Ignoramus, Ignorabimus? On Uncertainty in Ecological Inference
Bibliographic Data
| ID | 6331282 |
|---|---|
| Authors | Martin Elff (0000-0001-9032-9739, University of Mannheim), Thomas Gschwend (0000-0002-8656-9622, University of Mannheim), Ron Johnston (0000-0003-3031-8573, University of Bristol), Ron J Johnston |
| Year | 2008 |
| Volume | 16 |
| Issue | 1 |
| Pages | 70-92 |
| Publication date | 2008-01-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Political Analysis (JOURNAL) |
| Journal identifiers | ISSN: 1047-1987 • E-ISSN: 1476-4989 |
| Publisher | Cambridge University Press (CUP) (PUBLISHER) |
| DOI | 10.1093/pan/mpm030 |
| OpenAlex | W2146919595 |
| Language | EN |
| Citations received | 6 |
| References cited | 32 |
Models of ecological inference (EI) have to rely on crucial assumptions about the individual-level data-generating process, which cannot be tested because of the unavailability of these data. However, these assumptions may be violated by the unknown data and this may lead to serious bias of estimates and predictions. The amount of bias, however, cannot be assessed without information that is unavailable in typical applications of EI. We therefore construct a model that at least approximately accounts for the additional, nonsampling error that may result from possible bias incurred by an EI procedure, a model that builds on the Principle of Maximum Entropy. By means of a systematic simulation experiment, we examine the performance of prediction intervals based on this second-stage Maximum Entropy model. The results of this simulation study suggest that these prediction intervals are at least approximately correct if all possible configurations of the unknown data are taken into account. Finally, we apply our method to a real-world example, where we actually know the true values and are able to assess the performance of our method: the prediction of district-level percentages of split-ticket voting in the 1996 General Election of New Zealand. It turns out that in 95.5% of the New Zealand voting districts, the actual percentage of split-ticket votes lies inside the 95% prediction intervals constructed by our method
Data mining · Econometrics · Entropy (arrow of time · Inference · Principle of maximum entropy · Statistics · Ticket · Unavailability · Voting · Computer Science · Ecosystem dynamics and resilience · Gaussian Processes and Bayesian Inference · Mathematics · Sustainability and Ecological Systems Analysis · Artificial Intelligence
Encountering Alan Wilson, filling the gaps in data sets (from the knowns to the unknowns) … and disciplinary history/progress
Beyond Judicialization
Opening out ageing
The comparative study of split-ticket voting
Ecological inference under unfavorable conditions
Combining Aggregate Data and Exit Polls for the Estimation of Voter Transitions
Information Theory and Statistical Mechanics
A Mathematical Theory of Communication
Iff the Assumption Fits
Using Ecological Inference Point Estimates as Dependent Variables in Second-Stage Linear Regressions
Split-Ticket Patterns in Mixed-Member Proportional Election Systems
Race-Related Differences in Self-Reported and Validated Turnout
Ecological Inference and Entropy-Maximizing
Voter Transition Probability Estimates
Logical Inconsistency in EI‐Based Second‐Stage Regressions
Assessing South Carolina's 1990s congressional districting
Ecological Regressions and Behavior of Individuals
Analyzing Incomplete Political Science Data
A New Approach to the Study of Ticket Splitting
Binomial-Beta Hierarchical Models for Ecological Inference
Some Alternatives to Ecological Correlation
| Citations per year | 0.35 |
|---|---|
| Citation span | 2009 - 2021 (13) |
| Highly cited | No |