Change search
Refine search result
1234567 51 - 100 of 402
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 51.
    Carlson, Michael
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Salabasis, Mickael
    A data-swapping technique using ranks: a method for disclosure control2002In: Research in Official Statistics, ISSN 1023-098X, Vol. 6, no 2, p. 35-64Article in journal (Refereed)
    Abstract [en]

    A data-swapping technique based on ranks is described and suggested as a possible approach to statistical disclosure control. The proposed method is intended to be applied to quantitative data and utilises the rank structure of disjoint subsets of an original data set; values of one subset are exchanged for values of other subsets. The procedure retains the validity of a sample on an intra-variate level but the association between pairs of variables is typically weakened. Theoretical and simulation results indicate that the proposed method performs reasonably well in the bivariate normal case.

  • 52.
    Chinapah, Eva
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Psychology.
    Carlson, Michael
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Bergman, Lars R.
    Stockholm University, Faculty of Social Sciences, Department of Psychology.
    Magnusson, David
    Stockholm University, Faculty of Social Sciences, Department of Psychology.
    Modelling the Relationship Between Values, Intentions and Behavior: A Simultaneous LISREL Analysis Over Time1998Report (Other academic)
    Abstract [en]

    Translation of own norms and perception of parents' and friends' values into actual behaviour were studied in the context of the theory of reasoned action. A LISREL model based on this theory was constructed, and the fit and generalizability of the model tested across gender and time. The same norm questionnaire assessing adolescents' own values, their own intentions and actual behavior and perception of parents' and friends' was administered to two samples of approximately 15-year-old adolescents on two occasions (in 1969 and in 1995, in the same town). A LISREL model with an acceptabel fit was obtained, and its structural parameters indicated a strong relationship between adolescents' own evaluations, own intentions and actual behavior. The model was also tenable acorss gender and time. No significant differences were found between groups across gender and time with regard to the four parameters of the structural part of the model which indicate the relationships bwtween the latent variables.

  • 53.
    Corander, Jukka
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    On Bayesian graphical model determination2000Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    A graphical model specifies a graph representation of the independence structure of a multivariate distribution, where nodes represent variables and edges association between variables.

    This thesis introduces methodology for determination of graphical models for multivariate distributions within the exponential family. Model determination is understood in the present context as quantification of the uncertainty about the association structure, given empirical observations. Only models with symmetric associations between variables are considered. The distributions investigated are multinomial, multinormal and conditional Gaussian (CG) distributions. Local graphical models which generalize the graphical loglinear models for multinomial distributions are introduced. These models allow conditional associations to be absent locally, in parts of the sample space.

    A unifying theme is that the models are represented in terms of affine restrictions to the parameters of a regular exponential model. All introduced methods are applicable to the complete class of graphical models, consisting of both decomposable and non-decomposable models. Various real data sets investigated earlier in the graphical modeling literature are used to illustrate the methods.

    Two different measures of model uncertainty are considered: the posterior probability and the relative expected utility of a model. Posterior probabilities are estimated by a Markov chain Monte Carlo sampling method. The other measure of model uncertainty is derived in a decision theoretic framework under reference priors for the model parameters.

    The expected logarithmic utility of a model is decomposed into predictive performance and relative cost. The predictive performance is measured by posterior expectation of the negative entropy of the distribution induced by a graphical model. This expectation has an analytic expression for decomposable models, while a simulation consistent estimate can be obtained for non-decomposable models. The expected logarithmic utility is asymptotically equivalent to the Schwarz criterion under a certain cost function.

  • 54.
    Dalén, Jörgen
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Price measurement and index construction: some contributions to theory and application1995Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    Four different problems are treated, all concerned with problems arising when compiling price indexes in official statistics. One deals with the computation of so called elementary aggregates, low level indexes for single products, when proper weights for the observations are not available. The second part treats different options for applying hedonic indexes. The third report concerns variance estimation, i.e. computing margins of error due to sampling for a consumer price index. Finally, the fourth part analyses different sources of error in a consumer price index and proposes a model structure for aggregating these errors. An overview (in Swedish) over current topics in index construction introduces this volume.

  • 55. Dang, Khue-Dung
    et al.
    Quiroz, Matias
    Kohn, Robert
    Minh-Ngoc, Tran
    Villani, Mattias
    Stockholm University, Faculty of Social Sciences, Department of Statistics. Linköping University, Sweden; ARC Centre of Excellence for Mathematical and Statistical Frontiers (ACEMS), Australia.
    Hamiltonian Monte Carlo with Energy Conserving Subsampling2019In: Journal of machine learning research, ISSN 1532-4435, E-ISSN 1533-7928, Vol. 20, p. 1-31, article id 100Article in journal (Refereed)
    Abstract [en]

    Hamiltonian Monte Carlo (HMC) samples efficiently from high-dimensional posterior distributions with proposed parameter draws obtained by iterating on a discretized version of the Hamiltonian dynamics. The iterations make HMC computationally costly, especially in problems with large data sets, since it is necessary to compute posterior densities and their derivatives with respect to the parameters. Naively computing the Hamiltonian dynamics on a subset of the data causes HMC to lose its key ability to generate distant parameter proposals with high acceptance probability. The key insight in our article is that efficient subsampling HMC for the parameters is possible if both the dynamics and the acceptance probability are computed from the same data subsample in each complete HMC iteration. We show that this is possible to do in a principled way in a HMC-within-Gibbs framework where the subsample is updated using a pseudo marginal MH step and the parameters are then updated using an HMC step, based on the current subsample. We show that our subsampling methods are fast and compare favorably to two popular sampling algorithms that use gradient estimates from data subsampling. We also explore the current limitations of subsampling HMC algorithms by varying the quality of the variance reducing control variates used in the estimators of the posterior density and its gradients.

  • 56. Drevin, J.
    et al.
    Hallqvist, J.
    Sonnander, K.
    Rosenblad, Andreas
    Stockholm University, Faculty of Social Sciences, Department of Statistics. Uppsala University Hospital, Sweden.
    Pingel, R.
    Bjelland, E. K.
    Childhood abuse and unplanned pregnancies: a cross-sectional study of women in the Norwegian Mother and Child Cohort Study2020In: British Journal of Obstetrics and Gynecology, ISSN 1470-0328, E-ISSN 1471-0528, Vol. 127, no 4, p. 438-446Article in journal (Refereed)
    Abstract [en]

    Objective To study if childhood emotional, physical and sexual abuse are determinants for having an unplanned pregnancy, if the categories of abuse interact, and if a potential bias due to the selection of the participants (collider stratification bias) could explain the effect of childhood abuse.

    Design A cross-sectional study.

    Setting The study is based on the Norwegian Mother and Child Cohort Study (MoBa) and uses data from the Medical Birth Registry of Norway.

    Sample Women participating in the MoBa for the first time, >= 18 years of age who responded to questions regarding childhood abuse and pregnancy planning (n = 76 197).

    Methods Data were collected using questionnaires. We conducted analyses using modified Poisson regressions and the relative excess risks due to interaction (RERI). Sensitivity analyses were performed.

    Main outcome measure An unplanned pregnancy (yes/no).

    Results Exposure to childhood emotional (adjusted relative risk (RR) 1.14, 95% CI 1.10-1.19), physical (adjusted RR 1.11, 95% CI 1.04-1.18) and sexual (adjusted RR 1.20, 95% CI 1.14-1.27) abuse increased the risk of having an unplanned pregnancy. The effects could not be explained by the collider stratification bias. The different combinations of categories of abuse did not show any interaction effects.

    Conclusions Childhood emotional, physical and sexual abuses separately increase the risk of having an unplanned pregnancy. The results indicate that victims of childhood abuse are in greater need of support to achieve their reproductive goals. Tweetable abstract Childhood abuse increases the risk of having an unplanned pregnancy. #reproductivehealth #epitwitter.

  • 57.
    Fackle Fornius, Ellinor
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    D-optimal Designs for Quadratic Logistic Regression Models2007In: International Journal of Statistical Sciences, ISSN 1683-5603, Vol. 6, no Special issue, p. 269-303Article in journal (Refereed)
    Abstract [en]

    D-optimal designs are derived for certain quadratic logistic regression models. The performance of the D-optimal designs regarding maximum likelihood estimation of model parameters and estimation of the optimum of the response function is studied for different sample sizes. Comparisons are made with a couple of non-optimal designs. There were found to be disagreements between the asymptotic distribution and the small sample distribution of the maximum likelihood estimator. The designs are also evaluated as to what extent they suffer from the problem of non-existence of the maximum likelihood estimator. The probability that the maximum likelihood estimate exists is compared for the various designs. Non-existence proved to be a substantial problem for these quadratic logistic models.

  • 58.
    Fackle Fornius, Ellinor
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Optimal Design of Experiments for the Quadratic Logistic Model2008Doctoral thesis, monograph (Other academic)
    Abstract [en]

    Optimal design of experiments for binary data is the topic of this thesis. A particular logistic model including a quadratic term in the linear predictor is considered. Determining an optimal design for this model is complicated by the fact that the optimal design is dependent on the unknown true parameters. Methods to obtain locally c- and D-optimal designs are illustrated. c-optimal designs are derived via the canonical design space. This space offers an useful geometric interpretation of the design problem. Using the canonical design space it is shown how the number of design points in a c-optimal design varies depending on the parameter being estimated. Furthermore, formulae for finding the design points along with the corresponding design weights are derived. The small sample performance of the locally optimal designs is compared to the performances of some non-optimal designs in a simulation study. The evaluations are made in terms of mean squared error of the maximum likelihood estimator. The small sample distribution of the maximum likelihood estimator is demonstrated to be quite different from the asymptotic distribution. It was also concluded that non-existence of the maximum likelihood estimator is a critical problem for the quadratic logistic model. The designs differed considerably in this respect and this problem also turned out to be parameter dependent. As a solution to this problem another type of parameter estimator is suggested, which is also evaluated in the simulation study. It performs better in this respect, but not completely satisfactory because it fails in other respects. Two kinds of sequential design approaches are proposed for the purpose of finding the point of optimum response. One is a parametric optimal design approach where c-optimal designs are updated sequentially. The other one is a nonparametric stochastic approximation approach. The suggested designs are evaluated and compared via simulations. Based on the simulation results the c-optimal design approach was consistently favored. Sequential estimation proved to be an effective way to handle the parameter dependence issue.

  • 59.
    Fackle Fornius, Ellinor
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Sequential Designs for Binary Data with the Purpose to Maximize the Probability of Response2008In: Communications in statistics. Simulation and computation, ISSN 0361-0918, E-ISSN 1532-4141, Vol. 37, no 6, p. 1219-1238Article in journal (Refereed)
    Abstract [en]

    Two kinds of sequential designs are proposed for finding the point that maximizes the probability of response assuming a binary response variable and a quadratic logistic regression model. One is a parametric optimal design approach and the other one is a nonparametric stochastic approximation approach. The suggested sequential designs are evaluated and compared in a simulation study. In summary the parametric approach performed very well whereas its competitor failed in some cases.

  • 60.
    Fackle-Fornius, Ellinor
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Festschrift in Honor of Hans Nyquist on the Occasion of his 65th Birthday2015Collection (editor) (Refereed)
  • 61.
    Fackle-Fornius, Ellinor
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Miller, Frank
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Nyquist, Hans
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Implementation of maximin efficient designs in dose-finding studies2015In: Pharmaceutical statistics, ISSN 1539-1604, E-ISSN 1539-1612, Vol. 14, no 1, p. 63-73Article in journal (Refereed)
    Abstract [en]

    This paper considers the maximin approach for designing clinical studies. A maximin efficient design maximizes the smallest efficiency when compared with a standard design, as the parameters vary in a specified subset of the parameter space. To specify this subset of parameters in a real situation, a four-step procedure using elicitation based on expert opinions is proposed. Further, we describe why and how we extend the initially chosen subset of parameters to a much larger set in our procedure. By this procedure, the maximin approach becomes feasible for dose-finding studies. Maximin efficient designs have shown to be numerically difficult to construct. However, a new algorithm, the H-algorithm, considerably simplifies the construction of these designs.We exemplify the maximin efficient approach by considering a sigmoid Emax model describing a dose–response relationship and compare inferential precision with that obtained when using a uniform design. The design obtained is shown to be at least 15% more efficient than the uniform design.

  • 62.
    Fackle-Fornius, Ellinor
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Nyquist, Hans
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Optimal Allocation for Comparing Treatment Effects2010Conference paper (Other academic)
    Abstract [en]

    Suppose the mean responses from m-1 treatment groups in an experiment are to be compared to the mean of a control group. A uniform allocation of observations over the treatment groups is then often used. However, other allocation schemes can give a better precision in the inference. This is particularly emphasised when the variances of the responses are different in different treatment groups. Here we consider optimal allocation according to the A- and D_{A}-criteria for the cases of equal as well as different variances of the responses in the treatment groups. We also consider the case when costs for observations are different in different treatment groups. As expected, optimal allocation depends on the variances of the responses in the treatment groups. If the variances are unknown, a minimax strategy can be used. This means that allocation is made subject to the worst case as the variances are varied within specified intervals. In general, minimax designs are difficult to find. However, for the case of treatment groups, as is considered here, we show that the minimax strategy is very simple to apply. The efficiency of allocations according to the minimax strategy is compared to the uniform as well as the locally optimal D_{A}- and A-optimal allocations.

  • 63.
    Fackle-Fornius, Ellinor
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Nyquist, Hans
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Optimal allocation to treatment groups under variance heterogeneity2015In: Statistica sinica, ISSN 1017-0405, E-ISSN 1996-8507, Vol. 25, no 2, p. 537-549Article in journal (Refereed)
    Abstract [en]

    The problem of allocating experimental units to treatment groups when variance heterogeneity over treatment groups is present is considered. A(A)- and D-A-optimal allocations are derived for estimation of linear combinations of treatment means. Explicit expressions for the design weights are provided for the A(A)-optimal design. The minimax strategy is introduced as an approach to handle unknown variances. Efficiencies of minimax allocations are evaluated.

  • 64.
    Fackle-Fornius, Ellinor
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Wänström, Linda
    Construction of Minimax Designs for the Trinomial Spike Model in Contingent Valuation Experiments2013In: mODa 10 – Advances in Model-Oriented Design and Analysis: Proceedings of the 10th International Workshop in Model-Oriented Design and Analysis Held in Łagów Lubuski, Poland, June 10–14, 2013 / [ed] Dariusz Ucinski, Anthony C. Atkinson, Maciej Patan, Springer, 2013, p. 63-72Chapter in book (Refereed)
    Abstract [en]

    This paper concerns design of contingent valuation experiments when interest is in knowing whether respondents have positive willingness to pay and if so, if they are willing to pay a certain amount for a specified good. A trinomial spike model is used to model the response. Locally D- and c-optimal designs are derived and it is shown that any locally optimal design can be deduced from the locally optimal design for the case when one of the model parameters is standardized. It is demonstrated how information about the parameters, e.g. from pilot studies, can be used to construct minimax and maximin efficient designs, for which the best guaranteed value of the criterion function or efficiency function is sought under the assumption that the parameter values are within certain regions. The proposed methodology is illustrated in an application where the value of environmentally friendly produced clothes is evaluated.

  • 65.
    Fackle-Fornius, Ellinor
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Wänström, Linda
    Minimax D-optimal designs of contingent valuation experiments: willingness to pay for environmentally friendly clothes2014In: Journal of Applied Statistics, ISSN 0266-4763, E-ISSN 1360-0532, Vol. 41, no 4, p. 895-908Article in journal (Refereed)
    Abstract [en]

    This paper demonstrates how to plan a contingent valuation experiment to assess the value of ecologically produced clothes. First, an appropriate statistical model (the trinomial spike model) that describes the probability that a randomly selected individual will accept any positive bid, and if so, will accept the bid A, is defined. Secondly, an optimization criterion that is a function of the variances of the parameter estimators is chosen. However, the variances of the parameter estimators in this model depend on the true parameter values. Pilot study data are therefore used to obtain estimates of the parameter values and a locally optimal design is found. Because this design is only optimal given that the estimated parameter values are correct, a design that minimizes the maximum of the criterion function over a plausable parameter region (i.e. a minimax design) is then found.

  • 66. Flygare, Ann-Marie
    et al.
    Hedlin, Dan
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Empirical Study on the Size of Nonresponse Bias2018In: JSM Proceedings, Survey Research Methods Section, Alexandria, VA, 2018Conference paper (Other academic)
    Abstract [en]

    There are expressions for nonresponse bias, all of which require population quantities. In one expression for nonresponse bias, due to Bethlehem (1988, 2009), the bias is approximately equal to a function of the population covariance between the study variable and the response propensity (probability) and the population mean of the propensities. The covariance is hard to estimate (due to nonresponse). To empirically examine the covariance and the nonresponse bias, we have done two studies where the sample values of survey variables are known and the response propensities are estimated.The first study is a mail survey of a population of residents in the city of Solna in Sweden,20-74 years of age. The questionnaire consists of items on marital status and income; we have obtained the true values of those from the Swedish Tax Agency. We also know birth country, the type of area of residents, specific age and gender of each sampled individual.The second study is a web survey at Stockholm University, the population is faculty employees at the department of psychology. This survey is a census and the variables that we regard as our study variables are income from university and total income. The true values of income from university are given by the HR-department and total income from the Tax Agency.

  • 67.
    Fornius, Ellinor Fackle
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Nyquist, Hans
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Using the Canonical Design Space to Obtain c-Optimal Designs for the Quadratic Logistic Model2010In: Communications in Statistics - Theory and Methods, ISSN 0361-0926, E-ISSN 1532-415X, Vol. 39, no 1, p. 144-157Article in journal (Refereed)
    Abstract [en]

    c-optimal designs for estimating the model parameters of the quadratic logistic regression model are considered. The designs are constructed via the canonical design space. It is shown that the number of design points varies between 1 and 4 depending on the parameter being estimated. Furthermore, formulae for finding the design points along with the corresponding design weights are derived.

  • 68.
    Frank, Ove
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Assessing dependence, independence, and conditional independence2015In: Festschrift in Honor of Hans Nyquist on the Occation of His 65th Birthday / [ed] Ellinor Fackle-Fornius, Stockholm: Stockholm University, 2015, p. 100-115Chapter in book (Refereed)
  • 69.
    Frank, Ove
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Network sampling2011In: International Encyclopedia of Statistical Science / [ed] Miodrag Lovric, Berlin: Springer, 2011, p. 404-Chapter in book (Other academic)
  • 70.
    Frank, Ove
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Network surveys2010In: Official statistics: methodology and applications in honour of Daniel Thorburn / [ed] Michael Carlson, Hans Nyquist, Mattias Villani, Stockholm: Department of Statistics, Stockholm University , 2010, p. 51-60Chapter in book (Other academic)
  • 71.
    Frank, Ove
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Probabilistic network models2011In: International Encyclopedia of Statistical Science / [ed] Miodrag Lovric, Berlin: Springer, 2011, p. 458-Chapter in book (Other academic)
  • 72.
    Frank, Ove
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Social Network Analysis, Estimation, and Sampling in2015In: Encyclopedia of Complexity and Systems Science / [ed] Robert A. Meyers, New York: Springer Berlin/Heidelberg, 2015, p. 1-26Chapter in book (Refereed)
  • 73.
    Frank, Ove
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Social Network Analysis, Estimation and Sampling in2009In: Encyclopedia of Complexity and Systems Science / [ed] Robert A. Meyers, New York: Springer , 2009, p. 8213-8231Chapter in book (Other academic)
  • 74.
    Frank, Ove
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Statistical information tools for multivariate discrete data2011In: Modern Mathematical Tools and Techniques in Capturing Complexity / [ed] Leandro Pardo, Narayanaswamy Balakrishnan, María Ángeles Gil, Berlin Heidelberg: Springer, 2011, p. 177-190Chapter in book (Other academic)
  • 75.
    Frank, Ove
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Survey sampling in networks2011In: The SAGE handbook of social network analysis / [ed] John Scott and Peter J. Carrington, London: Sage Publications, 2011, p. 389-403Chapter in book (Other academic)
  • 76.
    Frank, Ove
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Tid för nya metoder i tillämpad statistik.2011In: Qvintensen, ISSN 2000-1819, no 2, p. 14-16Article in journal (Other (popular science, discussion, etc.))
  • 77.
    Frank, Ove
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Carrington, Peter J.
    Estimation of offending and co-offending using available data with model support2007In: The Journal of mathematical sociology, ISSN 0022-250X, E-ISSN 1545-5874, Vol. 31, no 1, p. 1-46Article in journal (Refereed)
    Abstract [en]

    Police data under-report the numbers of crimes and of offenders, the numbers of offenders participating in individual criminal incidents (incident sizes) and the numbers of incidents in which individual offenders participate (offender activity). Criminal participation in incidents is a concept that underlies and unifies all of these phenomena, so that the numbers of incidents and of offenders, and incident size distributions and offender activity distributions, can all be derived from the criminal participation matrix. Two related probability models are presented that permit the estimation of numbers of incidents and offenders, incident size distributions, offender activity distributions, and co-offending distributions, from police-reported crime data, and data on the reporting of crime to police. The models are estimated, using data from the Canadian Uniform Crime Reporting Survey and national victimization surveys for the period 1995 - 2001.

  • 78.
    Frank, Ove
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Shafie, Termeh
    University of Konstanz, Germany.
    Multigraph Complexity, Data Aggregation, and Statistical Analysis2013Report (Other academic)
  • 79.
    Frank, Ove
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Shafie, Termeh
    Multivariate Entropy Analysis of Network Data2016In: Bulletin of Sociological Methodology, ISSN 0759-1063, E-ISSN 2070-2779, Vol. 129, p. 45-63Article in journal (Refereed)
    Abstract [en]

    Multigraphs with numerical or qualitative attributes defined on vertices and edges can benefit from systematic methods based on multivariate entropies for describing and analysing the interdependencies that are present between vertex and edge attributes. This is here illustrated by application of these tools to a subset of data on the social relations among Renaissance Florentine families collected by John Padgett. Using multivariate entropies we show how it is possible to systematically check for tendencies in data that can be described as independencies or conditional independencies, or as dependencies allowing certain combinations of variables to predict other variables. We also show how different structural models can be tested by divergence measures obtained from the multivariate entropies.

  • 80.
    Frank, Ove
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Shafie, Termeh
    Random multigraphs and aggregated triads with fixed degrees2018In: Network Science, ISSN 2050-1242, Vol. 6, no 2, p. 232-250Article in journal (Refereed)
    Abstract [en]

    Random multigraphs with fixed degrees are obtained by the configuration model or by so called random stub matching. New combinatorial results are given for the global probability distribution of edge multiplicities and its marginal local distributions of loops and edges. The number of multigraphs on triads is determined for arbitrary degrees, and aggregated triads are shown to be useful for analyzing regular and almost regular multigraphs. Relationships between entropy and complexity are given and numerically illustrated for multigraphs with different number of vertices and specified average and variance for the degrees.

  • 81. Franzen, Karin
    et al.
    Johansson, Jan-Erik
    Andersson, Gunnel
    Pettersson, Nicklas
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Nilsson, Kerstin
    Urinary incontinence in women is not exclusively a medical problem: A population-based study on urinary incontinence and general living conditions2009In: Scandinavian Journal of Urology and Nephrology, ISSN 0036-5599, E-ISSN 1651-2065, Vol. 43, no 3, p. 226-232Article in journal (Refereed)
    Abstract [en]

    Objective. The aim of the study was to analyse differences in general health and general living conditions between women with and without urinary incontinence (UI). Material and methods. This cross-sectional population-based study was conducted in Orebro County, Sweden. A public health questionnaire, Life and Health, was sent to a randomly selected sample of the population. The questionnaire consisted of 87 questions on broad aspects of general and psychiatric health. An additional questionnaire was enclosed for those respondents who reported experiencing UI. The data were analysed using binary logistic regression. The final study population constituted 4609 women, 1332 of whom had completed both questionnaires. The remaining 3277 had completed only the Life and Health questionnaire. Effect measures were odds ratios (ORs) with corresponding 95% confidence intervals (CIs). Results. Statistically significant associations were found between UI and the occurrence of musculoskeletal pain (OR 1.45, 95% CI 1.20-1.76), fatigue and sleeping disorders (OR 1.59, 95% CI 1.30-1.95), feelings of humiliation (OR 1.29, 95% CI 1.12-1.50), financial problems (OR 1.36, 95% CI 1.11-1.66), and reluctance to seek medical care (OR 1.43, 95% CI 1.21-1.68). Conclusion. UI among women is commonly associated with a number of different psychosocial problems as well as an expressed feeling of vulnerability.

  • 82.
    Franzén, Jessica
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Bayesian Cluster Analysis: Some Extensions to Non-standard Situations2008Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    The Bayesian approach to cluster analysis is presented. We assume that all data stem from a finite mixture model, where each component corresponds to one cluster and is given by a multivariate normal distribution with unknown mean and variance. The method produces posterior distributions of all cluster parameters and proportions as well as associated cluster probabilities for all objects. We extend this method in several directions to some common but non-standard situations. The first extension covers the case with a few deviant observations not belonging to one of the normal clusters. An extra component/cluster is created for them, which has a larger variance or a different distribution, e.g. is uniform over the whole range. The second extension is clustering of longitudinal data. All units are clustered at all time points separately and the movements between time points are modeled by Markov transition matrices. This means that the clustering at one time point will be affected by what happens at the neighbouring time points. The third extension handles datasets with missing data, e.g. item non-response. We impute the missing values iteratively in an extra step of the Gibbs sampler estimation algorithm. The Bayesian inference of mixture models has many advantages over the classical approach. However, it is not without computational difficulties. A software package, written in Matlab for Bayesian inference of mixture models is introduced. The programs of the package handle the basic cases of clustering data that are assumed to arise from mixture models of multivariate normal distributions, as well as the non-standard situations.

  • 83.
    Franzén, Jessica
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Bayesian Inference for a Mixture Moddel using the Gibbs SamplerManuscript (Other academic)
  • 84.
    Franzén, Jessica
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Classification with the Possibility of a Deviant Group: An Approach to Twelve-Year-Old StudentsIn: Multivariate Behavioral ResearchArticle in journal (Refereed)
  • 85.
    Franzén, Jessica
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Implementation of the MBCA Matlab Program for Model-Based Cluster AnalysisManuscript (Other academic)
  • 86.
    Franzén, Jessica
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Longitudinal, Model-Based Clustering with Missing DataManuscript (Other academic)
  • 87.
    Franzén, Jessica
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Successive Clustering of Longitudinal Data: A Bayesian ApproachManuscript (Other academic)
  • 88.
    Franzén, Jessica
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics. Swedish University of Agricultural Sciences, Sweden.
    Thorburn, Daniel
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Urioste, Jorge I.
    Strandberg, Erling
    Genetic evaluation of mastitis liability and recovery through longitudinal analysis of transition probabilities2012In: Genetics Selection Evolution, ISSN 0999-193X, E-ISSN 1297-9686, Vol. 44, article id 10Article in journal (Refereed)
    Abstract [en]

    Background: Many methods for the genetic analysis of mastitis use a cross-sectional approach, which omits information on, e.g., repeated mastitis cases during lactation, somatic cell count fluctuations, and recovery process. Acknowledging the dynamic behavior of mastitis during lactation and taking into account that there is more than one binary response variable to consider, can enhance the genetic evaluation of mastitis. Methods: Genetic evaluation of mastitis was carried out by modeling the dynamic nature of somatic cell count (SCC) within the lactation. The SCC patterns were captured by modeling transition probabilities between assumed states of mastitis and non-mastitis. A widely dispersed SCC pattern generates high transition probabilities between states and vice versa. This method can model transitions to and from states of infection simultaneously, i.e. both the mastitis liability and the recovery process are considered. A multilevel discrete time survival model was applied to estimate breeding values on simulated data with different dataset sizes, mastitis frequencies, and genetic correlations. Results: Correlations between estimated and simulated breeding values showed that the estimated accuracies for mastitis liability were similar to those from previously tested methods that used data of confirmed mastitis cases, while our results were based on SCC as an indicator of mastitis. In addition, unlike the other methods, our method also generates breeding values for the recovery process. Conclusions: The developed method provides an effective tool for the genetic evaluation of mastitis when considering the whole disease course and will contribute to improving the genetic evaluation of udder health.

  • 89.
    Franzén, Jessica
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Thorburn, Daniel
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Urioste, Jorge I
    Sveriges lantbruksuniversitet, Uppsala.
    Strandberg, Erling
    Sveriges lantbruksuniversitet, Uppsala.
    Use of transition probabilities for estimation of mastitis resistance2010Conference paper (Refereed)
  • 90. Friede, Tim
    et al.
    Posch, Martin
    Zohar, Sarah
    Alberti, Corinne
    Benda, Norbert
    Comets, Emmanuelle
    Day, Simon
    Dmitrienko, Alex
    Graf, Alexandra
    Guenhan, Burak Kuersad
    Hee, Siew Wan
    Lentz, Frederike
    Madan, Jason
    Miller, Frank
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Ondra, Thomas
    Pearce, Michael
    Roever, Christian
    Toumazi, Artemis
    Unkel, Steffen
    Ursino, Moreno
    Wassmer, Gernot
    Stallard, Nigel
    Recent advances in methodology for clinical trials in small populations: the InSPiRe project2018In: Orphanet Journal of Rare Diseases, ISSN 1750-1172, E-ISSN 1750-1172, Vol. 13, article id 186Article, review/survey (Refereed)
    Abstract [en]

    Where there are a limited number of patients, such as in a rare disease, clinical trials in these small populations present several challenges, including statistical issues. This led to an EU FP7 call for proposals in 2013. One of the three projects funded was the Innovative Methodology for Small Populations Research (InSPiRe) project. This paper summarizes the main results of the project, which was completed in 2017. The InSPiRe project has led to development of novel statistical methodology for clinical trials in small populations in four areas. We have explored new decision-making methods for small population clinical trials using a Bayesian decision-theoretic framework to compare costs with potential benefits, developed approaches for targeted treatment trials, enabling simultaneous identification of subgroups and confirmation of treatment effect for these patients, worked on early phase clinical trial design and on extrapolation from adult to pediatric studies, developing methods to enable use of pharmacokinetics and pharmacodynamics data, and also developed improved robust meta-analysis methods for a small number of trials to support the planning, analysis and interpretation of a trial as well as enabling extrapolation between patient groups. In addition to scientific publications, we have contributed to regulatory guidance and produced free software in order to facilitate implementation of the novel methods.

  • 91. Gerhardsson, Emma
    et al.
    Rosenblad, Andreas
    Stockholm University, Faculty of Social Sciences, Department of Statistics. Uppsala University, Sweden.
    Mattsson, Elisabet
    Funkquist, Eva-Lotta
    Mothers' Adaptation to a Late Preterm Infant When Breastfeeding2020In: Journal of Perinatal & Neonatal Nursing, ISSN 0893-2190, E-ISSN 1550-5073, Vol. 34, no 1, p. 88-95Article in journal (Refereed)
    Abstract [en]

    The aim of this study was to psychometrically test the Adaptation to the Late Preterm Infant when Breastfeeding Scale (ALPIBS) and also to test how a mother's self-efficacy predicts adaptation to a late preterm infant when breastfeeding. This study had a longitudinal and prospective design, and data collection was consecutive. Mothers (n = 105) with infants born between and weeks were recruited from a neonatal intensive care unit or a maternity unit. The ALPIBS was developed using exploratory factor analysis, and the association between breastfeeding self-efficacy and ALPIBS score was examined using linear regression analysis. The Breastfeeding Self-Efficacy Scale-Short Form instrument was used to measure self-efficacy in breastfeeding. A higher degree of self-efficacy was significantly associated with a higher degree of adaptation to the late preterm infant's breastfeeding behavior (P < .001). We identified 4 separate underlying factors measured by 11 items in the ALPIBS: (A) breastfeeding is a stressful event; (B) the infant should breastfeed as often as he or she wants; (C) a mother has to breastfeed to be a good mother; and (D) it is important to ensure control over the infant's feeding behavior. There is a link between self-efficacy and ALPIBS score, and self-efficacy is a modifiable factor that influences breastfeeding.

  • 92.
    Ghilagaber, Gebrenegus
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Advances in modelling maternal and child health in Africa: what have we learned and what is next?2014In: Advanced techniques for modelling maternal and child health in Africa / [ed] Ngianga-Bakwin Kandala; Gebrenegus Ghilagaber, Dordrecht: Springer Netherlands, 2014, p. 321-325Chapter in book (Refereed)
  • 93.
    Ghilagaber, Gebrenegus
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Analysis of grouped survival data: a synthesis of various traditions and application to modeling childhood mortality in Eritrea2014In: Advanced techniques for modelling maternal and child health in Africa / [ed] Ngianga-Bakwin Kandala, Gebrenegus Ghilagaber, Dordrecht: Springer, 2014, p. 107-122Chapter in book (Refereed)
  • 94.
    Ghilagaber, Gebrenegus
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Another Look at Chow’s Test for the Equality of Two Heteroscedastic Regression Models2004In: Quality & Quantity: International Journal of Methodology, Vol. 38, no 1, p. 81-93Article in journal (Refereed)
  • 95.
    Ghilagaber, Gebrenegus
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Book Review of P. Lavallée (2007), Indirect Sampling. Springer, New York.2007In: Population Review, Vol. 46, no 2, p. 63-65Article, book review (Other (popular science, discussion, etc.))
  • 96.
    Ghilagaber, Gebrenegus
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Childhood Mortality in Egypt, Eritrea, and Uganda: A Multilevel, Multiprocess Model with Unobserved Heterogeneity2002In: 67th Annual Meeting of the Population Association of America, Atlanta - Georgia, 9-11 May 2002. Contribution to Session 29 (Statistical Modeling with Clustering and Heterogeneity), 2002Conference paper (Other (popular science, discussion, etc.))
  • 97.
    Ghilagaber, Gebrenegus
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Correcting for selection biases in evaluating the effects of health inputs on child survival2002In: 23rd ISCB (The International Society for Clinical Biostatistics) Annual Conference, Dijon - France, Sept. 9-13, 2002. Contribution to the Session on Survival Models 5., 2002Conference paper (Other (popular science, discussion, etc.))
  • 98.
    Ghilagaber, Gebrenegus
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Disentangling selection and causality in assessing the effects of health inputs on child survival: case studies from east Africa2014In: Advanced Techniques for Modelling Maternal and Child Health in Africa / [ed] Ngianga-Bakwin Kandala, Gebrenegus Ghilagaber, Dordrecht: Springer Netherlands, 2014, p. 11-28Chapter in book (Refereed)
  • 99.
    Ghilagaber, Gebrenegus
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Disentangling Selection and Causality in Assessing the Effects of Health Inputs on Child Survival:: Evidence from East Africa2004Report (Other academic)
  • 100.
    Ghilagaber, Gebrenegus
    Stockholm University, Faculty of Social Sciences, Department of Statistics.
    Environmental recidivism in Sweden: distributional shape and effects of sanctions on duration of compliance2018In: Quality and quantity, ISSN 0033-5177, E-ISSN 1573-7845, Vol. 52, no 2, p. 21p. 869-882Article in journal (Refereed)
    Abstract [en]

    The study examines the association between the size of previous environmental sanction charges and subsequent compliance towards environmental regulations. Data used for the study come from about 9000 Swedish firms fined sometime between January 2002 and December 2012. Probabilities of compliance across various levels of sanctions are estimated using life-table methods and tested for equality using standard nonparametric methods. Association between size of sanction charges and subsequent behaviour is modelled by proportional hazard model for the rate of recidivism as well as by a family of flexible parametric accelerated failure-time models for the duration of compliance. The results show that duration of compliance may be described by a log-normal distribution. Further, it is demonstrated that sanctions charges do have significant detering effects on the risk of recidivism though the strength of the detering effect depends on whether or not we account for other possible correlates of recidivism. Possible explanations of the results and their policy implications are discussed; limitations of the current study highlighted; and potential extensions for future studies outlined. 

1234567 51 - 100 of 402
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf