| 1. |
- Laukaityte, Inga, 1980-
(author)
-
Statistical modeling in international large-scale assessments
- 2016
-
Doctoral thesis (other academic/artistic)abstract
- This thesis contributes to the area of research based on large-scale educational assessments, focusing on the application of multilevel models. The role of sampling weights, plausible values (response variable imputed multiple times) and imputation methods are demonstrated by simulations and applications to TIMSS (Trends in International Mathematics and Science Study) and PISA (Programme for International Student Assessment) data.The large-scale assessments use multistage sampling design, which means that the units such as schools, classrooms, or students at some or all stages are selected with unequal probabilities. In order to make valid estimates and inferences sampling weights should be used. Thus, in the first paper, we examine different approaches and give recommendations concerning handling sampling weights in multilevel models when analyzing large-scale assessments.Due to limitations in time and the number of students, the complex surveys use matrix sampling of items. This means that a response variable, i.e. students' performance, contains a large amount of information that is missing by design. Therefore, in order to estimate students' proficiency, TIMSS and PISA use the plausible values approach, which results in a set of five plausible values – proficiencies, computed for each student. In the second paper, different user strategies concerning plausible values for multilevel models as well as means and variances are examined with both real and simulated data. Missing information that is present because of the matrix sampling design for instance like the one used in PISA, can be arranged into a non-monotone missing data pattern, where all variables are incomplete and highly positively correlated. In the third paper, we compare a few imputation methods: a single imputation from a conditional distribution (with and without weights) and multiple imputation, for data with a non-monotone missing pattern (with no complete variables) and high positive correlation between variables.In several of the recent international large-scale assessments, students in Sweden demonstrate a decreasing performance. Some previous research has shown that changes in performance depend on students’ performance levels. In the fourth paper, we studied the relationship between student performance and the between-school variance and tried to identify factors associated with student performance in mathematics in PISA in low-, medium-, and high- performing schools in the Nordic countries.
|
|
| 2. |
- Strömbäck Hjärne, Marcus, 1979-
(author)
-
A fair score? : group independent validity arguments for college admission tests
- 2020
-
Doctoral thesis (other academic/artistic)abstract
- This thesis aims to investigate fair use of test scores for admission to higher education. In this thesis, fairness is narrowed down to an instrumental definition relating to a fair interpretation of test scores. The focus is on the use of the Swedish Scholastic Aptitude Test (SweSAT) for admission decisions. The main questions targeted are whether the scores generated from an adaptation with extended time for test takers with dyslexia are fair and whether the SweSAT-scores may disadvantage students with an immigrant background.The thesis is based on validity theory and an established argument-based validity concept is used to link the results to crucial aspects of fairness. This thesis adds explicit fairness-related issues in some detail to this already established framework used for validity research related to the SweSAT. This approach involves some propositions about fairness, each of which can be investigated empirically which, to some extent, has been conducted in separate studies in this thesis.The individual studies contain a variety of results. In the first study, sub-scores of the SweSAT was found to have differential values for certain groups of test takers. This could cause unfairness if the sub-scores are used for admission decisions, but it also indicates that the internal structure of the test is inconsistent across groups. In the second article, the SweSAT was found to be speeded, meaning that the time limit is affecting the test score, and that test takers with dyslexia generally benefit from being given extra time to complete the test. It could not be ruled out that the extra time causes a beneficial experience of lower speededness compared to the rest of the test population, who take the test with no extra time. In the third article, we discover, to our surprise, that immigrant groups generally perform worse than expected in higher education when the expectations are based on their SweSAT and upper secondary school grades. In other words, the instruments used does not create an unintentional obstacle for immigrants in general since the ability of these groups to complete higher education is overestimated when grades and SweSAT-Scores are used for selection. However, in the final article, test items that may cause an unfair disadvantage for immigrant students was identified.In summary, the results contribute to expanding and, to some extent, strengthening the validity of using the SweSAT for admission. However, certain fairness issues have been noted.
|
|
| 3. |
- Gyllencreutz, Lina, 1979-
(author)
-
To prevent without over-protecting : children and senior citizens injured during outdoor activities
- 2015
-
Doctoral thesis (other academic/artistic)abstract
- Background: Injuries are a common public health problem. Non-fatal injuries may result in pain and disabilities. Falls are a common causes of non-fatal injuries and many of these injuries occur during some physical activity. Children and senior citizens are two groups of special interest as their body constitution makes them more vulnerable to injuries than the general population. Outdoor environments influence the risk of injury as people are generally physically active when outdoor. Despite a higher risk for injury, physical activity is a common recommendation for a healthy lifestyle. Children and senior citizens should be able to safely participate in outdoor activities and gain health benefits. There is a need to highlight the complexity of balancing injury risk and the healthy benefits of outdoor activities among these two groups.Aim: The overall aim of this thesis was to investigate injuries among children and senior citizens sustained during outdoor activities and explore experiences and perceptions on risk and possibilities to increase safety in the outdoor environment.Methods: The studies were performed in northern Sweden. Theparticipants were children through the age of 12 (Studies I & II) and senior citizens aged 65 and older (Studies III & IV). In Studies I and III, a crosssectional retrospective study design was used. The data were collected from an Injury Data Base (IDB) at a hospital with a catchment area of 60 kilometres in a well-defined population. Data in Study III was complemented with a study-specific questionnaire. Injury data were analysed descriptively. Study II was a field-study that included 14 days of observations, six focus-group interviews with children, and four focus-group interviews with teachers. The three data sources were taken together and analysed using qualitative content analysis. Study IV was a focus-group interview study with 31 senior citizens divided into six focus-groups. Data in Study IV was analysed with qualitative content analysis.Results: In Study I, 795 children attended the emergency department from 2007 through 2009 and were registered in the IDB with non-minor injuries, such as fractures. The most commonly reported activities contributing to injuries were play, sport, and transport. Other factors contributing to the incident were often related to the ground surface. Contributing products were, for example, trampolines, climbing frames, bicycles, and downhill skis. In the field study (Study II), children at schoolyards were seen climbing high in trees, speeding down slides, or fighting with sticks in the woods. Different perspectives on risk and safety influenced or restricted the children’s outdoor play activities. In Study III, 300 senior citizens were registered in the IDB after injuries from pedestrian falls from January 2009 through April 2011. Women were overrepresented. Sixty percent suffered non-minor injuries. Fracture was the most common injury type. Environmental factors, especially ice, snow, and irregularities on the ground surface were the most commonly described causes to the injury incidents. As the incidents happened in public transport areas, the respondents indicated that they hold the local authorities responsible for poor sidewalk and road maintenance. However, they admitted their own responsibility in preventing similar incidents by changing their behaviour and using safety products. The senior citizens in the focus-group interview study (Study IV) described how they needed to adjust to age-related changes when outdoors, for example, by taking responsibility and using common sense. Facilitating possibilities for outdoor mobility increased with the feelings of safety within the outdoor environment and when using safety devices. To the contrary, fear of falling, shortcomings of safety devices, and dangerous elements such as ice, snow, and interactions with bicyclists constrained outdoor mobility.Conclusion: Non-minor injuries such as fractures among children and senior citizens that are sustained during outdoor activities must be a focus of injury prevention. Different perspectives on risk and safety influence children’s outdoor play at the schoolyard and senior citizens’ outdoor mobility. There is a need for balance between teachers’ common sense knowledge and the knowledge base of injury prevention. In the same manner, there is a need for balance between healthy activities and an acceptable injury risk for participating in outdoor activities. Nurses are well suited to work with this complexity and to optimize these efforts both at schools and in other public settings.
|
|
