| |  Verfügbarkeit |
| Autoren | Zinn, Sabine; Würbach, Ariane |
|---|
| Institution | Nationales Bildungspanel; Leibniz-Institut für Bildungsverläufe |
|---|
| Titel | A statistical approach to account for heaping patterns. An application to self-reported income data. |
|---|
| URL | https://www.neps-data.de/Portals/0/Working Papers/WP_XXXX.pdf |
|---|
| Erscheinungsjahr | 2014 |
|---|
| Seitenzahl | 26 S. |
|---|
| Verlag | Bamberg: Leibniz Institute for Educational Trajectories, National Educational Panel Study |
|---|
| Reihe | NEPS working papers. Band 40 |
|---|
| Dokumenttyp | Monographie; Graue Literatur; online |
|---|
| Beigaben | Literaturangaben, Tabellen |
|---|
| Sprache | englisch |
|---|
| Forschungsschwerpunkt | Bildungspanel (NEPS) |
|---|
| Schlagwörter | Einkommensentwicklung; Erhebung; Datenanalyse; Selbsteinschätzung; Fehleranalyse |
|---|
| Abstract | Self-reported income information particularly suffers from misreporting due to the sensitivity of the issue and the error-proneness of the memory. This leads to an intentional coarsening of the data, which is called heaping or rounding. If it does not occur completely at random-which is usually not the case-heaping and rounding has detrimental effects on the results of statistical analysis. For instance, it has an effect on empirical statistics (e.g., percentiles) as well as on inferences from multivariate analyses. Conventional statistical methods do not consider this kind of reporting bias, and thus might produce invalid inference. In this paper, we describe a novel statistical modeling approach that allows us to deal with self-reported heaped income data in an adequate way. We suggest modeling heaping mechanisms and the true underlying model in combination. This way we are able to simultaneously estimate the parameters of the true distribution and to determine the heaping pattern present in the data. To describe the true net income distribution, we use the 3-parametric Dagum distribution. Heaping points are identified from the data by applying a heuristic procedure comparing a hypothetical income distribution and the empirical one. To determine heaping behavior, we employ two distinct models: On the one hand, we assume piecewise constant heaping probabilities, and on the other hand, heaping probabilities are considered to increase steadily with proximity to a heaping point. We validate our novel approach by a range of simulation studies. To illustrate the capacity of the novel approach, we conduct a case study using income data from the adult cohort of the German National Educational Panel Study. (Orig.). |
|---|
| Förderkennzeichen | 01GJ0888 |
|---|
