Bayesian Model Averaging and Weighted Average Least Squares: Equivariance, Stability, and Numerical Issues

Luca, Giuseppe De; Magnus, Jan R.

doi:10.2139/ssrn.1894610

Cited by 23 publications

(14 citation statements)

References 18 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Keeping the institutional indicators as the focus parameters for the analysis, Bayesian averaging was conducted first on all regressors (focus and auxiliary) over a space of 2,097,152 possible models (1,048,576 possible models for each of the ROA and ROE specifications). The criterion for determining robust correlation with the outcome variable for the auxiliary regressors was suggested by De Luca and Magnus (2011), and involves retaining auxiliary variables which have an absolute value of t-ratios over 1 (which also satisfies the criteria that their two standard error confidence intervals do not include zero). This approach avoids the ad hoc rule of thumb of Kass and Wasserman (1995), which removes Bweak^variables (i.e.…”

Section: Baseline Specificationsmentioning

confidence: 99%

See 1 more Smart Citation

Après le déluge: Institutions, the Global Financial Crisis, and Bank Profitability in Transition

Hartwell

2015

Open Econ Rev

View full text Add to dashboard Cite

While the determinants of bank profitability have been well-explored, the influence of institutions on bank performance is less understood, especially in the transition context. Given the presence of a financial crisis such as the one that struck the global economy from 2007 onward, did the underlying institutional structure of a country help to mitigate the effects of the crisis on banks? Utilizing a new database of 1600 banks across 30 transition economies, this paper applies Bayesian model averaging, fixed-effects, and IV-GMM methodology to test the effect of institutions on bank profitability in a crisis period. Results are conclusive across models that investorspecific property rights aided bank profitability during the crisis. The effect of democracy on banks is much more ambiguous but appears to negatively influence profitability indirectly through interest group channels and bank concentration. These results hold across a variety of specifications and robustness tests.

show abstract

Section: Baseline Specificationsmentioning

confidence: 99%

“…This approach avoids the ad hoc rule of thumb of Kass and Wasserman (1995), which removes Bweak^variables (i.e. those with a posterior inclusion probability of 0.5-0.75, see Eicher et al 2011), but has less predictive power than the Bmedian^model used by De Luca and Magnus (2011).…”

Section: Baseline Specificationsmentioning

confidence: 99%

Après le déluge: Institutions, the Global Financial Crisis, and Bank Profitability in Transition

Hartwell

2015

Open Econ Rev

View full text Add to dashboard Cite

show abstract

“…As stressed by De Luca and Magnus (2012) standard econometric practice of using the same data for model selection (the choice of explanatory variables) and estimating -while ignoring that the resulting estimators are in fact pretest estimators -leads to false inference, since traditional statistical test theory is not directly applicable. Approaches to deal with this difficulty is the "extreme bounds analysis" (see Sturm and de Haan 2005;Hartwig and Sturm 2012) and the "Bayesian model averaging" (BMA) technique within a linear regression model (see Magnus et al 2010, andDe Luca andMagnus 2011). Here, the BMA technique is applied.…”

Section: _________________________mentioning

confidence: 99%

The Impact of National Financial Regulation on Macroeconomic and Fiscal Performance after the 2007 Financial Shock – Econometric Analyses Based on Cross-Country Data

Hagen

2013

Economics

View full text Add to dashboard Cite

Using cross-country data, this paper estimates the impact of the 2007 financial shock on countries' macroeconomic developments conditional on national financial regulations before the crisis. For this purpose, the "financial reform index" developed by Abiad et al. (A New Database of Financial Reforms, 2008a) is used. The econometric analyses indicate that countries with more deregulated financial markets experienced deeper recessions, stronger employment losses, and larger government budget deficits. Against the background of the ongoing global crisis and the results of other studies, the usefulness of liberalized financial markets for macroeconomic stability and economic development should be rigorously reconsidered. JEL E32 G18 C21

show abstract

“…Thirdly, the number of potential predictors can be large, and this raises a serious statistical problem for model selection strategy. In the midst of uncertainty about the choice of the predictor variables to be included in the model, care should be To overcome this problem, model averaging techniques have been introduced (see Magnus and Durbin (1999); Danilov and Magnus (2004); Magnus, Powell and Prüfer (2010); De Luca, Giuseppe and Magnus (2011)). These techniques are unlike standard model estimators that are based on some pre-tests and post-tests for model estimation, thus, the techniques have a coherent way of making inference on the regression parameters of interests by taking into account the uncertainty due to both the estimation and the model selection steps.…”

Section: Introductionmentioning

confidence: 99%

Investigating Predictors of Inflation in Nigeria: BMA and WALS Techniques

Tumala¹,

Olubusoye²,

Yaaba³

et al. 2018

AJAS

View full text Add to dashboard Cite

Abstract. The recent economic conundrum arising from the fall in the international oil price has threatened the maintenance of price stability, a key function of the central bank, therefore the need to investigate predictors of inflationary measures arises. The model averaging method considers uncertainty as part of the model selection, and include information from all candidate models. We analysed a wide spectrum of inflation predictors and all possible models for Nigeria CPI inflation using the Bayesian Model Averaging and Weighted Average Least Squares. The study uses fifty-nine (59) predictor variables cutting across all sectors of the Nigerian economy and three (3) measures of inflation, namely; all items consumer price index, core consumer price index and food consumer price index. (to be continued in page 302) Full Abstract (ENGLISH) The recent economic conundrum arising from the fall in the international oil price has threatened the maintenance of price stability, a key function of the central bank, therefore the need to investigate predictors of inflationary measures arises. The model averaging method considers uncertainty as part of the model selection, and include information from all candidate models. We analysed a wide spectrum of inflation predictors and all the possible models for Nigeria CPI inflation using the Bayesian Model Averaging and Weighted Average Least Squares. The study uses fifty-nine (59) predictor variables cutting across all sectors of the Nigerian economy and three (3) measures of inflation, namely; all items consumer price index, core consumer price index and food consumer price index. The results from both model averaging techniques showed that maximum lending rate, world food price index and Bureau de change exchange rate are the significant drivers of inflationary measures among focus variables, while foreign assets, credit to private sectors, net credit to government and real effective exchange rate are the drivers of inflationary measures, for the auxiliary variables, strongly supporting the monetarist and open economy views on inflation. The structuralist view is reported to be relatively weaker because government expenditure is only significant at 10.0 per cent.Résumé (FRENCH) L'énigmeéconomique récente découlant de la chute des cours internationaux du pétrole a menacé le maintien de la stabilité des prix, des principales fonctions de la Banque centrale, la nécessité d'enquêter sur les prédicteurs de mesures inflationnistes se pose donc. Le modèle avec une moyenne de méthode considère l'incertitude dans le cadre de la sélection du modèle et inclure les informations de tous les modèles de candidat. Nous avons analysé un largeéventail d'indicateurs de l'inflation et tous les modèles possibles pour le Nigéria IPC en utilisant le modèle bayésien en moyenne et pondérée moyenne des moindres carrés. L'étude utilise des variables prédictives de cinquante-neuf 59 coupe tous les secteurs de l'économie nigériane et 3 trois mesures de l'inflation, a savoir ; tout indice prix consommat...

show abstract

Bayesian Model Averaging and Weighted Average Least Squares: Equivariance, Stability, and Numerical Issues

Cited by 23 publications

References 18 publications

Après le déluge: Institutions, the Global Financial Crisis, and Bank Profitability in Transition

Après le déluge: Institutions, the Global Financial Crisis, and Bank Profitability in Transition

The Impact of National Financial Regulation on Macroeconomic and Fiscal Performance after the 2007 Financial Shock – Econometric Analyses Based on Cross-Country Data

Investigating Predictors of Inflation in Nigeria: BMA and WALS Techniques

Contact Info

Product

Resources

About