# Tag Info

7

The only "indicators" that I believe add value in academic research are time series smoothing functions. ( I don't call them indicators because they are all lagging thus do not indicate anything into the future). There is clear empirical evidence and a number of academic papers have been published that show that none of the common indicators (common defined ...

6

I think the answer to your question is very dependent on the respective indicators. It can be argued for example that moving averages not only smooth out time series but because they are a shifted version of the original series signals on crossovers make use of the momentum factor. In general you might want to check out the book Evidence Based Technical ...

6

Concur with Thomas for most part, though I would recommend you to sign up for a trial with Dow Jones Newswire. I like the API and app that Newsware ( http://www.newsware.com/) makes available. It is not suitable for hft but I use it in order to stay informed and look up often used mnemonics. I think they have a pretty capable API and I remember they offer ...

4

It would be relatively trivial to implement a web scraper for any website you were interested in gathering news from - see Beautiful Soup for Python. This would allow you to gather and analyse news data from multiple sources in a way that may be more robust than relying on a single service. For example, you could screen scrape a certain website for the news ...

4

You are right. In the CIR++, $\alpha$ parameter is absorbed into $\phi$. With the CIR++, $\phi(t)$ will allow you to have to have negative rates. You will calibrate your $\phi$ to fit the discount factors. The shifted idea is the one used to handle negative rates problem in caplet, swaption...

4

I know two papers explaining how to calibrate this kind of models, and one of them explain the impact of the quality of the fit on a pricing model: Aït-Sahalia, Y. (2002, January). Maximum likelihood estimation of discretely sampled diffusions: A closed-form approximation approach. Econometrica 70 (1), 223-262. Azencott, R., Y. Gadhyan, and R. Glowinski (...

3

News is not free, and hence you won't find a company offering machine readable news services for free. My best suggestion is to ask a machine readable news company for a day's worth of historical data. Even that might not work, however, as they won't waste their time if they don't think you're going to buy their service.

3

The hypothesis $H_0: β_1=β_2=\dots =β_{k−1}=0$ is normally tested by the $F$-test for the regression. You are carrying out 3 independent tests of your coefficients (Do you also have a constant in the regression or is the constant one of your three variables?) If you do three independent tests at a 5% level you have a probability of over 14% of finding one ...

2

These are independent variables so the hypothesis applies to each parameter independently.

2

Typically "average" lines are used to get rid of noise in the original data. It seems pretty logical to smooth intra week fluctuations when working with a year of data.

2

If you are an academic interested in this field I would suggest contacting Sirca. Thomson Reuters is active with academics through their partnership with Sirca in Australia (www.sirca.org.au). Sirca has other machine readable text products available.

2

Just a quick fix. Looking at the wikipedia entry of EGARCH: $g(\zeta_t)$ (the unit-scale random variable) seems correct - as you say.

2

I would argue that there is some path-dependency involved. The BS model is considered the big breakthrough and it presented the world with some kind of tractable toy model. After that people saw that you had to adjust the model to account for all kinds of stylized facts (e.g. non-constant volatility for different strikes, over time and so on). Yet finite ...

2

One does not estimate the local volatility at a given $T$ and $K$. Instead, Dupire's formula actually gives $\sigma(T,K)$ for all $T$ and $K$. $$\sigma^2(t_0,S_0;T,K)= \frac{\frac{\partial C}{\partial T} + (r - q)K \frac{\partial C}{\partial K} + qC}{\frac{1}{2} K^2 \frac{\partial^2C}{\partial K^2}}$$ where $C(t_0,S_0;T,K)$ are the call prices for ...

2

The typical approach is: you only use option data from the last day. Furthermore, you only include those points that are liquid enough. One approach to this is to weigh the modelling error of an option by its bid-ask spread and vega. Using data from multiple days is not a good approach, because you might have options with the same strike but different ...

2

The Heston model is represented by the bivariate system of stochastic differential equations (SDE) \begin{align} & d{{S}_{t}}=rS_tdt+{\sqrt\upsilon_t} d{{W}_{1}}(t) \\ & d{{\upsilon}_{t}}=\kappa(\theta-\upsilon_t) dt+\sigma{\sqrt\upsilon_t}d{{W}_{2}}(t) \\ \end{align} The most popular way to estimate the parameters of the Heston model is with loss ...

1

In the industry the model I have used is the 'shifted Sabr' where: $dx(t) = \sigma(t) [x(t)-c]^\beta dW(t)$ $d\sigma(t) = \alpha \sigma(t) dZ(t)$ $dW(t)\ dZ(t) = \rho\ dt$ This allows for rates down to the parameter $c$. If you set, for example, $c=-200bp$ then you can have negative rates. You can define a CIR variant in an analogous way. I have used ...

1

t.f thanks for the answer. You say that yields can't go negative in CIR. But if r0 (say 1d rate) is negative (which is the case in many govies today), I guess yields can be negative? And you will in this case be able to actually calibrate a CIR, which gives negative yields in the short end? My question might seem a bid odd, but I was just wondering? But ...

1

As you say, in the CIR model with usual assumptions the short rate cannot go negative. This means that yields in the model are always poaitive, so it will not be a good fit to a yield curve which is negative for short maturities. If you really do want the CIR model, there is a weird extension you could try:  dr_t = \kappa (\theta - r_t) dt + \sigma \...

1

I would also say that the pricing of some exotic products require to compute expectations of functions of the random variable at consideration, and these functions may grow more than linearly : you need finite moments in order for the prices of these exotic derivatives to be bounded.

1

On a pure technical aspect, a model does not need to have a finite variance. In the context of option pricing, what you need it a way to replicate the behaviour of the stock price. Once you have it you need to find a corresponding risk-neutral measure. There you will have the first difficulty, with infinite variance, the corresponding hedging strategy is ...

1

To get it out the way: you cannot ask 'what model is better' without a reference to what its use is. Do you want to test for the mean or the AR parameter to trade it? Do you want to calculate VaR? Do you want to forecast volatility over one period? Or over 1000 periods? Or higher moments? Do you want to simulate volatility over one period? Or longer? For ...

Only top voted, non community-wiki answers of a minimum length are eligible