Dooruj Rambaccussing

FORECASTING WITH SOCIAL MEDIA: EVIDENCE FROM TWEETS ON SOCCER MATCHES

Social media is now used as a forecasting tool by a variety of firms and agencies. But how useful are such data in forecasting outcomes? Can social media add any information to that produced by a prediction/betting market? We source 13.8 million posts from Twitter, and combine them with contemporaneous Betfair betting prices, to forecast the outcomes of English Premier League soccer matches as they unfold. Using a microblogging dictionary to analyze the content of Tweets, we find that the aggregate tone of Tweets contains significant information not in betting prices, particularly in the immediate aftermath of goals and red cards. (JEL G14, G17)

A test of the long memory hypothesis based on self-similarity

Abstract This paper develops a new test of true versus spurious long memory, based on log-periodogram estimation of the long memory parameter using skip-sampled data. A correction factor is derived to overcome the bias in this estimator due to aliasing. The procedure is designed to be used in the context of a conventional test of significance of the long memory parameter, and a composite test procedure is described that has the properties of known asymptotic size and consistency. The test is implemented using the bootstrap, with the distribution under the null hypothesis being approximated using a dependent-sample bootstrap technique to approximate short-run dependence following fractional differencing. The properties of the test are investigated in a set of Monte Carlo experiments. The procedure is illustrated by applications to exchange rate volatility and dividend growth series.

Fractional Integration of the Price-Dividend Ratio in a Present-Value Model of Stock Prices

We find evidence of antipersistence in returns and dividend growth, while the price-dividend ratio appears to exhibit nonstationary long memory, which seems contradictory in the present-value context. We reconcile these findings by showing that the aggregation of antipersistent expected dividend growth and expected returns gives the price-dividend ratio non-standard properties: a) asymptotically, the moving average coefficients decay hyperbolically at the same rate as the underlying antipersistent expected dividend growth and expected returns series; b) the spectral density at the zero frequency is finite and bounded away from zero as in short memory processes; c) close to zero frequency the spectral density is convex, which can imitate long memory in finite samples. Taking these features into account, we extend and estimate the present-value model by allowing for fractionally integrated processes in expected returns and dividend growth. We show this improves the models forecasting power in-sample and out-of-sample.

Fluctuations in the UK equity market: what drives stock returns?

ABSTRACT Present value parameters from a state-space model are estimated for the UK FT All-Share Index. The estimated parameters are used to construct a time series of expected future returns and expected future values of dividend growth, both of which are found to be time-varying with persistent components. Variations in the price-dividend ratio appear to be driven primarily by the variance in expected returns. A comparison with the findings from a present value-constrained vector autoregression model indicates that the latter forecasts future realized returns and dividend growth better than the series constructed using a state-space approach. Furthermore, when the model is estimated for monthly and quarterly data, expected dividend growth is found to be more persistent.