I have a time series containing the daily close price for a stock and I would like to perform a 10 days forecast of the volatility.

I'm trying to follow this tutorial: https://talksonmarkets.files.wordpress.com/2012/09/time-series-analysis-with-arima-e28093-arch013.pdf

This is my data and its autocorrelation:

> closing_price$CloseDayPriceA
 [1] 0.0610 0.0605 0.0590 0.0575 0.0590 0.0585 0.0610 0.0590 0.0615 0.0610 0.0625
[12] 0.0605 0.0600 0.0650 0.0650 0.0710 0.0740 0.0730 0.0765 0.0770 0.0755 0.0765
[23] 0.0760 0.0775 0.0850 0.0955 0.0975 0.1155 0.1365 0.1200 0.1270 0.1230 0.1210
[34] 0.1040 0.1155 0.1355 0.1315 0.1310 0.1265 0.1250 0.1230 0.1245 0.1240 0.1235
[45] 0.1225 0.1185 0.1110 0.1130 0.1170 0.1150 0.1120 0.1135 0.1135 0.1085 0.1100
[56] 0.1090 0.1075 0.1050 0.1030 0.0960 0.0955 0.0970 0.0960 0.0915 0.0910
> a = acf(closing_price$CloseDayPriceA)
> a

Autocorrelations of series ‘closing_price$CloseDayPriceA’, by lag

     0      1      2      3      4      5      6      7      8      9     10 
 1.000  0.955  0.908  0.864  0.813  0.759  0.714  0.680  0.625  0.570  0.511 
    11     12     13     14     15     16     17     18 
 0.446  0.381  0.314  0.242  0.170  0.106  0.048 -0.017 

The data is clearly not stationary. I can make it stationary by differencing:

diff_price = diff(closing_price$CloseDayPriceA)

or alternatively by fitting an AR(1) model and taking the residuals:

arimaA = arima(closing_price$CloseDayPriceA, order = c(1, 0, 0))

Now the squared residuals are still autocorrelated as shown by their ACF. For this reason I apply a GARCH model:


    garchA=garchFit(formula = ~garch(2, 1), data = arimaA$residuals, trace = F)

My questions are:

  1. Does the procedure that I am following make sense?
  2. How can I make a 10 days forecast and compute the 10 days volatility?

EDIT: This should be the code:

A = closing_price$CloseDayPriceA
A.log = log(A)
log_rtn = diff(A.log)
A.garch = garchFit(formula = ~garch(1, 1), data = log_rtn, trace = F)
A.est = predict(A.garch, 30, plot=T)
  • $\begingroup$ Your added code looks alright to me. $\endgroup$ Commented Aug 21, 2016 at 11:03
  • $\begingroup$ I am still having some problems. 1) I can not get the volatility estimated in the predicted days (is this 0?, I would like a value from the code) 2) the plot is strange. It range over 40 days while it should be in 56 + 30 days $\endgroup$
    – Donbeo
    Commented Aug 21, 2016 at 11:07
  • $\begingroup$ From the help file: "returns a data frame with the foloowing columns: "meanForecast", meanError, and "standardDeviation". The number of records equals the number of forecasting steps n.ahead." $\endgroup$ Commented Aug 21, 2016 at 11:11
  • $\begingroup$ So standard deviation is $\hat\sigma$? I though it was related to the confidence interval of the predicted r $\endgroup$
    – Donbeo
    Commented Aug 21, 2016 at 11:13
  • $\begingroup$ Given the assumed family of distributions (e.g. normal), mean and variance may completely characterize it (but this does not work for all distributions). So when you have normality, $\hat\sigma$ and $\hat r$, you know all. $\endgroup$ Commented Aug 21, 2016 at 11:20

1 Answer 1


When modelling stock prices, it is quite common to transform the original prices $P_{t}$ to logarithmic returns $r_t:=\ln(P_{t})-\ln(P_{t-1})$ and then employ a GARCH model.

Logarithmic returns reflect price changes relative to price levels. If the price was fluctuating at around the same level, logarithmic returns would behave similarly to simple returns (just be scaled by roughly a constant); then not taking logarithms could be justified. But since the price is roughly a random walk, it does not stay around any fixed level for too long, and hence there is a difference between logarithmic and simple returns. Simple returns have an amplitude that changes with the price level, while logarithmic returns have a roughly constant amplitude. Therefore, modelling logarithmic returns is more convenient.

Given a GARCH model for (logarithmic) returns, you can predict the volatility iteratively:

$$ \begin{aligned} \hat\sigma_{t+1}^2 &= \hat\omega + \hat\alpha r_{t}^2 + \hat\beta \sigma_{t}^2 \\ \hat r_{t+1}^2 &= \hat\sigma_{t+1}^2 \\ \hat\sigma_{t+2}^2 &= \hat\omega + \hat\alpha r_{t+1}^2 + \hat\beta \hat\sigma_{t+1}^2 \\ \hat r_{t+2}^2 &= \hat\sigma_{t+2}^2 \\ &\dotsc \end{aligned} $$

In R, use function predict on a fitted object from garchFit, in your case, garchA; see p. 30-31 of the "fGarch" manual for details.

In the above I assumed you are not using an ARMA model for the conditional mean of returns. Predictability in the level of returns via ARMA would be a little naive to expect and would be a sign of market inefficiency. Without ARMA, the point forecast of $r_{t+h}=0$ for $h>0$.
However, if you decide to use ARMA, replace $r_t$ and $\hat r_t$ with $\hat\varepsilon_t$ in the GARCH formulas above, where $\hat\varepsilon_t$ is a residual from the ARMA model. Also, the point forecast is generally nonzero and is given by the ARMA model.

Also, if you use ARMA, estimate both ARMA and GARCH simultaneously (rather than first estimating ARMA and then fitting GARCH on its residuals). This will yield consistent and efficient parameter estimates. This can be done with the same garchFit function as you are using now.

  • $\begingroup$ If I understood correctly using r(t) = Log(P(t)) - Log(P(t-1)) instead of P(t) makes the series stationary. This is roughly the same effect that ARMA has. Said that I can model r(t) directly with garch. Once I get the prediction for r(T+1),..,r(T+10) how do I estimate the volatility? $\endgroup$
    – Donbeo
    Commented Aug 21, 2016 at 10:41
  • $\begingroup$ The iterative formulas above give the answer. predict(garchFit...) will do the job for you in R. Also, differencing instead of fitting an AR(1) model should be preferred. AR(1) does not behave well when the data has a unit root like stock prices typically do. $\endgroup$ Commented Aug 21, 2016 at 10:45
  • $\begingroup$ I'm getting strange results. My mean forecast is constant. My ask you to write some code? I want to be sure that I understood correctly $\endgroup$
    – Donbeo
    Commented Aug 21, 2016 at 10:49
  • $\begingroup$ I say that in my answer: the point forecast is zero. This is normal. If you were able to predict stock returns, you could be a millionaire. Regarding code, you only need to take logarithmic returns first and then use two functions: garchFit and then predict. That's all. $\endgroup$ Commented Aug 21, 2016 at 10:50
  • $\begingroup$ Ok but if the forecast is in general constant why is this methodology commonly used to predict stock market? (I'm not very interested in the prediction I want only to make sure that I am understanding the concept) $\endgroup$
    – Donbeo
    Commented Aug 21, 2016 at 10:56

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.