Generalized ordered linear regression with regularization

2012 ◽  
Vol 60 (3) ◽  
pp. 481-489 ◽  
Author(s):  
J.M. Łęski ◽  
N. Henzel
Keyword(s):  
Linear Regression ◽  
Linear Models ◽  
Linear Regression Analysis ◽  
Gradient Algorithm ◽  
Weighted Averaging ◽  
Criterion Function ◽  
Regression Problem ◽  
Quadratic Minimization ◽  
Minimization Problems ◽  
Model Residuals

Abstract Linear regression analysis has become a fundamental tool in experimental sciences. We propose a new method for parameter estimation in linear models. The ’Generalized Ordered Linear Regression with Regularization’ (GOLRR) uses various loss functions (including the ǫ-insensitive ones), ordered weighted averaging of the residuals, and regularization. The algorithm consists in solving a sequence of weighted quadratic minimization problems where the weights used for the next iteration depend not only on the values but also on the order of the model residuals obtained for the current iteration. Such regression problem may be transformed into the iterative reweighted least squares scenario. The conjugate gradient algorithm is used to minimize the proposed criterion function. Finally, numerical examples are given to demonstrate the validity of the method proposed.

scholarly journals Sex differences in the link between blood cobalt concentrations and insulin resistance in adults without diabetes

2021 ◽  
Vol 26 (1) ◽  
Author(s):  
Yong Chen ◽  
Haobin Huang ◽  
Xiaowei He ◽  
Weiwei Duan ◽  
Xuming Mo
Keyword(s):  
Insulin Resistance ◽  
Linear Regression ◽  
Linear Models ◽  
Fasting Glucose ◽  
Adult Population ◽  
Linear Regression Analysis ◽  
Cobalt Concentration ◽  
Model Assessment ◽  
Homeostatic Model Assessment ◽  
Cobalt Exposure

Abstract Background Little is known about the effects of environmental cobalt exposure on insulin resistance (IR) in the general adult population. We investigated the association between cobalt concentration and IR. Methods A total of 1281 subjects aged more than 20 years with complete blood cobalt data were identified from the National Health and Nutrition Examination Survey (NHANES) 2015–2016 cycle. Blood cobalt levels were analyzed for their association with IR among all populations and subgroups by sex. Regression coefficients and 95% confidence intervals (CIs) of blood cobalt concentrations in association with fasting glucose, insulin and homeostatic model assessment of insulin resistance (HOMA-IR) were estimated using multivariate linear regression after adjusting for age, sex, ethnicity, alcohol consumption, body mass index, education level, and household income. A multivariate generalized linear regression analysis was further carried out to explore the association between cobalt exposure and IR. Results A negative association between blood cobalt concentration (coefficient = − 0.125, 95% CI − 0.234, − 0.015; P = 0.026) and HOMA-IR in female adults in the age- and sex-adjusted model was observed. However, no associations with HOMA-IR, fasting glucose, or insulin were found in the overall population. In the generalized linear models, participants with the lowest cobalt levels had a 2.74% (95% CI 0.04%, 5.50%) increase in HOMA-IR (P for trend = 0.031) compared with subjects with the highest cobalt levels. Restricted cubic spline regression suggested that a non-linear relationship may exist between blood cobalt and HOMA-IR. Conclusions These results provide epidemiological evidence that low levels of blood cobalt are negatively associated with HOMA-IR in female adults.

Choroidal luminal and stromal areas and choriocapillaris perfusion are characterised by a non-linear quadratic relation in healthy eyes

2020 ◽  
pp. bjophthalmol-2020-316479 ◽  
Author(s):  
Enrico Borrelli ◽  
Maria Cristina Gabela ◽  
Riccardo Sacconi ◽  
Lea Querques ◽  
Giovanna Vella ◽  
...  
Keyword(s):  
Regression Analysis ◽  
Linear Regression ◽  
Healthy Subjects ◽  
Linear Models ◽  
Linear Regression Analysis ◽  
Quadratic Function ◽  
Initial Increase ◽  
Linear Quadratic ◽  
Cross Sectional ◽  
Non Linear

PurposeTo assess the associations among different optical coherence tomography (OCT) structural and angiography quantitative metrics used to characterise the choroid in healthy subjects.MethodsIn this cross-sectional study, macular structural OCT and OCT angiography (OCTA) images were acquired from healthy subjects. The main outcome measures were: (i) choriocapillaris (CC) flow deficits percentage (FD%), (ii) choroidal luminal (LA) and stromal (SA) areas and (iii) choroidal vascularity index (CVI), which was calculated as the LA divided by the total choroidal area. These measurements were generated using previously published algorithms and were separately computed in the foveal and extrafoveal regions.ResultsEighty-five eyes from 85 subjects (44 males, 41 females) were included in the analysis. Mean±SD age was 47.9±22.4 years (range: 19.0 to 85.0 years). Linear regression analysis displayed no significant associations between CC FD% and other parameters (LA, SA and CVI). Importantly, non-linear regression analysis showed that the relations of LA and SA to CC FD% were all best fitted by a quadratic function. Compared with the linear models, the use of the quadratic function allowed a relative increase in the R2 coefficients. No significant non-linear associations were found between CC FD% and CVI.ConclusionBased on our models, changes in the luminal and stromal areas in the choroid lead to an initial increase in CC perfusion. Subsequently, further increases in LA and SA amounts are accompanied by a progressive increment in CC FD%.

Statistical Inference and Application for Partially Linear Models

2015 ◽  
Vol 733 ◽  
pp. 910-913
Author(s):  
Jing Zhang ◽  
Hong Xia Guo
Keyword(s):  
Linear Regression ◽  
Regression Model ◽  
Linear Model ◽  
Linear Regression Model ◽  
Linear Models ◽  
Linear Regression Analysis ◽  
Principal Component ◽  
Partial Linear Model ◽  
Partially Linear Regression Model ◽  
Partially Linear

As partially linear regression model contains parameters part and the nonparametric part, it is better than the linear model. Partially linear regression model is more freedom, flexible, and can seize the characteristics of data. This passage first reduces the dimension of expenditure index data using principal component analysis. Then based on the dimension-reduced data, a partial linear model is established to forecast expenditure on army. The results show a great advantage over those by stepwise linear regression analysis.

PENGARUH FAKTOR-FAKTOR INTERNAL PERBANKAN TERHADAP NON PERFORMING FINANCING PADA BANK UMUM SYARIAH

2019 ◽  
Vol 6 (2) ◽  
pp. 115-130
Author(s):  
Eka Ambara Harci Putranta ◽  
Lilik Ambarwati
Keyword(s):  
Linear Regression ◽  
Multiple Linear Regression ◽  
Linear Regression Analysis ◽  
Multiple Linear Regression Analysis ◽  
Capital Adequacy ◽  
Annual Reports ◽  
Regression Methods ◽  
Capital Adequacy Ratio ◽  
Negative Effect ◽  
Independent Variable

The study aims to analyze the influence of internal banking factors in the form of: Capital Adequency Ratio (CAR), Financing to Deposit Ratio (FDR) and Total Assets (TA) to Non Performing Financing at Sharia Banks. This research method used multiple linear regression analysis with the help of SPSS 16.00 software which is used to see the influence between the independent variables in the form of Capital Adequacy Ratio (CAR), Financing to Deposit Ratio (FDR) and Total Assets (TA) to Non Performing Financing. The sample of this study was 3 Islamic Commercial Banks, so there were 36 annual reports obtained through purposive sampling, then analyzed using multiple linear regression methods. The results showed that based on the F Test, the independent variable had an effect on the NPF, indicated by the F value of 17,016 and significance of 0,000, overall the independent variable was able to explain the effect of 69.60%. While based on the partial t test, showed that CAR has a significant negative effect, Total assets have a significant positive effect with a significance value below 0.05 (5%). Meanwhile FDR does not affect NPF.

ANALISIS PENGARUH INFLASI, KURS DAN IHSG TERHADAP RETURN REKSA DANA SAHAM PT NIKKO SECURITIES INDONESIA PERIODE 2014-2017

2019 ◽  
Vol 2 (2) ◽  
pp. 103
Author(s):  
Muhammad Rois Rois ◽  
Manarotul Fatati Fatati ◽  
Winda Ihda Magfiroh
Keyword(s):  
Regression Analysis ◽  
Exchange Rate ◽  
Linear Regression ◽  
Multiple Linear Regression ◽  
Stock Price ◽  
Price Index ◽  
Linear Regression Analysis ◽  
Multiple Linear Regression Analysis ◽  
Equity Fund ◽  
Stock Price Index

This study aims to determine the effect of Inflation, Exchange Rate and Composite Stock Price Index (IHSG) to Return of PT Nikko Securities Indonesia Stock Fund period 2014-2017. The study used secondary data obtained through documentation in the form of PT Nikko Securities Indonesia Monthly Net Asset (NAB) report. Data analysis is used with quantitative analysis, multiple linear regression analysis using eviews 9. Population and sample in this research are PT Nikko Securities Indonesia. The result of multiple linear regression analysis was the coefficient of determination (R2) showed the result of 0.123819 or 12%. This means that the Inflation, Exchange Rate and Composite Stock Price Index (IHSG) variables can influence the return of PT Nikko Securities Indonesia's equity fund of 12% and 88% is influenced by other variables. Based on the result of the research, the variables of inflation and exchange rate have a negative and significant effect toward the return of PT Nikko Securities Indonesia's equity fund. While the variable of Composite Stock Price Index (IHSG) has a negative but not significant effect toward Return of Equity Fund of PT Nikko Securities Indonesia

Struktur Organisasi, Desain Kerja, Budaya Organisasi Dan Pengaruhnya Terhadap Produktivitas Karyawan Studi Kasus Pada PT. XX Di Jakarta

Liquidity ◽  
2018 ◽  
Vol 1 (2) ◽  
Author(s):  
Yanti Budiasih
Keyword(s):  
Organizational Culture ◽  
Regression Analysis ◽  
Linear Regression ◽  
Organizational Structure ◽  
Research Method ◽  
Linear Regression Analysis ◽  
Multiple Linear Regression Analysis ◽  
Job Design ◽  
Employee Productivity ◽  
Dominant Influence

The objectives of this study are to analyze changes in organizational structure, job design, organizational culture and its influence on employee productivity at PT. XX in Jakarta and to identify variables that have a dominant influence on the productivity of employees. The research method used is using multiple linear regression analysis. The results show that the all variables simultaneously and partially change the organizational structure, job design, and organizational culture has a significant impact on employee productivity at PT. XXin Jakarta.

The Contribution of Sexual Identity Towards the Students’ Perception of Lesbian, Gay, Bisexual, and Transgender

10.32698/0642 ◽  
2019 ◽  
Vol 2 (2) ◽  
pp. 120
Author(s):  
Wiwi Delfita ◽  
Neviyarni S. ◽  
Riska Ahmad
Keyword(s):  
Regression Analysis ◽  
Linear Regression ◽  
Sexual Identity ◽  
Student Perceptions ◽  
Undergraduate Students ◽  
Linear Regression Analysis ◽  
Sampling Technique ◽  
Simple Linear Regression ◽  
Simple Linear Regression Analysis ◽  
Bisexual And Transgender

Some students perceive lesbian, gay, bisexual, and transgender (LGBT) positively, even though LGBT is a sexual deviation that is not appropriate with values and norms. There are several factors that influence an individual's perception of LGBT, including sexual identity. This study aims at looking at the contribution of sexual identity to student perceptions about LGBT. This research used a quantitative approach with a descriptive method and a simple linear regression analysis. The sample of this research was 385 taken from 15.752 undergraduate students of Universitas Negeri Padang which the sample was drawn by using the Slovin formula and continued with a Proportional Random Sampling technique. The instrument used was the Guttman model's sexual identity scale and the scale of students' perceptions of the LGBT Likert model. After analyzing the data with the descriptive technique and the simple linear regression analysis, the results showed that sexual identity significantly contributed to the students' perceptions of LGBT. This research has implications as a basis for counselors to help students avoid sexual identity mismatches and prevent the emergence of positive perceptions of LGBT.

Pengaruh Penghargaan Terhadap Kinerja Karyawan pada CV. Dino Manunggal Karsa Bogor

2019 ◽  
Vol 4 (2) ◽  
pp. 17
Author(s):  
Dedy Mulyadi ◽  
Didik Purwanto
Keyword(s):  
Linear Regression ◽  
Performance Assessment ◽  
Correlation Coefficient ◽  
Linear Regression Analysis ◽  
Strong Relationship ◽  
Simple Linear Regression ◽  
New Employees ◽  
Company Policy ◽  
Effective Manner ◽  
Relationship Of

The question of compensation in addition to sensitive to be driving someone to worl due to an effect on morale and discipline employees. Therefore , any  agency or any organization should be able to provide compensation equal to the workload  to create a workforce that efficient and effective manner can be realized. Amaore than that, the company’s goal to improve performance. Performance assessment is a subjective process that involves human judgments. Thus, performance assessment is very likely wrong and very easily influonced by sources that are not actual, so it must be taken into account and considered reasinable. Frformance appraisals are considered  to meet the target if it has a good impact on new employees who rated their performance. Simple linear regression analysis using SPSS version 12:00 data processing obtained tegression equation Y = 0,487 X 74 + with an explanation of X = award, 74 = constant, 0.487 = coefficient awards, and Y = performance based on simple linear regression equation in case of increase of one unit of the  performance award will be increased 0.487 units. If company policy negates the performance award will remain at a constant rate (74) units . (A) Test results obtained thitung significant constants of (12.574) > t table for (1.960 then reject Ho constanta significant meaning. (B) significant Test award coefficient t count the results obtained by (2.164)> t table foe (1.96) then reject Ho the mean coeffent of appreciation affect the performance . (C) correlation coefficient analysis is done by calculating the product moment corration (pearson)  to test  whether or not a strong  relationship between the variables X  dan Y , based on the results of cakculations with SPSS  table valuse obtained by calculating the  correlation coefficient r (0.3100> r on the table for a = 0,05 (0.291) then reject Ho, which means there is a relationship of respect for performance. When we enter these valuse in the table shows the interpretation of the correlation coefficient between the interval from 0.20 to 0.399 which has a low relationship

Pengaruh Kepemimpinan dan Disiplin Kerja Terhadap Kinerja Karyawan: Studi Kasus PT Sucofindo Palembang Indonesia

MBIA ◽  
2019 ◽  
Vol 18 (1) ◽  
pp. 76-84
Author(s):  
Muhammad Idris ◽  
Dian Novita Sari
Keyword(s):  
Regression Analysis ◽  
Linear Regression ◽  
Random Sampling ◽  
Linear Regression Analysis ◽  
Secondary Data ◽  
Multiple Linear Regression Analysis ◽  
Primary Data ◽  
Collection Method ◽  
Analysis Techniques ◽  
Analysis Technique

The problem in this study is whether there is an influence of leadership and work discipline on the employees’ performance of PT.Sucofindo Palembang City. This research includes associative research. The sample in this study were 88 respondents, with propotionate random sampling analysis technique. The data used were primary data and secondary data. Data collection method through questionnare. Analysis techniques using multiple linear regression analysis, F test (Simultaneoys) and t test (partial) and determination coeffiecient. The results show that there is influence of leadership and work discipline on the performance of PT.Sucofindo Palembang City.

Sign in / Sign up

Export Citation Format

Share Document