Lo notes the determination of weights can be expressed as a more general classification
problem. Other techniques might be applied; in particular, machine-learning algorithms
such as the perceptron algorithm or support vector machines. He suggests further study
is required to find the best approach, but the standard linear regression approach does
perform well.
To establish that the final NEIs have empirical significance, Lo undertakes detailed
event study analysis. He uses the NEI series to define an event. An event is defined to
take place when the index exceeds a certain threshold (say 0.995). He then removes any
events that follow in less than one hour of another event. This guards against identifying
‘‘new’’ events which are actually based on old news. The behaviour of exchange rates
before and after these events is then studied. Two time-series are considered: the log
returns and the deseasonalized squared log returns. He then tests the null hypothesis
that the distribution of log returns/deseasonalized squared log returns are the same
before and after the events. He uses samples of one hour centred on the events.
We can visually assess the impact of events on the volatility of the EUR/USD
exchange rate.
(1) Figure 1.6 shows the averaged volatility event window. The pre-event (averaged)
volatility is shown by a bold line, and the post-event (averaged) volatility is shown
by a faint line. There is a peak at the centre where there is a significant increase in
volatility.
(2) Figure 1.7 shows the density function of pre-event samples and post-event samples
of deseasonalized squared log returns. The shift to the right indicates an upward
shift in volatility on average.
As well as visual inspection, statistical tests can be introduced to compare the pre-event
and post-event samples. At-test can be used to test equality of the means in the two
samples. Levene’s test can be used to determine whether there has been a change in
standard deviation. The ^2 goodness-of-fit test can be used to determine whether the two
samples are likely to have come from different distributions.Indices and FX implied volatility
Lo finds that the event studies confirm that the constructed event indices, on average,16 The Handbook of News Analytics in FinanceFigure 1.6.Pre- and post-event squared returns: shown as bold and faint lines.