我們發現Eberhardt(2012)提出的Stata指令xtmg 再計算穩健平均估計量時，將所有係數間的共變異數回報為零。因為穩健平均估計量的之間的共變異數非常難以計算，我們使用拔靴法來進行估計。
在這篇文章中，我們提出了新的指令，xtmgboots，這指令可以將橫截面的重複抽樣方法運用在穩健平均估計量上，並快速幫助我們計算係數之間的共變異數。
我們的重複抽樣主要參考Kapetanios (2008)所提出的方法。透過進行假設檢定的模擬來呈現我們變異數的正確性，並將其運用在實證資料(Bond et al. (2010); Eberhardt and Presbitero (2015))上來呈現此方法的可行性。

We found that xtmg command in Stata proposed by Eberhardt (2012) reports the off-diagonal elements of the variance-covariance matrix of robust mean group estimators as zero. Since the computation of robust mean group estimators’ covariance should be very complex, we consider using pairwise bootstrap to estimate the distribution of robust mean group estimator. In this thesis, we introduce a new command, xtmgboots, which applies the cross-sectional resampling on the mean group estimator with robust regression.
Robust mean group estimators are estimated by xtmg command of Stata and resampling procedure mainly followed by Kapetanios (2008). We carry out a simulation to show the rejection probability base on pairwise variance is correct, and apply it to empirical panel data(Bond et al. (2010); Eberhardt and Presbitero (2015)) to show the feasibility of our procedure.

Markus Eberhardt. Estimating panel time-series models with heterogeneous slopes. The Stata Journal, 12(1):61–71, 2012.
George Kapetanios. A bootstrap procedure for panel data sets with many cross-sectional units. The Econometrics Journal, 11(2):377–395, 2008.
Steve Bond, Asli Leblebicioǧlu, and Fabio Schiantarelli. Capital accumulation and growth: a new look at the empirical evidence. Journal of Applied Econometrics, 25(7):1073–1099, 2010.
Markus Eberhardt and Andrea F Presbitero. Public debt and growth: Heterogeneity and non-linearity. Journal of international Economics, 97(1):45–58, 2015.
M Hashem Pesaran and Ron Smith. Estimating long-run relationships from dynamic heterogeneous panels. Journal of econometrics, 68(1):79–113, 1995.
Markus Eberhardt and Francis Teal. Structural change and cross-country growth empirics. The World Bank Economic Review, 27(2):229–271, 2013.
Markus Eberhardt, Christian Helmers, and Hubert Strauss. Do spillovers matter when estimating private returns to R&D? Review of Economics and Statistics, 95(2):436–448, 2013.
Patrick Schulte, Heinz Welsch, and Sascha Rexhäuser. ICT and the demand for energy: Evidence from OECD countries. Environmental and resource economics, 63(1):119–146, 2016.
Nahla Samargandi, Jan Fidrmuc, and Sugata Ghosh. Is the relationship between financial development and economic growth monotonic? evidence from a sample of middle-income countries. World development, 68:66–81, 2015.
Ruhul A Salim, Kamrul Hassan, and Sahar Shafiei. Renewable and non-renewable energy consumption and economic activities: Further evidence from OECD countries. Energy economics, 44:350–360, 2014.
Mariarosaria Comunale. Dutch disease, real effective exchange rate misalignments and their effect on GDP growth in EU. Journal of International Money and Finance, 73:350–370, 2017.
Sílvia Gonçalves and Benoit Perron. Bootstrapping factor-augmented regression models. Journal of Econometrics, 182(1):156–173, 2014.
Gonçalves Sílvia and Kaffo Maximilien. Bootstrap inference for linear dynamic panel data models with individual fixed effects. Journal of Econometrics, 186(2):407–426, 2015.
Antonio F Galvao and Gabriel Montes-Rojas. On bootstrap inference for quantile regression panel data: A monte carlo study. Econometrics, 3(3):654–666, 2015.
Cheng Hsiao, M Hashem Pesaran, A Kamil Tahmiscioglu, et al. Bayes estimation of short-run coefficients in dynamic panel data models, 1998.
Lawrence C Hamilton. How robust is robust regression? Stata Technical Bulletin, 1(2), 1992.
Vincenzo Verardi and Christophe Croux. Robust regression in Stata. The Stata Journal, 9(3):439–453, 2009.
M Hashem Pesaran. Estimation and inference in large heterogeneous panels with a multifactor error structure. Econometrica, 74(4):967–1012, 2006.