Skip to main content
Log in

Testing for cross-sectional dependence in a panel factor model using the wild bootstrap \(F\) test

  • Regular Article
  • Published:
Statistical Papers Aims and scope Submit manuscript

Abstract

This paper considers testing for cross-sectional dependence in a panel factor model. Based on the model considered by Bai (Econometrica 71: 135–171, 2003), we investigate the use of a simple \(F\) test for testing for cross-sectional dependence when the factor may be known or unknown. The limiting distributions of these \(F\) test statistics are derived when the cross-sectional dimension and the time-series dimension are both large. The main contribution of this paper is to propose a wild bootstrap \(F\) test which is shown to be consistent and which performs well in Monte Carlo simulations especially when the factor is unknown.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Notes

  1. These common shocks could be macroeconomic, political, environmental, health, and/or sociological shocks in nature to mention a few, see Andrews (2005).

  2. Bai (2009) and Bai et al. (2009) allow for weak cross-sectional dependence among the idiosyncratic error terms. Under these assumptions, even when there is no common factor, there may still be cross-sectional dependence due to the remainder disturbance term.

  3. In a different context, Schott (2005) proposes a Lagrange multiplier type test to test the independence of random variables when both the dimension and sample are large.

  4. To keep things simple, the number of factors is assumed to be one. The information criteria approach of Bai and Ng (2002) can be used as an alternative method for testing for cross-sectional dependence by testing whether the number of factors is zero or larger than zero. This method is also useful when the number of factors is unknown.

  5. In the statistics literature, Boos and Brownie (1995) and Akritas and Arnold (2000) consider the asymptotic distribution of the ANOVA \(F\) statistic for this case where \(n\) and \(T\) denote the number of treatments and replications per treatment, respectively. Under their settings, it is shown that

    $$\begin{aligned} \sqrt{n}\left( F_{n}-1\right) \overset{d}{\rightarrow }N\left( 0,\frac{2T}{ T-1}\right) \end{aligned}$$

    where \(F_{n}\) is the \(F\) statistic under their setting as \(n\rightarrow \infty \) with fixed \(T\). They also show that the asymptotics above hold in a two-way fixed effects model as well. Extending these results to the interaction effects model, Bathke (2004) shows that the limiting normal distribution can be still achievable with the \(F\) statistic centered at 1. Interestingly, in the econometrics literature, Orme and Yamagata (2006) consider an \(F\) test for individual effects in a panel data model and derive similar limiting distributions.

  6. Alternatively, one may want to use the following bootstrap DGP suggested by Mammen (1993b) especially when the distribution of the error terms is sufficiently asymmetric.

    $$\begin{aligned} \varepsilon _{it}^{*}=\left\{ \begin{array}{l} \frac{-\left( \sqrt{5}-1\right) }{2} \text{ with} \text{ probability} p=\frac{\left( \sqrt{5}+1\right) }{2\sqrt{5}} \\ \frac{\left( \sqrt{5}+1\right) }{2} \text{ with} \text{ probability} 1-p \end{array} .\right. \end{aligned}$$

    However, in their simulations, Davidson and Flachaire (2008) show that the version we adopt here performs at least as good as this version even when the disturbances are asymmetric.

  7. \(E\left( \varepsilon _{it}^{*3}\right) =1\) is often added for the bootstrap error literature.

References

  • Andrews DWK (2005) Cross-section regression with common shocks. Econometrica 73:1551–1585

    Article  MathSciNet  MATH  Google Scholar 

  • Akritas M, Arnold S (2000) Asymptotics for analysis of variance when the number of levels is large. J Am Stat Assoc 449:212–226

    Article  MathSciNet  Google Scholar 

  • Bai J (2003) Inferential theory for factor models of large dimensions. Econometrica 71:135–171

    Article  MathSciNet  MATH  Google Scholar 

  • Bai J (2009) Panel data models with interactive fixed effects. Econometrica 77:1229–1279

    Article  MathSciNet  MATH  Google Scholar 

  • Bai J, Kao C, Ng S (2009) Panel cointegration with global stochastic trends. J Econom 149:82–99

    Article  MathSciNet  Google Scholar 

  • Bai J, Ng S (2002) Determining the number of factors in approximate factor models. Econometrica 70: 191–221

    Google Scholar 

  • Bathke A (2004) The ANOVA F test can still be used in some balanced designs with unequal variances and nonnormal data. J Stat Plan Inference 126:413–422

    Article  MathSciNet  MATH  Google Scholar 

  • Boos DD, Brownie C (1995) ANOVA and rank tests when the number of treatments is large. Stat Probab Lett 23:183–191

    Article  MathSciNet  MATH  Google Scholar 

  • Davidson R, Flachaire E (2008) Wild bootstrap, tamed at last. J Econom 146:162–169

    Article  MathSciNet  Google Scholar 

  • Gonçalves S, Perron B (2010) Bootstrapping factor-augmented regression models. Université de Montréal, Working Paper

  • Johnson NL, Kotz S, Balakrishinan N (1995) Distributions in statistics: continuous univariate distributions. Wiley, New York

    Google Scholar 

  • Krämer W (1989) On the robustness of the F-test to autocorrelation among disturbances. Econ Lett 30:37–40

    Article  Google Scholar 

  • Krämer W, Michels S (1997) Autocorrelation- and heteroskedasticity-consistent T-values with trending data. J Econom 76:141–147

    Article  MATH  Google Scholar 

  • Liu RY (1988) Bootstrap procedures under some non-IID models. Ann Stat 16:1696–1708

    Article  MATH  Google Scholar 

  • Mammen E (1993a) When does bootstrap work?. Asymptotic results and simulations. Springer, New York

    Google Scholar 

  • Mammen E (1993b) Bootstrap and wild bootstrap for high dimensional linear models. Ann Stat 21:255–285

    Article  MathSciNet  MATH  Google Scholar 

  • Orme CD, Yamagata T (2006) The asymptotic distribution of the F-test statistic for individual effects. Econom J 9:404–422

    Article  MathSciNet  MATH  Google Scholar 

  • Schott JR (2005) Testing for complete independence in high dimensions. Biometrika 92:951–956

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Badi H. Baltagi.

Additional information

This paper is dedicated to Walter Krämer for his important contributions to statistics and econometrics.

Appendices

Appendix

A Proof of Theorem 1

Proof

Now we have

$$\begin{aligned} F_{\lambda }=\frac{R_{\lambda }}{\widehat{\sigma }^{2}} \end{aligned}$$

where \(R_{\lambda }=\frac{\left( RRSS-URSS\right) }{n}\) and \(\widehat{\sigma }^{2}=\frac{URSS}{\left( nT-n\right) }\) using a set up which is similar to Orme and Yamagata (2006). Rearranging the terms, we have

$$\begin{aligned} \sqrt{n}\left( F_{\lambda }-1\right) =\frac{1}{\widehat{\sigma }^{2}}\sqrt{n} \left( R_{\lambda }-\widehat{\sigma }^{2}\right). \end{aligned}$$

Expanding the equations, we have

$$\begin{aligned} R_{\lambda }-\widehat{\sigma }^{2}&= \frac{\left( RRSS-URSS\right) }{n}-\frac{URSS}{\left( nT-n\right) } \\&= \frac{1}{n}\sum _{i=1}^{n}\sum _{t=1}^{T}\left[ -\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) ^{2}F_{t}^{2}+2\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) u_{it}F_{t}\right] \\&-\frac{1}{n\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}\left[ u_{it}^{2}+\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) ^{2}F_{t}^{2}-2\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) u_{it}F_{t}\right] \\&= -\frac{1}{nT}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \sqrt{T}\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) \right\} ^{2}F_{t}^{2} \\&+\frac{2}{n\sqrt{T}}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \sqrt{T}\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) \right\} u_{it}F_{t} \\&-\frac{1}{n\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}u_{it}^{2}-\frac{1}{nT(T-1)}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \sqrt{T}\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) \right\} ^{2}F_{t}^{2} \\&+\frac{2}{n\sqrt{T}\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \sqrt{T}\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) \right\} u_{it}F_{t} \\&= I+II+III+IV+V. \end{aligned}$$

Consider \(I\).

$$\begin{aligned} I&= -\frac{1}{n}\sum _{i=1}^{n}\left[ \sqrt{T}\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) \right] ^{2}\left[ \frac{1}{T}\sum _{t=1}^{T}F_{t}^{2}\right] \\&= -\frac{1}{n}\sum _{i=1}^{n}\left[ \frac{1}{\sqrt{T}}\sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}\left[ \frac{1}{T}\sum _{t=1}^{T}F_{t}^{2}\right] ^{-1}. \end{aligned}$$

For \({ II}\),

$$\begin{aligned} II&= \frac{2}{n\sqrt{T}}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \sqrt{T}\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) \right\} u_{it}F_{t} \\&= \frac{2}{n}\sum _{i=1}^{n}\left[ \frac{1}{\sqrt{T}} \sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}\left[ \frac{1}{T} \sum _{t=1}^{T}F_{t}^{2}\right] ^{-1}. \end{aligned}$$

Then

$$\begin{aligned} I+II=\frac{1}{n}\sum _{i=1}^{n}\left[ \frac{1}{\sqrt{T}} \sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}\left[ \frac{1}{T} \sum _{t=1}^{T}F_{t}^{2}\right] ^{-1}=O_{p}\left( 1\right). \end{aligned}$$

For \(III\),

$$\begin{aligned} III=-\frac{1}{n}\sum _{i=1}^{n}\frac{1}{T-1}\sum _{t=1}^{T}u_{it}^{2}=O_{p} \left( 1\right). \end{aligned}$$

For \(IV\) and \(V\), as already shown above,

$$\begin{aligned} IV=-\frac{1}{T-1}\frac{1}{n}\sum _{i=1}^{n}\left\{ \sqrt{T}\left( \widetilde{ \lambda }_{i}-\lambda _{i}\right) \right\} ^{2}\left( \frac{1}{T} \sum _{t=1}^{T}F_{t}^{2}\right) =O_{p}\left( \frac{1}{T}\right) \end{aligned}$$

and

$$\begin{aligned} V&= \frac{2}{n\sqrt{T}\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \sqrt{T}\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) \right\} u_{it}F_{t} \\&= \frac{1}{T-1}\frac{2}{n}\sum _{i=1}^{n}\left[ \frac{1}{\sqrt{T}} \sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}\left[ \frac{1}{T} \sum _{t=1}^{T}F_{t}^{2}\right] ^{-1} \\&= O_{p}\left( \frac{1}{T}\right) . \end{aligned}$$

After rearranging all the terms, one obtains

$$\begin{aligned} R_{\lambda }-\widehat{\sigma }^{2}&= \frac{1}{n}\sum _{i=1}^{n}\left[ \frac{1 }{\sqrt{T}}\sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}\left[ \frac{1}{T} \sum _{t=1}^{T}F_{t}^{2}\right] ^{-1} \\&-\frac{1}{n}\sum _{i=1}^{n}\frac{1}{T}\sum _{t=1}^{T}u_{it}^{2}+O_{p}\left( \frac{1}{T}\right) . \end{aligned}$$

It is easy to see that

$$\begin{aligned} \sqrt{n}\left( R_{\lambda }-\widehat{\sigma }^{2}\right) =\frac{1}{\sqrt{n}} \sum _{i=1}^{n}\left( \left( \frac{1}{\sqrt{T}}\sum _{t=1}^{T}u_{it}F_{t} \right) ^{2}\phi _{F}^{-1}-\sigma ^{2}\right) +O_{p}\left( \frac{\sqrt{n}}{T} \right) . \end{aligned}$$

Now we obtain

$$\begin{aligned} \frac{1}{\sqrt{n}}\sum _{i=1}^{n}\left( \left( \frac{1}{\sqrt{T}} \sum _{t=1}^{T}u_{it}F_{t}\right) ^{2}\phi _{F}^{-1}-\sigma ^{2}\right) \overset{d}{\rightarrow }N\left( 0,2\sigma ^{4}\right) \end{aligned}$$

by Assumption 4.

Finally,

$$\begin{aligned} \sqrt{n}\left( F_{\lambda }-1\right) =\frac{1}{\widehat{\sigma }^{2}}\sqrt{n} \left( R_{\lambda }-\widehat{\sigma }^{2}\right) \overset{d}{\rightarrow } N(0,2) \end{aligned}$$

as \(\left( n,T\right) \rightarrow \infty \) if \(\frac{\sqrt{n}}{T}\rightarrow 0.\) Note that \(\frac{T}{n}\rightarrow c\) with \(0<c<\infty \) implies that \( \frac{\sqrt{n}}{T}=\frac{n}{T}\frac{1}{\sqrt{n}}\rightarrow 0.\)

B Proof of Theorem 2

Proof

First we consider

$$\begin{aligned} \frac{URSS}{\left( nT-n\right) }&= \frac{1}{n\left( T-1\right) } \sum _{i=1}^{n}\sum _{t=1}^{T}\left( y_{it}-\widehat{\lambda }_{i}\widehat{F} _{t}\right) ^{2} \\&= \frac{1}{n\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}\left[ u_{it}-\left( \widehat{\lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) \right] ^{2} \\&= \frac{1}{n\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}u_{it}^{2}+\frac{ 1}{n\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}\left( \widehat{\lambda } _{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) ^{2} \\&-\frac{2}{n\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}\left( \widehat{ \lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) u_{it} \\&= I+II+III. \end{aligned}$$

Consider \(I\). One can easily verify that

$$\begin{aligned} I=\frac{1}{n\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}u_{it}^{2}=\sigma ^{2}+o_{p}\left( 1\right) \end{aligned}$$

as \(\left( n,T\right) \rightarrow \infty \). Note from (Bai (2003), p. 166), that \(\widehat{\lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\) can be expanded as

$$\begin{aligned} \widehat{\lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}&= \frac{1}{\sqrt{n}} \lambda _{i}\left( \frac{\sum _{i=1}^{n}\lambda _{i}^{2}}{n}\right) ^{-1} \frac{1}{\sqrt{n}}\sum _{k=1}^{n}\lambda _{k}u_{kt} \\&+\frac{1}{\sqrt{T}}F_{t}\left( \frac{\sum _{t=1}^{T}F_{t}^{2}}{T}\right) ^{-1}\frac{1}{\sqrt{T}}\sum _{s=1}^{T}F_{s}u_{is}+O_{p}\left( \frac{1}{\delta _{nt}^{2}}\right) \\&= \phi _{\lambda }^{-1}\frac{1}{\sqrt{n}}\lambda _{i}\frac{1}{\sqrt{n}} \sum _{k=1}^{n}\lambda _{k}u_{kt}+\phi _{F}^{-1}\frac{1}{\sqrt{T}}F_{t}\frac{1 }{\sqrt{T}}\sum _{s=1}^{T}F_{s}u_{is}+O_{p}\left( \frac{1}{\delta _{nt}^{2}} \right). \end{aligned}$$

For \(II\).

$$\begin{aligned} II&= \frac{1}{n\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}\left( \widehat{\lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) ^{2}\!=\!\frac{1}{nT}\sum _{i=1}^{n}\sum _{t=1}^{T}\left( \phi _{\lambda }^{-1}\frac{ 1}{\sqrt{n}}\lambda _{i}\left( \frac{1}{\sqrt{n}}\sum _{k=1}^{n}\lambda _{k}u_{kt}\right) \right.\\&\left.+\,\phi _{F}^{-1}\frac{1}{\sqrt{T}}F_{t}\left( \frac{1}{ \sqrt{T}}\sum _{s=1}^{T}F_{s}u_{is}\right) \right) ^{2}+o_{p}\left( 1\right) \\&= \phi _{\lambda }^{-2}\frac{1}{nT}\sum _{i=1}^{n}\sum _{t=1}^{T}\frac{1}{n} \lambda _{i}^{2}\left( \frac{1}{\sqrt{n}}\sum _{k=1}^{n}\lambda _{k}u_{kt}\right) ^{2}\\&+\,\phi _{F}^{-2}\frac{1}{nT}\sum _{i=1}^{n}\sum _{t=1}^{T} \frac{1}{T}F_{t}^{2}\left( \frac{1}{\sqrt{T}}\sum _{s=1}^{T}F_{s}u_{is} \right) ^{2} \\&+\,2\phi _{\lambda }^{-1}\phi _{F}^{-1}\frac{1}{nT}\sum _{i=1}^{n} \sum _{t=1}^{T}\frac{1}{\sqrt{nT}}\lambda _{i}F_{t}\left( \frac{1}{\sqrt{n}} \sum _{k=1}^{n}\lambda _{k}u_{kt}\right) \left( \frac{1}{\sqrt{T}} \sum _{s=1}^{T}F_{s}u_{is}\right) \!+\!o_{p}\left( 1\right)\\&= II_{a}+II_{b}+II_{c}+o_{p}\left( 1\right) . \end{aligned}$$

Consider \(II_{a}.\)

$$\begin{aligned} \phi _{\lambda }^{-2}\frac{1}{nT}\sum _{i=1}^{n}\sum _{t=1}^{T}\frac{1}{n} \lambda _{i}^{2}\left( \frac{1}{\sqrt{n}}\sum _{k=1}^{n}\lambda _{k}u_{kt}\right) ^{2}&= \phi _{\lambda }^{-1}\frac{1}{nT}\sum _{t=1}^{T}\left( \frac{1}{\sqrt{n}} \sum _{k=1}^{n}\lambda _{k}u_{kt}\right) ^{2}+o_{p}\left( 1\right) \\&= \phi _{\lambda }^{-1}\frac{1}{n}\frac{1}{nT}\sum _{t=1}^{T}\sum _{i=1}^{n} \sum _{k=1}^{n}\lambda _{i}\lambda _{k}u_{it}u_{kt}+o_{p}\left( 1\right) \\&= \frac{1}{n}\phi _{\lambda }^{-1}\phi _{\lambda }\sigma ^{2}+o_{p}\left( 1\right) \\&= O_{p}\left( \frac{1}{n}\right) . \end{aligned}$$

Similarly,

$$\begin{aligned} II_{b}=O_{p}\left( \frac{1}{T}\right) . \end{aligned}$$

Consider \(II_{c}.\)

$$\begin{aligned} II_{c}&= 2\phi _{\lambda }^{-1}\phi _{F}^{-1}\frac{1}{nT}\left[ \frac{1}{ \sqrt{n}}\sum _{i=1}^{n}\left( \lambda _{i}\left( \frac{1}{\sqrt{T}} \sum _{s=1}^{T}F_{s}u_{is}\right) \right) \right]\\&\left[ \frac{1}{\sqrt{T}} \sum _{t=1}^{T}\left( F_{t}\left( \frac{1}{\sqrt{n}}\sum _{k=1}^{n}\lambda _{k}u_{kt}\right) \right) \right] \\&= O_{p}\left( \frac{1}{nT}\right) . \end{aligned}$$

Hence

$$\begin{aligned} II=O_{p}\left( \frac{1}{\delta _{nt}^{2}}\right) +o_{p}\left( 1\right) . \end{aligned}$$

Consider \(III\).

$$\begin{aligned} III&= \frac{2}{n\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}\left( \widehat{\lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) u_{it} \\&\!= \frac{2}{nT}\sum _{i=1}^{n}\sum _{t=1}^{T}\left( \phi _{\lambda }^{-1}\frac{ 1}{\sqrt{n}}\lambda _{i}\frac{1}{\sqrt{n}}\sum _{k=1}^{n}\lambda _{k}u_{kt}\!+\!\phi _{F}^{-1}\frac{1}{\sqrt{T}}F_{t}\frac{1}{\sqrt{T}} \sum _{s=1}^{T}F_{s}u_{is}\right) u_{it}\!+\!o_{p}\left( 1\right) \\&= O_{p}\left( \frac{1}{n}\right) +O_{p}\left( \frac{1}{T}\right) =O_{p}\left( \frac{1}{\delta _{nt}^{2}}\right) +o_{p}\left( 1\right) . \end{aligned}$$

Now, we write

$$\begin{aligned}&\sqrt{n}\left( R_{\lambda }-\widehat{\sigma }^{2}\left( \sqrt{\frac{T}{n}} +1\right) \right) \\&\quad =\sqrt{n}\frac{\left( RRSS-URSS\right) }{n}-\sqrt{n} \frac{URSS}{\left( nT-n\right) }\left( \sqrt{\frac{T}{n}}+1\right) \\&\quad =\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\sum _{t=1}^{T}\left[ -\left( \widehat{ \lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) ^{2}+2\left( \widehat{ \lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) u_{it}\right] \\&\qquad -\frac{1}{\sqrt{n}\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}\left[ u_{it}^{2}+\left( \widehat{\lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) ^{2}-2\left( \widehat{\lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) u_{it}\right] \\&\quad =-\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \left( \widehat{ \lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) \right\} ^{2}+\frac{2}{\sqrt{n}}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \left( \widehat{ \lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) u_{it}\right\} \\&\qquad -\left( \sqrt{\frac{T}{n}}+1\right) \frac{1}{\sqrt{n}\left( T-1\right) } \sum _{i=1}^{n}\sum _{t=1}^{T}u_{it}^{2} \\&\qquad -\left( \sqrt{\frac{T}{n}}+1\right) \frac{1}{\sqrt{n}(T-1)} \sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \left( \widehat{\lambda }_{i}\widehat{F} _{t}-\lambda _{i}F_{t}\right) \right\} ^{2} \\&\qquad +\left( \sqrt{\frac{T}{n}}+1\right) \frac{2}{\sqrt{n}\left( T-1\right) } \sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \left( \widehat{\lambda }_{i}\widehat{F} _{t}-\lambda _{i}F_{t}\right) u_{it}\right\} \\&\quad =I+II+III+IV+V. \end{aligned}$$

Note that \(IV=O_{p}\left( \frac{\sqrt{T}}{\delta _{nt}^{2}}\right) \) and \( V=O_{p}\left( \frac{\sqrt{T}}{\delta _{nt}^{2}}\right) \) as shown above. Now we assume that

$$\begin{aligned} \frac{\sqrt{T}}{n}\rightarrow 0. \end{aligned}$$

Note that \(\frac{\sqrt{T}}{\delta _{nt}^{2}}\rightarrow 0\) when \(\frac{\sqrt{ T}}{n}\rightarrow 0.\) Also \(\frac{T}{n}\rightarrow c\) implies that \(\frac{ \sqrt{T}}{n}=\frac{T}{n}\frac{1}{\sqrt{T}}\rightarrow 0.\) Clearly,

$$\begin{aligned}&\sqrt{n}\left( R_{\lambda }-\widehat{\sigma }^{2}\left( \sqrt{\frac{T}{n}} +1\right) \right) =-\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \left( \widehat{ \lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) \right\} ^{2}\\&\quad +\frac{1}{ \sqrt{n}}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \left( \widehat{\lambda }_{i} \widehat{F}_{t}-\lambda _{i}F_{t}\right) u_{it}\right\} -\left( \sqrt{\frac{T }{n}}+1\right) \frac{1}{\sqrt{n}T}\sum _{i=1}^{n} \sum _{t=1}^{T}u_{it}^{2}+o_{p}\left( 1\right) . \end{aligned}$$

Consider the first term.

$$\begin{aligned}&-\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \left( \widehat{ \lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) \right\} ^{2} \\&\quad =-\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\sum _{t=1}^{T}\left( \phi _{\lambda }^{-1}\frac{1}{\sqrt{n}}\lambda _{i}\frac{1}{\sqrt{n}}\sum _{k=1}^{n}\lambda _{k}u_{kt}+\phi _{F}^{-1}\frac{1}{\sqrt{T}}F_{t}\frac{1}{\sqrt{T}} \sum _{s=1}^{T}F_{s}u_{is}\right) ^{2}+o_{p}\left( 1\right) \\&\quad \!=\!-\phi _{\lambda }^{-2}\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\sum _{t=1}^{T}\frac{ 1}{n}\lambda _{i}^{2}\left( \frac{1}{\sqrt{n}}\sum _{k=1}^{n}\lambda _{k}u_{kt}\right) ^{2}\!-\!\phi _{F}^{-2}\frac{1}{n}\sum _{i=1}^{n}\sum _{t=1}^{T} \frac{1}{T}F_{t}^{2}\left( \frac{1}{\sqrt{T}}\sum _{s=1}^{T}F_{s}u_{is} \right) ^{2} \\&\qquad -2\,\phi _{\lambda }^{-1}\phi _{F}^{-1}\frac{1}{n}\sum _{i=1}^{n} \sum _{t=1}^{T}\frac{1}{\sqrt{nT}}\lambda _{i}F_{t}\left( \frac{1}{\sqrt{n}} \sum _{k=1}^{n}\lambda _{k}u_{kt}\right) \left( \frac{1}{\sqrt{T}} \sum _{s=1}^{T}F_{s}u_{is}\right) +o_{p}\left( 1\right) \\&\quad =I+II+III. \end{aligned}$$

Consider \(I+II\).

$$\begin{aligned}&I+II =-\phi _{\lambda }^{-2}\frac{1}{\sqrt{n}}\left( \frac{1}{n} \sum _{i=1}^{n}\lambda _{i}^{2}\right) \sum _{t=1}^{T}\left( \frac{1}{\sqrt{n}} \sum _{k=1}^{n}\lambda _{k}u_{kt}\right) ^{2}\\&\qquad -\phi _{F}^{-2}\frac{1}{\sqrt{n}} \sum _{i=1}^{n}\left( \frac{1}{T}\sum _{t=1}^{T}F_{t}^{2}\right) \left( \frac{1 }{\sqrt{T}}\sum _{s=1}^{T}F_{s}u_{is}\right) ^{2} \\&\quad =-\frac{1}{\sqrt{n}}\sum _{t=1}^{T}\phi _{\lambda }^{-1}\left( \frac{1}{ \sqrt{n}}\sum _{k=1}^{n}\lambda _{k}u_{kt}\right) ^{2}-\frac{1}{\sqrt{n}} \sum _{i=1}^{n}\phi _{F}^{-1}\left( \frac{1}{\sqrt{T}} \sum _{s=1}^{T}F_{s}u_{is}\right) ^{2}+o_{p}\left( 1\right) . \end{aligned}$$

Consider \(III\).

$$\begin{aligned}&\phi _{\lambda }^{-1}\phi _{F}^{-1}\frac{1}{\sqrt{n}}\sum _{i=1}^{n} \sum _{t=1}^{T}\frac{1}{\sqrt{nT}}\lambda _{i}F_{t}\left( \frac{1}{\sqrt{n}} \sum _{k=1}^{n}\lambda _{k}u_{kt}\right) \left( \frac{1}{\sqrt{T}} \sum _{s=1}^{T}F_{s}u_{is}\right) \\&\quad =\phi _{\lambda }^{-1}\phi _{F}^{-1}\frac{1}{\sqrt{n}}\left( \frac{1}{ \sqrt{n}}\sum _{i=1}^{n}\lambda _{i}\left( \frac{1}{\sqrt{T}} \sum _{s=1}^{T}F_{s}u_{is}\right) \right) \left( \frac{1}{\sqrt{T}} \sum _{t=1}^{T}F_{t}\left( \frac{1}{\sqrt{n}}\sum _{k=1}^{n}\lambda _{k}u_{kt}\right) \right) \\&\quad =O_{p}\left( \frac{1}{\sqrt{n}}\right) . \end{aligned}$$

Consider the second term.

$$\begin{aligned} 2\frac{1}{n}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \left( \widehat{\lambda } _{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) u_{it}\right\}&= 2\frac{1}{n}\sum _{t=1}^{T}\phi _{\lambda }^{-1}\left( \frac{1}{\sqrt{n}} \sum _{i=1}^{n}\lambda _{i}u_{it}\right) ^{2}\\&+2\frac{1}{n}\sum _{i=1}^{n}\phi _{F}^{-1}\left( \frac{1}{\sqrt{T}}\sum _{t=1}^{T}F_{t}u_{it}\right) ^{2}+o_{p}\left( 1\right) . \end{aligned}$$

Therefore

$$\begin{aligned}&-\frac{1}{n}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \left( \widehat{\lambda } _{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) \right\} ^{2}+\frac{1}{n} \sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \left( \widehat{\lambda }_{i}\widehat{F} _{t}-\lambda _{i}F_{t}\right) u_{it}\right\} \\&\quad =\frac{1}{n}\sum _{t=1}^{T}\phi _{\lambda }^{-1}\left( \frac{1}{\sqrt{n}} \sum _{k=1}^{n}\lambda _{k}u_{kt}\right) ^{2}+\frac{1}{n}\sum _{i=1}^{n}\phi _{F}^{-1}\left( \frac{1}{\sqrt{T}}\sum _{s=1}^{T}F_{s}u_{is}\right) ^{2}+o_{p}\left( 1\right) . \end{aligned}$$

We know that

$$\begin{aligned}&\frac{1}{\sqrt{n}}\sum _{t=1}^{T}\phi _{\lambda }^{-1}\left( \frac{1}{\sqrt{ n}}\sum _{k=1}^{n}\lambda _{k}u_{kt}\right) ^{2}+\frac{1}{\sqrt{n}} \sum _{i=1}^{n}\phi _{F}^{-1}\left( \frac{1}{\sqrt{T}} \sum _{s=1}^{T}F_{s}u_{is}\right) ^{2} \\&\quad =\frac{1}{\sqrt{T}}\sum _{t=1}^{T}\phi _{\lambda }^{-1}\left( \frac{1}{ \sqrt{n}}\sum _{k=1}^{n}\lambda _{k}u_{kt}\right) ^{2}\left( \sqrt{\frac{T}{n} }\right) +\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\phi _{F}^{-1}\left( \frac{1}{ \sqrt{T}}\sum _{s=1}^{T}F_{s}u_{is}\right) ^{2}. \end{aligned}$$

Hence

$$\begin{aligned}&\frac{1}{\sqrt{n}}\sum _{t=1}^{T}\left[ \phi _{\lambda }^{-1}\left( \frac{1}{ \sqrt{n}}\sum _{k=1}^{n}\lambda _{k}u_{kt}\right) ^{2}-\sqrt{\frac{T}{n}} \sigma ^{2}\right]\\&\quad +\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\left[ \phi _{F}^{-1}\left( \frac{1}{\sqrt{T}}\sum _{s=1}^{T}F_{s}u_{is}\right) ^{2}-\sigma ^{2}\right] \overset{d}{\rightarrow }N\left( 0,4\left( c+1\right) \sigma ^{4}\right) \end{aligned}$$

by Assumption 4 and because \(\frac{1}{\sqrt{n}}\sum _{k=1}^{n} \lambda _{k}u_{kt}\) and \(\frac{1}{\sqrt{T}}\sum _{s=1}^{T}F_{s}u_{is}\) are asymptotically independent. Therefore

$$\begin{aligned} \sqrt{n}\left( R_{\lambda }-\widehat{\sigma }^{2}\left( \sqrt{\frac{T}{n}} +1\right) \right) \overset{d}{\rightarrow }N\left( 0,4\left( c+1\right) \sigma ^{4}\right) \end{aligned}$$

as \(\left( n,T\right) \rightarrow \infty \) and \(\frac{T}{n}\rightarrow c.\) Finally

$$\begin{aligned} \sqrt{n}\left( F_{\lambda }-\left( \sqrt{\frac{T}{n}}+1\right) \right) \overset{d}{\rightarrow }N\left( 0,4\left( c+1\right) \right) \end{aligned}$$

as required.\(\square \)

C Proof of Theorem 3

Proof

First we revisit Theorems 1 and 2 with

$$\begin{aligned} u_{it}=\sigma _{i}e_{it}. \end{aligned}$$

Now suppose \(F_{t}\) is known.

$$\begin{aligned} \sqrt{n}\left( R_{\lambda }-\widehat{\sigma }^{2}\right)&= \frac{\left( RRSS-URSS\right) }{\sqrt{n}}-\frac{URSS}{\sqrt{n}\left( T-1\right) } \\&= -\frac{1}{\sqrt{n}T}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \sqrt{T}\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) \right\} ^{2}F_{t}^{2} \\&+\,\frac{2}{\sqrt{n}\sqrt{T}}\sum _{i=1}^{n}\sum _{t=1}^{T}\left\{ \sqrt{T} \left( \widetilde{\lambda }_{i}\!-\!\lambda _{i}\right) \right\} u_{it}F_{t} -\frac{1}{\sqrt{n}\left( T\!-\!1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}u_{it}^{2}\\&-\frac{1}{\sqrt{n}T(T-1)}\sum _{i=1}^{n} \sum _{t=1}^{T}\left\{ \sqrt{T}\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) \right\} ^{2}F_{t}^{2} \\&+\frac{2}{\sqrt{n}\sqrt{T}\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T} \left\{ \sqrt{T}\left( \widetilde{\lambda }_{i}-\lambda _{i}\right) \right\} u_{it}F_{t} \\&= I+II+III+IV+V. \end{aligned}$$

Recall that

$$\begin{aligned} I+II&= \frac{1}{\sqrt{n}}\sum _{i=1}^{n}\left[ \frac{1}{\sqrt{T}} \sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}\left[ \frac{1}{T} \sum _{t=1}^{T}F_{t}^{2}\right] ^{-1} \\&= \frac{1}{\sqrt{n}}\sum _{i=1}^{n}\phi _{F}^{-1}\left[ \frac{1}{\sqrt{T}} \sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}+o_{p}\left( 1\right) . \end{aligned}$$

We know Assumption 4 that

$$\begin{aligned} \frac{1}{\sqrt{T}}\sum _{t=1}^{T}u_{it}F_{t}\overset{d}{\rightarrow }N\left( 0,\Phi _{i}\right) \end{aligned}$$

where

$$\begin{aligned} \Phi _{i}&= p\lim _{T\rightarrow \infty }\frac{1}{T}\sum _{s=1}^{T} \sum _{t=1}^{T}E\left[ F_{t}F_{s}u_{is}u_{it}\right] \\&= p\lim _{T\rightarrow \infty }\frac{1}{T}\sum _{s=1}^{T}\sum _{t=1}^{T}\sigma _{i}^{2}E\left[ F_{t}F_{s}e_{is}e_{it}\right] \\&= \sigma _{i}^{2}\phi _{F}. \end{aligned}$$

Consider III.

$$\begin{aligned} \frac{1}{\sqrt{n}\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}u_{it}^{2}&= \frac{1}{\sqrt{n}\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}u_{it}^{2} \\&= \frac{1}{\sqrt{n}\left( T-1\right) }\sum _{i=1}^{n}\sigma _{i}^{2}\sum _{t=1}^{T}e_{it}^{2} \\&= \frac{1}{\sqrt{n}}\sum _{i=1}^{n}\sigma _{i}^{2}+o\left( 1\right) . \end{aligned}$$

It is easy to see that \(IV\) and \(V\) are \(O_{p}\left( \frac{\sqrt{n}}{T} \right) .\) Then

$$\begin{aligned}&\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\phi _{F}^{-1}\left[ \frac{1}{\sqrt{T}} \sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}-\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\sigma _{i}^{2} \\&= \frac{1}{\sqrt{n}}\left( \sum _{i=1}^{n}\phi _{F}^{-1}\left[ \frac{1}{ \sqrt{T}}\sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}-\sigma _{i}^{2}\right) . \end{aligned}$$

It follows that

$$\begin{aligned} \frac{\sum _{i=1}^{n}\left( \left[ \frac{\frac{1}{\sqrt{T}} \sum _{t=1}^{T}u_{it}F_{t}}{\sqrt{\phi _{F}}}\right] ^{2}-\sigma _{i}^{2}\right) }{\sqrt{2\sum _{i=1}^{n}\sigma _{i}^{4}}}\overset{d}{ \rightarrow }N\left( 0,1\right) \end{aligned}$$

or

$$\begin{aligned} \frac{\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\left( \phi _{F}^{-1}\left[ \frac{1}{ \sqrt{T}}\sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}-\sigma _{i}^{2}\right) }{ \sqrt{2\frac{1}{n}\sum _{i=1}^{n}\sigma _{i}^{4}}}\overset{d}{\rightarrow } N\left( 0,1\right) . \end{aligned}$$

Hence

$$\begin{aligned} \frac{1}{\sqrt{n}}\sum _{i=1}^{n}\left( \phi _{F}^{-1}\left[ \frac{1}{\sqrt{T} }\sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}-\sigma _{i}^{2}\right) \overset{d}{ \rightarrow }N\left( 0,2\lim _{n\rightarrow \infty }\frac{1}{n} \sum _{i=1}^{n}\sigma _{i}^{4}\right) . \end{aligned}$$

Finally

$$\begin{aligned} \sqrt{n}\left( F_{\lambda }-1\right) \overset{d}{\rightarrow }N\left( 0,2 \frac{\lim _{n\rightarrow \infty }\frac{1}{n}\sum _{i=1}^{n}\sigma _{i}^{4}}{ \left( \lim _{n\rightarrow \infty }\frac{1}{n}\sum _{i=1}^{n}\sigma _{i}^{2}\right) ^{2}}\right) \end{aligned}$$

if

$$\begin{aligned}&\frac{\sqrt{n}}{T}\rightarrow 0,\\&\lim _{n\rightarrow \infty }\frac{1}{n}\sum _{i=1}^{n}\sigma _{i}^{4}<\infty \end{aligned}$$

and

$$\begin{aligned} \lim _{n\rightarrow \infty }\frac{1}{n}\sum _{i=1}^{n}\sigma _{i}^{2}<\infty . \end{aligned}$$

Next we assume \(F_{t}\) is unknown. Recall

$$\begin{aligned} \frac{URSS}{\left( nT-n\right) }&= \frac{1}{n\left( T-1\right) } \sum _{i=1}^{n}\sum _{t=1}^{T}u_{it}^{2}+\frac{1}{n\left( T-1\right) } \sum _{i=1}^{n}\sum _{t=1}^{T}\left( \widehat{\lambda }_{i}\widehat{F} _{t}-\lambda _{i}F_{t}\right) ^{2} \\&-\frac{2}{n\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}\left( \widehat{ \lambda }_{i}\widehat{F}_{t}-\lambda _{i}F_{t}\right) u_{it} \\&= I+II+III. \end{aligned}$$

We know that \(II+\) \(III=O_{p}\left( \frac{1}{\delta _{nT}^{2}}\right) .\) Following similar steps as in the proof of Theorem 2 we obtain

$$\begin{aligned} \sqrt{n}\left( F_{\lambda }-\left( \sqrt{\frac{T}{n}}+1\right) \right) \overset{d}{\rightarrow }N\left( 0,4\left( c+1\right) \frac{ \lim _{n\rightarrow \infty }\frac{1}{n}\sum _{i=1}^{n}\sigma _{i}^{4}}{\left( \lim _{n\rightarrow \infty }\frac{1}{n}\sum _{i=1}^{n}\sigma _{i}^{2}\right) ^{2}}\right) . \end{aligned}$$

Next we allow

$$\begin{aligned} u_{it}=\sigma _{t}e_{it} \end{aligned}$$

and we examine

$$\begin{aligned}&\frac{1}{\sqrt{n}\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}u_{it}^{2} =\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\left( \lim _{n\rightarrow \infty }\frac{1 }{T}\sum _{t=1}^{T}\sigma _{t}^{2}\right) +o_{p}\left( 1\right) \end{aligned}$$

which lead to

$$\begin{aligned} \sqrt{n}\left( F_{\lambda }-1\right) \overset{d}{\rightarrow }N\left( 0,2\right) \end{aligned}$$

if \(F_{t}\) is known and

$$\begin{aligned} \sqrt{n}\left( F_{\lambda }-\left( \sqrt{\frac{T}{n}}+1\right) \right) \overset{d}{\rightarrow }N\left( 0,4\left( c+1\right) \right) \end{aligned}$$

if \(F_{t}\) is unknown.

Finally we set \(u_{it}=\sigma _{it}e_{it}.\) Notice that

$$\begin{aligned} \frac{1}{\sqrt{n}\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}u_{it}^{2}&= \frac{1}{\sqrt{n}\left( T-1\right) }\sum _{i=1}^{n}\sum _{t=1}^{T}\sigma _{it}^{2}e_{it}^{2} \\&= \frac{1}{\sqrt{n}T}\sum _{i=1}^{n}\sum _{t=1}^{T}\sigma _{it}^{2}+o_{p}\left( 1\right) . \end{aligned}$$

Recall that

$$\begin{aligned} \frac{1}{\sqrt{T}}\sum _{t=1}^{T}u_{it}F_{t}\overset{d}{\rightarrow }N\left( 0,\Phi _{i}\right) \end{aligned}$$

where

$$\begin{aligned} \Phi _{i}=\phi _{F}\omega _{i} \end{aligned}$$

with

$$\begin{aligned} \omega _{i}^{2}=\lim _{T\rightarrow \infty }\frac{1}{T}\sum _{t=1}^{T}\sigma _{it}^{2}. \end{aligned}$$

Recall

$$\begin{aligned} \left[ \frac{\frac{1}{\sqrt{T}}\sum _{t=1}^{T}u_{it}F_{t}}{\sqrt{\phi _{F}\omega _{i}^{2}}}\right] ^{2}\overset{d}{\rightarrow }\chi _{1}^{2} \end{aligned}$$

and

$$\begin{aligned} \frac{\sum _{i=1}^{n}\left( \left[ \frac{\frac{1}{\sqrt{T}} \sum _{t=1}^{T}u_{it}F_{t}}{\sqrt{\phi _{F}}}\right] ^{2}-\omega _{i}^{2}\right) }{\sqrt{2\sum _{i=1}^{n}\omega _{i}^{4}}}\overset{d}{ \rightarrow }N\left( 0,1\right) \end{aligned}$$

or

$$\begin{aligned} \frac{\frac{1}{\sqrt{n}}\sum _{i=1}^{n}\left( \phi _{F}^{-1}\left[ \frac{1}{ \sqrt{T}}\sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}-\omega _{i}^{2}\right) }{ \sqrt{2\frac{1}{n}\sum _{i=1}^{n}\omega _{i}^{4}}}\overset{d}{\rightarrow } N\left( 0,1\right) . \end{aligned}$$

Hence

$$\begin{aligned} \frac{1}{\sqrt{n}}\sum _{i=1}^{n}\left( \phi _{F}^{-1}\left[ \frac{1}{\sqrt{T} }\sum _{t=1}^{T}u_{it}F_{t}\right] ^{2}-\omega _{i}^{2}\right) \overset{d}{ \rightarrow }N\left( 0,2\lim _{n\rightarrow \infty }\frac{1}{n} \sum _{i=1}^{n}\omega _{i}^{4}\right) . \end{aligned}$$

Finally

$$\begin{aligned} \sqrt{n}\left( F_{\lambda }-1\right) \overset{d}{\rightarrow }N\left( 0,2 \frac{\lim _{n\rightarrow \infty }\frac{1}{n}\sum _{i=1}^{n}\omega _{i}^{4}}{ \left( \lim _{n\rightarrow \infty }\frac{1}{n}\sum _{i=1}^{n}\omega _{i}^{2}\right) ^{2}}\right) \end{aligned}$$

if \(F_{t}\) is known and

$$\begin{aligned} \sqrt{n}\left( F_{\lambda }-\left( \sqrt{\frac{T}{n}}+1\right) \right) \overset{d}{\rightarrow }N\left( 0,4\left( c+1\right) \frac{ \lim _{n\rightarrow \infty }\frac{1}{n}\sum _{i=1}^{n}\omega _{i}^{4}}{\left( \lim _{n\rightarrow \infty }\frac{1}{n}\sum _{i=1}^{n}\omega _{i}^{2}\right) ^{2}}\right) \end{aligned}$$

if \(F_{t}\) is unknown.\(\square \)

Rights and permissions

Reprints and permissions

About this article

Cite this article

Baltagi, B.H., Kao, C. & Na, S. Testing for cross-sectional dependence in a panel factor model using the wild bootstrap \(F\) test. Stat Papers 54, 1067–1094 (2013). https://doi.org/10.1007/s00362-013-0499-9

Download citation

  • Received:

  • Revised:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00362-013-0499-9

Keywords

Mathematics Subject Classification (2000)

Navigation