IDEAS home Printed from
   My bibliography  Save this paper

Forecasting Levels of log Variables in Vector Autoregressions


  • Gunnar Bardsen
  • Helmut Luetkepohl


Sometimes forecasts of the original variable are of interest although a variable appears in logarithms (logs) in a system of time series. In that case converting the forecast for the log of the variable to a naive forecast of the original variable by simply applying the exponential transformation is not optimal theoretically. A simple expression for the optimal forecast under normality assumptions is derived. Despite its theoretical advantages the optimal forecast is shown to be inferior to the naive forecast if specification and estimation uncertainty are taken into account. Hence, in practice using the exponential of the log forecast is preferable to using the optimal forecast.

Suggested Citation

  • Gunnar Bardsen & Helmut Luetkepohl, 2009. "Forecasting Levels of log Variables in Vector Autoregressions," Economics Working Papers ECO2009/24, European University Institute.
  • Handle: RePEc:eui:euiwps:eco2009/24

    Download full text from publisher

    File URL:
    File Function: main text
    Download Restriction: no

    Other versions of this item:

    References listed on IDEAS

    1. Helmut Lütkepohl & Fang Xu, 2012. "The role of the log transformation in forecasting economic variables," Empirical Economics, Springer, vol. 42(3), pages 619-638, June.
    2. Arino, Miguel A. & Franses, Philip Hans, 2000. "Forecasting the levels of vector autoregressive log-transformed time series," International Journal of Forecasting, Elsevier, vol. 16(1), pages 111-116.
    3. Johansen, Soren, 1995. "Likelihood-Based Inference in Cointegrated Vector Autoregressive Models," OUP Catalogue, Oxford University Press, number 9780198774501.
    4. Bénédicte Vidaillet & V. D'Estaintot & P. Abécassis, 2005. "Introduction," Post-Print hal-00287137, HAL.
    Full references (including those not matched with items on IDEAS)


    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.

    Cited by:

    1. Proietti, Tommaso & Lütkepohl, Helmut, 2013. "Does the Box–Cox transformation help in forecasting macroeconomic time series?," International Journal of Forecasting, Elsevier, vol. 29(1), pages 88-99.
    2. Matteo Luciani & David Veredas, 2012. "A model for vast panels of volatilities," Working Papers 1230, Banco de España;Working Papers Homepage.
    3. Pascual, Lorenzo & Ruiz, Esther & Fresoli, Diego, 2011. "Bootstrap forecast of multivariate VAR models without using the backward representation," DES - Working Papers. Statistics and Econometrics. WS ws113426, Universidad Carlos III de Madrid. Departamento de Estadística.
    4. Matteo Luciani & David Veredas, "undated". "A simple model for vast panels of volatilities," ULB Institutional Repository 2013/136239, ULB -- Universite Libre de Bruxelles.
    5. Mayr, Johannes & Ulbricht, Dirk, 2015. "Log versus level in VAR forecasting: 42 million empirical answers—Expect the unexpected," Economics Letters, Elsevier, vol. 126(C), pages 40-42.
    6. Nick Taylor, 2016. "Realised Variance Forecasting Under Box-Cox Transformations," Bristol Accounting and Finance Discussion Papers 16/4, School of Economics, Finance, and Management, University of Bristol, UK.
    7. Danny Lo, 2015. "Essays in Market Microstructure and Investor Trading," PhD Thesis, Finance Discipline Group, UTS Business School, University of Technology, Sydney, number 22.
    8. Fresoli, Diego & Ruiz, Esther & Pascual, Lorenzo, 2015. "Bootstrap multi-step forecasts of non-Gaussian VAR models," International Journal of Forecasting, Elsevier, vol. 31(3), pages 834-848.
    9. Lo, Danny K. & Hall, Anthony D., 2015. "Resiliency of the limit order book," Journal of Economic Dynamics and Control, Elsevier, vol. 61(C), pages 222-244.
    10. Luetkepohl Helmut & Xu Fang, 2011. "Forecasting Annual Inflation with Seasonal Monthly Data: Using Levels versus Logs of the Underlying Price Index," Journal of Time Series Econometrics, De Gruyter, vol. 3(1), pages 1-23, February.

    More about this item


    Vector autoregressive model; cointegration; forecast root mean square error;

    JEL classification:

    • C32 - Mathematical and Quantitative Methods - - Multiple or Simultaneous Equation Models; Multiple Variables - - - Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models; Diffusion Processes; State Space Models

    NEP fields

    This paper has been announced in the following NEP Reports:


    Access and download statistics


    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eui:euiwps:eco2009/24. See general information about how to correct material in RePEc.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Julia Valerio). General contact details of provider: .

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service hosted by the Research Division of the Federal Reserve Bank of St. Louis . RePEc uses bibliographic data supplied by the respective publishers.