I am running a panel fixed effects regression on 21 countries and 16 years. Its a secondary data taken from OECD website mostly. My model looks like this:

$$ \log{(GDP/Labor)}_{i} = \beta_0 +\beta_1 \log{(RnD)}_{i,t-1}+\beta_2 \log{(Human Capital)}_{i,t-1}+\beta_3 \log{(x_j*(RnD_j)}_{t-1}+\epsilon_t $$

Rndi = Research and Development expenditure of country i
Rndj = Research and Development expenditure of country j
HC = Index of Human Capital

1). I have following problems with this model:

1) all variables have strong trend and they are expected to be non-stationary however, Im-Pesaran-Shin and Levin-Lin-Chu tests are giving contradictory results about non-stationarity so I cannot conclude about non-stationarity. In your opinion, which test is better for panel regressions? Also, is there any test I can do for cointegration in stata for panel regressions in addition to Westlund test? if I dont find evidence for cointeration, do I first difference the data? I lose ALOT of information and everything becomes insignificant if I do that.

2) One of the primary goals of my paper is to test for moderation effects of human capital on knowledge spillovers and productivity nexus. Problem is that there is a serious multicollinearity problem. VIF goes as high as 1000! How can I test for moderating effects other than using interactions? Moreover, in some cases I also find strong multicollinearity between my key variables and it really makes everything significant at < 0.001 with R2 less than 50.

3) How important is it to include year dummies in regressions? I lose all significance of my variables and things become very bad in terms of signs as well for my core variables when I use year dummies.

I will be extremely grateful if you could please advice.

Thanks alot


  • $\begingroup$ Since there are so many forms of dynamic model, it would be useful to see the actual model equation. $\endgroup$
    – Alexis
    May 4, 2014 at 23:25
  • $\begingroup$ Thank you Alexis for the comment. Here is the equation log(GDP/Labor)i = f(Log Human Capitali, Log R&D Stocki, Log (R&Dj*importsj/total imports i), log(technology gap measured relative to US), year dummies, log(capital stock/labor) All these variables are lagged one year to partially reduce endogeniety problem. I am running fixed effects models right now. $\endgroup$
    – Ali-Jena
    May 5, 2014 at 9:03
  • 1
    $\begingroup$ Ali, please edit your question (edit button at lower left, between "share" and "flag") to include the formula. Also, try to use the MathJax markup (effectively LaTeX in-line math commands, bracketed by dollar signs... so $\log{(GDP/Labor)}_{i}$ gives $\log{(GDP/Labor)}_{i}$, etc.). $\endgroup$
    – Alexis
    May 5, 2014 at 14:43
  • $\begingroup$ Thank you Alexis. Its so nice to be here already that I am learning bits of LaTeX. I have been planning to learni this for long long time. $\endgroup$
    – Ali-Jena
    May 6, 2014 at 16:06

1 Answer 1


Question 1

If your outcome variable is integrated, you might consider using a single-equation generalized error correction model (GECM) as per Banerjee (1993) and De Boef (2001), as this model is agnostic to the stationarity of the predictors.

You might evaluate the stationarity of your outcome using:

$\log{(GDP/Labor)_{ti}} \sim \rho_{i}\log{(GDP/Labor)_{t-1i}} + \zeta_{ti} + \mu_{\rho_{i}}$,

$\zeta_{ti}$ measures all disturbances to $\log{(GDP/Labor)_{ti}}$ in each time $t$ (assumed distributed normal), and
$\mu_{\rho_{i}}$ measures state-level variation in $\log{(GDP/Labor)_{ti}}$ (assumed distributed normal).

If $|\rho_{i}| \approx 1$, then you've got nearly integrated data, and the GECM, which also has the attractive properties of disentangling long-run effects, from both instantaneous change short term effects and from lagged short term effects.

The general form of the single equation GECM is:

$\Delta y_{t} = \beta_{0} + \beta_{c}\left[y_{t-1}-\left(\mathbf{X}_{t-1}\right)\right] + \mathbf{B}_{\Delta\mathbf{X}}\Delta\mathbf{X}_{t} + \mathbf{B}_{\mathbf{X}}\mathbf{X}_{t-1} + \varepsilon$,

where: $\Delta$ is the first difference operator (e.g. $\Delta y_{t} = y_{t} - y_{t-1}$), and $\varepsilon$ may be decomposed into mixed effects (e.g. by including $\beta_{0i}$, for country-level random intercepts).

instantaneous short run effects are given by $\beta_{\Delta\mathbf{X}}$,
lagged short run effects are given by $\beta_{\mathbf{X}} - \beta_{c} - \beta_{\Delta\mathbf{X}}$, and
long run effects are given by $\left(\beta-{c}-\beta_{\mathbf{X}}\right)/\beta_{c}$.

This specification assumes a homogeneity of error correction processes. I haven't yet tried to derive a heterogeneous error correction specification...

In Stata you can perform Hadri's test for unit-root in panel data on the residuals of such a model, to check them for stationarity.

Question 2

I do not know that I can say much useful here.

Question 3

The time dummies can be included in the GECM model, and presumably other dynamic times series models, often they are used as indicators of, for example, policies going into effect. I have done something similar, but used (time-varying) proportions (rather than 0/1 indicator variables) to represent the portion of the time period during which a policy was in effect (e.g. some policies go into effect January 1, some July 1, some December 21, etc.). On the other hand: you don't have tons of data, so I suppose it depends how many new variables you are adding.


Banerjee, A., Dolado, J. J., Galbraith, J. W., and Hendry, D. F. (1993). Co-integration, error correction, and the econometric analysis of non-stationary data. Oxford University Press, USA.

De Boef, S. (2001). Modeling equilibrium relationships: Error correction models with strongly autoregressive data. Political Analysis, 9(1):78–94.

  • $\begingroup$ thank you very much Alexis. I will thoroughly read Benerjee GECM method and try to apply it in my case. I had a presentation today on the same paper. SOmeone suggested Hausman-Taylor method and Arellano-Bond for dynamic modelling. Do you know if this works if I want to include more than one lag in my regression? Someone also suggested multi equation VAR modelling to account for potential endogeneity problem. Do you think any of these will work? Ofcourse first I am going to study what you have suggested but I am just trying to put all possible choices on the table. $\endgroup$
    – Ali-Jena
    May 7, 2014 at 19:23
  • $\begingroup$ Ali-Jena, I am largely ignorant of those methods. I suggested the GECM because there were so many similarities in your description of your data and problem to an analysis in which I found the GECM to be useful. That said, there are differences also, so you mileage may vary. :) $\endgroup$
    – Alexis
    May 8, 2014 at 1:39
  • $\begingroup$ thank zou Alexis.. sems like i have a very large set of literature to read. Atleast i know the direction now. Thank you for all the help. I will come back here if I get stuck somewhere. $\endgroup$
    – Ali-Jena
    May 9, 2014 at 12:36

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.