Accounting for Excess Zeros and Sample Selection in Poisson and Negative Binomial Regression Models

By William H. Greene. 1994

How researchers see this paper

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

Citations in the corpus

A Bayesian model for repeated measures zero-inflated count data with application to outpatient psychiatric service use (2010, background): “These include hurdle models (Mullahy, 1986; Heilbron, 1989) and zero-inflated count models (Lambert, 1992; Greene, 1994).”
A Two-Part Random-Effects Model for Semicontinuous Longitudinal Data (2001, methodology): “Greene (1994) de ned a sample selection model for count data analogous to Heckman’s model in which the underlying precensored response is described by a Poisson or negative binomial regression.”
Trading Partners and Trading Volumes:Implementing the Helpman-Melitz-Rubinstein Model Empirically (2015, unknown): “HMR approach this problem in a way that is akin to the ad-hoc method used by Greene (1994) to address the sample selection problem in count data models.”
The importance of local forest benefits: Economic valuation of Non-Timber Forest Products in the Eastern Arc Mountains in Tanzania (2014, unknown): “When only a small proportion of all households collect an NTFP, such as thatch and charcoal, zero-inflated negative binomial models are employed to accommodate the distribution and the large number of zero observations of the dependent variable (Greene, 1994; Cameron and Trivedi, 2005).”
The Analysis of Count Data: A Gentle Introduction to Poisson Regression and Its Alternatives (2009, unknown): “If information identifying those individuals who are structural zeros is not available or the research interest is in the full population including non-drinkers, zero inflated Poisson models or zero inflated negative binomial models can be used (Greene, 1994; Hall & Zhengang, 2004; Long, 1997).”
What does a zero mean? Understanding false, random and structural zeros in ecology (2019, methodology): “…Yes ZINBb or ZANBc aNB, negative binomial (McCullagh & Nelder, 1989). bZIP, zero‐inflated poisson (Lambert, 1992) and ZINB, zero‐inflated negative binomial (Greene, 1994). cZAP, zero‐altered poisson and ZANB, zero‐altered negative binomial (Mullahy, 1986). where X = (X1, …, Xr) with Xj= (Xj1,……”
Functional Form and Heterogeneity in Models for Count Data (2007, background): “The second is the conventional ZIP model proposed by Lambert (1992), Heilbron (1994) and Greene (1994).”
US county-level determinants of inbound FDI: evidence from a two-step modified count data model (2001, methodology): “An empirical approach that accounts for this two-step process is discussed by Heilbron (1989), Lambert (1992), and Greene (1994), and has been termed a variety of names, including zero inflated Poisson (ZIP), zero altered Poisson (ZAP), hurdle model, or with zero’s (WZ) model.”
Political Institutions and Conservation by Local Governments (2005, methodology): “The standard model for count data is a Poisson regression model, which estimates the expected count at each unit of analysis (the incident rate, denoted (cid:1) i ) as a function of hypothesized independent variables (Greene 1994, 2000; Long 1997).”
Zero-Inflated Poisson and Zero-Inflated Negative Binomial Models Using the COUNTREG Procedure (2008, methodology): “In contrast, it is not possible to transform a zero-inflated Poisson model (respectively, a zero-inflated negative binomial model) to a plain Poisson (respectively, to a plain negative binomial model) by using any finite vector of coefficients (Greene 1994).”
Acquisition versus Greenfield Investment: The Location of Foreign Manufacturers in Italy (2004, methodology): “A more appropriate formulation for these data is the “Zero Altered Poisson” (ZAP) model (see Greene, 1994 ), where with probability qi the only possible observation is zero, and with probability (1-qi) a Poisson (i) random variable is observed.”
Growth Curve Models for Zero-Inflated Count Data: An Application to Smoking Behavior (2007, methodology): “The hurdle, or two-part Poisson model (Heilbron, 1989; King, 1989; Mullahy, 1986) and the ZIP model (Greene, 1994; Lambert, 1992) are two models that have been developed to account for excess zeros.”
Land Tenure Arrangements and Rural-Urban Migration in China (2011, methodology): “Due to this, we estimate the standard Poisson and Negative Binomial models (Cameron & Trivedi 1986), as well as the Zero-Inflated (Mullahy 1986) and Hurdle (Lambert 1992; Greene 1994) specifications of these models.”
International labor mobility and knowledge flow externalities (2008, methodology): “ZINB, as developed by Greene (1994), assumes that”