María Dolores Martínez-Miranda
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
María Dolores Martínez-Miranda has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Jens Perch Nielsen
Bayes Business School, City St George's University of London London UK
5 shared publications - María Luz Gámiz
Department of Statistics and Operational Research, University of Granada, 18071 Granada, Spain
4 shared publications - Wenceslao González-Manteiga
University of Santiago de Compostela
4 shared publications Enno Mammen
Heidelberg Univ, Inst Appl Math, Heidelberg, Germany
3 shared publications- Antonio Arcos
University of Granada
2 shared publications - Carolin Margraf
Cass Business School, University of London, London EC1Y 8TZ, UK
2 shared publications
Latest Publications
- Open Access
- 2 October 2024
- Published by Springer Nature in Financial Innovation
- Vol. 10 (1) , 1-16
Robustifying and simplifying high-dimensional regression with applications to yearly stock return and telematics data
The availability of many variables with predictive power makes their selection in a regression context difficult. This study considers robust and understandable low-dimensional estimators as building blocks to improve overall predictive power by optimally combining these building blocks. Our new algorithm is based on generalized cross-validation and builds a predictive model step-by-step from a simple mean to more complex predictive combinations. Empirical applications to annual financial returns and actuarial telematics data show its usefulness in the financial and insurance industries.
- 2 October 2024
- Published by Springer Nature in Financial Innovation
- Vol. 10 (1) , 1-16
Open AccessRobustifying and simplifying high-dimensional regression with applications to yearly stock return and telematics data
The availability of many variables with predictive power makes their selection in a regression context difficult. This study considers robust and understandable low-dimensional estimators as building blocks to improve overall predictive power by optimally combining these building blocks. Our new algorithm is based on generalized cross-validation and builds a predictive model step-by-step from a simple mean to more complex predictive combinations. Empirical applications to annual financial returns and actuarial telematics data show its usefulness in the financial and insurance industries.
- Open Access
- 5 July 2022
- Published by Wiley in Biometrical Journal
- Vol. 65 (1)
Goodness‐of‐fit tests in proportional hazards models with random effects
This paper deals with testing the functional form of the covariate effects in a Cox proportional hazards model with random effects. We assume that the responses are clustered and incomplete due to right censoring. The estimation of the model under the null (parametric covariate effect) and the alternative (nonparametric effect) is performed using the full marginal likelihood. Under the alternative, the nonparametric covariate effects are estimated using orthogonal expansions. The test statistic is the likelihood ratio statistic, and its distribution is approximated using a bootstrap method. The performance of the proposed testing procedure is studied through simulations. The method is also applied on two real data sets one from biomedical research and one from veterinary medicine.
- 5 July 2022
- Published by Wiley in Biometrical Journal
- Vol. 65 (1)
Open AccessGoodness‐of‐fit tests in proportional hazards models with random effects
This paper deals with testing the functional form of the covariate effects in a Cox proportional hazards model with random effects. We assume that the responses are clustered and incomplete due to right censoring. The estimation of the model under the null (parametric covariate effect) and the alternative (nonparametric effect) is performed using the full marginal likelihood. Under the alternative, the nonparametric covariate effects are estimated using orthogonal expansions. The test statistic is the likelihood ratio statistic, and its distribution is approximated using a bootstrap method. The performance of the proposed testing procedure is studied through simulations. The method is also applied on two real data sets one from biomedical research and one from veterinary medicine.
- 13 December 2021
- Published by Elsevier in Computational Statistics & Data Analysis
- Vol. 169, 107405
Missing link survival analysis with applications to available pandemic data
- 13 December 2021
- Published by Elsevier in Computational Statistics & Data Analysis
- Vol. 169, 107405
Missing link survival analysis with applications to available pandemic data
- Open Access
- 14 September 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (18) , 2260
Calendar Effect and In-Sample Forecasting Applied to Mesothelioma Mortality Data
In this paper, we apply and further illustrate a recently developed extended continuous chain ladder model to forecast mesothelioma deaths. Making such a forecast has always been a challenge for insurance companies as exposure is difficult or impossible to measure, and the latency of the disease usually lasts several decades. While we compare three approaches to this problem, we show that the extended continuous chain ladder model is a promising benchmark candidate for asbestosis mortality forecasting due to its flexible and simple forecasting strategy. Furthermore, we demonstrate how the model can be used to provide an update for the forecast of the number of deaths due to mesothelioma in Great Britain using in recent Health and Safety Executive (HSE) data.
- 14 September 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (18) , 2260
Open AccessCalendar Effect and In-Sample Forecasting Applied to Mesothelioma Mortality Data
In this paper, we apply and further illustrate a recently developed extended continuous chain ladder model to forecast mesothelioma deaths. Making such a forecast has always been a challenge for insurance companies as exposure is difficult or impossible to measure, and the latency of the disease usually lasts several decades. While we compare three approaches to this problem, we show that the extended continuous chain ladder model is a promising benchmark candidate for asbestosis mortality forecasting due to its flexible and simple forecasting strategy. Furthermore, we demonstrate how the model can be used to provide an update for the forecast of the number of deaths due to mesothelioma in Great Britain using in recent Health and Safety Executive (HSE) data.
- Open Access
- 1 January 2021
- Published by Elsevier in Insurance: Mathematics and Economics
- Vol. 96, 31-52
Calendar effect and in-sample forecasting
- 1 January 2021
- Published by Elsevier in Insurance: Mathematics and Economics
- Vol. 96, 31-52
Open AccessCalendar effect and in-sample forecasting
- Open Access
A Likelihood Approach to Bornhuetter–Ferguson Analysis
A new Bornhuetter–Ferguson method is suggested herein. This is a variant of the traditional chain ladder method. The actuary can adjust the relative ultimates using externally estimated relative ultimates. These correspond to linear constraints on the Poisson likelihood underpinning the chain ladder method. Adjusted cash flow estimates were obtained as constrained maximum likelihood estimates. The statistical derivation of the new method is provided in the generalised linear model framework. A related approach in the literature, combining unconstrained and constrained maximum likelihood estimates, is presented in the same framework and compared theoretically. A data illustration is described using a motor portfolio from a Greek insurer.
Open AccessA Likelihood Approach to Bornhuetter–Ferguson Analysis
A new Bornhuetter–Ferguson method is suggested herein. This is a variant of the traditional chain ladder method. The actuary can adjust the relative ultimates using externally estimated relative ultimates. These correspond to linear constraints on the Poisson likelihood underpinning the chain ladder method. Adjusted cash flow estimates were obtained as constrained maximum likelihood estimates. The statistical derivation of the new method is provided in the generalised linear model framework. A related approach in the literature, combining unconstrained and constrained maximum likelihood estimates, is presented in the same framework and compared theoretically. A data illustration is described using a motor portfolio from a Greek insurer.
- 3 July 2018
- Published by Taylor & Francis in Mathematical Population Studies
- Vol. 25 (3) , 123-142
Graphical goodness-of-fit test for mortality models
Candidate parametric mortality models are tested graphically. If the model is correct, the transformed data are distributed exponentially. The graphical test is based on scale and space inference. It involves smoothing of the hazard rate and simultaneous confidence intervals. It is applied to a frailty model used to set annuity reserves. Simulation and the comparison with other non-graphical tests shows that the graphical test helps localize discrepancies of empirical data with respect to the tested model.
- 3 July 2018
- Published by Taylor & Francis in Mathematical Population Studies
- Vol. 25 (3) , 123-142
Graphical goodness-of-fit test for mortality models
Candidate parametric mortality models are tested graphically. If the model is correct, the transformed data are distributed exponentially. The graphical test is based on scale and space inference. It involves smoothing of the hazard rate and simultaneous confidence intervals. It is applied to a frailty model used to set annuity reserves. Simulation and the comparison with other non-graphical tests shows that the graphical test helps localize discrepancies of empirical data with respect to the tested model.
- 23 June 2017
- Published by Taylor & Francis in Journal of Nonparametric Statistics
- Vol. 29 (3) , 636-668
Bandwidth selection for kernel density estimation with length-biased data
Length-biased data are a particular case of weighted data, which arise in many situations: biomedicine, quality control or epidemiology among others. In this paper we study the theoretical properties of kernel density estimation in the context of length-biased data, proposing two consistent bootstrap methods that we use for bandwidth selection. Apart from the bootstrap bandwidth selectors we suggest a rule-of-thumb. These bandwidth selection proposals are compared with a least-squares cross-validation method. A simulation study is accomplished to understand the behaviour of the procedures in finite samples.
- 23 June 2017
- Published by Taylor & Francis in Journal of Nonparametric Statistics
- Vol. 29 (3) , 636-668
Bandwidth selection for kernel density estimation with length-biased data
Length-biased data are a particular case of weighted data, which arise in many situations: biomedicine, quality control or epidemiology among others. In this paper we study the theoretical properties of kernel density estimation in the context of length-biased data, proposing two consistent bootstrap methods that we use for bandwidth selection. Apart from the bootstrap bandwidth selectors we suggest a rule-of-thumb. These bandwidth selection proposals are compared with a least-squares cross-validation method. A simulation study is accomplished to understand the behaviour of the procedures in finite samples.
- Open Access
- 18 July 2016
- Published by MDPI AG in Preprints.org
Graphical Diagnostic for Mortality Data Modeling
The main contribution of this paper is to develop a graphical tool to evaluate the suitability of a candidate parametric model to fit a data set. The practical motivation is to check the adequacy of the so called SAINT model proposed in Jarner and Kryger (2011). This model has been implemented in practice by an important European pension fund concerned with setting annuity reserves for all current or former employees of Denmark. So, one particular relevant question is whether this mortality model is actually fitting old-age. Our graphical test can be described as follows. First we transform the data by means of the parametric model which is being evaluated. Should the model be correct, the transformed data will be in accordance with an Exponential distribution with rate 1. Then we construct a family of local linear hazard estimates based on the data on the transformed scale. Finally we use the statistical tool SiZer to assess the goodness-of-fit of the Exponential distribution to the data on the transformed scale. If the model is correct the SiZer map should not reveal any significant feature in the family of kernel estimates. Our method allow us to establish a diagnostic regarding the validity of the SAINT model when describing mortality patterns in four different countries.
- 18 July 2016
- Published by MDPI AG in Preprints.org
Open AccessGraphical Diagnostic for Mortality Data Modeling
The main contribution of this paper is to develop a graphical tool to evaluate the suitability of a candidate parametric model to fit a data set. The practical motivation is to check the adequacy of the so called SAINT model proposed in Jarner and Kryger (2011). This model has been implemented in practice by an important European pension fund concerned with setting annuity reserves for all current or former employees of Denmark. So, one particular relevant question is whether this mortality model is actually fitting old-age. Our graphical test can be described as follows. First we transform the data by means of the parametric model which is being evaluated. Should the model be correct, the transformed data will be in accordance with an Exponential distribution with rate 1. Then we construct a family of local linear hazard estimates based on the data on the transformed scale. Finally we use the statistical tool SiZer to assess the goodness-of-fit of the Exponential distribution to the data on the transformed scale. If the model is correct the SiZer map should not reveal any significant feature in the family of kernel estimates. Our method allow us to establish a diagnostic regarding the validity of the SAINT model when describing mortality patterns in four different countries.
- Open Access
- 1 March 2016
- Published by Elsevier in Expert Systems with Applications
- Vol. 45, 400-409
Cash flow generalisations of non-life insurance expert systems estimating outstanding liabilities
- 1 March 2016
- Published by Elsevier in Expert Systems with Applications
- Vol. 45, 400-409
Open AccessCash flow generalisations of non-life insurance expert systems estimating outstanding liabilities