Significance testing in quantile regression

Volgushev, Stanislav; Birke, Melanie; Dette, Holger; Neumeyer, Natalie

doi:10.1214/12-ejs765

Cited by 15 publications

(17 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Significance testing of quantile regression is still very much in the exploratory stage, and no single approach has yet gained widespread support. For further discussion, see Volgushev et al(2013).…”

Section: Linear Quantile Regressionmentioning

confidence: 99%

Modeling the UK electricity price distributions using quantile regression

Hagfors

Bunn

Kristoffersen

et al. 2016

Energy

View full text Add to dashboard Cite

In this paper we develop fundamental quantile regression models for the UK electricity price in each trading period. Intraday properties of price risk, as represented by the predictive distribution rather than expected values, have previously not been fully analysed. The sample covers half hourly data from 2005 to 2012. From our analysis we are able to show how the sensitivity towards different fundamental factors changes across quantiles and time of day. In the UK the supply of electricity is to a large extent generated from coal and gas plants, thus the price of gas and coal, as well as the carbon emission price, are included as fundamental factors in our model. We also include the electricity price lagged by one day, as well as demand and margin forecasts. We find that the sensitivities vary across the price distribution. Our findings also suggest that the sensitivity to fundamental factors exhibit intraday variation. We find that the sensitivity to gas relative to coal is higher in high quantiles and lower in low quantiles. We have demonstrated a scenario analysis based on the quantile regression models, showing how changes in the values of the fundamentals influence the electricity price distribution.

show abstract

Section: Linear Quantile Regressionmentioning

confidence: 99%

Modeling the UK electricity price distributions using quantile regression

Hagfors

Bunn

Kristoffersen

et al. 2016

Energy

View full text Add to dashboard Cite

show abstract

“…The model used for our analysis is a quantile regression model [8,9]. This method allows us to investigate the relationship between the dependent and independent variables across the entire distribution, and provides us with a tool to get a better picture of how the fundamental factors affect the price in different quantiles.…”

Section: Modelmentioning

confidence: 99%

Using quantile regression to analyze the effect of renewables on EEX price formation

Hagfors

Paraschiv

Molnár

et al. 2016

Renew. Energy Environ. Sustain.

View full text Add to dashboard Cite

This paper develops fundamental quantile regression models for the German electricity market. The main focus of this work is to analyze the impact of renewable energies, wind and photovoltaic, on the formation of day-ahead electricity prices for all trading periods in the EEX. We find that the renewable energy sources overall has a mild price dampening effect, and that the negative prices often attributed to wind power is a rare event that mainly occurs during nighttime periods of unusually low price and demand.

show abstract

“…Properties of the rearrangement map in a statistical context have been previously considered by Dette et al (2006); Neumeyer (2007); Dette and Volgushev (2008); Chernozhukov et al (2010); Volgushev et al (2013), among others. In particular, Dette et al (2006); Neumeyer (2007); Dette and Volgushev (2008); Volgushev et al (2013) considered smoothed versions of the rearrangement map, and their results are not applicable in our setting. To the best of our knowledge, the only work that provides general results which can be used to obtain a Bahadur representation for the unsmoothed rearrangement map is the work by Chernozhukov et al (2010), hereafter CFG.…”

Section: Properties Of Distribution Functions With Respect To Lebesgumentioning

confidence: 96%

Smoothed Quantile Regression Processes for Binary Response Models

Volgushev

2019

Econom. Theory

Self Cite

View full text Add to dashboard Cite

In this paper, we consider binary response models with linear quantile restrictions. Considerably generalizing previous research on this topic, our analysis focuses on an infinite collection of quantile estimators. We derive a uniform linearisation for the properly standardized empirical quantile process and discover some surprising differences with the setting of continuously observed responses. Moreover, we show that considering quantile processes provides an effective way of estimating binary choice probabilities without restrictive assumptions on the form of the link function, heteroskedasticity or the need for high dimensional non-parametric smoothing necessary for approaches available so far. A uniform linear representation and results on asymptotic normality are provided, and the connection to rearrangements is discussed. * The idea of considering binary response quantile processes originated from discussions with Prof. Roger Koenker.

show abstract

Significance testing in quantile regression

Cited by 15 publications

References 30 publications

Modeling the UK electricity price distributions using quantile regression

Modeling the UK electricity price distributions using quantile regression

Using quantile regression to analyze the effect of renewables on EEX price formation

Smoothed Quantile Regression Processes for Binary Response Models

Contact Info

Product

Resources

About