| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
- Tajvidi, Nader
(författare)
-
Characterisation and Some Statistical Aspects of Univariate and Multivariate Generalised Pareto Distributions
- 1996
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Extreme value theory is about the distributions of very large or very small values in a time series or stochastic process. This has numerous applications connected with environmental science, civil engineering, materials science and insurance. A rather recent approach for modelling extreme events is the so called peak over threshold (POT) method. The generalised Pareto distribution (GPD) is a two-parameter family of distributions which can be used to model exceedances over a threshold. This thesis consists of three papers. The main focus is on some theoretical and applied statistical issues of univariate and multivariate extreme value modelling. In the first paper we compare the empirical coverage of standard bootstrap and likelihood-based confidence intervals for the parameters and 90\%-quantile of the GPD. By applying a general method of D. N. Lawley, small sample correction factors for likelihood ratio statistics of the parameters and quantiles of the GPD have been calculated. The article also investigates the performance of some bootstrap methods for estimation of accuracy measures of maximum likelihood estimators of parameters and quantiles of the GPD. In the second paper we give a multivariate analogue of the GPD and consider estimation of parameters in some specific bivariate generalised Pareto distributions (BGPD's). We generalise two of existing bivariate extreme value distributions and study maximum likelihood estimation of parameters in the corresponding BGPD's. The procedure is illustrated with an application to a bivariate series of wind data. The main interest in the thesis has been on practicality of the methods so when a new method has been developed, it's performance has been studied with the help of both real life data and simulations. In the third paper we use three previous articles as examples to illustrate difficulties which might arise in application of the theory and methods which may be used to solve them. A common theme in these articles is univariate and multivariate generalised Pareto distributions. However, the discussed problems are of a rather general nature and demonstrate some typical tasks in applied statistical research. We also discuss a general approach to design and implementation of statistical computations.
|
|
| 5. |
- Bergström, Inger, et al.
(författare)
-
Ekonomisystem i mindre företag
- 1993
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The study covers the design and use of accounting information system in small companies. When dicsussing the design of accounting information systems (AIS) we refer to the scope of the system and include management and financial accounting, budgets and ~alculations. We relate the use of AIS as a means to control business activities and include both management of individuals and activities. The study has been carried out of from the perspective of leadership. The aim has been to describe the design and use of AIS systems and to analyse and explain factors of importance to design and use AIS in small companies. The frame of reference comes to define research questions and analysis model. The model includes companies situation, management and leadership, structure of accounting department and the design and use of AIS. Three empirical studies have been done. Sub study 1, which is explorative, resulted in 5 hypotheses on the use of AIS in connection with company size, competitive situation, the manager's level of education, the manager's time spent on participation in day-to-day activities and how economy work is organised. Sub study 2 includes a survey with a response rate of 55% (394 companies). The hypothesis testing shows that there is a covariation between AIS and company size, manager's education and how economy work is organised. In sub study 3, personal interviews were carried out in 11 companies that had either been classified as high or low users of AIS in sub study 2. As a conclusion it is appropriate to modify the used analysis model and to focus more on the manager, even the hypothesis testing in sub study 2 shows that there is a covariation between i.e size and use of AIS. As a reason for this we have found that a special type of individuals become managers "in the large companies". From sub study 3 we have observed that managers classified as high users of AIS are those with a high level of formal education. They collect and use internal as well as external information to a high extent and their decision-making is analytic. The high users of AIS also have a positive attitude to growth and often choose output control. Managers classified as low users of AIS are often those with little formal education. They collect and use small amounts of information and their decision-making is intuitive. In addition they use behavioural control to induce employees to work towards company goals. The low users of AIS also have a negative attitude to growth. Many of the low users of AIS use external help for accounting. To increase the use of AIS in companies that use external aid the dialogue between bookkeeping agencies and their clients should be improved. A better dialogue may result in the use of concepts more in true with company activities, leading to reports produced on a suitable level of aggregation and with proper updating.
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
- Limberg, Louise
(författare)
-
Att söka information för att lära. En studie av samspel mellan informationssökning och lärande
- 1998
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- SUMMARY IN ENGLISH Information seeking, didactics and learning (IDOL) The research interest in exploring a teaching perspective of information seeking emerged out of earlier research findings on students’ information seeking and learning, resulting in conclusions that there is close interaction between the quality of students’ information seeking and the quality of their learning outcomes (Alexandersson & Limberg 2003; 2005; Limberg 1999). Another point of departure for the IDOL study was previous research findings that teachers have vague notions of how to teach information seeking related to students’ research based learning (i.a. Moore 2000). The purpose of the IDOL study was to explore and describe variation in teachers’ and librarians’ experiences of teaching information seeking. Theoretical points of departure The research interest in studying variation led to the adoption of a phenomenographic research approach, where the research is focused on people’s various ways of experiencing a certain phenomenon, in our case, teaching information seeking. The study was based on the assumption that there is a connection between teaching and learning in the object of learning. In the study, information seeking as an object of learning is closely related to the concept of information literacy. This implies that the object of learning is constituted by the goals (the intended learning outcomes) and contents of teaching. In this study we treated information seeking as the object of learning and information literacy as the goals of both teaching and learning. Design The IDOL project was designed as an interview study, closely connected to the teaching practices of the project participants, where the main research interest concerned the contents and methods of teaching information seeking, as seen by teachers and librarians. Individual interviews were conducted with pedagogues (librarians and teachers) from three schools on recurrent occasions over three years. Interviews took their points of departure in concrete assignments carried out with students during the period of the interviews. Questions were also asked about the difficulties identified by project participants that were related to students’ information seeking as well as the criteria they used for assessing the quality of students’ information seeking. Cooperation between librarians and teachers was another theme in the interviews. The selection of schools and participants was guided by the research interest in deriving rich variation in experiences. Altogether 13 teachers and 5 librarians in three schools participated. The teachers mainly taught social studies in grades 6-12 (12-19 year old students); one was a science teacher. In total, 45 interviews were conducted. The empirical material also encompassed examples of students’ reports as well as the pedagogues’ written instructions for student assignments including advice on information seeking. Analyses of the interviews focused on identifying and describing variation in experiences of information literacy education. Phenomenographic research findings are presented as categories of experiences of the phenomenon which is the object of research. It is important to observe that categories of conceptions are not tied to the different individual interviewees but are composed from the total interview material. This means that various conceptions can be expressed by the same individual. Synthesis of IDOL findings Findings from the IDOL study indicate some interesting contradictions between teaching contents on the one hand, and the intended object of learning as well as assessment criteria on the other hand. Experiences of teaching content focused on; (i) specific sources, (ii) demonstrating tools, (iii) a recommended order between types of sources, and (iv) the user’s experience of the information seeking process. The idea of teaching students about a specific order to follow between types of sources during their information seeking dominates the material. The evaluation of sources was mainly experienced as something that students’ were unable to master and was rarely mentioned as an object of teaching. The overall impression of experiences of teaching contents was a focus on procedural matters, i.e. choosing the ‘right’ source, finding the ‘right’ answer or using a tool in the ‘right’ way. More abstract concepts linked to conscious relevance judgements, the critical evaluation of sources or the relationship between information seeking and various contexts seldom emerged in our material. Thus, while project participants emphasized the importance for students to learn to reflect on their own learning and actions, to formulate relevant research questions, to use time effectively, to critically evaluate their sources, and to analyze and synthesize information from a variety of sources, these issues rarely appeared in participants’ descriptions of teaching content. A comparison between the categories of experiences of teaching contents and the categories of experiences of the intended objects of learning (learning goals) as well as the expressed assessment criteria, indicates a striking lack of consistency. There is hardly any correlation between experiences of teaching content and conceptions of goals and assessment criteria, besides the relationship between citing sources as teaching content and a correct bibliography as an assessment criterion. One particularly interesting finding from the study is the identification of three different ways of conceptualising students’ ways of mastering the critical evaluation of sources, as; (a) a process of maturity, (b) a personal characteristic, and (c) a process of conscious learning. Experiences according to a- and b- categories, i.e. the critical evaluation of sources as a matter of maturity or a personal characteristic, were much more salient in our material than the c-conception; that a critical approach to sources is the result of a process of conscious learning. The a- and b-categories implied that the teaching of the critical evaluation of sources was viewed as impossible or meaningless or frustrating. This means that students’ possibilities to learn critical approaches to sources in school may be hampered by teachers’ and librarians’ views that this ability is a futile object of teaching. The c-category implied serious and systematic efforts to teach the critical evaluation of sources, but as already mentioned, there were few examples of this view in our study. Findings further indicate that cooperation between librarians and teachers is experienced as (a) division of work tasks or (b) possibilities of crossing boundaries, or (c) possibilities of learning and development. While the a-category identifies differences between the two professions as obstacles for cooperation the b- and c-categories viewed differences in competencies as offering a particular potential for creative innovation. Discussion and conclusions of IDOL findings Experiences of teaching content as revealed in these findings indicate that teaching practices are highly restricted with regard to models and theories of information seeking. Conclusions from the IDOL study are that the mediation of information seeking requires deliberate reconsideration as far as teaching contents and methods are concerned, and the development of a more complex awareness of what it means to be information literate. The rich descriptions of variation resulting from the IDOL project combined with a research based theoretical view of information seeking provide well grounded proposals for the development of the didactics of information seeking.
|
|
