DISPOSITION EFFECT AMONG BRAZILIAN EQUITY FUND MANAGERS

LUCCHESI, EDUARDO POZZI; YOSHINAGA, CLAUDIA EMIKO; CASTRO JUNIOR, FRANCISCO HENRIQUE FIGUEIREDO DE

doi:10.1590/S0034-759020150104

Brasil

home Sumário navigate_before Anterior Atual Seguinte navigate_next

home Sumário

FORUM • Rev. adm. empres. 55 (1) • Jan-Feb 2015 • https://doi.org/10.1590/S0034-759020150104 linkcopy

DISPOSITION EFFECT AMONG BRAZILIAN EQUITY FUND MANAGERS

Efeito disposição entre gestores brasileiros de fundos de ações

Efecto disposición entre gestores brasileños de fondos de acciones

Authorship SCIMAGO INSTITUTIONS RANKINGS

The disposition effect predicts that investors tend to sell winning stocks too soon and ride losing stocks too long. Despite the wide range of research evidence about this issue, the reasons that lead investors to act this way are still subject to much controversy between rational and behavioral explanations. In this article, the main goal was to test two competing behavioral motivations to justify the disposition effect: prospect theory and mean reversion bias. To achieve it, an analysis of monthly transactions for a sample of 51 Brazilian equity funds from 2002 to 2008 was conducted and regression models with qualitative dependent variables were estimated in order to set the probability of a manager to realize a capital gain or loss as a function of the stock return. The results brought evidence that prospect theory seems to guide the decision-making process of the managers, but the hypothesis that the disposition effect is due to mean reversion bias could not be confirmed.

Loss aversion; disposition effect; prospect theory; mean reversion; logistic regression

Independent variable	Model 1		Model 2
Independent variable	Coefficient	Std. error	Coefficient	Std. error
CR_i,f,t	0.5256^* Note: The dependent variable is 1 when stocks were sold and zero otherwise. The independent variables are the stock continuous return (CR) and stock market excess return (MER), and the natural logarithm of the net asset value of the fund (NAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner accordingto the Huber/White procedure.	0.0378
MER_i,f,t			0.4609^* Note: The dependent variable is 1 when stocks were sold and zero otherwise. The independent variables are the stock continuous return (CR) and stock market excess return (MER), and the natural logarithm of the net asset value of the fund (NAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner accordingto the Huber/White procedure.	0.0400
lnNAV_f,t	0.0411^* Note: The dependent variable is 1 when stocks were sold and zero otherwise. The independent variables are the stock continuous return (CR) and stock market excess return (MER), and the natural logarithm of the net asset value of the fund (NAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner accordingto the Huber/White procedure.	0.0058	0.0415^* Note: The dependent variable is 1 when stocks were sold and zero otherwise. The independent variables are the stock continuous return (CR) and stock market excess return (MER), and the natural logarithm of the net asset value of the fund (NAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner accordingto the Huber/White procedure.	0.0058
Intercept	-1.1667^* Note: The dependent variable is 1 when stocks were sold and zero otherwise. The independent variables are the stock continuous return (CR) and stock market excess return (MER), and the natural logarithm of the net asset value of the fund (NAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner accordingto the Huber/White procedure.	0.1005	-1.1380^* Note: The dependent variable is 1 when stocks were sold and zero otherwise. The independent variables are the stock continuous return (CR) and stock market excess return (MER), and the natural logarithm of the net asset value of the fund (NAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner accordingto the Huber/White procedure.	0.1004
Likelihood Ratio	252.6107^* Note: The dependent variable is 1 when stocks were sold and zero otherwise. The independent variables are the stock continuous return (CR) and stock market excess return (MER), and the natural logarithm of the net asset value of the fund (NAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner accordingto the Huber/White procedure.		189.7605^* Note: The dependent variable is 1 when stocks were sold and zero otherwise. The independent variables are the stock continuous return (CR) and stock market excess return (MER), and the natural logarithm of the net asset value of the fund (NAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner accordingto the Huber/White procedure.

Independent variable	Model 3		Model 4
Independent variable	Coefficient	Std. error	Coefficient	Std. error
CR_i,f,t	0.2926^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0343
MER_i,f,t			0.1745^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0365
lnNAV_f,t	0.0374^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0057	0.0378^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0057
τ₁	1.0872^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0981	1.0723^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0981
τ₂	2.0433^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0987	2.0273^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0986
τ₃	2.5312^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0991	2.5153^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0990
τ₄	2.8854^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0995	2.8696^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0994
τ₅	3.1654^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1001	3.1497^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1000
Likelihood Ratio	113.8497^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.		67.1709^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variables used are the stock continuous return (CR), the stock market excess return (MER) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.

Independent variable	Model 5		Model 6		Model 7
Independent variable	Coefficient	Std. error	Coefficient	Std. error	Coefficient	Std. error
MERi,f,t	0.1030^** Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0465	0.0730	0.0477	0.1387*	0.0486
GDCi,f,t	0.0859^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0229	0.1176^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0235	0.0577^** Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0239
LDCi,f,t	0.0171	0.0259	0.0227	0.0261	0.0230	0.0269
lnNAVf,t	0.0382^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0057	0.0393^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0057	0.0402^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0058
τ₁	1.1095^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0989	1.1399^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0997	1.1321^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1013
τ₂	2.0649^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0994	2.0984^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1003	2.0982^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1018
τ₃	2.5530^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.0997	2.5894^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1006	2.5892^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1022
τ₄	2.9073^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1002	2.9463^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1011	2.9517^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1027
τ₅	3.1874^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1007	3.2298^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1017	3.2403^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.	0.1033
Likelihood Ratio	80.4838^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.		93.2341^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.		76.8127^* Note: The dependent variable used in the estimation was based on the latent variable (PRSi,f,t). The independent variable is the stock market excess return (MER), the dummy variable for consistency of gain (GCD), the dummy variable for consistency of loss (LCD) and the natural logarithm of the net asset value of the fund (lnNAV). The symbols , * e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner according to the Huber/White procedure.

vertical_align_top file_download show_chart

more_horizclose
- image
- translate
- link
- article
- vertical_align_top
- file_download
- show_chart
- image
- translate
- link
- article

location_on

Fundação Getulio Vargas, Escola de Administração de Empresas de S.Paulo Avenida Nove de Julho, 2.029, Bela Vista, CEP: 01313-902, Telefone: +55 (11) 3799-7718 - São Paulo - SP - Brazil
E-mail: rae@fgv.br

rss_feed Acompanhe os números deste periódico no seu leitor de RSS

Acessibilidade / Reportar erro

[TFN01t01] Total number of observations: 45,668

[TFN02t01] Note: The dependent variable is 1 when stocks were sold and zero otherwise. The independent variables are the stock continuous return (CR) and stock market excess return (MER), and the natural logarithm of the net asset value of the fund (NAV). The symbols *, ** e † denote the statistical significance of the coefficient at 1%, 5% and 10% levels, respectively. The estimated residuals were calculated in a robust manner accordingto the Huber/White procedure.