Non-Parametric Generalized Additive Models as a Tool for Evaluating Policy Interventions

The interrupted time series analysis is a quasi-experimental design used to evaluate the effectiveness of an intervention. Segmented linear regression models have been the most used models to carry out this analysis. However, they assume a linear trend that may not be appropriate in many situations. In this paper, we show how generalized additive models (GAMs), a non-parametric regression-based method, can be useful to accommodate nonlinear trends. An analysis with simulated data is carried out to assess the performance of both models. Data were simulated from linear and non-linear (quadratic and cubic) functions. The results of this analysis show how GAMs improve on segmented linear regression models when the trend is non-linear, but they also show a good performance when the trend is linear. A real-life application where the impact of the 2012 Spanish cost-sharing reforms on pharmaceutical prescription is also analyzed. Seasonality and an indicator variable for the stockpiling effect are included as explanatory variables. The segmented linear regression model shows good fit of the data. However, the GAM concludes that the hypothesis of linear trend is rejected. The estimated level shift is similar for both models but the cumulative absolute effect on the number of prescriptions is lower in GAM.

Download Full-text

Non-Linear Regression Modelling to Estimate the Global Warming Potential of a Newspaper

Entropy ◽

10.3390/e22050590 ◽

2020 ◽

Vol 22 (5) ◽

pp. 590

Author(s):

Alexis Lozano ◽

Pedro Cabrera ◽

Ana M. Blanco-Marigorta

Keyword(s):

Linear Regression ◽

Environmental Sustainability ◽

Regression Models ◽

Raw Materials ◽

Operating Conditions ◽

Raw Material ◽

Linear Regression Models ◽

Daily Production ◽

Non Linear ◽

The Impact

Technological innovations are not enough by themselves to achieve social and environmental sustainability in companies. Sustainable development aims to determine the environmental impact of a product and the hidden price of products and services through the concept of radical transparency. This means that companies should show and disclose the impact on the environment of any good or service. This way, the consumer can choose in a transparent manner, not only for the price. The use of the eco-label as a European eco-label, which bases its criteria on life cycle assessment, could provide an indicator of corporate social responsibility for a given product. However, it does not give a full guarantee that the product was obtained in a sustainable manner. The aim of this work is to provide a way of calculating the value of the environmental impacts of an industrial product, under different operating conditions, so that each company can provide detailed information on the impacts of its products, information that can form part of its "green product sheet". As a case study, the daily production of a newspaper, printed by coldset, has been chosen. Each process involved in production was configured with raw material and energy consumption information from production plants, manufacturer data and existing databases. Four non-linear regression models have been trained to estimate the impact of a newspaper’s circulation from five input variables (pages, grammage, height, paper type, and print run) with 5508 data samples each. These non-linear regression models were trained using the Levenberg–Marquardt nonlinear least squares algorithm. The mean absolute percentage errors (MAPE) obtained by all the non-linear regression models tested were less than 5%. Through the proposed correlations, it is possible to obtain a score that reports on the impact of the product for different operating conditions and several types of raw materials. Ecolabelling can be further developed by incorporating a scoring system for the impact caused by the product or process, using a standardised impact methodology.

Download Full-text

High-density Lipoprotein Cholesterol Is Negatively Correlated with Bone Mineral Density and Has Potential Predictive Value for Bone Loss

Lipids in Health and Disease ◽

10.1186/s12944-021-01497-7 ◽

2021 ◽

Vol 20 (1) ◽

Author(s):

Yuchen Tang ◽

Shenghong Wang ◽

Qiong Yi ◽

Yayi Xia ◽

Bin Geng

Keyword(s):

Bone Mineral Density ◽

Linear Regression ◽

Regression Models ◽

Generalized Additive Models ◽

Density Lipoprotein ◽

Additive Models ◽

Nonlinear Relationship ◽

Linear Regression Models ◽

Mineral Density ◽

Increased Risk

Abstract Background Many studies have shown that lipids play important roles in bone metabolism. However, the association between high-density lipoprotein cholesterol (HDL-C) and bone mineral density (BMD) is unclear. Therefore, this study aimed to investigate the linear or nonlinear relation between HDL-C levels and BMD and addressed whether the HDL-C levels had the potential values for predicting the risk of osteoporosis or osteopenia. Methods Two researchers independently extracted all information from the National Health and Nutrition Examination Survey (NHANES) database. Participants over 20 years of age with available HDL-C and BMD data were enrolled in the final analysis. The linear relationship between HDL-C levels and BMD was assessed using multivariate linear regression models. Moreover, the nonlinear relationship was also characterized by fitted smoothing curves and generalized additive models. In addition, the odds ratio (OR) for osteopenia and osteoporosis was evaluated with multiple logistic regression models. Results The weighted multivariable linear regression models demonstrated that HDL-C levels displayed an inverse association with BMD, especially among females and subjects aged 30 to 39 or 50 to 59. Moreover, the nonlinear relationship characterized by smooth curve fittings and generalized additive models suggested that (i) HDL-C levels displayed an inverted U-shaped relationship with BMD among women 30 to 39 or over 60 years of age; (ii) HDL-C levels exhibited a U-shaped association with BMD among women 20 to 29 or 50 to 59 years of age. In addition, females with high HDL levels (62-139 mg/dL) had an increased risk of osteopenia or osteoporosis. Conclusion This study demonstrated that HDL-C levels exhibit an inverse correlation with BMD. Especially in females, clinicians need to be alert to patients with high HDL-C levels, which may indicate an increased risk of osteoporosis or osteopenia. For these patients, close monitoring of BMD and early intervention may be necessary.

Download Full-text

FAKTOR DETERMINAN PENYALURAN KREDIT BANK PERSERO

Journal of Business Economics ◽

10.35760/eb.2018.v23i1.1812 ◽

2018 ◽

Vol 23 (1) ◽

pp. 60-71

Author(s):

Wigiyanti Masodah

Keyword(s):

Interest Rate ◽

Linear Regression ◽

Interest Rates ◽

Regression Models ◽

Linear Regression Models ◽

Negative Impacts ◽

Main Activity ◽

The Impact ◽

The Given ◽

Multiple Linear Regression Models

Offering credit is the main activity of a Bank. There are some considerations when a bank offers credit, that includes Interest Rates, Inflation, and NPL. This study aims to find out the impact of Variable Interest Rates, Inflation variables and NPL variables on credit disbursed. The object in this study is state-owned banks. The method of analysis in this study uses multiple linear regression models. The results of the study have shown that Interest Rates and NPL gave some negative impacts on the given credit. Meanwhile, Inflation variable does not have a significant effect on credit given. Keywords: Interest Rate, Inflation, NPL, offered Credit.

Download Full-text

Non-Linear Regression Models with Vibration Amplitude Optimization Algorithms in a Microturbine

Sensors ◽

10.3390/s22010130 ◽

2021 ◽

Vol 22 (1) ◽

pp. 130

Author(s):

Omar Rodríguez-Abreo ◽

Juvenal Rodríguez-Reséndiz ◽

L. A. Montoya-Santiyanes ◽

José Manuel Álvarez-Alvarado

Keyword(s):

Linear Regression ◽

Vibration Amplitude ◽

Regression Models ◽

Engineering Problem ◽

Coefficient Of Determination ◽

Model Parameters ◽

Gray Wolf ◽

Linear Regression Models ◽

Machinery Condition Monitoring ◽

Non Linear

Machinery condition monitoring and failure analysis is an engineering problem to pay attention to among all those being studied. Excessive vibration in a rotating system can damage the system and cannot be ignored. One option to prevent vibrations in a system is through preparation for them with a model. The accuracy of the model depends mainly on the type of model and the fitting that is attained. The non-linear model parameters can be complex to fit. Therefore, artificial intelligence is an option for performing this tuning. Within evolutionary computation, there are many optimization and tuning algorithms, the best known being genetic algorithms, but they contain many specific parameters. That is why algorithms such as the gray wolf optimizer (GWO) are alternatives for this tuning. There is a small number of mechanical applications in which the GWO algorithm has been implemented. Therefore, the GWO algorithm was used to fit non-linear regression models for vibration amplitude measurements in the radial direction in relation to the rotational frequency in a gas microturbine without considering temperature effects. RMSE and R2 were used as evaluation criteria. The results showed good agreement concerning the statistical analysis. The 2nd and 4th-order models, and the Gaussian and sinusoidal models, improved the fit. All models evaluated predicted the data with a high coefficient of determination (85–93%); the RMSE was between 0.19 and 0.22 for the worst proposed model. The proposed methodology can be used to optimize the estimated models with statistical tools.

Download Full-text