The following discussion papers may be revised afterward.
Please ask the author for the latest version of the papers.
- Hoshino, N. (2023) "Differentially private sampling from a
finite population".
Discussion Paper No. 74, Faculty of
Economics and Management, Kanazawa University.
- Hoshino, N. (2021) "Urn models closed under resizing".
ISM research memorandum, No. 1215, The Institute of
Statistical Mathematics.
- Hoshino, N. (2020) "Firm foundation for statistical
disclosure control".
Discussion Paper No. 52, Faculty of
Economics and Management, Kanazawa University.
(Published as "A firm foundation for statistical disclosure control" in
Japanese Journal of Statistics and Data Science
, Vol. 3, 721-746, 2020, after revision.)
- Hu, J. and Hoshino, N. (2018)
"The Quasi-Multinomial Synthesizer for Categorical Data".
Privacy in Statistical Databases PSD 2018, Lecture Notes in Computer Science,
Vol. 11126, 75-91.
- Hoshino, N. (2014) "Learning from the experience
of publishing useful anonymized data".
Information Processing Society of Japan Journal,
Vol. 50, No. 9, 1956-1963. (In Japanese.)
- Hoshino, N. (2013) "Evidence based anonymization".
Discussion Paper No.21, Faculty of
Economics and Management, Kanazawa University. (In Japanese, Published in
Journal of the Japan Statistical Society, Series J, Vol. 46, 1-42, 2016, after revision.)
- Hoshino, N. (2010) "Issues on disseminating Japanese official microdata".
Discussion Paper No.15, Faculty of
Economics, Kanazawa University. (In Japanese, Published in
Journal of the Japan Statistical Society, Series J, Vol. 40, 23-45, 2010, after revision.)
- Hoshino, N. (2008) "Random partitioning over a sparse contingency
table".
Discussion Paper No.12, Faculty of
Economics, Kanazawa University. (Published in
Annals of the Institute of Statistical Mathematics, Vol. 64, 457-474, 2012, after revision.)
- Hoshino, N. (2006) "The quasi-multinomial distribution as a tool
for disclosure risk assessment",
Discussion Paper No.9, Faculty of
Economics, Kanazawa University.
(Published in
Journal of Official Statistics, Vol. 25, 269-291, 2009,
after revision.)
- Hoshino, N. (2005) "On a limiting quasi-multinomial distribution",
Discussion Paper CIRJE-F-361, Center
for International Research on the Japanese Economy, Faculty of Economics,
The University of Tokyo.
- Hoshino, N. (2004) "Modeling strategy for the risk assessment of
privacy", Proceedings of the 16th RAMP Symposium, 133-148.
- Yamashita, T., Honda, M., Takatori, H., Nishino, R., Hoshino, N.
and Kaneko, S. (2004) "Genome-wide transcriptome mapping analysis
identifies organ-specific gene expression patterns along human
chromosomes", Genomics, Vol. 84, 867-875.
- Hoshino, N. (2003) "Microdata disclosure risk evaluation with
superpopulation models: a review", Proceedings of the Institute
of Statistical Mathematics, Vol. 51, No. 2, 297-319. (In Japanese.)
- Hoshino, N. (2002a)
"On limiting random partition structure
derived from the conditional inverse Gaussian-Poisson distribution",
Technical Report CMU-CALD-02-100, School of Computer Science,
Carnegie Mellon University.
(Published as "A discrete multivariate distribution resulting from
the law of small numbers" in
Journal of Applied Probability, Vol. 43, 852-866,
2006, after revision.)
- Hoshino, N. (2002b)
"Engen's extended negative binomial model revisited",
Discussion Paper 2002-1, Faculty of Economics, Kanazawa University.
(Published in
Annals of the Institute of Statistical Mathematics, Vol. 57,
369-387, 2005,
after revision.)
- Hoshino, N. (2001)
"On a conditional inverse Gaussian-Poisson distribution",
Technical Report CMU-CALD-01-102,
School of Computer Science, Carnegie Mellon University.
(Published as "Random clustering based on the conditional
inverse Gaussian-Poisson distribution" in
Journal of the Japan Statistical Society,
Vol. 33, 105-117, 2003, after revision.)
- Hoshino, N. (2000)
"Applying Pitman's sampling formula to microdata disclosure risk
assessment",
Discussion Paper 2000-1, Faculty of Economics, Kanazawa University.
(Published in
Journal of Official Statistics,
Vol. 17, 499-520, 2001, after revision.)
- Hoshino, N. and Takemura, A. (1998)
"On the relation between logarithmic series model and other
superpopulation models useful for microdata disclosure risk assessment",
Discussion Paper 98-F-8, Faculty of Economics, University of Tokyo.
(Published as "Relationship between logarithmic series model
and other superpopulation models useful for microdata
disclosure risk assessment" in
Journal of the Japan Statistical Society,
Vol.28, 125-134, 1998, after revision.)
- Hoshino, N. and Takemura, A. (1997)
"On Reduction of Finite Sample Variance by Extended Latin Hypercube
Sampling",
Discussion Paper 97-F-7, Faculty of Economics, University of Tokyo.
(Published in
Bernoulli, Vol. 6, 1035-1050, 2000, after revision.)
E-mail:
hoshino @
kenroku.kanazawa-u.ac.jp
Return