We propose a novel selectivity correction procedure to deal with survey attrition, at the crossroads of the "Heckit" and of the bounding approach of Lee (2009). As a substitute for the instrument needed in sample selectivity correction models, we use information on the number of attempts that...

It is often believed that without instrument, endogenous sample selection models are identified only if a covariate with a large support is available (see Chamberlain, 1986, and Lewbel, 2007). We propose a new identification strategy mainly based on the condition that the selection variable...

The randomized trial literature has helped to renew the fields of microeconometric policy evaluation by emphasizing identification issues raised by endogenous program participation. Measurement and attrition issues have perhaps received less attention. This paper analyzes the dramatic impact of...

This paper analyzes wage decomposition methodology in the context of panel data sample selection embedded in a correlated random effects setting. Identification issues unique to panel data are examined for their implications for wage decompositions. As an empirical example, we apply our...

We develop and estimate a panel data model explaining the answers to questions about subjective probabilities, using data from the US Health and Retirement Study. We explicitly account for nonresponse, rounding, and focal point 50 percent answers. Our results indicate that for three of the four...

The psychological basis for rank-dependent probability weighting, and for an inverse-S probability weighting function (PWF) in particular, has often been questioned. I examine the existence and shape of the PWF in a model allowing for optimism/pessimism over probability distributions and for...

Little is known about how gamblers estimate probabilities from multiple information sources. This paper reports on a preregistered study that administered an incentivized Bayesian choice task to n=465 participants (self-reported gamblers and non-gamblers). Our data failed to support our main...

To compare distributions of ordinal data such as individuals' responses on Likert-type scale variables summarizing subjective well-being, we should not apply the toolbox of methods developed for cardinal variables such as income. Instead we should use an analogous toolbox which takes account of...