liu.seSearch for publications in DiVA
Change search
Link to record
Permanent link

Direct link
von Rosen, Dietrich
Alternative names
Publications (10 of 68) Show all publications
Filipiak, K., von Rosen, D., Singull, M. & Rejchel, W. (2024). Estimation under inequality constraints in univariate and multivariate linear models. Linköping: Linköping University Electronic Press
Open this publication in new window or tab >>Estimation under inequality constraints in univariate and multivariate linear models
2024 (English)Report (Other academic)
Abstract [en]

In this paper least squares and maximum likelihood estimates under univariate and multivariate linear models with a priori information related to maximum effects in the models are determined. Both loss functions (the least squares and negative log-likelihood) and the constraints are convex, so the convex optimization theory can be utilized to obtain estimates, which in this paper are called Safety belt estimates. In particular, the complementary slackness condition, common in convex optimization, implies two alternative types of solutions, strongly dependent on the data and the restriction.

It is experimentally shown that, despite of the similarity to the ridge regression estimation under the univariate linear model, the Safety belt estimates behave usually better than estimates obtained via ridge regression. Moreover, concerning the multivariate model, the proposed technique represents a completely novel approach.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2024. p. 34
Series
LiTH-MAT-R, ISSN 0348-2960 ; 2024/01
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:liu:diva-201906 (URN)LiTH-MAT-R-2024/01 (ISRN)10.3384/LiTH-MAT-R-2024-01 (DOI)
Note

This is a technical report and has not been externally reviewed.

Available from: 2024-03-26 Created: 2024-03-26 Last updated: 2024-06-18Bibliographically approved
Umunoza Gasana, E., von Rosen, D. & Singull, M. (2024). Moments of the likelihood-based discriminant function. Communications in Statistics - Theory and Methods, 53(3), 1122-1134
Open this publication in new window or tab >>Moments of the likelihood-based discriminant function
2024 (English)In: Communications in Statistics - Theory and Methods, ISSN 0361-0926, E-ISSN 1532-415X, Vol. 53, no 3, p. 1122-1134Article in journal (Refereed) Published
Abstract [en]

The likelihood approach used in this paper leads to quadratic discriminant functions. Classification into one of two known multivariate normal populations with a known and unknown covariance matrix are separately considered, where the two cases depend on the sample size and an unknown squared Mahalanobis distance. Their exact distributions are complicated to obtain. Therefore, moments for the likelihood based discriminant functions are established to express the basic characteristics of respective distribution.

Place, publisher, year, edition, pages
Taylor & Francis Inc, 2024
Keywords
classification; discriminant function; maximum likelihood; moments
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:liu:diva-187405 (URN)10.1080/03610926.2022.2100909 (DOI)000828980500001 ()
Available from: 2022-08-22 Created: 2022-08-22 Last updated: 2024-09-10Bibliographically approved
Liu, S., Trenkler, G., Kollo, T., von Rosen, D. & Baksalary, O. M. (2024). Professor Heinz Neudecker and matrix differential calculus. Statistical papers, 65, 2605-2639
Open this publication in new window or tab >>Professor Heinz Neudecker and matrix differential calculus
Show others...
2024 (English)In: Statistical papers, ISSN 0932-5026, E-ISSN 1613-9798, Vol. 65, p. 2605-2639Article in journal (Refereed) Published
Abstract [en]

The late Professor Heinz Neudecker (1933-2017) made significant contributions to the development of matrix differential calculus and its applications to econometrics, psychometrics, statistics, and other areas. In this paper, we present an insightful overview of matrix-oriented findings and their consequential implications in statistics, drawn from a careful selection of works either authored by Professor Neudecker himself or closely aligned with his scientific pursuits. The topics covered include matrix derivatives, vectorisation operators, special matrices, matrix products, inequalities, generalised inverses, moments and asymptotics, and efficiency comparisons within the realm of multivariate linear modelling. Based on the contributions of Professor Neudecker, several results related to matrix derivatives, statistical moments and the multivariate linear model, which can literally be considered to be his top three areas of research enthusiasm, are particularly included.

Place, publisher, year, edition, pages
SPRINGER, 2024
Keywords
Matrix differential calculus; Random matrix; Statistical moment; Asymptotic distribution; Efficiency comparison; Multivariate linear model
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:liu:diva-198482 (URN)10.1007/s00362-023-01499-w (DOI)001077306400001 ()
Note

Funding Agencies|Finally, we would like to pay tribute to the late Drs. Risto Heijmans, Wolfgang Polasek, and Haruo Yanai, whose dedication to their colleagues and students continues to inspire us. Though they are no longer with us, their legacy lives on.

Available from: 2023-10-16 Created: 2023-10-16 Last updated: 2024-10-08Bibliographically approved
Szczepanska-Alvarez, A., Alvarez, A., Szwengiel, A. & von Rosen, D. (2024). Testing Correlation in a Three-Level Model. Journal of Agricultural Biological and Environmental Statistics, 29(2), 257-276
Open this publication in new window or tab >>Testing Correlation in a Three-Level Model
2024 (English)In: Journal of Agricultural Biological and Environmental Statistics, ISSN 1085-7117, E-ISSN 1537-2693, Vol. 29, no 2, p. 257-276Article in journal (Refereed) Published
Abstract [en]

In this paper, we present a statistical approach to evaluate the relationship between variables observed in a two-factors experiment. We consider a three-level model with covariance structure Sigma circle times psi(1) circle times psi(2), where Sigma is an arbitrary positive definite covariance matrix, and psi(1) and psi(2) are both correlation matrices with a compound symmetric structure corresponding to two different factors. The Rao's score test is used to test the hypotheses that observations grouped by one or two factors are uncorrelated. We analyze a fermentation process to illustrate the results. Supplementary materials accompanying this paper appear online.

Place, publisher, year, edition, pages
SPRINGER, 2024
Keywords
Three-level model; Rao's score test; Maximum likelihood estimation; Independence test; Factorial design; Kronecker product structured covariance matrix
National Category
Public Health, Global Health and Social Medicine
Identifiers
urn:nbn:se:liu:diva-200062 (URN)10.1007/s13253-023-00575-w (DOI)001101436100002 ()
Available from: 2024-01-15 Created: 2024-01-15 Last updated: 2025-02-20Bibliographically approved
Umunoza Gasana, E., von Rosen, D. & Singull, M. (2023). Edgeworth-type expansion of the density of the classifier when growth curves are classified via likelihood. Linköping: Linköping University Electronic Press
Open this publication in new window or tab >>Edgeworth-type expansion of the density of the classifier when growth curves are classified via likelihood
2023 (English)Report (Other academic)
Abstract [en]

In this paper, probabilities of misclassification of a two-step likelihood-based discriminant rule are established for the classification of growth curves. The defined two-step classifier considers the fact that the growth curves might not belong to any of the two predetermined populations. The distribution for the classifier is approximated via an Edgeworth-type expansion.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2023. p. 15
Series
LiTH-MAT-R, ISSN 0348-2960 ; 2023/02
Keywords
Edgeworth-type expansion, Growth Curve model; Likelihood-based classification; Misclassifications errors
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:liu:diva-193575 (URN)LiTH-MAT-R-2023/02 (ISRN)10.3384/LiTH-MAT-R-2023-02 (DOI)
Available from: 2023-05-08 Created: 2023-05-08 Last updated: 2023-08-22Bibliographically approved
Umunoza Gasana, E., von Rosen, D. & Singull, M. (2023). Moments of the Likelihood-based Classification Function using Growth Curves. Linköping: Linköping University Electronic Press
Open this publication in new window or tab >>Moments of the Likelihood-based Classification Function using Growth Curves
2023 (English)Report (Other academic)
Abstract [en]

The possibility that a new observation can be allocated to an unknown population is considered. von Rosen and Singull (2022) derived a classi cation rule taking into account this perspective. The classi cation rule consists of two criteria. In this paper, the mean and variance of these criteria needed to discriminate between two growth curves are established.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2023. p. 15
Series
LiTH-MAT-R, ISSN 0348-2960 ; 2023/01
Keywords
Classication analysis, growth curves, inverted-Wishart distribution, moments
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:liu:diva-192439 (URN)LiTH-MAT-R--2023/01--SE (ISRN)
Note

This is a technical report and has not been externally reviewed. 

Available from: 2023-03-17 Created: 2023-03-17 Last updated: 2023-06-08Bibliographically approved
Byukusenge, B., von Rosen, D. & Singull, M. (2023). On Residual Analysis in the GMANOVA-MANOVA Model. In: Balakrishnan, Narayanaswamy; Gil, María Ángeles; Martín, Nirian; Morales, Domingo; Pardo, María del Carmen (Ed.), Trends in Mathematical, Information and Data Sciences: A Tribute to Leandro Pardo: (pp. 287-305). Springer International Publishing
Open this publication in new window or tab >>On Residual Analysis in the GMANOVA-MANOVA Model
2023 (English)In: Trends in Mathematical, Information and Data Sciences: A Tribute to Leandro Pardo / [ed] Balakrishnan, Narayanaswamy; Gil, María Ángeles; Martín, Nirian; Morales, Domingo; Pardo, María del Carmen, Springer International Publishing , 2023, p. 287-305Chapter in book (Refereed)
Abstract [en]

In this article, the GMANOVA-MANOVA model is considered. Two different matrix residuals are established. The interpretation of the residuals is discussed and several properties are verified. A data set illustrates how the residuals can be used.

Place, publisher, year, edition, pages
Springer International Publishing, 2023
Series
Studies in Systems, Decision and Control, E-ISSN 2198-4190 ; 445
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:liu:diva-189840 (URN)10.1007/978-3-031-04137-2_24 (DOI)9783031041365 (ISBN)9783031041372 (ISBN)
Available from: 2022-11-09 Created: 2022-11-09 Last updated: 2023-01-26Bibliographically approved
Umunoza Gasana, E., von Rosen, D. & Singull, M. (2022). Approximated misclassification errors for the likelihood based discriminant function via Edgetworth-type expansion. Linköping
Open this publication in new window or tab >>Approximated misclassification errors for the likelihood based discriminant function via Edgetworth-type expansion
2022 (English)Report (Other academic)
Abstract [en]

The exact distribution of a classification function is often complicated to allow for easy numerical calculations of misclassification errors. The use of expansions is one way of dealing with this diculty. In this paper, approximate probabilities of misclassification of the maximum likelihood based discriminant function are established via an Edgeworth-type expansion based on the standard normal distribution for discriminating between two multivariate normal populations.

Place, publisher, year, edition, pages
Linköping: , 2022. p. 17
Series
LiTH-MAT-R, ISSN 0348-2960 ; 2021/08
Keywords
classification rule, discriminant analysis; Edgeworth-type expansion; missclassification errors
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:liu:diva-183306 (URN)LiTH-MAT-R--2021/08--SE (Local ID)LiTH-MAT-R--2021/08--SE (Archive number)LiTH-MAT-R--2021/08--SE (OAI)
Available from: 2022-03-02 Created: 2022-03-02 Last updated: 2023-05-05Bibliographically approved
von Rosen, D. & Singull, M. (2022). Classification of repeated measurements using growth curves. Linköping: Linköping University Electronic Press
Open this publication in new window or tab >>Classification of repeated measurements using growth curves
2022 (English)Report (Other academic)
Abstract [en]

In this paper we consider discrimination between two populations of repeated measurements using growth curve models. We establish a classification procedure that is likelihood based, in that sense that we compare the two likelihoods given that the new observation belongs to respectively population. We also discuss the possibility that we classify the new observation to an unknown population, which we show is natural when considering growth curves.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2022. p. 20
Series
LiTH-MAT-R, ISSN 0348-2960 ; 2021/01
Keywords
Repeated measurements; Discriminant analysis; Growth Curve model; Likelihood based
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:liu:diva-183305 (URN)LiTH-MAT-R--2021/01--SE (Local ID)LiTH-MAT-R--2021/01--SE (Archive number)LiTH-MAT-R--2021/01--SE (OAI)
Available from: 2022-03-02 Created: 2022-03-02 Last updated: 2022-06-21Bibliographically approved
Wamano, F., Atuhaire, L., Ngaruye, I., von Rosen, D. & Singull, M. (2022). Estimation of trends in household living standards in Uganda using a GMANOVA-MANOVA model with rank restrictions. Linköping
Open this publication in new window or tab >>Estimation of trends in household living standards in Uganda using a GMANOVA-MANOVA model with rank restrictions
Show others...
2022 (English)Report (Other academic)
Abstract [en]

Panel survey data from Uganda, as well as data from the 2014 Uganda Population and Housing Census data have been analysed. The Growth Curve model with rank restrictions on parameters was used to estimate the small area means.

The aim of the analysis was to assess change over time in household living standards (welfare), i.e., to investigate whether households display growth in living standards? whether households grow at the same rates? and whether households in different geographical areas of the country grow at the same rates?

Using a GMANOVA-MANOVA model with rank restrictions on parameters, it was established that growth in household standards of living in Uganda varied across small areas. Sub-regions (small areas) with the highest standards of living in Uganda at the endline were Central Urban region, Kampala Urban region and South Western Urban region, while the sub-regions with the lowest standards of living at the endline were North East Rural region, North East Urban region and Eastern Rural (region). The sub-regions with the highest growth rates in standards of living were Mid West Urban region, Mid North Rural region, and South Western Urban region. The sub-regions with the highest decline in standards of living were East Central Rural region, East Rural region and West Nile Urban region.

Place, publisher, year, edition, pages
Linköping: , 2022. p. 18
Series
LiTH-MAT-R, ISSN 0348-2960 ; 2021/02
Keywords
Extended Growth Curve model; rank restrictions on parameters; repeated surveys; small area estimation
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:liu:diva-183304 (URN)LiTH-MAT-R--2021/02--SE (Local ID)LiTH-MAT-R--2021/02--SE (Archive number)LiTH-MAT-R--2021/02--SE (OAI)
Available from: 2022-03-02 Created: 2022-03-02 Last updated: 2022-06-21Bibliographically approved
Organisations

Search in DiVA

Show all publications