Search results
1 – 10 of over 32000Kun-Huang Huarng and Tiffany Hui-Kuang Yu
The use of linear regression analysis is common in the social sciences. The purpose of this paper is to show the advantage of a qualitative research method, namely, structured…
Abstract
Purpose
The use of linear regression analysis is common in the social sciences. The purpose of this paper is to show the advantage of a qualitative research method, namely, structured qualitative analysis (SQA), over the linear regression method by using different characteristics of data.
Design/methodology/approach
Data were gathered from a study of online consumer behavior in Taiwan. The authors changed the content of the data to have different sets of data. These data sets were used to demonstrate how SQA and linear regression works individually, and to contrast the empirical analyses and empirical results from linear regression and SQA.
Findings
The linear regression method uses one equation to model different characteristics of data. When facing a data set containing a big and a small size of different characteristics, linear regression tends to provide an equation by modeling the characteristics of the big size data and subsuming those of the small size. When facing a data set containing similar sizes of data with different characteristics, linear regression tends to provide an equation by averaging these data. The major concern is that the one equation may not be able to reflect the data of various characteristics (different values of independent variables) that result in the same outcome (the same value of dependent variable). In contrast, SQA can identify various variable combinations (multiple relationships) leading to the same outcome. SQA provided multiple relationships to represent different sizes of data with different characteristics so it created consistent empirical results.
Research limitations/implications
Two research methods work differently. The popular linear regression tends to use one equation to model different sizes and characteristics of data. The single equation may not be able to cover different behaviors but may lead to the same outcome. Instead, SQA provides multiple relationships for different sizes of data with different characteristics. The analyses are more consistent and the results are more appropriate. The academics may re-think the existing literature using linear regression. It would be interesting to see if there are new findings for similar problems by using SQA. The practitioners have a new method to model real world problems and to understand different possible combinations of variables leading to the same outcome. Even the relationship obtained from a small data set may be very valuable to practitioners.
Originality/value
This paper compared online consumer behavior by using two research methods to analyze different data sets. The paper offered the manipulation of real data sets to create different data sizes of different characteristics. The variations in empirical results from both methods due to the various data sets facilitate the comparison of both methods. Hence, this paper can serve as a complement to the existing literature, focusing on the justification of research methods and on limitations of linear regression.
Details
Keywords
John Galakis, Ioannis Vrontos and Panos Xidonas
This study aims to introduce a tree-structured linear and quantile regression framework to the analysis and modeling of equity returns, within the context of asset pricing.
Abstract
Purpose
This study aims to introduce a tree-structured linear and quantile regression framework to the analysis and modeling of equity returns, within the context of asset pricing.
Design/Methodology/Approach
The approach is based on the idea of a binary tree, where every terminal node parameterizes a local regression model for a specific partition of the data. A Bayesian stochastic method is developed including model selection and estimation of the tree structure parameters. The framework is applied on numerous U.S. asset pricing models, using alternative mimicking factor portfolios, frequency of data, market indices, and equity portfolios.
Findings
The findings reveal strong evidence that asset returns exhibit asymmetric effects and non- linear patterns to different common factors, but, more importantly, that there are multiple thresholds that create several partitions in the common factor space.
Originality/Value
To the best of the authors' knowledge, this paper is the first to explore and apply a tree-structured and quantile regression framework in an asset pricing context.
Details
Keywords
Jeffrey J. Burks, David W. Randolph and Jim A. Seida
This study examines the use of linear regressions that include interaction terms, finding frequent interpretation errors in published accounting research. We provide insights on…
Abstract
This study examines the use of linear regressions that include interaction terms, finding frequent interpretation errors in published accounting research. We provide insights on how to estimate, interpret, and present interactive regression models, and explain seldom-used but easily-implemented methods to report conditional marginal effects. We also examine the use of interaction terms in tax and financial reporting trade-off studies, evaluating the conceptual fit between a regression model with interactions and alternative definitions of trade-off. Although we advocate the use of interactive models, noise levels common in accounting research greatly reduce the ability to detect interaction effects.
Details
Keywords
Wen Li, Wei Wang and Wenjun Huo
Inspired by the basic idea of gradient boosting, this study aims to design a novel multivariate regression ensemble algorithm RegBoost by using multivariate linear regression as a…
Abstract
Purpose
Inspired by the basic idea of gradient boosting, this study aims to design a novel multivariate regression ensemble algorithm RegBoost by using multivariate linear regression as a weak predictor.
Design/methodology/approach
To achieve nonlinearity after combining all linear regression predictors, the training data is divided into two branches according to the prediction results using the current weak predictor. The linear regression modeling is recursively executed in two branches. In the test phase, test data is distributed to a specific branch to continue with the next weak predictor. The final result is the sum of all weak predictors across the entire path.
Findings
Through comparison experiments, it is found that the algorithm RegBoost can achieve similar performance to the gradient boosted decision tree (GBDT). The algorithm is very effective compared to linear regression.
Originality/value
This paper attempts to design a novel regression algorithm RegBoost with reference to GBDT. To the best of the knowledge, for the first time, RegBoost uses linear regression as a weak predictor, and combine with gradient boosting to build an ensemble algorithm.
Details
Keywords
We compare the finite sample power of short- and long-horizon tests in nonlinear predictive regression models of regime switching between bull and bear markets, allowing for time…
Abstract
We compare the finite sample power of short- and long-horizon tests in nonlinear predictive regression models of regime switching between bull and bear markets, allowing for time varying transition probabilities. As a point of reference, we also provide a similar comparison in a linear predictive regression model without regime switching. Overall, our results do not support the contention of higher power in longer horizon tests in either the linear or nonlinear regime switching models. Nonetheless, it is possible that other plausible nonlinear models provide stronger justification for long-horizon tests.
Details
Keywords
James E. Payne and Ken Schwendeman
Given the absence of a formal forecasting model of property insurance surtax revenue for the state of Kentucky, this paper presents the insample and out-of-sample forecasts of…
Abstract
Given the absence of a formal forecasting model of property insurance surtax revenue for the state of Kentucky, this paper presents the insample and out-of-sample forecasts of four models: Holt linear trend algorithm, autoregressive model, linear trend/autoregressive model, and economic activity model based on annual fiscal year data from 1984 to 2001. The Holt linear trend algorithm and the linear trend/autoregressive model were reasonably close in their respective forecasting performance for both the in-sample and out-ofsample forecast horizons. However, the linear trend/autoregressive model exhibited some evidence of instability for the period 1992 to 1994. With respect to the out-of-sample forecasts, the Holt linear trend algorithm provided a better fit to the actual surtax data. Moreover, as time passes and additional data on the surtax becomes available, the models presented can easily be updated and reevaluated.
Md Vaseem Chavhan, M. Ramesh Naidu and Hayavadana Jamakhandi
This paper aims to propose the artificial neural network (ANN) and regression models for the estimation of the thread consumption at multilayered seam assembly stitched with lock…
Abstract
Purpose
This paper aims to propose the artificial neural network (ANN) and regression models for the estimation of the thread consumption at multilayered seam assembly stitched with lock stitch 301.
Design/methodology/approach
In the present study, the generalized regression and neural network models are developed by considering the fabric types: woven, nonwoven and multilayer combination thereof, with basic sewing parameters: sewing thread linear density, stitch density, needle count and fabric assembly thickness. The network with feed-forward backpropagation is considered to build the ANN, and the training function trainlm of MATLAB software is used to adjust weight and basic values according to the optimization of Levenberg Marquardt. The performance of networks measured in terms of the mean squared error and the layer output is set according to the sigmoid transfer function.
Findings
The proposed ANN and regression model are able to predict the thread consumption with more accuracy for multilayered seam assembly. The predictability of thread consumption from available geometrical models, regression models and industrial empirical techniques are compared with proposed linear regression, quadratic regression and neural network models. The proposed quadratic regression model showed a good correlation with practical thread consumption value and more accuracy in prediction with an overall 4.3% error, as compared to other techniques for given multilayer substrates. Further, the developed ANN network showed good accuracy in the prediction of thread consumption.
Originality/value
The estimation of thread consumed while stitching is the prerequisite of the garment industry for inventory management especially with the introduction of the costly high-performance sewing thread. In practice, different types of fabrics are stitched at multilayer combinations at different locations of the stitched product. The ANN and regression models are developed for multilayered seam assembly of woven and nonwoven fabric blend composition for better prediction of thread consumption.
Details
Keywords
Bingjun Li, Weiming Yang and Xiaolu Li
The purpose of this paper is to address and overcome the problem that a single prediction model cannot accurately fit a data sequence with large fluctuations.
Abstract
Purpose
The purpose of this paper is to address and overcome the problem that a single prediction model cannot accurately fit a data sequence with large fluctuations.
Design/methodology/approach
Initially, the grey linear regression combination model was put forward. The Discrete Grey Model (DGM)(1,1) model and the multiple linear regression model were then combined using the entropy weight method. The grain yield from 2010 to 2015 was forecasted using DGM(1,1), a multiple linear regression model, the combined model and a GM(1,N) model. The predicted values were then compared against the actual values.
Findings
The results reveal that the combination model used in this paper offers greater simulation precision. The combination model can be applied to the series with fluctuations and the weights of influencing factors in the model can be objectively evaluated. The simulation accuracy of GM(1,N) model fluctuates greatly in this prediction.
Practical implications
The combined model adopted in this paper can be applied to grain forecasting to improve the accuracy of grain prediction. This is important as data on grain yield are typically characterised by large fluctuation and some information is often missed.
Originality/value
This paper puts the grey linear regression combination model which combines the DGM(1,1) model and the multiple linear regression model using the entropy weight method to determine the results weighting of the two models. It is intended that prediction accuracy can be improved through the combination of models used within this paper.
Details
Keywords
Modeling helps to determine how structural parameters of fabric affect the surface of a fabric and also identify the way they influence fabric properties. Moreover, it helps to…
Abstract
Purpose
Modeling helps to determine how structural parameters of fabric affect the surface of a fabric and also identify the way they influence fabric properties. Moreover, it helps to estimate and evaluate without the complexity and time-consuming experimental procedures. The purpose of this study is to develop and select the best regression model equations for the prediction and evaluation of surface roughness of plain-woven fabrics.
Design/methodology/approach
In this study, a linear and quadratic regression model was developed for the prediction and evaluation of surface roughness of plain-woven fabrics, and the capability in accuracy and reliability of the two-model equation was determined by the root mean square error (RMSE). The Design-Expert AE11 software was used for developing the two model equations and analysis of variance “ANOVA.” The count and density were used for developing linear model equation one “SMD1” as well as for quadratic model equation two “SMD2.”
Findings
From results and findings, the effects of count and density and their interactions on the roughness of plain-woven fabric were found statistically significant for both linear and quadratic models at a confidence interval of 95%. The count has a positive correlation with surface roughness, while density has a negative correlation. The correlations revealed that models were strongly correlated at a confidence interval of 95% with adjusted R² of 0.8483 and R² of 0.9079, respectively. The RMSE values of the quadratic model equation and linear model equation were 0.1596 and 0.0747, respectively.
Originality/value
Thus, the quadratic model equation has better capability accuracy and reliability in predictions and evaluations of surface roughness than a linear model. These models can be used to select a suitable fabric for various end applications, and it was also used for tests and predicts surface roughness of plain-woven fabrics. The regression model helps to reduce the gap between the subjective and objective surface roughness measurement methods.
Details
Keywords
Feature extraction from 3D datasets is a current problem. Machine learning is an important tool for classification of complex 3D datasets. Machine learning classification…
Abstract
Purpose
Feature extraction from 3D datasets is a current problem. Machine learning is an important tool for classification of complex 3D datasets. Machine learning classification techniques are widely used in various fields, such as text classification, pattern recognition, medical disease analysis, etc. The aim of this study is to apply the most popular classification and regression methods to determine the best classification and regression method based on the geodesics.
Design/methodology/approach
The feature vector is determined by the unit normal vector and the unit principal vector at each point of the 3D surface along with the point coordinates themselves. Moreover, different examples are compared according to the classification methods in terms of accuracy and the regression algorithms in terms of R-squared value.
Findings
Several surface examples are analyzed for the feature vector using classification (31 methods) and regression (23 methods) machine learning algorithms. In addition, two ensemble methods XGBoost and LightGBM are used for classification and regression. Also, the scores for each surface example are compared.
Originality/value
To the best of the author’s knowledge, this is the first study to analyze datasets based on geodesics using machine learning algorithms for classification and regression.
Details