Related Experiment Video
Updated: Jan 2, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Whose data can we trust: How meta-predictions can be used to uncover credible respondents in survey data
Sonja Radas1,2, Drazen Prelec2
1Institute of Economics, Zagreb, Croatia.
Abstract:
Many areas of economics use subjective data, although it had been known to present problems regarding its reliability. To improve data quality, researchers may use scoring rules that reward respondents so that it is most profitable for them to tell the truth. However, if the subjects are not well informed about the topic or if they do not pay sufficient attention, they will produce data that could not be dependably used for decision-making even though subjects gave their honest answer. In this paper we show how meta-predictions (respondents' predictions about choices of others) can be used for identification of respondents who produce dependable data. We use purchase intention survey, a popular method to elicit early adoption forecasts for a new concept, as a test bed for our approach. We present results from three online experiments, demonstrating that corrected purchase intentions are closer to the real outcomes.
More Related Videos
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Related Concept Videos
Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
Predicting Reaction Outcomes
Surveys
Reliability and Validity
Accuracy and Errors in Hypothesis Testing
In hypothesis testing, the probability of making a Type I error, denoted as α, is commonly set at 0.05. This significance level indicates a 5%...
Hypothesis: Accept or Fail to Reject?
There are two ways to indicate that the null hypothesis is not rejected. 'Accept' the null...