Johan Fellman | Hanken School of Economics (original) (raw)
Papers by Johan Fellman
Teaching Statistics, 1989
Springer eBooks, 2011
There has been a large number of studies in which the scientists have built models for income dis... more There has been a large number of studies in which the scientists have built models for income distributions. As an alternative, some have built models for Lorenz curves. The step from Lorenz curve to distribution function is more difficult than the step from distribution function to Lorenz curve. There is a difference between advanced and simple Lorenz models. Advanced models with several parameters yield a better fit to data, but are difficult to connect to exact income distributions. Simple one-parameter models can more easily be associated with the corresponding income distribution, but when statistical analyses are performed the goodness of fit is often poor. In this study, simple models are considered and the results compared with results obtained by numerical methods without any assumptions concerning the Lorenz model.
Journal of biometrics & biostatistics, 2021
Early Human Development, Feb 1, 2020
Seasonality of demographic data has been of great interest. The seasonality depends mainly on cli... more Seasonality of demographic data has been of great interest. The seasonality depends mainly on climatic conditions, and the findings may vary from study to study. Commonly, the studies are based on monthly data. The population at risk plays a central role. For births or deaths over short periods, the population at risk is proportional to the lengths of the months. Hence, one must analyse the number of births (deaths) per day. If one studies the seasonality of multiple maternities, the population at risk is the total monthly number of confinements and the number of multiple maternities in a given month must be compared with the monthly number of all maternities. Consequently, one considers the monthly rates of multiple maternities, the monthly number of births is eliminated and one obtains an unaffected seasonality measure of the rates. In general, comparisons between the seasonality of different data sets presuppose standardization of the data to indices with common means, mainly 100. When seasonal models are applied, one must pay special attention to how well the applied model fits the data. If the goodness of fit is poor, non-significant models obtained can erroneously lead to statements that the seasonality is slight, although the observed seasonal fluctuations are marked. The estimated monthly models chosen are approximately orthogonal and they have little influence on the parameter estimates. Exact orthogonality should be obtained if the data are equidistant, that is, if the months are of equal length (e.g. 30 days), corresponding to 30 ∘. Exactly equidistant data can be observed when circadian rhythms (24 h) are studied. In this study, we compare seasonal models with models with exact orthogonality.
Acta geneticae medicae et gemellologiae, Apr 1, 1988
In a paper in this journal Alien and Hrubec (1988) refer to the author of this note. In order to ... more In a paper in this journal Alien and Hrubec (1988) refer to the author of this note. In order to bring the personal communication to a broader audience some results and some references are given here. Alien and Hrubec assume a Constant MZ ratio and suggest the model
International Encyclopedia of Statistical Science, 2011
Asian Journal of Probability and Statistics, May 24, 2018
The sex ratio (SR) is usually defined as the number of males per 100 females within an area or, a... more The sex ratio (SR) is usually defined as the number of males per 100 females within an area or, as in this study, the proportion of males among all births (P M). It has been observed that among newborns, there is typically a slight excess number for boys compared to girls. Consequently, the SR becomes greater than 100, which is around 106 in number, and the chance of new born males is around 0.515. Attempts have been made to identify the factors those are influencing the level of the P M. Previous researches stated that where prenatal losses are low, as in the Western countries, the SRs are also become high around 105 to 106, but in areas where the frequencies of prenatal losses are relatively high then the SRs are found to be low around 102. Later on several researches have focused on temporal, regional and seasonal fluctuations of SR. In general, factors that affect the SR within the families remain poorly understood. Attempts to identify such factors in national birth registers are also remained to be unsuccessful. Recently, SR studies have mainly concentrated on the identification of general but occasional factors. In this study, we tried to identify the effects of issues like maternal age and type of delivery (live-and stillborn, singletons and multiples) to identify the controlling parameters of sex ratio during birth. Post experimental outcome showed that there is no significant difference between live-and stillborn and maternal age had as no significant effect for controlling sex ratio. The SR is higher among singletons than that of multiples, but there is no significant difference obtained in SR between twins and triplets. Among singletons the temporal differences are non-significant, but for twins and triplets, significant temporal differences were obtained.
Theoretical Economics Letters, 2018
Scientists have analysed different methods for numerical estimation of Gini coefficients. Using L... more Scientists have analysed different methods for numerical estimation of Gini coefficients. Using Lorenz curves, various numerical integration attempts have been made to identify accurate estimates. Central alternative methods have been the trapezium, Simpson and Lagrange rules. They are all special cases of the Newton-Cotes methods. In this study, we approximate the Lorenz curve by polynomial regression models and integrate optimal regression models for numerical estimation of the Gini coefficient. The attempts are checked on theoretical Lorenz curves and on empirical Lorenz curves with known Gini indices. In all cases the proposed methods seem to be a good alternative to earlier methods presented in the literature.
Acta Paediatrica, Aug 14, 2016
This issue of Acta Paediatrica contains a paper by Grech and Borg that explores the seasonality o... more This issue of Acta Paediatrica contains a paper by Grech and Borg that explores the seasonality of sex ratios at birth and the effect of the famous volcanic eruption in April 2010, which caused widespread disruption to air traffic all over Europe. The authors report that a slight decline in male births was noted after the eruption and conclude that this provides further evidence that acute and violent incidents, including natural events, can affect the sex ratio. They also state that the sex ratio is a cheap and reliable indicator of the degree of stress experienced by a given population. This article is protected by copyright. All rights reserved.
Journal of Statistical and Econometric Methods, 2012
There has been a large number of studies in which the scientists have built models for income dis... more There has been a large number of studies in which the scientists have built models for income distributions. As an alternative, some have built models for Lorenz curves. The step from Lorenz curve to distribution function is more difficult than the step from distribution function to Lorenz curve. There is a difference between advanced and simple Lorenz models. Advanced models with several parameters yield a better fit to data, but are difficult to connect to exact income distributions. Simple one-parameter models can more easily be associated with the corresponding income distribution, but when statistical analyses are performed the goodness of fit is often poor. In this study, simple models are considered and the results compared with results obtained by numerical methods without any assumptions concerning the Lorenz model.
Theoretical Economics Letters, 2018
Income distributions are commonly unimodal and skew with a heavy right tail. Different skew model... more Income distributions are commonly unimodal and skew with a heavy right tail. Different skew models, such as the lognormal and the Pareto, have been proposed as suitable descriptions of income distribution and applied in specific empirical situations. More wide-ranging tools have been introduced as measures for general comparisons. In this study, we review the income analysis methods and apply them to specific Lorenz models.
Advances and Applications in Statistics
Let X be the pre- and Y be the post-transfer income. In earlier studies we have considered the cl... more Let X be the pre- and Y be the post-transfer income. In earlier studies we have considered the class of transfer policies where Y=h(X) is the post-transfer income and h(x) is non-negative, monotone increasing and continuous. We modify this class, allowing h(x) to be discontinuous. If h(x) is discontinuous, then it can have only a countable number of finite positive steps. If there exists an optimal policy which Lorenz dominates all policies in the class, then it must be continuous. We present necessary and sufficient conditions under which a given Lorenz curve L ¯(p) can be generated by a member of the class. These conditions are equivalent to the condition that the transformed variable stochastically dominates the initial variable.
Teaching Statistics, 1989
Springer eBooks, 2011
There has been a large number of studies in which the scientists have built models for income dis... more There has been a large number of studies in which the scientists have built models for income distributions. As an alternative, some have built models for Lorenz curves. The step from Lorenz curve to distribution function is more difficult than the step from distribution function to Lorenz curve. There is a difference between advanced and simple Lorenz models. Advanced models with several parameters yield a better fit to data, but are difficult to connect to exact income distributions. Simple one-parameter models can more easily be associated with the corresponding income distribution, but when statistical analyses are performed the goodness of fit is often poor. In this study, simple models are considered and the results compared with results obtained by numerical methods without any assumptions concerning the Lorenz model.
Journal of biometrics & biostatistics, 2021
Early Human Development, Feb 1, 2020
Seasonality of demographic data has been of great interest. The seasonality depends mainly on cli... more Seasonality of demographic data has been of great interest. The seasonality depends mainly on climatic conditions, and the findings may vary from study to study. Commonly, the studies are based on monthly data. The population at risk plays a central role. For births or deaths over short periods, the population at risk is proportional to the lengths of the months. Hence, one must analyse the number of births (deaths) per day. If one studies the seasonality of multiple maternities, the population at risk is the total monthly number of confinements and the number of multiple maternities in a given month must be compared with the monthly number of all maternities. Consequently, one considers the monthly rates of multiple maternities, the monthly number of births is eliminated and one obtains an unaffected seasonality measure of the rates. In general, comparisons between the seasonality of different data sets presuppose standardization of the data to indices with common means, mainly 100. When seasonal models are applied, one must pay special attention to how well the applied model fits the data. If the goodness of fit is poor, non-significant models obtained can erroneously lead to statements that the seasonality is slight, although the observed seasonal fluctuations are marked. The estimated monthly models chosen are approximately orthogonal and they have little influence on the parameter estimates. Exact orthogonality should be obtained if the data are equidistant, that is, if the months are of equal length (e.g. 30 days), corresponding to 30 ∘. Exactly equidistant data can be observed when circadian rhythms (24 h) are studied. In this study, we compare seasonal models with models with exact orthogonality.
Acta geneticae medicae et gemellologiae, Apr 1, 1988
In a paper in this journal Alien and Hrubec (1988) refer to the author of this note. In order to ... more In a paper in this journal Alien and Hrubec (1988) refer to the author of this note. In order to bring the personal communication to a broader audience some results and some references are given here. Alien and Hrubec assume a Constant MZ ratio and suggest the model
International Encyclopedia of Statistical Science, 2011
Asian Journal of Probability and Statistics, May 24, 2018
The sex ratio (SR) is usually defined as the number of males per 100 females within an area or, a... more The sex ratio (SR) is usually defined as the number of males per 100 females within an area or, as in this study, the proportion of males among all births (P M). It has been observed that among newborns, there is typically a slight excess number for boys compared to girls. Consequently, the SR becomes greater than 100, which is around 106 in number, and the chance of new born males is around 0.515. Attempts have been made to identify the factors those are influencing the level of the P M. Previous researches stated that where prenatal losses are low, as in the Western countries, the SRs are also become high around 105 to 106, but in areas where the frequencies of prenatal losses are relatively high then the SRs are found to be low around 102. Later on several researches have focused on temporal, regional and seasonal fluctuations of SR. In general, factors that affect the SR within the families remain poorly understood. Attempts to identify such factors in national birth registers are also remained to be unsuccessful. Recently, SR studies have mainly concentrated on the identification of general but occasional factors. In this study, we tried to identify the effects of issues like maternal age and type of delivery (live-and stillborn, singletons and multiples) to identify the controlling parameters of sex ratio during birth. Post experimental outcome showed that there is no significant difference between live-and stillborn and maternal age had as no significant effect for controlling sex ratio. The SR is higher among singletons than that of multiples, but there is no significant difference obtained in SR between twins and triplets. Among singletons the temporal differences are non-significant, but for twins and triplets, significant temporal differences were obtained.
Theoretical Economics Letters, 2018
Scientists have analysed different methods for numerical estimation of Gini coefficients. Using L... more Scientists have analysed different methods for numerical estimation of Gini coefficients. Using Lorenz curves, various numerical integration attempts have been made to identify accurate estimates. Central alternative methods have been the trapezium, Simpson and Lagrange rules. They are all special cases of the Newton-Cotes methods. In this study, we approximate the Lorenz curve by polynomial regression models and integrate optimal regression models for numerical estimation of the Gini coefficient. The attempts are checked on theoretical Lorenz curves and on empirical Lorenz curves with known Gini indices. In all cases the proposed methods seem to be a good alternative to earlier methods presented in the literature.
Acta Paediatrica, Aug 14, 2016
This issue of Acta Paediatrica contains a paper by Grech and Borg that explores the seasonality o... more This issue of Acta Paediatrica contains a paper by Grech and Borg that explores the seasonality of sex ratios at birth and the effect of the famous volcanic eruption in April 2010, which caused widespread disruption to air traffic all over Europe. The authors report that a slight decline in male births was noted after the eruption and conclude that this provides further evidence that acute and violent incidents, including natural events, can affect the sex ratio. They also state that the sex ratio is a cheap and reliable indicator of the degree of stress experienced by a given population. This article is protected by copyright. All rights reserved.
Journal of Statistical and Econometric Methods, 2012
There has been a large number of studies in which the scientists have built models for income dis... more There has been a large number of studies in which the scientists have built models for income distributions. As an alternative, some have built models for Lorenz curves. The step from Lorenz curve to distribution function is more difficult than the step from distribution function to Lorenz curve. There is a difference between advanced and simple Lorenz models. Advanced models with several parameters yield a better fit to data, but are difficult to connect to exact income distributions. Simple one-parameter models can more easily be associated with the corresponding income distribution, but when statistical analyses are performed the goodness of fit is often poor. In this study, simple models are considered and the results compared with results obtained by numerical methods without any assumptions concerning the Lorenz model.
Theoretical Economics Letters, 2018
Income distributions are commonly unimodal and skew with a heavy right tail. Different skew model... more Income distributions are commonly unimodal and skew with a heavy right tail. Different skew models, such as the lognormal and the Pareto, have been proposed as suitable descriptions of income distribution and applied in specific empirical situations. More wide-ranging tools have been introduced as measures for general comparisons. In this study, we review the income analysis methods and apply them to specific Lorenz models.
Advances and Applications in Statistics
Let X be the pre- and Y be the post-transfer income. In earlier studies we have considered the cl... more Let X be the pre- and Y be the post-transfer income. In earlier studies we have considered the class of transfer policies where Y=h(X) is the post-transfer income and h(x) is non-negative, monotone increasing and continuous. We modify this class, allowing h(x) to be discontinuous. If h(x) is discontinuous, then it can have only a countable number of finite positive steps. If there exists an optimal policy which Lorenz dominates all policies in the class, then it must be continuous. We present necessary and sufficient conditions under which a given Lorenz curve L ¯(p) can be generated by a member of the class. These conditions are equivalent to the condition that the transformed variable stochastically dominates the initial variable.