| 1. |
- Sallnäs Pysander, Eva-Lotta, Professor, 1970-, et al.
(författare)
-
Nature and digitalization challenging the traditional playground
- 2024
-
Ingår i: Urban Forestry & Urban Greening. - : Elsevier BV. - 1618-8667 .- 1610-8167. ; 93
-
Tidskriftsartikel (refereegranskat)abstract
- Playing outdoors in nature with peers has been attributed most importance for children's healthy development but is increasingly marginalized because of the attractiveness of screen-based play. Careful merging of digital technology into outdoor play environments rich on nature elements could potentially help bridge digital play with more traditional play activities outdoors. A systematic comparison was made of outdoor play in more or less green settings, with and without digital installations or traditional play equipment. The separate and combined role of digital artefacts, play equipment and natural elements, were investigated, with particular focus on the effects of merging digital materials into nature. A group of children aged 6-8 were involved in a field study in a three-week period playing in a traditional playground, a forest and in a forest with digitally enhanced play artefacts. Children ' s play behavior was evaluated using a behavioral tracking method, a questionnaire and a contextual interview with the children, and a physical activity measure, in combination with inventories including maps to document the design, and the ecological and physical status of the settings. The study documents differences in children's play behavior across the three settings. It differs most between the digital forest setting and the forest setting regarding the play categories imaginative play, physical play and rule play and the digital forest setting stands out when it comes to expressive play. It is discussed how particular attributes in the physical environment influence the overall play flow and the interactive effects of natural material and digital material. Ecologically, the forest and the forest with digitally enhanced artefacts were more diverse than the traditional playground, but the natural material present was important for play in all settings.
|
|
| 2. |
- Billingsley, Sunnee, 1976-, et al.
(författare)
-
Diagonal Reference Models in Longitudinal Analyses of Fertility and Mortality
- 2016
-
Ingår i: Abstrect.
-
Konferensbidrag (refereegranskat)abstract
- Diagonal reference models (DRM) are considered the only correct method of estimating an effect of social mobility that is distinct from origin and destination status. This method has become standard in analyses of other social phenomena as well. This study considers how diagonal reference models (DRM) may be applied to demographic processes (mortality and fertility) that are analyzed longitudinally and compares findings between a standard demographic approach and the DRM. Overall, the difference we see between the DRM and others is that DRM picks up weakly significant effects we otherwise do not see. This finding indicates that we gain social mobility effects rather than lose them when we use a DRM model, which means the standard demographic approach appears to run the risk of underestimating a mobility effect at worst.
|
|
| 3. |
- Ghilagaber, Gebrenegus, 1958-, et al.
(författare)
-
Adjusting for selection bias in assessing the relationship between sibship size and cognitive performance
- 2015
-
Ingår i: Journal of the Royal Statistical Society. - : Oxford University Press (OUP). - 0964-1998 .- 1467-985X. ; 178:4, s. 925-944
-
Tidskriftsartikel (refereegranskat)abstract
- Consistent negative correlations between sibship size and cognitive performance (as measured by IQ and other mental aptitude tests) have been observed in past empirical studies. However, the issue of potential selection process in the decision to have larger families (largersibship size) has been partly neglected in past single- and multilevel investigations. The present work extends existing knowledge in three aspects: (1) as factors affecting decision to increase family size may vary across the number and composition of current family size, we propose a sequential probit model (as opposed to binary or ordered models) for the propensity to increase sibship size; (2) we investigate if families who choose to increase family size are a representative random sample of the population of families or there exists selection; (3) in order to disentangle selection and causality we propose a multilevel multiprocess modelling where a continuous model for performance is estimated jointly with a sequential probit model for family-size decisions. The issues are illustrated through analyses of scores on PIAT tests among children of the NLSY79. We found substiantial between-family heterogeneity in the propensity to increase family size - thereby providing empirical evidence in support of the admixture hypothesis. Ignoring such adverse selection led to overestimation of the negative effects of sibship size on cognitive performance but our multiprocess modelling could mitigate the biasing effects of selection.
|
|
| 4. |
|
|
| 5. |
- Ghilagaber, Gebrenegus, 1958-, et al.
(författare)
-
Adjustment of Anticipatory Covariates in Retrospective Surveys : An Expected Likelihood Approach
- 2023
-
Ingår i: Stats. - : MDPI. - 2571-905X. ; 6:4, s. 1179-1197
-
Tidskriftsartikel (refereegranskat)abstract
- We address an inference issue where the value of a covariate is measured at the date of the survey but is used to explain behavior that has occurred long before the survey. This causes bias because the value of the covariate does not follow the temporal order of events. We propose an expected likelihood approach to adjust for such bias and illustrate it with data on the effects of educational level achieved by the time of marriage on risks of divorce. For individuals with anticipatory educational level (whose reported educational level was completed after marriage), conditional probabilities of having attained the reported level before marriage are computed. These are then used as weights in the expected likelihood to obtain adjusted estimates of relative risks. For our illustrative data set, the adjusted estimates of relative risks of divorce did not differ significantly from those obtained from anticipatory analysis that ignores the temporal order of events. Our results are slightly different from those in two other studies that analyzed the same data set in a Bayesian framework, though the studies are not fully comparable to each other.
|
|
| 6. |
- Ghilagaber, Gebrenegus, 1958-, et al.
(författare)
-
Another Look at the Relationship Between Cohabitation and Marriage
- 2016
-
Ingår i: Abstract.
-
Konferensbidrag (refereegranskat)abstract
- Whether informal cohabitation is a prelude to marriage or a permanent replacement to it has been a question of interest for researchers in the past decades. The methdological approaches proposed to answer this question have been based on information on subsequent behaviour of cohabiting couples. In this paper we propose an approach based on the theoretical relationship between crude and net probabilities of marriage in a competing-risk framwork. Analyses based on family dynamics among Swedish men born 1936-1964 show that probabilities of marriage increase if cohabitation was eliminated (and that probabilities of cohabitation increase if marriage was eliminated). Further, the gains in net probablities increase at the prime ages of family formation (20-28) but are less signicant at other ages. Such results support (at least for the data at hand) the argument that informal cohabitation serves as a prelude to marriage rather than a permanent replacement to it.
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
|
|
| 11. |
- Ghilagaber, Gebrenegus, 1958-
(författare)
-
Developing an Empirical Demographic Typology of African Countries at the Turn of the Century : The Use of Principal Components-, Cluster- and Discriminant Analyses
- 2022
-
Ingår i: Eritrean Studies Journal. - : The Red Sea Press Inc.. ; 1:1, s. 49-79
-
Tidskriftsartikel (refereegranskat)abstract
- Using a combination of multivariate techniques, this paper attemptsto build a classification for 53 African countries with respect to their demographic profiles. Principal Components Analys is applied on 13 demographic indicators allowed for a choice of 3 Principal Components which accounted for 84% of the total variation in the original indicators. The first principal component that accounted for 53% of the variation in the original variables is acontrast between fertility, mortality, and proportion of young peopleon the one hand, and life expectancy and proportion of older people on the other. The second component, accounting for 23%of the variation, is reflection of the actual (1998) and forecasted (2025 and 2050) population sizes. The third component, accounting for 8% of the variation, is basically the population density.Cluster Analysis was then applied on these three Principal Components with a view of constructing a classification of the countries. The empirical results reveal that the countries in Northern Africa make their own cluster and that only two countries from the other part of Africa fall in this cluster of North African countries. Further, the three most populated countries of Sub-Saharan Africa make their own cluster. Else, the results show no unique spatial mix of the other countries. A separate discriminant analysis, on the other hand, classifies the seven North African countriesin one cluster (100 % correct classification). Among the 16 countries in West Africa 69 % were classified correctly while the corresponding figures of correct classification for East, Central and Southern Africa were 65 %, 63 % and 60 %, respectively. Thus, the results support a classification of Africa into North Africa and the rest (Sub-Saharan Africa) with respect to demographic profiles. However, any attempt to classify countries in the rest (Sub-Saharan) Africa with respect to their demographicbe havior should be based on other (such as socioeconomic, political, etc.) indicators rather than on spatial classification. A deeper investigation on similarities of the countries that fall in respective clusters and a follow-up of the study with more recent data could be areas worth investigating in the future.
|
|
| 12. |
- Ghilagaber, Gebrenegus, 1958-, et al.
(författare)
-
Diagonal Reference Modeling of Effects of Couples' Educational Differences on Women's Health Care Utilisation in Sub-Saharan Africa
- 2019
-
Konferensbidrag (refereegranskat)abstract
- Studies on associations between education and demographic- orhealth-outcome have traditionally used womanís education (alone orin combination with partnerís education) as regressors in models relating covariates to the outcome. In this study, we adapt modelsdeveloped in the social mobility litearture to examine e§ects of differences between couplesíeducational levels on womenís propensity toutilise facilities (specically deliver in health facilities). Diagonal Reference Modeling (DRM) which accounts for origin (womanís education),destination (partnerís education), and ímobilityí(di§erences betweencouplesíeducational levels) is applied on data from Demographic andHealth Surveys (DHS) in Öve African countries (Angola, Ethiopia,Kenya, Namibia, and Nigeria). The results reveal strong e§ects ofeducational di§erences on womenís decision to deliver at health facilities. More importantly, such strong e§ects would be concealed if datais analyzed using standard modeling approaches. Use of Diagonal Reference Models is strongly recommended if correct policy interventionsare to be implemented.
|
|
| 13. |
|
|
| 14. |
|
|
| 15. |
|
|
| 16. |
|
|
| 17. |
- Ghilagaber, Gebrenegus, 1958-, et al.
(författare)
-
Regional Differences in the Effects of Education on Parity Progression Ratios in Ethiopia : A Random Effect Sequential Probit Modeling Approach
- 2022
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Sequential probit approach is used to model differentials in the effects of women’seducation on parity progression in Ethiopia. Since reasons to have a first childmay differ from those to have, say, a second or third child, we allow the effects ofcovariates on the progression propensities to vary between parities in the same model.Data used for illustration come from the Ethiopian Mini Demographic and HealthSurvey of 2019 in which 8885 women from 11 regions were interviewed. Resultsshow that the sequential model provides more insight than conventional modelswhen exploring the association between education and parity progression. We alsofound similarities and differences in the effects of education on parity progressionamong the regions. A random effect term to account for women’s clustering withinhouseholds was significant in a model for the entire country but disappeared whenregion was included as a covariate in the model.
|
|
| 18. |
|
|
| 19. |
|
|
| 20. |
- Ghilagaber, Gebrenegus, 1958-, et al.
(författare)
-
Stratified Multilevel Modelling of Survival Data : Application to Modelling Regional Differences in Transition to Parenthood in Ethiopia
- 2022
-
Ingår i: Modern Biostatistical Methods for Evidence-Based Global Health Research. - Cham : Springer Nature Switzerland AG. - 9783031110115 - 9783031110122 ; , s. 431-456
-
Bokkapitel (refereegranskat)abstract
- This chapter presents a multilevel extension of the Cox proportional hazards model where a shared frailty term is included to account for clustering of women within households. The extended model is used to analyze regional differences in the intensity of transition to parenthood among 15019 Ethiopian women aged 15–49 years old in the country’s Demographic and Health Survey of 2016. Women’s birth cohort, residence and educational level were used as background variables. Conventional Cox proportional hazards models and two multilevel models (with gamma distributed and log-normal distributed frailty terms) are fitted to data for the entire country and, separately, for each of the nine regions and two city administrations. We found that household frailty effects are fairly small in the nine regions but the log-normal frailties were significant in the entire country and the two city administrations which are relatively heterogeneous with inhabitants from many ethnic groups. We also found regional differences in the effects of the background variables on the intensity of transition to parenthood but the effects were generally stable across the three models in each region. Overall, we recommend use of multilevel survival models to account for clustering of women into households and proper care in the choice of distribution of the household random effects.
|
|
| 21. |
- Ghilagaber, Gebrenegus, 1958-, et al.
(författare)
-
Stratified Shared- and Correlated-Frailty Modeling of Regional Differences in Transition to Parenthood in Ethiopia
- 2022
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Multilevel Cox proportional hazards models with shared- and correlated-frailty termsto account for clustering of women within households is used to analyse regionaldifferences in transition to parenthood among 15019 Ethiopian women from thecountry’s Demographic and Health Survey (DHS) of 2016. We found that bothgamma- and lognormal-distributed shared household frailty effects are fairly smallin the nine regions though the log-normal frailties were significant in the entirecountry and the two city administrations which are relatively heterogeneous withinhabitants from many ethnic groups. Allowing for correlation between the randomeffects within households revealed significant clustering effects in almost all regions.We also found regional differences in the effects of background variables on the intensity of transition to parenthood. Overall, we recommend use of correlated frailtymodels to account for clustering of women into households and proper care in thechoice of distribution of the household random effects.
|
|
| 22. |
- Holle, Hannah, et al.
(författare)
-
Evaluation of the normal gastrointestinal tract in cats using dual-phase computed tomography
- 2023
-
Ingår i: Journal of Small Animal Practice. - : Wiley. - 0022-4510 .- 1748-5827. ; 64:7, s. 463-476
-
Tidskriftsartikel (refereegranskat)abstract
- Objectives: In cats, although ultrasonography remains the preferred modality to evaluate the gastrointestinal tract, computed tomographic (CT) examination of the abdomen is commonly performed. However, a normal description of the gastrointestinal tract is lacking. This study describes the conspicuity and contrast enhancement pattern of the normal gastrointestinal tract in cats using dual-phase CT.Materials and Methods: Pre- and dual-phase postcontrast (early scan at 30 seconds and late scan mean at 84 seconds) abdominal CT exams of 39 cats without history, clinical signs or diagnosis of gastrointestinal disease were reviewed. The gastrointestinal tract was examined for conspicuity and enhancement pattern using commercially available viewing software (Osirix, v.6.5.2), and diameters of 16 gastrointestinal segments were recorded and compared with published radiographic and ultrasonographic reference values.Results: Of the 624 gastrointestinal segments, 530 (84.9%) were identified on precontrast studies and 545 (87.3%) segments on postcontrast studies. Of the gastrointestinal wall segments, 257 (41.2%) were identified on precontrast studies and 314 (50.3%) on postcontrast studies. Gastrointestinal segment diameters correlated well with published normal values, whereas wall thickness measurements usually were smaller compared with sonographic normal values. Early mucosal surface enhancement was frequently seen in the gastric cardia and fundus and ileocolic junction, and a mainly transmural wall enhancement in other gastrointestinal segments.Clinical Significance: Dual-phase CT allows for the identification of gastrointestinal tract segments and walls in cats. Contrast enhancement improves conspicuity and demonstrates wall layering in the cardia, fundus and ileocolic junction.
|
|
| 23. |
- Liang, Yuli, 1985-, et al.
(författare)
-
Bayesian Survival Analysis with the Extended Generalized Gamma Model : Application to Demographic and Health Survey Data
- 2022
-
Ingår i: <em>Modern Biostatistical Methods for Evidence-Based Global Health Research</em>. - Cham : Springer. - 9783031110115 - 9783031110122 ; , s. 287-318
-
Bokkapitel (refereegranskat)abstract
- We extend the existing family of flexible survival models by assembling models scattered across the literature into a more knit form and under the same umbrella. New special cases are obtained not only by constraining the shape and scale parameters of the extended generalized gamma (EGG) model to fixed constants, but also by imposing relationships (such as equality, reciprocal, and negative reciprocal) between them. Apart from common parametric distributions such as exponential, Weibull, gamma, and log normal, the further extended family includes Rayleigh, inverse Rayleigh, ammag, inverse ammag, and half-normal distributions. The models are applied, in a Bayesian framework, on time to entry into first marriage among Eritrean men and women based on data from the 2010 Population and Health Survey. The application demonstrates that the further extended family of distributions provides a wide range of alternatives for a baseline distribution in the analysis of survival data. The empirical results reveal that the inverse gamma model fits best the data for men. It also performs closely as good as the EGG model in the data for women as well as in the combined sample.
|
|
| 24. |
- Liang, Yuli, et al.
(författare)
-
Further Extensions of the Extended Generalized Gamma Model and Their Application to Bayesian Modeling of Family Initiation in Eritrea
- 2022
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Existing family of flexible survival models is further extended by assembling models scattered across the literature under the same umbrella. New special cases areobtained not only by constraining the shape and scale parameters to fixed constants,but also by imposing relationships (like equality, reciprocal, and negative reciprocal) between them. Apart from common parametric distributions like exponential,Weibull, gamma, and log-normal; the further extended family includes Rayleigh, inverse Rayleigh, Ammag, inverse Ammag, and half-normal distributions. The modelsare applied, in a Bayesian framework, on time to entry into first marriage amongEritrean men and women based on data from the 2010 Population and Health Survey.The further extended family of distributions provides a wide range of alternativesfor a baseline distribution in the analysis of survival data. The Inverse gamma modelfits the men-data best while it performs as good as the EGG model in the womenand combined sample.
|
|
| 25. |
- Munezero, Parfait, 1986-, et al.
(författare)
-
Dynamic Bayesian Adjustment of Educational Gradients in Divorce Risks : Disentangling Causation and Misclassification
- 2019
-
Konferensbidrag (refereegranskat)abstract
- We address a problem in causal inference from retrospective surveys where the value of a covariate is measured at the date of the survey but is used to explain behaviour that has occurred long before the survey. This causes bias because the anticipatory covariate does not follow the temporal order of events. We propose a Bayesian dynamic modelling approach that allows effects of the anticipatory covariate to vary over time and, thereby, restore its value at the event of interest. The issues are illustrated with data on the effects of anticipatory educational level on divorce risks among Swedish men. The overall results show that failure to adjust for the anticipatory nature of education leads to underestimation of the relative risks of divorce across educational levels. The results build, in part, on previous analyses of the same data set but also reveal that the degree of underestimation varies over marriage durations.
|
|
| 26. |
- Munezero, Parfait, 1986-, et al.
(författare)
-
Dynamic Bayesian Modelling of Educational and Residential Differences in Family Initiation among Eritrean Men and Women
- 2022
-
Ingår i: Modern Biostatistical Methods for Evidence-Based Global Health Research. - Cham : Springer Nature Switzerland AG. - 9783031110115 - 9783031110122 ; , s. 319-337
-
Bokkapitel (refereegranskat)abstract
- We propose a dynamic Bayesian survival model for analyzing differentials in the timing of family initiation. Such formulation relaxes the strong assumption of constant hazard ratio in conventional proportional hazards models and allows covariate effects to vary over time. Inference is fully Bayesian, and efficient sequential Monte Carlo (particle filter) is used to sample from the posterior distribution. We illustrate the proposed model with data on entry into first marriage among Eritrean men and women surveyed in the 2010 Eritrean Population and Health Survey. Results from the conventional proportional hazards model indicate significant differences in family initiation among all educational and residential groups. In the dynamic model, on the other hand, only one educational and one residential group among the women and only one residential group among the men differ from their respective baseline groups. Since the empirical relative intensities of entry into first marriage vary across respondents’ ages, we argue that the proposed dynamic model captures differentials in family initiation more accurately.
|
|
| 27. |
|
|
| 28. |
- Spånberg, Erik, 1990-
(författare)
-
Variational Inference of Dynamic Factor Models
- 2022
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- When we make difficult and crucial decisions, forecasts are powerful and important tools. For that purpose, statistical models can be our most effective aid. Ideally, these models can incorporate large sets of multifaceted data. However, time and computational power may limit our ability to utilize such tools effectively, not least in changeable situations that require frequent updates.This thesis takes a popular model for big data analysis, the dynamic factor model (DFM), and makes it more viable for fast-paced analytics in practice. The DFM assumes that data is driven by latent and unobserved dynamic factors. By estimating these factors, we may gain deeper insights of our data and ultimately predictive power. An appealing method for DFM-estimation is Bayesian inference, producing probability distributions (called posterior distributions) of factors and parameters.We develop variational inference, which approximates Bayesian inference, in order to estimate DFMs very quickly. By this method, DFMs can be estimated in a fraction of computational time relative to standard approaches; hourly long estimations reduce to seconds or a few minutes.Additionally, we allow for any arbitrary missing data pattern. We can consider data of various sizes and shapes, including different sample sizes, unsynchronized publications and mixed frequencies.In the first paper, we develop an “Expectation Maximization” algorithm to find the maximum point of the posterior distribution of DFM parameters. This can be seen as a reduced case of variational inference. A simulation study shows that the method is preferable to the more common maximum likelihood approach.In the second paper we develop variational inference of standard DFMs. Empirical examples show that this method approximates posterior distributions of factors and parameters very well and quickly. Predictive distributions, both in and out of sample, are practically indistinguishable from standard counterparts of much slower simulation techniques.In the third paper we extend the approach to explicitly sort the relevant and irrelevant parts of the data, corresponding to each individual factor. We employ so called “spike-and-slab” priors, such that individual connections between factors and data can be switched on or off. These “switches” become part of the estimation problem. Simulation studies show that the method identifies the connections well.The fourth paper is an application. We construct a very large DFM to predict Swedish macroeconomy, including 250 quarterly and 500 monthly times series, with different sample sizes and publication dates. To our knowledge, this is the largest prediction model on Swedish macroeconomy to date. We introduce a non-dogmatic structural framework, where we direct the analysis to certain features without strictly deciding them. This produces factor estimates interpretable in terms of consumption, production, prices, financial markets and more. Each time series and forecast can be decomposed according to these interpretations. A forecast evaluation shows good prediction precision of blocks of time series, as well as some key series individually. The model can be updated quickly, making it operable in practice, due to the speed acquired from variational inference.
|
|
| 29. |
|
|
