Non-Parametric Causality Detection: An Application to Social Media and Financial Data
arXiv:1601.03610 · doi:10.1016/j.physa.2017.04.101
Abstract
According to behavioral finance, stock market returns are influenced by emotional, social and psychological factors. Several recent works support this theory by providing evidence of correlation between stock market prices and collective sentiment indexes measured using social media data. However, a pure correlation analysis is not sufficient to prove that stock market returns are influenced by such emotional factors since both stock market prices and collective sentiment may be driven by a third unmeasured factor. Controlling for factors that could influence the study by applying multivariate regression models is challenging given the complexity of stock market data. False assumptions about the linearity or non-linearity of the model and inaccuracies on model specification may result in misleading conclusions. In this work, we propose a novel framework for causal inference that does not require any assumption about the statistical relationships among the variables of the study and can effectively control a large number of factors. We apply our method in order to estimate the causal impact that information posted in social media may have on stock market returns of four big companies. Our results indicate that social media data not only correlate with stock market returns but also influence them.
arXiv commentPhysica A: Statistical Mechanics and its Applications 2017
References in corpus (10)
- Matching Methods for Causal Inference: A Review and a Look Forward
- Twitter mood predicts the stock market
- Measuring Information Transfer
- Challenges of Big Data Analysis
- Granger causality and transfer entropy are equivalent for Gaussian variables
- Estimating high-dimensional directed acyclic graphs with the PC-algorithm
- Kernel-based Conditional Independence Test and Application in Causal Discovery
- Multivariate Granger Causality and Generalized Variance
- Learning high-dimensional directed acyclic graphs with latent and selection variables
- Predicting Financial Markets: Comparing Survey, News, Twitter and Search Engine Data