Ausgehend von der Selbstbestimmungstheorie wird in der Dissertation angenommen, dass bestimmte Merkmale des Unterrichts das Autonomieerleben von Schülern und Schülerinnen positiv oder negativ beeinflussen. Hypothese: Autonomiefördernder Unterricht erhöht das Interesse und die erlebte Kompetenz. Ausgehend von einem dynamischen Verständnis von Unterrichtskontexten, wird der Einfluss von Lernsituation und individuellen motivationalen Ressourcen auf das Motivationserleben der Lernenden in einem intraindividuellen Ansatz untersucht. Unterrichtserleben und Motivation von Schülern und Schülerinnen wurden in einem Prä-Post-Design über den Zeitraum eines Jahres untersucht. Kernstück ist eine 3-wöchige Erhebungsphase, in der Unterrichtserleben und Motivation täglich für drei Fächer erfasst wurden. Manuskript I der Dissertation basiert auf der Interessenstheorie und zeigt den differenziellen Einfluss von stabilem individuellen Interesse und variablen Unterrichtsmerkmalen auf das Erleben von Interesse im Unterricht. Manuskript II zeigt, dass das fachspezifische Selbstkonzept und die wahrgenommenen Unterrichtsmerkmale das Kompetenzerleben der Schüler beeinflussen. Die Autonomieunterstützung im Unterricht hat über das die Autonomie fördernde Klima und Kontrollverhalten der Lehrkraft hinaus einen Effekt auf das Kompetenzerleben der Schüler und Schülerinnen. Manuskript III untersucht individuelle Unterschiede und zeigt, dass manche Schüler stärkere Schwankungen ihres fachspezifischen Selbstkonzepts erleben als andere. Selbstkonzeptinstabilität geht mit Prüfungsangst einher und ist ein Prädiktor für schlechtere Noten. Die vorliegende Dissertation konnte somit in einem intraindividuellen Ansatz zeigen, dass Lernsituation und individuelle Schülerressourcen zur Motivation in konkreten Lernumwelten beitragen. / This dissertation focuses on how student motivation emerges and changes in the day-to-day classroom context. Drawing on self-determination theory, it proposes that specific features of the classroom instruction—and of what teachers say and do—may either support or frustrate students’ need for autonomy. Autonomy-supportive instruction is hypothesized to enhance interest and competence perception in the classroom. At the same time, students’ classroom experience is affected by their individual resources such as interest, integrated values, or positive self-concepts. Given the dynamic nature of the classroom context, the overarching aim of this dissertation is to take a short-term, intraindividual approach to understand how both the learning situation and individual motivational resources shape students’ motivational experience. The dissertation comprises three manuscripts investigating student motivation in a pre–post design over a 1 year period, including a 3-week lesson-specific measurement phase in which students’ classroom experience were assessed daily. Drawing on interest theory, manuscript I shows that stable individual interest and perceived characteristics of classroom instruction make distinct contributions to students’ day-to-day interest experience. Similarly, manuscript II shows that both domain-specific self-concept and perceived characteristics of classroom instruction shape students’ felt competence in lessons. In particular, empirical support was found for the hypothesis that cognitive autonomy support has effects on student motivation over and above the effects of autonomy-supportive climate and controlling behaviors. From an individual differences perspective, manuscript III shows that some students experience higher day-to-day fluctuation in their domain-specific self-concepts than others. Self-concept instability was found to be associated with test anxiety and to predict lower school grades 1 year later. Taking a short-term intraindividual approach, this dissertation thus shows that both the learning situation and individual student resources contribute to motivation in context. An understanding of how motivation evolves over different contexts and time frames of instructional events, in everyday classroom life, and across the school career can usefully inform theories of motivation in context.

在本文中，分別就四種不同參數組合（包括六個模式）的二維交叉實驗設計，採用一般線性模式法及二樣本t檢定法予以分析，並探討模式間與分析方法間的異同。此外，在二維重覆測量交叉實驗設計方面，我們也分別以單變量分裂區集變異數分析法及多變量變異數分析法進行探討。 / Four possible parametrizations ( including six models ) are considered in this study to clearify some ambigous issues related to a 2*2 cross-over design. Each model is analyzed using both the GLM procedure and two-sample t test. In addition, we also discuss issues related to the 2*2 repeated measurements cross-over design by using the univariate split-plot and multivariate analysis of variance techniques.

Classification of data from repeated measurements is useful in various disciplines, for example that of medicine. This thesis explores how classification trees (CART) can be used for classifying repeated measures data. The reader is introduced to variations of the CART algorithm which can be used for classifying the data set and tests the performance of these algorithms on a data set that can be modelled using bilinear regression. The performance is compared with that of a classification rule based on linear discriminant analysis. It is found that while the performance of the CART algorithm can be satisfactory, using linear discriminant analysis is more reliable for achieving good results. / Klassificering av data från upprepade mätningar är användbart inom olika discipliner, till exempel medicin. Denna uppsats undersöker hur klassificeringsträd (CART) kan användas för att klassificera upprepade mätningar. Läsaren introduceras till varianter av CART-algoritmen som kan användas för att klassificera datamängden och testar prestandan för dessa algoritmer på en datamängd som kan modelleras med hjälp av bilinjär regression. Prestandan jämförs med en klassificeringsregel baserad på linjär diskriminantanalys. Det har visar sig att även om prestandan för CART-algoritmen kan vara tillfredsställande, är användning av linjär diskriminantanalys mer tillförlitlig för att uppnå goda resultat.

Professional respondents in research panels: comparing trained and fresh members of an online panel The diploma thesis deals with the topic of changes in responding of research panel members, which are caused by their previous experience with research process. Various manifestations of this phenomenon, often labelled as the "panel conditioning effect", are described and supported by corresponding empirical evidence. The observations of panel conditioning effect come from longitudinal panel design as well as online access panels. The author proposes logically structured differentiation of the effect. Based on this categorization, several hypotheses about the differences between trained and fresh members of an Internet panel are raised and tested in dedicated online research. The results reveal significant differences between recently-registered and long-term members of the panel, both in their response strategies and in demographic structure of the groups. Yet the overall outcome do not indicate, that interviewing trained respondents would necessarily lead to lower-quality data.

This thesis focuses on statistical and machine learning methods designed for sequential and repeated measurement data. We start off by considering the classic general linear model (MANOVA) followed by its generalization, the growth curve model (GMANOVA), designed for analysis of repeated measurement data. By considering a binary classification problem of normal data together with the corresponding maximum likelihood estimators for the growth curve model, we demonstrate how a classification rule based on linear discriminant analysis can be derived which can be used for repeated measurement data in a meaningful way. We proceed to the topics of neural networks which serve as our second method of classification. The reader is introduced to classic neural networks and relevant subtopics are discussed. We present a generalization of the classic neural network model to the recurrent neural network model and the LSTM model which are designed for sequential data. Lastly, we present three types of data sets with an total of eight cases where the discussed classification methods are tested. / Den här uppsatsen introducerar klassificeringsmetoder skapade för data av typen upprepade mätningar och sekventiell data. Den klassiska MANOVA modellen introduceras först som en grund för den mer allmäna tillväxtkurvemodellen(GMANOVA), som i sin tur används för att modellera upprepade mätningar på ett meningsfullt sätt. Under antagandet av normalfördelad data så härleds en binär klassificeringsmetod baserad på linjär diskriminantanalys, som tillsammans med maximum likelihood-skattningar från tillväxtkurvemodellen ger en binär klassificeringsregel för data av typen upprepade mätningarn. Vi fortsätter med att introducera läsaren för klassiska neurala nätverk och relevanta ämnen diskuteras. Vi generaliserar teorin kring neurala nätverk till typen "recurrent" neurala nätverk och LSTM som är designade för sekventiell data. Avslutningsvis så testas klassificeringsmetoderna på tre typer av data i totalt åtta olika fall.