Panel regression in Excel
This tutorial shows how to set up and interpret a panel regression using the XLSTAT-R engine in Excel.
What is Panel regression?
Panel regression is a modeling method adapted to panel data, also called longitudinal data or cross-sectional data. It is widely used in econometrics, where the behavior of statistical units (i.e. panel units) is followed across time. Those units can be firms, countries, states, etc. Panel regression allows controlling both for panel unit effect and for time effect when estimating regression coefficients.
The panel regression function developed in XLSTAT-R calls the plm function from the plm package in R (Yves Croissant).
Data set for launching a Panel Regression analysis in XLSTAT-R
The data correspond to Grunfeld’s investment data. References:
Baltagi, Badi H. (2001) Econometric Analysis of Panel Data, 2nd ed., John Wiley and Sons;
Baltagi, Badi H. (2013) Econometric Analysis of Panel Data, 5th ed., John Wiley and Sons;
Grunfeld, Yehuda (1958) The Determinants of Corporate Investment, Ph.D. thesis, Department of Economics, University of Chicago.
Kleiber, C./Zeileis, A. (2010) “The Grunfeld Data at 50”, German Economic Review, 11(4), pp. 404–417, http://dx.doi.org/10.1111/j.1468-0475.2010.00513.x;
The data contains 5 columns corresponding to:
Firm: Panel unit
Inv: Gross investment
Value of the firm
Capital: Stock of plant and equipment
The goal here is to model gross investment according to value and capital, while controlling for Firm (panel units) and year (time).
Setting up a Panel regression in XLSTAT-R
Open XLSTAT-R / plm / Panel regression(plm)
In the general tab, select the inv column under the dependent variables field.
Select the value & capital data under the Quantitative Explanatory Variables field.
Select the Year data under the Time field and Firm data under the Individuals field.
In the Options tab, choose the two-ways effect. This will build a model that controls both for time and panel units. Select a Random model to consider time and panel units effect as random. For fixed effects, you should select a Within model.
Click OK to launch computations.
Interpretation of an Panel regression output
The p-value associated to the F statistic shows that the model is significantly different from a null model.
The coefficients table shows that value and capital have a significant positive effect on Gross investment.
Was this article useful?