A two-stage estimator for heterogeneous panel models with common factors

Castagnetti, Carolina; Rossi, Eduardo; Trapani, Lorenzo

doi:10.1016/j.ecosta.2017.10.005

Cited by 11 publications

(8 citation statements)

References 29 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most importantly, we find that the unobserved common factor is imposed on each bank. These findings have previously been unexplored in the literature on interest rate transmission, but our findings are consistent with the contemporary literature on growth and credit spreads (Castagnetti et al 2017;Eberhardt & Teal 2013). Incomplete heterogeneity and positive asymmetry have been significantly verified, reaffirming the market power hypothesis, and indicating variations in bank mortgage rate setting conduct.…”

Section: Introductionsupporting

confidence: 91%

“…Our dynamic heterogeneous panel-data models for linearity (symmetry) and nonlinearity (asymmetry) build on a common-factor AMG method (Bond & Eberhardt 2013;Castagnetti et al 2017;Eberhardt & Bond 2009). This approach allows the capture of bank-specific Owing to the novel advantages of the AMG estimator, it is selected from the common correlated effect mean group (CCE) estimator (Pesaran 2006) and the dynamic CCE (DCCE) estimator (Chudik & Pesaran 2015), the innovative common-factor models for macro panel data.…”

Section: Empirical Amg Modelsmentioning

confidence: 99%

“…Their price-setting policies are significantly subject to common phenomena ranging from national policy changes to global economic shocks such as the recent financial and sovereign debt crises. The contemporary literature on growth and econometrics has established solid foundations in the presence of CD properties in the macro panel data which arise from common factors, nationally and globally (Bai & Ng 2004;Castagnetti, Rossi, & Trapani 2017;Eberhardt & Teal 2013). However, this issue has remained untouched in the literature on interest rate transmission.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

International funding cost and heterogeneous mortgage interest-rate pass-through: a bank-level analysis

2018

View full text Add to dashboard Cite

This study examines the transmission of the cost-of-funds rates, domestically and internationally, to owner-occupied housing interest rates at the bank level for the period 2002(7)-2015(12) in Australia. Three main issues, cross-sectional dependence, parameter heterogeneity, and asymmetry, have been considered using the linear and nonlinear commonfactor Augmented Mean Group estimators. Significant unobservable coefficients in all estimates ascertain that unobserved common factors arising from both national and global shocks have a significant influence on mortgage rate transmission. The results of sizable heterogeneity and asymmetry, found in all estimates while controlling for cross-sectional correlations, highlight the substantial effect of the foreign-funds rate on long-run mortgage price-setting. We find a closer connection between mortgage interest rates and international funding cost; we have also confirmed a declining transmission of the policy rate after the 2008 global financial crisis. Keywords Asymmetry, heterogeneity, cross-sectional dependence, interest rate pass-through, bank mortgages, AMG models JEL Classifications G21, E43, E52, E58 of funds reflects the whole range of diverse liabilities (Fabbro & Hack 2011). Recent global extreme shocks have induced a higher level of credit risk, liquidity risk, and competition, making the cost of market funding more expensive (ECB 2013). These significant changes in world financial markets violate the underlying assumption of an alignment between policy rates and retail interest rates (Naraidoo & Raputsoane 2015). This study examines heterogeneity and asymmetry in the transmission of the cost-of-funds rates, domestically and internationally, to home-loan interest rates, controlling for crosssection dependence. Our country selection has been made owing to the importance of Australian housing and housing finance markets from the perspectives of an effective monetary policy and wealth effects on consumption (Jansen 2013; Robstad 2018). Australia is one of the top five world largest mortgage markets, just standing behind Denmark, Norway, and Netherlands, whose ratios of total mortgage credit to annual economy output (GDP) are greater than 100% (IMF 2017). Globally, Australia possesses the highest ratio of housing loans to total bank loans at 64%, a ratio that has continuously increased since the GFC (IMF 2017). Its mortgage market is highly oligopolistic: the dominance of four major banks constitutes over 85% of total market share (presented in Fig. B1, Appendix B). Only Australia, of these five, raises considerable mortgage funds from wholesale sources; the others source their funds mainly from domestic deposits. A significant portion, around 35%, of Australia's mortgage funding is sourced from world financial markets (Ralston & Davis 2011; Wilkins et al. 2016). This heavy reliance on foreign borrowings also poses a serious practical question for policy makers and banking regulators: housing finance markets with these characteristics are highly associated with ho...

show abstract

Section: Introductionsupporting

confidence: 91%

Section: Empirical Amg Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

International funding cost and heterogeneous mortgage interest-rate pass-through: a bank-level analysis

2018

View full text Add to dashboard Cite

show abstract

“…The (implicit) assumption of a common slope coefficient β 0 is standard in the literature (see, for example, Bai, 2009, andMoon andWeidner, 2015). We speculate that our results can be extended to accommodate heterogeneous slope coefficients as in, for example, Castagnetti et al (2015), Castagnetti et al (2019), Li et al (2020), and Huang et al (2021).…”

Section: Model and Estimation Proceduresmentioning

confidence: 61%

Interactive Effects Panel Data Models with General Factors and Regressors

Peng

Westerlund

et al. 2020

SSRN Journal

View full text Add to dashboard Cite

“…Therefore, heterogeneous slopes help model differences that are left unexplained (see the discussion in Hsiao andPesaran, 2008, andPesaran andSmith, 1995). We take this into account by following studies on factors, such as Castagnetti et al (2019) and Westerlund and Kaddoura (2022) (in fixed-T setup), who worked on theoretical extensions to heterogeneous slopes, and adopt random coefficient framework. Particularly, we assume a popular Swammy-type structure…”

Section: Introductionmentioning

confidence: 99%

Complete Theory for CCE Under Heterogeneous Slopes and General Unknown Factors

Stauskas

2022

Oxf Bull Econ Stat

View full text Add to dashboard Cite

A recent study of Westerlund (CCE in Panels with General Unknown Factors, The Econometrics Journal, 21, 264‐276, 2018) showed that a very popular common correlated effects (CCE) estimator is significantly more applicable than it was thought before. Specifically, the common factors can have much more general time series properties than stationarity. This helps to alleviate the uncertainty over deterministic model components (e.g. trends) since they can be treated as unknown, similarly to unobserved stochastic (possibly non‐stationary) factors. While very promising, these theoretical results concern only the baseline scenario of the pooled (CCEP) estimator in the restrictive case of homogeneous model parameters, which is asymptotically biased and requires bias correction. Economic theory often hints at individuals exhibiting slope heterogeneity, which is a more realistic case when CCE is unbiased. Therefore, it is natural to extend the findings on general unknown factors to the case of unit‐specific slopes and understand if unbiasedness still holds, which would be an empirically handy feature. It is especially interesting, because many previous studies on heterogeneous slopes did not rigorously account for the usual situation when the factors are proxied by more explanatory variables than needed. Hence, the current study introduces more completeness in the CCE theory. We demonstrate that save for some regularity conditions, CCEP and the mean group (CCEMG) estimators are asymptotically normal and unbiased under heterogeneous slopes and general unknown factors.

show abstract

A two-stage estimator for heterogeneous panel models with common factors

Cited by 11 publications

References 29 publications

International funding cost and heterogeneous mortgage interest-rate pass-through: a bank-level analysis

International funding cost and heterogeneous mortgage interest-rate pass-through: a bank-level analysis

Interactive Effects Panel Data Models with General Factors and Regressors

Complete Theory for CCE Under Heterogeneous Slopes and General Unknown Factors

Contact Info

Product

Resources

About