Arbitrary inflation in fractional models
The analysis of subjective probabilities, that are fractional or share variables by definition, is becoming increasingly widespread in both economics and the social sciences in general.
To avoid nonsensical predictions, empirical predictions for such variables must respect the fact that they are necessarily bounded on the 0-1 (or, 0-100, for percentage-type responses) interval. In addition, where the response variable of interest corresponds to a self-report on a fixed scale, individuals are often drawn to particular focal-point responses, resulting in distinct spikes in the empirical distribution.
In this paper, we suggest a simple model that accounts for all of the nuances of such data, including its fractional and bounded nature as well as arbitrary inflation at such focal-points (which may appear at any point in the interval and are highly likely at the endpoints).
We estimate our model using data drawn from Michigan Health and Retirement Study and the Italian Survey of Income and Wealth relating to an individual's subjective marginal propensity to consume.
Speaker Profile
Professor Mark Harris, Curtin University
Prof Harris joined Curtin University in 2011 as a Professor, and is currently a John Curtin Distinguished Professor in the School of Accounting, Economics and Finance. Prior to Curtin, he held teaching and research appointments at Monash University and University of Melbourne. Mark has made significant contributions to the field of Applied Economics and is currently both an Australian Research Council (ARC) College of Experts Member and Medical Research Future Fund (MRFF) Grant Assessment Committee Member. His research and publication interests have been focused on the areas of applied economics and econometrics, in particular dynamic panel data models, and their applications, as well as the application of discrete and limited dependent variable models. Recently Mark has undertaken a significant amount of research into the broad area of Health Economics, Big Data and trade flows. He gained his PhD from Monash University, Australia, in 1997, and a BA (Honours), First Class, Economics, in 1989, from the University of Sussex, UK. He teaches primarily into the econometric streams.
Weekly seminar series
As part of our centre's vibrant research culture, we host a weekly seminar series. Visiting and invited researchers present current research relating to the economics of health and wellbeing, and the healthcare sector. Visitors are welcome to join these sessions where discussion and debate is encouraged.
For further information on our seminar series, please contact shannon.stanwell@monash.edu
Event Details
- Date:
- 23 August 2023 at 12:00 pm – 1:00 pm
- Venue:
- In-person at Caulfield campus, Building H, Level 9, Room H9.21
- Categories:
- CHE Seminar; Health Economics
Description
The analysis of subjective probabilities, that are fractional or share variables by definition, is becoming increasingly widespread in both economics and the social sciences in general.
To avoid nonsensical predictions, empirical predictions for such variables must respect the fact that they are necessarily bounded on the 0-1 (or, 0-100, for percentage-type responses) interval. In addition, where the response variable of interest corresponds to a self-report on a fixed scale, individuals are often drawn to particular focal-point responses, resulting in distinct spikes in the empirical distribution.
In this paper, we suggest a simple model that accounts for all of the nuances of such data, including its fractional and bounded nature as well as arbitrary inflation at such focal-points (which may appear at any point in the interval and are highly likely at the endpoints).
We estimate our model using data drawn from Michigan Health and Retirement Study and the Italian Survey of Income and Wealth relating to an individual's subjective marginal propensity to consume.
Speaker Profile
Professor Mark Harris, Curtin University
Prof Harris joined Curtin University in 2011 as a Professor, and is currently a John Curtin Distinguished Professor in the School of Accounting, Economics and Finance. Prior to Curtin, he held teaching and research appointments at Monash University and University of Melbourne. Mark has made significant contributions to the field of Applied Economics and is currently both an Australian Research Council (ARC) College of Experts Member and Medical Research Future Fund (MRFF) Grant Assessment Committee Member. His research and publication interests have been focused on the areas of applied economics and econometrics, in particular dynamic panel data models, and their applications, as well as the application of discrete and limited dependent variable models. Recently Mark has undertaken a significant amount of research into the broad area of Health Economics, Big Data and trade flows. He gained his PhD from Monash University, Australia, in 1997, and a BA (Honours), First Class, Economics, in 1989, from the University of Sussex, UK. He teaches primarily into the econometric streams.
Weekly seminar series
As part of our centre's vibrant research culture, we host a weekly seminar series. Visiting and invited researchers present current research relating to the economics of health and wellbeing, and the healthcare sector. Visitors are welcome to join these sessions where discussion and debate is encouraged.
For further information on our seminar series, please contact shannon.stanwell@monash.edu