Quantile regression: an alternative approach to modelling forest area burned by individual fires

2018 ◽  
Vol 27 (8) ◽  
pp. 538 ◽  
Author(s):  
Baburam Rijal
Keyword(s):  
Quantile Regression ◽  
Forest Ecosystems ◽  
Fire Regime ◽  
Model Fitting ◽  
Ordinary Least Squares ◽  
Mean Value ◽  
Mixed Effects ◽  
Least Squares Regression ◽  
Fire Size ◽  
Large Fires

Components of a fire regime have long been estimated using mean-value-based ordinary least-squares regression. But, forest and fire managers require predictions beyond the mean because impacts of small and large fires on forest ecosystems and wildland–urban interfaces are different. Therefore, different action plans are required to manage potential fires of varying sizes that demand size-based modelling tools. The objective of this study was to compare two model-fitting techniques, namely quantile mixed-effects (QME) model and ordinary linear mixed-effects (LME) model for constructing distributions of model-predicted small and large fires. I examined these techniques by modelling the fire size of individual escaped wildfires. Results showed that the LME-predicted fire size approximately coincided to the 0.75 quantile. The LME model produced more biased predictions at the two extremes, both of which manifest great importance in forest ecosystems and fire management. Modelling the distributions for small and large fires using quantile regression can reduce such biases along with giving unbiased mean estimates. This study concludes that quantile modelling is an effective approach to complement ordinary regression that helps predict the size-based risks of individual fires more precisely, and that could allow managers to better plan resources when managing fires.

scholarly journals Improving estimations in quantile regression model with autoregressive errors

2018 ◽  
Vol 22 (Suppl. 1) ◽  
pp. 97-107 ◽  
Author(s):  
Bahadır Yuzbasi ◽  
Yasin Asar ◽  
Samil Sik ◽  
Ahmet Demiralp
Keyword(s):  
Quantile Regression ◽  
Regression Model ◽  
Simulation Experiment ◽  
Ordinary Least Squares ◽  
Least Squares Regression ◽  
White Noise Process ◽  
Respiratory Mortality ◽  
Explanatory Variables ◽  
Quantile Regression Model ◽  
Regression Approach

An important issue is that the respiratory mortality may be a result of air pollution which can be measured by the following variables: temperature, relative humidity, carbon monoxide, sulfur dioxide, nitrogen dioxide, hydrocarbons, ozone, and particulates. The usual way is to fit a model using the ordinary least squares regression, which has some assumptions, also known as Gauss-Markov assumptions, on the error term showing white noise process of the regression model. However, in many applications, especially for this example, these assumptions are not satisfied. Therefore, in this study, a quantile regression approach is used to model the respiratory mortality using the mentioned explanatory variables. Moreover, improved estimation techniques such as preliminary testing and shrinkage strategies are also obtained when the errors are autoregressive. A Monte Carlo simulation experiment, including the quantile penalty estimators such as lasso, ridge, and elastic net, is designed to evaluate the performances of the proposed techniques. Finally, the theoretical risks of the listed estimators are given.

scholarly journals Using Quantile Regression to Estimate Intervention Effects Beyond the Mean

2019 ◽  
Vol 79 (5) ◽  
pp. 883-910 ◽  
Author(s):  
Spyros Konstantopoulos ◽  
Wei Li ◽  
Shazia Miller ◽  
Arie van der Ploeg
Keyword(s):  
Quantile Regression ◽  
Least Squares ◽  
Large Scale ◽  
Social Science Research ◽  
Empirical Work ◽  
Science Research ◽  
Ordinary Least Squares ◽  
Least Squares Regression ◽  
Intervention Effects ◽  
Education Data

This study discusses quantile regression methodology and its usefulness in education and social science research. First, quantile regression is defined and its advantages vis-à-vis vis ordinary least squares regression are illustrated. Second, specific comparisons are made between ordinary least squares and quantile regression methods. Third, the applicability of quantile regression to empirical work to estimate intervention effects is demonstrated using education data from a large-scale experiment. The estimation of quantile treatment effects at various quantiles in the presence of dropouts is also discussed. Quantile regression is especially suitable in examining predictor effects at various locations of the outcome distribution (e.g., lower and upper tails).

Agglomeration and innovation: Selection or true effect?

2019 ◽  
Vol 52 (2) ◽  
pp. 423-448
Author(s):  
Li Fang
Keyword(s):  
Cost Effectiveness ◽  
Quantile Regression ◽  
Selection Effect ◽  
Cost Benefit ◽  
Ordinary Least Squares ◽  
Least Squares Regression ◽  
Firm Innovation ◽  
Industrial Policies ◽  
Agglomeration Effect ◽  
Patent Applications

This paper separates two mechanisms through which agglomeration increases average firm innovation: selection (less innovative firms being forced out of agglomerations) and true agglomeration (firms become more innovative). I apply a quantile regression to estimate the distribution of firm innovation and separate these two mechanisms. Linking a unique establishment-level dataset with the patent dataset in the state of Maryland for the period 2004–2013, I find that a 1-mile radius area with above-median employment concentration significantly encourages firm innovation. An average establishment that files for at least one patent during the study period increases citation-weighted patent applications by 31.2% to 31.5% in such employment centers. I also find evidence of selection: non-innovators are 1.3% less likely to survive in agglomerations. The coexistence of agglomeration and selection causes the result of an ordinary least squares regression to be upwardly biased. By eliminating the selection effect, this study more precisely estimates the agglomeration effect, which can be applied to cost–benefit and cost-effectiveness analyses of urban and industrial policies.

Identifying the readiness of patients in implementing telemedicine in northern Louisiana for an oncology practice

2016 ◽  
Vol 23 (3) ◽  
pp. 181-196 ◽  
Author(s):  
Varadraj Gurupur ◽  
Kruparaj Shettian ◽  
Peixin Xu ◽  
Scott Hines ◽  
Mitzi Desselles ◽  
...  
Keyword(s):  
Ordinary Least Squares ◽  
Mean Value ◽  
Reliability Test ◽  
Least Squares Regression ◽  
Cronbach’S Alpha ◽  
Test Analysis ◽  
Cronbach's Alpha ◽  
Rural And Urban ◽  
Alpha Reliability ◽  
Oncology Practice

This study identified the readiness factors that may create challenges in the use of telemedicine among patients in northern Louisiana with cancer. To identify these readiness factors, the team of investigators developed 19 survey questions that were provided to the patients or to their caregivers. The team collected responses from 147 respondents from rural and urban residential backgrounds. These responses were used to identify the individuals’ readiness for utilising telemedicine through factor analysis, Cronbach’s alpha reliability test, analysis of variance and ordinary least squares regression. The analysis results indicated that the favourable factor (positive readiness item) had a mean value of 3.47, whereas the unfavourable factor (negative readiness item) had a mean value of 2.76. Cronbach’s alpha reliability test provided an alpha value of 0.79. Overall, our study indicated a positive attitude towards the use of telemedicine in northern Louisiana.

Quantile Regression Analysis and Other Alternatives to Ordinary Least Squares Regression

Methodology ◽  
2014 ◽  
Vol 10 (3) ◽  
pp. 81-91 ◽  
Author(s):  
Harry Haupt ◽  
Friedrich Lösel ◽  
Mark Stemmler
Keyword(s):  
Regression Analysis ◽  
Quantile Regression ◽  
Least Squares ◽  
Corporal Punishment ◽  
Ordinary Least Squares ◽  
Study Data ◽  
Physical Punishment ◽  
Least Squares Regression ◽  
Prevention Project ◽  
Quantile Regression Analysis

Data analyses by classical ordinary least squares (OLS) regression techniques often employ unrealistic assumptions, fail to recognize the source and nature of heterogeneity, and are vulnerable to extreme observations. Therefore, this article compares robust and non-robust M-estimator regressions in a statistical demonstration study. Data from the Erlangen-Nuremberg Development and Prevention Project are used to model risk factors for physical punishment by fathers of 485 elementary school children. The Corporal Punishment Scale of the Alabama Parenting Questionnaire was the dependent variable. Fathers’ aggressiveness, dysfunctional parent-child relations, various other parenting characteristics, and socio-demographic variables served as predictors. Robustness diagnostics suggested the use of trimming procedures and outlier diagnostics suggested the use of robust estimators as an alternative to OLS. However, a quantile regression analysis provided more detailed insights beyond the measures of central tendency and detected sources of considerable heterogeneity in the risk structure of father’s corporal punishment. Advantages of this method are discussed with regard to methodological and content issues.

A spatio-temporal analysis of the relationship between housing renovation, socioeconomic status, and urban forest ecosystems

2018 ◽  
Vol 46 (6) ◽  
pp. 1115-1131 ◽  
Author(s):  
James WN Steenberg ◽  
Pamela J Robinson ◽  
Peter N Duinker
Keyword(s):  
Tree Mortality ◽  
Forest Ecosystems ◽  
Urban Forest ◽  
Common Knowledge ◽  
Canopy Cover ◽  
Ordinary Least Squares ◽  
Tree Planting ◽  
Least Squares Regression ◽  
Building Permit ◽  
The Relationship

Urban forest ecosystems are increasingly recognized as necessary components of a city's overall sustainability. The number of municipal governments planning and implementing urban forest management programs is rising, as the benefits of urban forest ecosystems are becoming common knowledge. However, the urban forest is an exceedingly complex and vulnerable social–ecological system that presents a wide array of management challenges. One area of concern that is understudied and worthy of investigation is the effects of housing renovation activities and neighborhood revitalization on the urban forest. The purpose of this study is to investigate the possibility of renovation activity as a significant source of disturbance in urban forest ecosystems. We conducted ordinary least squares regression and geographically weighted regression analyses using canopy cover, building permit data, and socioeconomic variables in Toronto, Canada. We then conducted a parcel-level assessment of tree mortality using ortho-imagery from 2003 and 2014 and government open data describing 16 years of renovation activity. Findings suggest that renovation activity, as indicated by building permit abundance, is a possible cause of tree mortality and subsequently a source of urban forest disturbance. Our findings also suggest that the relationship between renovation activity and canopy cover is highly complex, and is likely influenced by residential tree planting rates, land use mix, and different trajectories of urban change.

scholarly journals Insights from analysing tourist expenditure using quantile regression

2016 ◽  
Vol 23 (5) ◽  
pp. 1138-1145 ◽  
Author(s):  
António Almeida ◽  
Brian Garrod
Keyword(s):  
Quantile Regression ◽  
Least Squares ◽  
Empirical Studies ◽  
Ordinary Least Squares ◽  
Estimation Technique ◽  
Least Squares Regression ◽  
Data Set ◽  
Detailed Understanding ◽  
Tourism Destinations ◽  
Single Data

Mature tourism destinations are increasingly needing to diversify their products and markets. To be successful, such strategies require a very detailed understanding of potential tourists’ levels and patterns of spending. Empirical studies of tourist expenditure have tended to employ ordinary least squares regression for this purpose. There are, however, a number of important limitations to this technique, chief among which is its inability to distinguish between tourists who have higher- and lower-than-average levels of spending. As such, some researchers recommend the use of an alternative estimation technique, known as quantile regression, which does allow such distinctions to be made. This study uses a single data set, collected among rural tourists in Madeira, to analyse the determinants of tourist expenditure using both techniques. This enables direct comparison to be made and illustrates the additional insights to be gained using quantile regression.

scholarly journals Machine learning to predict final fire size at the time of ignition

2019 ◽  
Vol 28 (11) ◽  
pp. 861 ◽  
Author(s):  
Shane R. Coffield ◽  
Casey A. Graff ◽  
Yang Chen ◽  
Padhraic Smyth ◽  
Efi Foufoula-Georgiou ◽  
...  
Keyword(s):  
Machine Learning ◽  
Fire Regime ◽  
Vapour Pressure Deficit ◽  
Burned Area ◽  
Fire Size ◽  
Tree Model ◽  
Ignition Point ◽  
Machine Learning Classification ◽  
Large Fires ◽  
Insight Into

Fires in boreal forests of Alaska are changing, threatening human health and ecosystems. Given expected increases in fire activity with climate warming, insight into the controls on fire size from the time of ignition is necessary. Such insight may be increasingly useful for fire management, especially in cases where many ignitions occur in a short time period. Here we investigated the controls and predictability of final fire size at the time of ignition. Using decision trees, we show that ignitions can be classified as leading to small, medium or large fires with 50.4±5.2% accuracy. This was accomplished using two variables: vapour pressure deficit and the fraction of spruce cover near the ignition point. The model predicted that 40% of ignitions would lead to large fires, and those ultimately accounted for 75% of the total burned area. Other machine learning classification algorithms, including random forests and multi-layer perceptrons, were tested but did not outperform the simpler decision tree model. Applying the model to areas with intensive human management resulted in overprediction of large fires, as expected. This type of simple classification system could offer insight into optimal resource allocation, helping to maintain a historical fire regime and protect Alaskan ecosystems.

scholarly journals Weighted Quantile Regression Forests for Bimodal Distribution Modeling: A Loss Given Default Case

Entropy ◽  
2020 ◽  
Vol 22 (5) ◽  
pp. 545 ◽  
Author(s):  
Michał Gostkowski ◽  
Krzysztof Gajowniczek
Keyword(s):  
Quantile Regression ◽  
Bimodal Distribution ◽  
Ordinary Least Squares ◽  
Mean Value ◽  
Loss Given Default ◽  
Ensemble Technique ◽  
Internal Rating ◽  
Enabling Institutions ◽  
The Impact ◽  
Weighted Quantile Regression

Due to various regulations (e.g., the Basel III Accord), banks need to keep a specified amount of capital to reduce the impact of their insolvency. This equity can be calculated using, e.g., the Internal Rating Approach, enabling institutions to develop their own statistical models. In this regard, one of the most important parameters is the loss given default, whose correct estimation may lead to a healthier and riskless allocation of the capital. Unfortunately, since the loss given default distribution is a bimodal application of the modeling methods (e.g., ordinary least squares or regression trees), aiming at predicting the mean value is not enough. Bimodality means that a distribution has two modes and has a large proportion of observations with large distances from the middle of the distribution; therefore, to overcome this fact, more advanced methods are required. To this end, to model the entire loss given default distribution, in this article we present the weighted quantile Regression Forest algorithm, which is an ensemble technique. We evaluate our methodology over a dataset collected by one of the biggest Polish banks. Through our research, we show that weighted quantile Regression Forests outperform “single” state-of-the-art models in terms of their accuracy and the stability.

Sign in / Sign up

Export Citation Format

Share Document