Posts Tagged ‘ GARCH ’

Variance targeting in garch estimation

September 24, 2012
By
Variance targeting in garch estimation

What is variance targeting in garch estimation?  And what is its effect? Previously Related posts are: A practical introduction to garch modeling Variability of garch estimates garch estimation on impossibly long series The last two of these show the variability of garch estimates on simulated series where we know the right answer.  In response to … Continue reading...

Read more »

garch estimation on impossibly long series

September 20, 2012
By
garch estimation on impossibly long series

The variability of garch estimates when the series has 100,000 returns. Experiment The post “Variability of garch estimates” showed estimates of 1000 series that were each 2000 observations long.  Here we do the same thing except that the series each have 100,000 observations. That would be four centuries of daily data.  It’s not presently feasible … Continue reading...

Read more »

Variability of garch estimates

September 17, 2012
By
Variability of garch estimates

Not exactly pin-point accuracy. Previously Two related posts are: A practical introduction to garch modeling garch and long tails Experiment 1000 simulated return series were generated.  The garch(1,1) parameters were alpha=.07, beta=.925, omega=.01.  The asymptotic variance for this model is 2.  The half-life is about 138 days. The simulated series used a Student’s t distribution … Continue reading...

Read more »

garch and long tails

August 27, 2012
By
garch and long tails

How much does garch shorten long tails? Previously Pertinent blog posts include: “A practical introduction to garch modeling” “The distribution of financial returns made simple” “Predictability of kurtosis and skewness in S&P constituents” Induced tails Part of the reason that the distributions of returns have long tails is because of volatility clustering.  It’s not really … Continue reading...

Read more »

ARMA Models for Trading

August 21, 2012
By
ARMA Models for Trading

In this tutorial I am going to share my R&D and trading experience using the well-known from statistics Autoregressive Moving Average Model (ARMA). There is a lot written about these models, however, I strongly recommend Introductory Time Series with R, which I find is a perfect combination between light theoretical background and practical implementations in

Read more »

A practical introduction to garch modeling

July 6, 2012
By
A practical introduction to garch modeling

We look at volatility clustering, and some aspects of modeling it with a univariate GARCH(1,1) model. Volatility clustering Volatility clustering — the phenomenon of there being periods of relative calm and periods of high volatility — is a seemingly universal attribute of market data.  There is no universally accepted explanation of it. GARCH (Generalized AutoRegressive … Continue reading...

Read more »

Cross sectional spread of stock returns

June 18, 2012
By
Cross sectional spread of stock returns

A look at a simplistic measure of stock-picking opportunity. Motivation The interquartile range (the spread of the middle half of the data) has recently been added to the market portrait plots.  Putting those numbers into historical context was the original impulse. However, this led to thinking about change in stock-picking opportunity over time. Data Daily … Continue reading...

Read more »

garch() uncertainty

May 16, 2012
By
garch() uncertainty

As part of an on-going paper with Kerrie Mengersen and Pierre Pudlo, we are using a GARCH(1,1) model as a target. Thus, the model is of the form which is a somehow puzzling object: the latent (variance) part is deterministic and can be reconstructed exactly given the series and the parameters. However, estimation is not

Read more »

AIB Stock Price, EGARCH-M, and rgarch

May 17, 2011
By
AIB Stock Price, EGARCH-M, and rgarch

This post examines conditional heteroskedasticity models in the context of daily stock price data for Allied Irish Banks (AIB), specifically how to test for conditional heteroskedasticity in a series, how to approach model specification and estimation when time-varying volatility is present, and how to forecast with these models; all of this is done in R,

Read more »