 # Time Series Analysis - Random Walks!!

David Brice, CFA, has tried to use an AR(1) model to predict a given exchange rate. Brice has concluded the exchange rate follows a random walk without a drift. The current value of the exchange rate is 2.2. Under these conditions, which of the following would be least likely? A) The forecast for next period is 2.2. B) The residuals of the forecasting model are autocorrelated. C) The mean reverting level is undefined. D) The process is not covariance stationary.

Would this not be A? Random Walk should be Xt = Xt-1 + Error

C? pretty close to a flat out guess. i haven’t reviewed quant, especially time series, in a long time! in a random walk, isn’t the best predictor of xt, xt-1?

B

b for me

A) The forecast for next period is 2.2. Corret -> xt = xt-1 B) The residuals of the forecasting model are autocorrelated. NOT NECESSARY ----------- ANS = B?? C) The mean reverting level is undefined. Correct b1=1 MRL = undefined D) The process is not covariance stationary. Correct

barthezz you’re back!

lets rock this baby florinpop… good seeing you guys out here. A. Xt = Xt-1 + Error, and expected value is zero.

B is correct. However, if it was random walk WITH a drift, then A would be wrong.

My understanding is that both A) and D) are correct. An AR(1) model based on random walk is not covariance stationary

B

JoeyDVivre Wrote: ------------------------------------------------------- > B crap … following would be LEAST likely