{"paper_id":"2309.13096","title":"Econometric Model Using Arbitrage Pricing Theory and Quantile Regression to Estimate the Risk Factors Driving Crude Oil Returns","authors":["Sarit Maitra","Vivek Mishra","Sukanya Kundu","Manav Chopra"],"paper_date":"2023-09-22","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2309.13096v2","page_url":"https://thequant.space/flowcharts/econometric-model-using-arbitrage-pricing-theory-and-quantil/","scores":{"empirical_rigor":6,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper implements Arbitrage Pricing Theory to identify underlying risk factors and applies Quantile Regression to estimate their effects across the distribution of WTI returns.","quote":"The two main contributions to this paper are: ● implementation of APT to identify the underlying risk factors driving ROC, ● application of QR to estimate the effect of these risk factors on different segments of the distribution of WTI returns.","summary":"This work adopts a novel approach to determine the risk and return of crude oil stocks by employing Arbitrage Pricing Theory (APT) and Quantile Regression (QR).The APT identifies the underlying risk factors likely to impact crude oil returns.Subsequently, QR estimates the relationship between the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Risk factor sensitivities (betas) are estimated using linear regression.","type":"model","stated":"explicit","quote":"The βs are estimated by using linear regression."},{"assumption":"Series are differenced to achieve stationarity.","type":"statistical","stated":"explicit","quote":"‘D’ prefix added to the relevant dataset after differencing to stabilize the series."},{"assumption":"Errors are heteroscedastic, assessed with Breusch‑Pagan test.","type":"statistical","stated":"explicit","quote":"Heteroscedasticity was assessed using the Breusch-Pagan test."},{"assumption":"No autocorrelation in residuals, tested with Durbin‑Watson and Breusch‑Godfrey tests.","type":"statistical","stated":"explicit","quote":"the Durbin-Watson (DW) test result of 1.98 indicates that there is no autocorrelation."},{"assumption":"Quantile regression is appropriate because return distributions are leptokurtic.","type":"statistical","stated":"explicit","quote":"Descriptive statistics show relevant distributions are leptokurtic, justifying quantile regression to detect herding bias in tails."},{"assumption":"The linear APT model assumes expected return is a linear function of factor exposures plus an idiosyncratic risk premium.","type":"model","stated":"explicit","quote":"The fundamental tenet of APT is that an asset's expected return is a linear function of how exposed it is to different risk factors plus a particular risk premium (idiosyncratic risk) that is unique to that asset."}]},"datasets":{"status":"available","items":[{"name":"FRED macroeconomic monthly data (5 years)","provider":"Federal Reserve Economic Data (FRED)","kind":"macro","access":"public","period":"five years of monthly data","universe":null,"quote":"The study used five years of monthly data from the FRED Economic Database to estimate betas, using yield data for crude oil, specifically the WTI crude oil spot price...","known_id":"fred"},{"name":"WTI crude oil spot price","provider":"FRED","kind":"market-prices","access":"public","period":"five years of monthly data","universe":null,"quote":"using yield data for crude oil, specifically the WTI crude oil spot price, to provide insights.","known_id":"fred"},{"name":"S&P 500 index (SPY)","provider":"FRED / market data","kind":"benchmark","access":"public","period":"five years of monthly data","universe":null,"quote":"The S&P 500 index, represented by the SPY, was chosen as the benchmark for the US equity market...","known_id":"fred"},{"name":"Macro variables (DGS3MO, DGS5, INDPRO, CPIAUCSL, UNRATE, M1SL, CCU, VIX, GPR)","provider":"FRED and external sources","kind":"macro","access":"public","period":"five years of monthly data","universe":null,"quote":"Table 2 presents selected variables, macroeconomic indicators, and other relevant data sources for the research question.","known_id":"fred"}],"known":[{"id":"fred","name":"FRED","provider":"Federal Reserve Bank of St. Louis","kind":"macro","access":"public","quote":"A. Data source and variables The study used five years of monthly data from the FRED Economic Database to estimate betas, using yield data for crude oil, specifically the WTI crude oil spot price, to provide insights.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"Market return (SP 500) has a negative effect on crude oil returns at the median and 90th quantiles, but not at lower or higher quantiles.","kind":"statistical","quote":"the market return (erSP) has a negative effect on crude oil returns at the median and 90th quantiles, but not at the lower or higher quantiles."},{"finding":"Industrial production, global economic policy uncertainty, and treasury yield curve have positive effects on crude oil returns across all quantiles.","kind":"statistical","quote":"Production (dPROD), global economic policy uncertainty (dGPE), and the treasury yield curve (dSPREAD) all have positive effects on crude oil returns across all quantiles."},{"finding":"Money supply (dMONEY) has a large negative effect on crude oil returns at the 25th quantile.","kind":"statistical","quote":"the money supply (dMONEY) has a large negative effect on crude oil returns at the 25th quantile."},{"finding":"Unemployment rate (dUNRATRE) shows a positive but not statistically significant effect on WTI returns at all quantiles.","kind":"statistical","quote":"dUNRATRE has a positive effect on WTI returns, but not significant at any of the quantiles (Qn 0.25, Qn 0.5, Qn 0.75, and Qn 0.9)."},{"finding":"Inflation (dINFLATION) has a considerable positive effect on crude oil returns at the 25th and 50th quantiles, but not at higher quantiles.","kind":"statistical","quote":"dINFLATION has a considerable positive effect on crude oil returns at the 25th and 50th quantiles, but not at higher quantiles."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":18,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T18:21:52Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}