitive advantage. Also, risk culture and remote working should be encouraged because of the covid-19 pandemic to prevent the self-development training enterprise from bleeding. Keywords: Attitude, Behaviour, Competence, Entrepreneurial Adaptability, Remote Working, Covid-19 Pandemic DOI: 10.7176/JEP/12-34-05 Publication date: December 31 st 2021

Robust optimization of multistage process: response surface and multi-response optimization approaches

Abstract A multistage system refers to a system contains multiple components or stages which are necessary to finish the final product or service. To analyze these problems, the first step is model building and the other is optimization. Response surfaces are used to model multistage problem as an efficient procedure. One regular approach to estimate a response surface using experimental results is the ordinary least squares (OLS) method. OLS method is very sensitive to outliers, so some multivariate robust estimation methods have been discussed in the literature in order to estimate the response surfaces accurately such as multivariate M-estimators. In optimization phase, multi-response optimization methods such as global criterion (GC) method and ε-constraints approaches are different methods to optimize the multi-objective-multistage problems. An example of the multistage problem had been estimated considering multivariate robust approaches, besides applying multi-response optimization approaches. The results show the efficiency of the proposed approaches.

PENGARUH VARIABEL EKONOMI MAKRO TERHADAP PEMBIAYAAN PERBANKAN SYARIAH PERIODE 2010-2018

The purpose of the research is to examine and analyze the effect of macroeconomic variables GDP and inflation on Islamic banking financing in Indonesian. Islamic bank financing is the dependent variable, whereas GDP, reference interest rates, and inflation are the independent variable. The data used is Islamic banking financing, GDP, reference interest rates, and inflation in Indonesian from 2010-1018. This empirical study uses a quantitative approach and method of OLS (Ordinary Least Square). The results of this research indicate that the GDP variable has positive and statistically significant effect on Islamic banking financing, the variable reference interest rates (BI Rate and BI Rate 7days Repo Rate) have negative and statistically significant effect on Islamic banking financing, the inflation variable has positive and statistically significant effect on Islamic banking financing.

The Impact of Peer-to-Peer (P2P) Lending on Business Development of Small and Medium-Sized Enterprises

The problem faced by most micro-entrepreneurs in Indonesia is financing business. Peer-to-peer (P2P) lending is a non-bank financial institution that can be an alternative source of financing because of the requirements and easy application usage. This study aims to analyze the impact of peer-to-peer lending on business expenses, business turnover, total employment, total sales of products, and profits before and after obtaining a peer-to-peer lending loan and analyze factors affecting the increase in business turnover after getting a loan through peer-to-peer lending. The methods used in this study include the descriptive analysis method, paired t-test, and ordinary least square (OLS). The paired t-test results indicate that there is a significant difference between business expenses, business turnover, the amount of labor, the number of product sales, and profit before and after obtaining a peer-to-peer lending loan. The result of analysis with the OLS method shows that the length of business and expenditure of the business has a significant effect on the development of respondents' business turnover.

How does machine learning compare to conventional econometrics for transport data sets? A test of ML versus MLE

AbstractMachine learning (ML) is being used regularly in many different fields. This paper compares traditional econometric methods that have better explanations of data analysis to ML methods, focusing on predicting, understanding and unpacking ML methods which have higher prediction accuracies of four key transport‐planning variables: household vehicle‐miles traveled (continuous variable), household vehicle ownership (count variable), mode choice (categorical variable), and land use change (categorical variable with strong spatial interactions). Here, the results of ten ML methods are compared to methods of ordinary least squares (OLS), multinomial logit (MNL), negative binomial and spatial auto‐regressive (SAR). The U.S.’s 2017 National Household Travel Survey and land use data sets from the Dallas‐Ft. Worth region of Texas are used. Results suggest traditional econometric methods work pretty well on the more continuous responses (VMT and vehicle ownership), but the random forest (RF), gradient boosting decision trees (GBDT), and extreme gradient boosting (XGBoost) methods delivered the best results, though the RF model required 30 to almost 60 times more computing time than XGBoost and GBDT methods. The RF, GBDT, XGBoost, light gradient boosting method (lightGBM), and catboost offer better results than other methods for the two “classification” cases, with lightGBM being the most time‐efficient. Importantly, ML methods captured the plateauing effect modelers may expect when extrapolating covariate effects.

Spatial Analysis and Comparison of the Economic Burden of Common Diseases: An Investigation of 5.7 Million Rural Elderly Inpatients in Southeast China, 2010-2016.

Background: As China embraced an aging society, the burden of age-related diseases had increased dramatically. Knowledge about spatial distribution characteristics of disease burden and the influencing factors of medical expenditure is of great significance to the formulation of health policies. However, related research in rural China is still insufficient.Methods: A total of 5,744,717 records of hospitalized rural elderly in southeast China were collected from 2010 to 2016. We described the temporal trends of hospitalization medical expenditure and the prevalence of catastrophic health expenses (CHE) in the rural elderly by common diseases. Then, geographical information tools were used for visualization of geographic distribution patterns of CHE, the ordinary least squares methods (OLS) and geographically weighted regression (GWR) were employed to examine the influencing factors of medical expenditure.Results: The number of CHE hospitalizations and the total number of hospitalizations for the rural elderly people increased by 2.1 times and 2.2 times, respectively, from 2010 to 2016. Counties with a high prevalence of CHE were clustered in the eastern coastal area (Moran's I = 0.620, P < 0.001, General G < 0.001, P < 0.001). Unspecified transport accidents, cardiovascular disease, and essential hypertension were the top causes of CHE in the rural elderly. Adequate hospital beds (P < 0.05) and reasonable utilization and distribution of town-level (P < 0.001) and county-level hospitals (P < 0.001) may help reduce medical expenditures.Conclusions: In the context of an aging society, the disease burden for the elderly in rural areas should arouse more attention. These findings highlight the importance of age-related disease prevention and the rational allocation of medical resources in rural areas.

The Impact of Foreign Direct Investment (FDI) on Economic Growth (EG): Evidence from Djibouti

The achievement of EG and development is considered the core objective for both Developing Countires (DCs) and Least Developed Countries (LDCs), so countries try to get adequate funding to achieve this goal through optimal macroeconomic policies and different strategies. Countries prefer other mechanisms with less burden and cost to achieve economic growth, such as FDI flows. International development-oriented institutions such as WB and IMF recommend and consider FDI flows as the most important factors of the modern technology transfer, management, and know-how, which is necessarily needed in the local investment projects in poor countries, Therefore FDI represents optimal external sources of growth.The objective of this study is to explain the impact of FDI on the EG of Djibouti. To achieve this objective the study used a secondary annual time series data for the period 1985-2019 by the method of Ordinary Least Square (OLS).The study results showed that FDI in the case of Djibouti tends to be statistically insignificant effects on Djibouti‘s EG; on the other hand other factors such as the Human Development Index (HDI) and Gross Fixed Capital Formation (GFCF), Trade Openness (TOP) shows significant effects on the Gross Domestic Product (GDP). Finally, the Consumer Price Index (CPI) has no significance in the EG of Djibouti.The findings provide critical information to Djibouti policy decision-makers to make an informed decision with regard to attracting investment and policies in encouraging foreign investors to invest in the country.

An Estimation of Dates Production Function in Karbala Governorate For The Agricultural Season 2020 (Al-jadual Al-gharby District A case Study)

This study aimed to detect the most important factor that affects dates production. About 108 questionary forms collecttted palm orchard farmers in Karbala to estimate the dates production function in Karbala governorate for the agricultural season 2021 (the district of Al-jadual Al-Gharby). The study distributed those formmmsss for about 10% of the total palm orchards in Al-jadual Al-Gharby district of the holy governorate of Karbala. The study used the method of ordinary Least squares (OLS) to estimate the mathematical model of the function. The results showed that the double Logarithmic function in terms of its estimation of the estimated Coefficients by one unit leads to a corresponding change in the produced quality of dates and the same direction by 0.188 0.808) % respectively, and that the capital variable is more in fluently in production than the work variable. As for the total production elasticity (the sum of the partial elasticities of the resources used), which represents returns to scale, it amounted to about (0.996), which indicates a decrease in the return to scale.

The Impact of Foreign Direct Investment (FDI) on Economic Growth (EG) : Evidence from Djibouti

Abstract: The achievement of EG and development is considered the core objective for both Developing Countires (DCs) and Least Developed Countries (LDCs), so countries try to get adequate funding to achieve this goal through optimal macroeconomic policies and different strategies. Countries prefer other mechanisms with less burden and cost to achieve economic growth, such as FDI flows. International development-oriented institutions such as WB and IMF recommend and consider FDI flows are the most important factors of the modern technology transfer, management, and know-how, which is necessarily needed in the local investment projects in poor countries, so FDI represents optimal external sources of growth. The objective of this study is to explain the impact of FDI on the EG of Djibouti. To achieve this objective the study used a secondary annual time series data for the period 1985-2019 by the method of Ordinary Least Square (OLS). The study results showed that FDI in the case of Djibouti tends to be statistically insignificant effects and a limited impact on Djibouti‘s EG, Moreover,other factors such as the Human Development Index(HDI), and Gross Fixed Capital Formation(GFCF), Trade Openness(TOP) shows significant effects on the Gross Domestic Product (GDP). Finally, the Consumer Price Index (CPI) has no significance in the EG of Djibouti. The findings provide critical information to Djibouti policy decision-makers to make an informed decision with regard to attracting investment sectors and policies in encouraging foreign investors to invest in the country. KEYWORDS: Foreign Direct Investment, Economic Growth, Djibouti, Empirical Analysis.

Optimal data processing in the ballistic laser gravimeter under the effect of correlated interference

Abstract&#x0D; In order to develop optimal data processing algorithms in ballistic laser gravimeters under the effect of correlated interference, the method of generalized least squares is applied. In this case, to describe the interference, a mathematical model of the autoregression process is used, for which the inverse correlation matrix has a band type and is expressed through the values of the autoregression coefficients. To convert the “path-time” data from the output of the coincidence circuit of ballistic laser gravimeters to a process uniform in time, their local quadratic interpolation is used.&#x0D; Algorithms for data processing in a ballistic gravimeter, developed on the basis of a method of weighted least squares using orthogonal Hahn polynomials, are considered. To implement a symmetric measurement method, the symmetric Hahn polynomials, characterized by one parameter, are used.&#x0D; The method of mathematical modelling is used to study the gain in the accuracy of measuring the gravitational acceleration by the synthesized algorithms in comparison with the algorithm based on the method of least squares. It is shown that auto seismic interference in ballistic laser gravimeters with a symmetric measurement method can be significantly reduced by using a mathematical model of the second-order autoregressive process in the method of generalized least squares. A comparative analysis of the characteristics of the algorithms developed using the method of generalized least squares, the method of weighted least squares and the method of ordinary least squares is carried out.

Modeling the Future Value Distribution of a Life Insurance Portfolio

This paper addresses the problem of approximating the future value distribution of a large and heterogeneous life insurance portfolio which would play a relevant role, for instance, for solvency capital requirement valuations. Based on a metamodel, we first select a subset of representative policies in the portfolio. Then, by using Monte Carlo simulations, we obtain a rough estimate of the policies’ values at the chosen future date and finally we approximate the distribution of a single policy and of the entire portfolio by means of two different approaches, the ordinary least-squares method and a regression method based on the class of generalized beta distribution of the second kind. Extensive numerical experiments are provided to assess the performance of the proposed models.

Effect of Working After Retirement on the Mental Health of Older People: Evidence From China.

There is little empirical research on the effect of working after retirement on the mental health of the older adults in China. To fill this gap in the literature, this study examines the effects of working after retirement on the mental health of the older adults using data from the China Family Panel Studies. We employed the methods of ordinary least squares, ordered logit, and propensity score matching–difference in differences (PSM–DID). Results show that working after retirement is negatively related to mental health of the older adults in China. The deterioration effect of post-retirement work mainly impacts those aged over 60 years, women, and those with lower education background, urban household registration, higher pension, and higher social status. Working after retirement is negatively related to mental health through the mediating effects of deteriorating interpersonal relationships and lower positive attitude. It is necessary to consider mental health effects and their population differences to evaluate the impact and improve the quality of policies of active aging.

NONLINEAR MODELS BASED ON QUANTILES IN THE FITTING OF GROWTH CURVES OF PEPPER GENOTYPES

This study aimed to fit nonlinear regression models to model the growth of the characters fruit length (FL) and fruit width (FW) of pepper genotypes (Capsicum annuum L.) over time using the method of ordinary least squares (OLS); and identify the model with the best fit and compare it to the model obtained via nonlinear quantile regression (QR) in the 0.25, 0.5, and 0.75 quantiles. Three regression models (Logistic, Gompertz, and von Bertalanffy) and four fit quality evaluators were adopted: Akaike information criterion, residual mean absolute deviation, and parametric and intrinsic curvature measurements. Five commercial genotypes of pepper were evaluated. Characters FL and FW were evaluated weekly from seven days after flowering, totaling ten measurements. In the estimation by OLS, the Logistic and von Bertalanffy models were considered adequate according to the quality evaluators. In the comparison between the models above by OLS and QR, the superiority of models obtained by QR was verified for the character FL. For the character FW, QR was efficient in three out of the five genotypes, being a valuable alternative in the study of fruit growth.

Residual stress analysis of multi-pass cold spinning process

Uncontrolled residual stresses have significant effects on the service time and defects of the spun parts. Nowadays, X-Ray Diffraction (XRD) method has been widely used in the residual stress measurement of industry products with different forming processes. The calculated residual stress is usually obtained from the data fitting slope of strain and angle with Ordinary Least Squares (OLS) method. But this fitting method is not always suitable for the big fluctuant data. In this paper, the Weighted Least Square (WLS) method is used for the data fitting and compared with the OLS method. The nickel-based superalloy GH3030 and iron-based superalloy GH1140 are applied in the multi-pass cold spinning experiments. The residual stress distributions of normal, potential crack and wrinkle workpieces are discussed with the grain structure. The results show that WLS method has better goodness of fit compared with OLS method. The residual stress distributions have special relationship with potential crack, wrinkle workpiece and grain structure.

Leaf water potential of field crops estimated using NDVI in ground-based remote sensing-opportunities to increase prediction precision.

Remote-sensing using normalized difference vegetation index (NDVI) has the potential of rapidly detecting the effect of water stress on field crops. However, this detection has typically been accomplished only after the stress effect led to significant changes in crop green biomass, leaf area index, angle and position, and few studies have attempted to estimate the uncertainties of the regression models. These have limited the informed interpretation of NDVI data in agricultural applications. We built a ground-based sensing cart and used it to calibrate the relationships between NDVI and leaf water potential (LWP) for wheat, corn, and cotton growing under field conditions. Both the methods of ordinary least-squares (OLS) and weighted least-squares (WLS) were employed in data analysis, and measurement errors in both LWP and NDVI were considered. We also used statistical resampling to test the effect of measurement errors of LWP on the uncertainties of model coefficients. Our data showed that obtaining a high value of the coefficient of determination did not guarantee a high prediction precision in the obtained regression models. Large prediction uncertainties were estimated for all three crops, and the regressions obtained were not always significant. The best models were obtained for cotton with a prediction uncertainty of 27%. We found that considering measurement errors for both LWP and NDVI led to reduced uncertainties in model coefficients. Also, reducing the sample size of LWP measurement led to significantly increased uncertainties in the coefficients of the linear models describing the LWP-NDVI relationship. Finally, potential strategies for reducing the uncertainty relative to the range of NDVI measurement are discussed.

Fiscal Policy &amp; Real Sector Output in Nigeria: 1994- 2019

This study examined the effect of fiscal policy implementation on the real sector of the Nigerian economy. An econometric model was estimated using the method of ordinary least squares and data were obtained from the Central Bank of Nigeria (CBN’s) statistical bulletin for the period 1994-2019. The independent variables were government capital expenditure, government recurrent expenditure, and tax revenue, while the dependent variable was the real sector GDP. The study also tested the null hypotheses that fiscal policy has no significant relationship with real GDP From our findings, Capital Expenditure did not have a significant relationship with the Nominal GDP of the Real Sector, which means that changes in Capital Expenditure did not contribute significantly in predicting the growth of the real sector. On the other hand, Recurrent Expenditure and Tax Revenue were statistically significant to the real sector GDP. Also, our results show that all the predictor variables were jointly significant at the 0.05 level. Therefore, the study recommended that measures be put in place for a more coordinated approach to fiscal policy implementation and a sustainable plan to limit and control the level of government borrowing in order to avoid undesirable effects that comes with government crowding out the private sector.