28 votes
Accepted

Why aren't econometric models used more in Quant Finance?

It's an interesting question. I particularly agree with the $\mathbb{Q}-\mathbb{P}$ dichotomy mentioned by many. I would add to the other answers that, come to think of it, the Black-Scholes ...
  • 14.1k
16 votes

Why aren't econometric models used more in Quant Finance?

I think you need to differentiate between Q-quants vs P-quants. The former might not use Econometrics, but P-quants use them a lot.
  • 4,247
11 votes

Why aren't econometric models used more in Quant Finance?

Traditional econometric (time series) models are of little or no value in forecasting market prices for purposes of "making money", i.e, generating excess return over a benchmark in an asset ...
  • 3,470
10 votes

Why should we expect geometric Brownian motion to model asset prices?

To provide a straight forward answer: It is not a good model. It never was, it never will be. Until we all do not come up with a better model that provides better modeling accuracy while it is equally ...
  • 14.1k
7 votes

Why aren't econometric models used more in Quant Finance?

My answer is very much in the spirit of Kiwiakos' answer. E.g. in this paper (where I am one of the coauthors) we use VMA (vector moving average) models (in the multivariate case) and AR models in ...
  • 13.3k
7 votes

Why aren't econometric models used more in Quant Finance?

Having thought about this I think the following reason is also important and wasn't mentioned so far: When you look at the inner working of this whole class of econometric models it all boils down to ...
  • 27k
7 votes
Accepted

Reconciling Two Claims About Volatility Under Fat Tails

I don't think the claim that "Lévy alpha-stable distributions are better descriptors of returns" is universally accepted. While Mandelbrot (and others before him) has correctly identified ...
  • 118
6 votes

Why should we expect geometric Brownian motion to model asset prices?

If at first you don't have a model at all, then geometric Brownian motion is not bad. As others before me said: log-returns are normally distributed in this model. This is debatable and there are ...
  • 13.3k
6 votes
Accepted

Modelling and forecasting mixed frequency financial data

MIDAS is useful when you have a low frequency series and you want to include high frequency data in the regression. So for instance, if you want to forecast quarterly GDP data and want to include ...
  • 5,311
6 votes
Accepted

Model to Predict the Change in IV of an Option

One approach that I have seen being used is to try to model the (joint) dynamics of the forward at-the-money volatility as well as its first one or two derivatives. The idea is to find a ...
5 votes

Using Financial Ratios to get credit rating or PD

This is what Moody's does to calculate default probabilities, but I don't believe they give a whole lot of detail on their exact methodology because they sell their models as software. I quickly found ...
5 votes

Why should we expect geometric Brownian motion to model asset prices?

Brownian motion - because it is simple, and results in intuitive closed form solutions, and it's not a terrible description of asset prices, especially when employed in high-frequency event time. ...
  • 1,122
5 votes
Accepted

Portfolio of sum of two Bachelier processes

Since $dW_A$ and $dW_B$ are already correlated as per the way you construct it, your portfolio being the sum of the two is already correlated. If you want it very explicitity written out, then you ...
  • 1,411
5 votes
Accepted

Model reference price of Limit order book

This reference price is also sometimes called intrinsic price. One of the simplest ways to improve it in regards to the mid-price (assuming you have the depth data) is the following: define a ...
  • 962
5 votes
Accepted

GARCH volatility modeling, squared returns, and convergence

Assume that your stationary time series (here a daily close-to-close log-returns' series) is modelled as follows $\forall t \in \mathcal{T}=\{1,...,N\}$ \begin{align} r_t &= E_{t-1}[r_t] + \...
  • 14.1k
5 votes
Accepted

how are financial data with sparse and asynchronous features imputed in predictive modeling?

There is large literature on MIDAS (mixed-frequency data sampling) models, the leading scholars being Eric Ghysels and Rossen Valkanov — google their research for references. However, the ...
5 votes
Accepted

Why do we not use copula for forward starting options?

One is exploring forward volatility of a price of a single asset (joint distributions from within a process), the other explores correlation of two prices at the same time for two different ...
  • 5,028
4 votes

What are the main differences between discrete and continuous time models when modeling asset price dynamics?

Continuous time has a so-called elegance, but it is rarely correct. Most Q-measure people rarely care about correctness anyway, since they usually don't root their models in statistics. With no ...
  • 1,018
4 votes

Why do we usually use normal distribution and not Laplace distribution to generate stochastic process?

It is very natural to think that why assumption of Normal distribution is made for stochastic process $W_t$ when other more appropriate and valid distribution is available specially for modelling ...
  • 2,168
4 votes

Why do we usually use normal distribution and not Laplace distribution to generate stochastic process?

If you're willing to drop the requirement to have continuous paths, or rather, if you're willing to relax it, it is possible to have a bigger class of stochastic processes called Lévy processes. The ...
  • 1,487
4 votes
Accepted

why calibrate volatility and fix the mean reversion

Fixing the mean reversion, and parameterizing the volatility as a step function or as a piecewise linear function, the volatility can be bootstrapped exactly to a set of vanilla options sorted by ...
4 votes

Pros and cons of mean equation equal to zero in a GARCH model

When you model log-returns $(Y_t)$ by $Y_t=\varepsilon_t$ where $\varepsilon_t|\mathcal{F}_{t-1}\sim N(0,\sigma^2_t)$ and a standard GARCH($p,q$) model with $$\sigma_t^2=\omega+\sum_{i=1}^p \alpha_{i}\...
  • 14k
4 votes
Accepted

Do different prices under different models admit arbitrage?

This phenomenon is not limited to interest rate derivatives. Any time a product is priced to model - be it equity derivatives, commodity derivatives, simple cash products whose price is not observable ...
4 votes
Accepted

Understanding out-of-sample performance metrics for Realized Volatility

You can compare the losses against each model and determine the "best" model to be the one with the smallest losses. In many cases for larger studies, the results might be ambiguous where ...
  • 3,903
3 votes

How to estimate parameters of geometric brownian motion with time-varying mean?

I would say Take log of first equation to get rid of dependence on $x_t$ Apply Kalman filter equations to estimate parameters I believe Conrad and Kaul (1988) J of Business do exactly what you ...
  • 4,247
3 votes
Accepted

Black-Litterman, how to choose the uncertainty in the views $\Omega$ for smooth transitions from prior to posterior

In practice, $\Omega$ (the covariance of the investor views) often 'inherits' the market covariance $\Sigma$. A convenient choice is $ \Omega = \left( 1/c -1 \right) P \Sigma P^T$ where $c$ is a ...
  • 876
3 votes
Accepted

Credit Rating or Probability of Default from Financial Ratios

Most of the papers concern CDS spreads which you will need to convert to a PD. Paper using country specific fundamentals: http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2517018 This paper uses ...
3 votes

Why should we expect geometric Brownian motion to model asset prices?

Basically, Black-Scholes is an "industry standard" formula. It is widely used by practitioners and usually augmented with extra specifications or intuition. It has a closed form solution, which is ...
  • 1,021
3 votes

How to tune Kalman filter's parameter?

If you have a linear/gaussian state space model and you're using a Kalman Filter, you can use maximum likelihood estimation or the EM algorithm. I personally prefer the former since you don't need to ...
  • 534
3 votes
Accepted

How popular is the Linear Gauss Markov (LGM) model?

In Andersen & Piterbarg's book, LGM is referred to as "The Hagan and Woodward Parameterization" and treated separately in 11.3.2.6. The fact that this practice-oriented book devotes a couple of ...

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