排序方式: 共有19条查询结果,搜索用时 15 毫秒
1.
Longitudinal data frequently arises in various fields of applied sciences where individuals are measured according to some ordered variable, e.g. time. A common approach used to model such data is based on the mixed models for repeated measures. This model provides an eminently flexible approach to modeling of a wide range of mean and covariance structures. However, such models are forced into a rigidly defined class of mathematical formulas which may not be well supported by the data within the whole sequence of observations. A possible non-parametric alternative is a cubic smoothing spline, which is highly flexible and has useful smoothing properties. It can be shown that under normality assumption, the solution of the penalized log-likelihood equation is the cubic smoothing spline, and this solution can be further expressed as a solution of the linear mixed model. It is shown here how cubic smoothing splines can be easily used in the analysis of complete and balanced data. Analysis can be greatly simplified by using the unweighted estimator studied in the paper. It is shown that if the covariance structure of random errors belong to certain class of matrices, the unweighted estimator is the solution to the penalized log-likelihood function. This result is new in smoothing spline context and it is not only confined to growth curve settings. The connection to mixed models is used in developing a rough testing of group profiles. Numerical examples are presented to illustrate the techniques proposed. 相似文献
2.
Tapio Nummi 《Journal of applied statistics》2000,27(2):235-243
In this paper, we propose a method for the analysis of growth curve models when also the regressor variable may be measured with errors. Two classes of structure for errors in regressors are discussed. For complete and balanced data, estimators for the model parameters are derived under the maximum-likelihood framework. Numerical examples are provided to illustrate the proposed technique. 相似文献
3.
Tapio Palokangas 《LABOUR》2004,18(2):191-205
This paper presents a growth model with two sectors. In the high‐tech sector, R&D increases productivity and union–firm bargaining determines wages, but in the traditional sector there are neither R&D nor labour unions. The government is able to regulate union bargaining power. The main results are as follows. Because firms try to escape wage increases through the improvement of productivity by R&D, the increase in union bargaining power boosts R&D and growth. It is welfare enhancing to strengthen (weaken) unions when the growth rate is below (above) some critical level. A specific rule is presented for when de‐unionization is socially desirable. 相似文献
4.
Food-chain changes in urban and industrial sites may limit breeding-time resources (e.g. food availability) for small insectivorous passerines. We used a long-term data set of pied flycatchers (Ficedula hypoleuca), collected from one of the most polluted sites in Finland during the past 23 years to study the effects of metal pollution on body condition of breeding females. Our results show that body mass started to decline already some days before hatching, indicating a preparation of females to forthcoming chick feeding period. We did not find long-term temporal trends in female body condition index (BCI) in spite of considerably reduced metal emissions during the study period. However, females had higher BCI in polluted than in unpolluted areas during the incubation period. For both incubation and nestling periods the body condition was lower for later breeders, though the condition index decreased slightly faster in relation to hatching date in polluted areas, which may be due to more drastic decrease in nutrition rich food abundance. Temperature and clutch size were positively associated with BCI during the incubation period, but not in the nestling period. Overall, our data suggest that environmental pollution modifies important life-history traits, potentially via indirect effects of higher environmental variability and changed phenology in polluted environment. 相似文献
5.
Tapio Nummi Jyrki Möttönen 《Journal of the Royal Statistical Society. Series C, Applied statistics》2004,53(3):495-505
Summary. In a modern computer-based forest harvester, tree stems are run in sequence through the measuring equipment root end first, and simultaneously the length and diameter are stored in a computer. These measurements may be utilized for example in the determination of the optimal cutting points of the stems. However, a problem that is often passed over is that these variables are usually measured with error. We consider estimation and prediction of stem curves when the length and diameter measurements are subject to errors. It is shown that only in the simplest case of a first-order model can the estimation be carried out unbiasedly by using standard least squares procedures. However, both the first- and the second-degree models are unbiased in prediction. Also a study on real stem is used to illustrate the models that are discussed. 相似文献
6.
Paulette V. Hunter Thomas Hadjistavropoulos William E. Smythe David C. Malloy Sharon Kaasalainen Jaime Williams 《Journal of Aging Studies》2013,27(3):276-287
Purpose of the studyInterest in person-centred dementia care has flourished in the last two decades. Despite growing interest in the development and implementation of person-centred approaches to dementia care, important empirical questions remain. For instance, although Kitwood (1997) emphasized that personhood, a status extended by others, is at the heart of person-centred care, to our knowledge, no one has demonstrated empirically that beliefs about patient status influence how care is provided. The purpose of this series of three studies was to operationalize Kitwood's definition of personhood in order to test this hypothesis.Design and methodsTo operationalize Kitwood's definition of personhood, we generated items to create the Personhood in Dementia Questionnaire (PDQ; Study 1). We then completed preliminary tests of the PDQ's convergent and discriminant validity (Study 2). Finally, we examined the PDQ's relationships with other constructs such as burnout and job satisfaction, and we used linear regression to test the hypothesis that health providers' beliefs about personhood influence intended approaches to dementia care (Study 3).ResultsIn Study 1, we generated a pool of 64 potential questionnaire items. In Study 2, a 20-item version of the PDQ demonstrated good internal consistency, resistance to socially desirable responding, and evidence of convergent and discriminant validity. In Study 3, PDQ scores accounted for a significant proportion of variance in health providers' intended approaches to dementia care, including pain management. PDQ scores were not related to job satisfaction or to most aspects of burnout.ImplicationsThese results provide the first direct empirical evidence of Kitwood's (1997) theory that beliefs about patient personhood have the potential to influence health providers' care decisions, including decisions about pain management. 相似文献
7.
Tapio Nummi Tiina Hakanen Liudmila Lipiäinen Ulla Harjunmaa Matti K. Salo Marja-Terttu Saha 《Journal of applied statistics》2014,41(7):1422-1435
The aim of this study is to investigate the early development of body mass index (BMI), a standard tool for assessing the body shape and average level of adiposity for children and adults. The main aim of the study is to identify the primary trajectories of BMI development and to investigate the changes of certain growth characteristics over time. Based on our longitudinal data of 4223 Finnish children, we took anthropometric measurements from birth up to 15 years of age for birth years 1974, 1981, 1991 and 1995, but only up to 11 years of age for the birth year 2001. As a statistical method, we utilized trajectory analysis with the methods of nonparametric regression. We identified four main trajectories of BMI growth. Two of these trajectories do not seem to follow the normal growth pattern. The highest growth track appears to yield to a track that may yield to overweight and the low birth BMI track shows that the girls’ track differs that of boys on the same track, and on the normal tracks. The so-called adiposity rebound time decreased over time and started earlier for those on the overweight track. According to our study, this kind of acceleration of growth might be more of a general phenomenon that also relates to the other phases of BMI development. The major change seems to occur especially for those children on high growth tracks. 相似文献
8.
Tapio Kaasalainen 《Journal of Housing for the Elderly》2013,27(3):271-294
ABSTRACTElderly housing policies in Finland emphasize aging in place and preparing the existing housing stock for the predicted increase in the aged population. Timely home modifications that enhance mobile accessibility are a focal target for these policies. This article introduces the idea of mass-customizable architectural accessibility improvement models (AIMs) that have been developed for typical Finnish flats. The applicability and generalizability of an AIM designed for an archetypal two-room flat is tested by applying it to nine case buildings in the city of Tampere. The model was found to be beneficial for 42 of the 45 rooms in the research material. 相似文献
9.
Tapio Palokangas 《LABOUR》2014,28(4):359-375
This document examines optimal capital taxation with wage‐setting labour unions when the government taxes consumption, labour, and capital. The results are as follows. If unions can commit themselves to particular wages for a long period, then there is no hold‐up problem. Otherwise, the hold‐up problem creates a positive link from capital accumulation to the wage. The optimal labour subsidy is positive and greater in the presence than in the absence of the hold‐up problem. The optimal capital subsidy is zero in the absence, but positive in the presence of the hold‐up problem. 相似文献
10.
Tapio Malinen 《Australian and New Zealand Journal of Family Therapy》2001,22(4):214-216
This article is a carnival: besides Peter Lang, the protagonist it gives appearance and voice to many other people, as in a play or dance. In this dialogue, facts are not considered to be anything given; they are constructed in the relationships and interactions, thoughts formulate themselves in the carnival whirl of language. The postmodern team appearing in the article have taken their voices from the literature. They are saying partly what they have said in print partly what they might have said – or will be saying in the future. What happened to the director of the discussion was the same thing that can, in a best‐case scenario, happen to a therapist: the director was simultaneously the writer and the product of the story. Through it he died and was reborn. You can never predict the future through the past because the past changes all the time (Mihail Bakhtin). To be systemic means you accept everything, defy everything, accept nothing. Life is like a carnival or like a parody (Peter Lang). 相似文献