Estimating Standard Errors in Finance Panel Data Sets: Comparing Approaches

Abstract

In both corporate finance and asset pricing empirical work, researchers are often confronted with panel data. In these data sets, the residuals may be correlated across firms and across time, and OLS standard errors can be biased. Historically, the two literatures have used different solutions to this problem. Corporate finance has relied on Rogers standard errors, while asset pricing has used the Fama-MacBeth procedure to estimate standard errors. This paper will examine the different methods used in the literature and explain when the different methods yield the same (and correct) standard errors and when they diverge. The intent is to provide intuition as to why the different approaches sometimes give different answers and thus give researchers guidance for their use.

Efeito Calendário e Finanças Comportamentais no Segmento de Fundos Multimercados

“…No modelo de efeitos aleatórios, os sinais dos betas foram idênticos aos observados no modelo com dados empilhados, para todas as variáveis (exceção para a constante do modelo). Na busca pelo aumento da robustez dos resultados, foram incluídas variáveis dummy para ano no modelo de pesquisa, com o intuito de aglomerar os efeitos do fundo, pois os resíduos de um fundo podem estar correlacionados ao longo do tempo (Petersen, 2009). Os resultados das duas principais variáveis deste estudo foram robustos a esse procedimento, permanecendo com sinal negativo e estatisticamente significativo (variáveis Segunda e Seg_Crise).…”

The Effect of Performance on Israeli Equity Fund Flows

“…The following approaches; White standard errors (1980) and one-way cluster robust standard errors by firm and/or time are common in financial research. However, White standard errors solve the problem of heteroscedasticity and assume that observations are uncorrelated and one-way cluster robust standard errors address only one of two dependencies but not both (Petersen 2009). We compare these common methods to the two-way cluster robust standard errors (CL-2), which is robust to both time series and cross sectional correlation.…”

Determinants of Problem Loans: Non-performing Loans vs. Loan Quality Deterioration

“…Consequently, CRSK variable is measured by NPLs. We estimate T statistics using White standard errors clustered by firm and by year, which account for heteroscedasticity and serial correlation (Petersen, 2009;Thompson, 2011).…”