Cochran-Hansen Prize 2023
Competition for Young Survey Statisticians from Developing and Transitional Countries
In celebration of its 25th anniversary in 1999, the International Association of Survey Statisticians (IASS) established the Cochran-Hansen Prize, which is awarded every two years for the best paper on survey research methods submitted by a young statistician from a developing or transition country. In the 2023 edition, the Cochran-Hansen Prize consists of research expenses in a total of €1500 to be executed until February 3rd, 2025.
As the prize winner will be invited to present his or her paper at the 64th World Statistics Congress of the International Statistical Institute (https://www.isi2023.org/conferences/ottawa-2023/) to be held in Ottawa, Canada, 16-20 July 2023, this value will cover the WSC registration. The remaining expenses may include registration at WSC short courses, books, journal subscriptions or publication fees, registration, and travel expenses for attending conferences or short courses, and travel expenses of research visits. Credit should be given to IASS support in the conference presentations or in the publications supported by the Cochran-Hansen Prize.
Participation in the competition for the prize is restricted to young statisticians from developing countries (https://www.isi-web.org/capacity-building/developing-countries) that are living in such countries and were born in 1988 or later.
A paper submitted for the competition must consist of original work which is either unpublished or has been published after February 3rd, 2021. A paper may be based on a university thesis and should be written in English. The deadline for submission of papers for the 2023 prize is February 3rd, 2023. All papers must be sent to the chair of the IASS 2021 Cochran-Hansen Prize Committee, Prof. Nikos Tzavidis, email address firstname.lastname@example.org
Each submission must be accompanied by a cover letter, stating the author’s year of birth, nationality, and country of residence. The cover letter should also indicate if the paper submitted is based on a PhD thesis and, in the case of a joint paper, the contribution to the paper made by the prize competitor. The papers submitted will be reviewed by members of the Cochran-Hansen Prize Committee appointed by the IASS. The decision of the Committee will be final. The prize winner will be notified on or before March 31st, 2023, by email.
For further information, please contact Prof. Nikos Tzavidis
University of Southampton, UK
Cochran-Hansen Prize Laureates 1999-2023
- 2023: Alejandra Arias-Salazar (Costa Rica) and Ziqing Dong (China)
- 2021: Guilherme Anthony Pinheiro Jacob, Brazil
- 2019: Diego Andres Perez Ruiz, Mexico
- 2017: Girish Chandra, India
- 2015: Santanu Pramanik, India and Kevin Carl Santos, Philippines
- 2013: Emilio Lopez Escobar, Mexico
- 2011: Solange Correa, Brazil
- 2009: Hukum Chandra, India
- 2007: Marcel de Toledo Vieira, Brazil
- 2005: Maiki Ilves, Estonia
- 2003: Krishna Mohan Palipudi, India
- 2001: Kristiina Rajaleid, Estonia
- 1999: Noor Muhammad Farid, Indonesia and Enal Pungas, Estonia
Cochran-Hansen Prize 2021
The committee for the Cochran-Hansen competition for young survey statisticians from developing or transition countries has decided to award the 2021 prize to Guilherme Anthony Pinheiro Jacob from Brazil. He receives the award for the paper Estimation of gross flows under nonresponse and complex sampling design.
The work of the committee
The 2021 prize committee consisted of Isabel Molina from Universidad Carlos III de Madrid (chair), Yves Tillé from Université de Neuchâtel and Jean-François Beaumont, from Statistics Canada. It has evaluated two candidate papers by young authors from South Africa and Brazil. Both papers are unpublished. One paper has two authors, but the candidate’s role and main contribution have been clarified. The committee members have individually assessed and ranked all papers and the final choice of the prize winner was made unanimously in a video conference held 15th March 2021.
The winning paper and motivation
The paper presents methods to estimate gross flows, which describe the changes in the distribution of a categorical variable along two different time points observed in a longitudinal survey. It also describes the new R package surf developed by the candidate, which implements these methods, producing estimates of the model parameters, together with their standard errors, as well as Rao-Scott adjusted Pearson chi-squared test (Rao and Scott 1981). The implemented methods adjust for possibly nonrandom nonresponse according to Stasny (1987) and it accounts for complex designs, by using the Maximum Pseudo-Likelihood extension by Gutiérrez (2014). The paper also presents an application, in which gross labour flows are analyzed using real data from Brazil’s Continuous National Household Sample Survey (PNADC). The estimation of gross flows from longitudinal surveys is an important problem for survey research and survey practice. Moreover, the R package represents a great tool for practitioners and the application conducted is of interest.
- Rao, J. N. K. and Scott, A. J. (1981). The Analysis of Categorical Data from Complex Sample Surveys: Chi-Squared Tests for Goodness of Fit and Independence in Two-Way Tables. Journal of the American Statistical Association, 76, 221-230, https://www.tandfonline.com/doi/abs/10.1080/01621459.1981.10477633
- Stasny, E. A. (1987). Some Markov-Chain Models for Nonresponse in Estimating Gross Labor Force Flows. Journal of Official Statistics, 3, 359-373.
- Gutiérrez, H. A. (2014). Modelos para estimar cambios brutos en encuestas rotativas con ausencia de resposta en diseños de muestreo complejos. Ph.D. thesis, Universidad Nacional de Colombia, Facultad de Ciencias, Departamento de Estadística, Bogotá, Colombia.
Short Bio of the Prize Winner
Guilherme A. Pinheiro Jacob was born on June 21st, 1991 in Manaus, Amazonas, Brazil. He studied for a B.Sc in Economics at the Federal University of Amazonas in Manaus, Brazil, and completed a MSc. in “Population, Territory and Public Statistics” at the National School of Statistical Sciences (ENCE/IBGE) in Rio de Janeiro, Brazil, where he is currently a PhD candidate. He was also Leslie Kish Fellow at the University of Michigan’s 2020 Sampling Program for Survey Statisticians.
Cochran-Hansen Prize 2019
The experience of Diego Andres Perez Ruiz is detailed on pg.8 of The Survey Statistician no. 81
Cochran-Hansen Prize 2017
The winner of the 2017 Cochran-Hansen Prize was Girish Chandra (India). The title of his paper was:
Ranked set sampling approach for estimating response of developmental programs with linear impacts under successive phases
Girish Chandra presented his paper at the 61st World Statistics Congress in Marrakech 16-21 July, 2017
Report on the Cochran-Hansen Prize 2015
The Cochran-Hansen Prize of the IASS is awarded every two years for the best paper on survey research methods submitted by a young statistician from a developing or transition country. Participation in competition for the 2015 prize was restricted to young statisticians from developing and transition countries who were living in such countries and were born in 1980 or after. The definition of the target countries was based on the list of countries adhered by the International Statistical Institute. The Cochran-Hansen Prize consists of books and journal subscriptions in the value of EUR 500.
A total of 16 papers were submitted for the 2015 competition. Eight papers from seven different countries (Cameroon, India, Iran, Nigeria, Philippines, Turkey and South Africa) were accepted for review by the members of the Cochran-Hansen Prize Committee appointed by the IASS. The committee members were Risto Lehtonen, Jean Opsomer and Marcel de Toledo Vieira.
The reviewed papers were interesting, timely and covered widely the area of survey research methods. Two papers were ranked highest in the independent review by the jury members. The jury decided to award these two best papers. The winners are Santanu Pramanik (Research Scientist, Public Health Foundation of India) and Kevin Carl P. Santos (Assistant Professor, University of the Philippines-Diliman School of Statistics).
The paper entitled “Selection of Prior for the Variance Component and Approximations for Posterior Moments in the Fay-Herriot Model” by Santanu Pramanik is based on his PhD thesis in statistics completed at University of Maryland. The abstract of the paper summarizes the method as follows.
“In the Fay-Herriot model, a prior distribution for the variance component allows posterior moments to be approximated with the Laplace method, avoiding computer intensive Monte Carlo Markov chains. The extremely skewed posterior distribution of the variance component results from the asymmetry of the parameter space with variance parameters constrained to be positive. The prior avoids the extreme skewness of the posterior in contrast to the commonly used uniform prior. With this prior, the mean squared error and coverage in the approximate hierarchical Bayes method are satisfactory when used to estimate small area means. Computation time is shorter than with Monte Carlo Markov chains. The approximations give easy interpretations of Bayesian methods and highlight frequentist properties of the parameters”
The paper entitled “Improving Predictive Accuracy of Logistic Regression Model Using Ranked Set Samples” by Kevin Carl P. Santos is based on his M.S thesis in statistics completed at the School of Statistics of the University of Philippines-Diliman, School of Statistics. As summarized in the abstract of the paper:
“Logistic regression is often confronted with separation of likelihood problem and rare events. We propose to address this issue by drawing sample using ranked set sampling (RSS). Simulation studies illustrated the advantage in terms of predictive ability of logistic regression with RSS in small populations regardless of the distribution of the binary responses. As the sample and population sizes increase, the predictive ability of model from RSS also improves but it becomes comparable to fitted models using simple random samples (SRS). Furthermore, RSS mitigates the problem of separation of likelihood especially when the population size is relatively large. Lastly, even in the presence of ranking errors, RSS still yielded higher predictive power than its SRS counterpart.”
The prize winners were invited to present their papers at the 2015 World Statistics Congress of the ISI. The IASS congratulates the winners. The IASS wants to thank all authors who submitted a paper to the competition.