Bias in Conditional and Unconditional Fixed Effects Logit Estimation: A Correction

By T. Coupé. Political Analysis, 2005

63 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Estimating Grouped Data Models with a Binary-Dependent Variable and Fixed Effects via a Logit versus a Linear Probability Model: The Impact of Dropped Units (2019, background): “Thebiasof LogitFE is very small in these cases (Katz 2001; Greene 2004; Coupé 2005) and the e iciency loss of LogitFE as compared to conditional logit is tiny (Beck 2018a).”
POLITICAL CAPABILITIES, POLICY RISK, AND INTERNATIONAL INVESTMENT STRATEGY: EVIDENCE FROM THE GLOBAL ELECTRIC POWER GENERATION INDUSTRY † (2010, methodology): “7 Studies using Monte Carlo simulations to assess the finitesample properties of the two estimators have found that the bias in the unconditional estimator is negligible in groups containing 16 or more alternatives, and small for those containing between nine and 15 choices (Katz, 2001: 383–384; Cou”