Tuesday, August 5, 2014

My Talk at the JSM

Tomorrow morning (Wednesday 6 August) I'll be presenting at the Joint Statistical Meetings in Boston.

The title for my talk is "Modelling Asymmetries in the Market for Gasoline in Western Canada", and it's based on some research that I have underway on this topic. 

The question that's addressed in this work is: "Are the upward and downward movements in retail gasoline prices, that follow increases and decreases in crude oil prices, symmetric?" There's a common perception that the "flow-through" from oil prices to gasoline prices is faster when prices are rising than when they are falling. I use ARDL models with an explicit allowance for possible asymmetry to test this hypothesis.

I'll have more to say on this when the work is completed, but in the meantime you can see some partial results by downloading the slides for my talk here.

© 2014, David E. Giles


  1. Dear Dr. Giles,

    Your effort and hard work through this blog is highly appreciated. In your slides of your talk (p. 12) you find Modified ECM to allow for possible asymmetry. Can you kindly explain how you did that in E-views? I’m running similar idea for the US market, but I don’t know how to do the asymmetry. Your help here is highly appreciated.
    Another important topic that I think many are interested in and waiting for your great explanation about is “smooth transition autoregression” (STAR) as testing for nonlinearity. I think the two famous tests are exponential smooth transition autoregression (ESTAR), and logistic STAR (LSTAR). I hope to see a post about such important issue.

    1. I've put an example of one of my EViews workfiles here:


  2. Hi Dr. Giles,
    Thank you for sharing your knowledge with us.I am interested in price asymmetry. I am wondering if you are planning to do a post about asymmetry?

    thank you

    1. Abdullah - hopefully, at some stage.

  3. Thank you for the effort made to help us. I only have one question: Do we multiply the negative sign with the values into the brackets (as it is the case with VAR model)?
    Example: Cointeq = LEMP - (-0.3033*LGPD + 0.3691*LPMI + 7.5969 )