+ Reply to Thread
Results 1 to 3 of 3

Thread: Dickey-Fuller test for stationarity for log-log model

  1. #1
    Points: 32, Level: 1
    Level completed: 64%, Points required for next Level: 18

    Posts
    4
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Dickey-Fuller test for stationarity for log-log model




    Hi there, just discovered this thriving forum!

    Basically, I have a time-series data set of various prices, income, and quantity from which I want to regress a log-log demand function. I suspect that some of the variables trends over time. Therefore, if I want to perform a Dickey-Fuller test for stationarity, do I perfom this on the absolute values of the variables, or do I perform it on the logarithm of these variables?

  2. #2
    TS Contributor
    Points: 6,786, Level: 54
    Level completed: 18%, Points required for next Level: 164

    Location
    Sweden
    Posts
    524
    Thanks
    44
    Thanked 112 Times in 100 Posts

    Re: Dickey-Fuller test for stationarity for log-log model

    On the logarithms! If the processes all are of the same integration order (I(1) for example), you can test for cointegration and from there on build an error correction model. Otherwise I guess a VAR- or ADL-model is suitable.

  3. The Following User Says Thank You to Englund For This Useful Post:

    mocka (03-21-2013)

  4. #3
    Points: 32, Level: 1
    Level completed: 64%, Points required for next Level: 18

    Posts
    4
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: Dickey-Fuller test for stationarity for log-log model


    Thanks, that clarifies things! Do you suggest to build an error correction model, or would it be easier/better to adjust the given prices and income for inflation by using the time-series of a price index, then running the log-log regression on these adjusted values?

+ Reply to Thread

           




Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats