| 1. |
- Andersson, Björn, 1984-, et al.
(författare)
-
Sensitivity analysis of violations of the faithfulness assumption
- 2014
-
Ingår i: Journal of Statistical Computation and Simulation. - : Taylor & Francis Group. - 0094-9655 .- 1563-5163. ; 84:7, s. 1608-1620
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- We study implications of violations of the fatihfulness condition due to parameter cancellations on estimation of the DAG skeleton. Three settings are investigated: when i) faithfulness is guaranteed ii) faithfulness is not guaranteed and iii) the parameter distributions are concentrated around unfaithfulness (near-unfaithfulness). In a simulation study the effetcs of the different settings are compared using the PC and MMPC algorithms. The results show that the performance in the faithful case is almost unchanged compared to the unrestricted case whereas there is a general decrease in performance under the near-unfaithful case as compared to the unrestricted case. The response to near-unfaithful parameterisations is similar between two algorithms, with the MMPC algorithm having higher true positive rates and the PC algorithm having lower false positive rates.
|
|
| 2. |
- Berhan, Yonas, 1970-, et al.
(författare)
-
Impact of parental socioeconomic status on excess mortality in subjects with childhood onset type-1 diabetes
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Aims/Hypothesis: The aim of this study was to analyze the possible impact of parental and individual socioeconomic status (SES) on all cause mortality in a population based cohort of childhood onset T1D.Methods: Subjects recorded in the Swedish Childhood Diabetes Registry (SCDR) January 1 1978 to December 31 2008 were included (n=14 409). The SCDR was linked to the Swedish Cause of Death Register (CDR) and the Longitudinal Integration Database for Health Insurance and Labour Market Studies (LISA). SES measures (education and income support) wtypeere retrieved from the LISA for the years 1990-2010. Mortality data were retrieved from the CDR as of December 31, 2010.Results: At a mean follow-up of 24.4 years (maximum 47.5), 238 deaths occurred in a total of 357 048 person-years at risk. In crude analyses, low maternal education predicted mortality for male cases only (p=0.046), while parental income support predicted mortality in both sexes (p<0.001 for both). In Cox models stratified by age at death groups and adjusted for age at onset and sex, parental income support predicted mortality among young adults ( ≥18 years of age) but not for children. Including the adult patient´s own SES in a Cox model showed that individual income support to the patient predicted mortality occurring at ≥ 24 years of age when adjusting for age at onset, sex and parental SES.Conclusions/Interpretation: Low parental SES, mirrored by the need of income support, increases mortality risk in childhood onset type-1 diabetics who died after the age of 18 years.
|
|
| 3. |
|
|
| 4. |
- Ciocanea-Teodorescu, Iuliana, et al.
(författare)
-
Causal inference in survival analysis under deterministic missingness of confounders in register data
- 2023
-
Ingår i: Statistics in Medicine. - : John Wiley & Sons. - 0277-6715 .- 1097-0258. ; 42:12, s. 1946-1964
-
Tidskriftsartikel (refereegranskat)abstract
- Long-term register data offer unique opportunities to explore causal effects of treatments on time-to-event outcomes, in well-characterized populations with minimum loss of follow-up. However, the structure of the data may pose methodological challenges. Motivated by the Swedish Renal Registry and estimation of survival differences for renal replacement therapies, we focus on the particular case when an important confounder is not recorded in the early period of the register, so that the entry date to the register deterministically predicts confounder missingness. In addition, an evolving composition of the treatment arms populations, and suspected improved survival outcomes in later periods lead to informative administrative censoring, unless the entry date is appropriately accounted for. We investigate different consequences of these issues on causal effect estimation following multiple imputation of the missing covariate data. We analyse the performance of different combinations of imputation models and estimation methods for the population average survival. We further evaluate the sensitivity of our results to the nature of censoring and misspecification of fitted models. We find that an imputation model including the cumulative baseline hazard, event indicator, covariates and interactions between the cumulative baseline hazard and covariates, followed by regression standardization, leads to the best estimation results overall, in simulations. Standardization has two advantages over inverse probability of treatment weighting here: it can directly account for the informative censoring by including the entry date as a covariate in the outcome model, and allows for straightforward variance computation using readily available software.
|
|
| 5. |
|
|
| 6. |
- Eikenboom, Anna M, et al.
(författare)
-
Quality of Conduct and Reporting of Propensity Score Methods in Studies Investigating the Effectiveness of Antimicrobial Therapy
- 2022
-
Ingår i: Open Forum Infectious Diseases. - : Oxford University Press. - 2328-8957. ; 9:4
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Propensity score methods are becoming increasingly popular in infectious disease medicine to correct for confounding in observational studies. However, applying and reporting propensity score techniques correctly requires substantial knowledge of these methods. The quality of conduct and reporting of propensity score methods in studies investigating the effectiveness of antimicrobial therapy is yet undetermined.Methods: A systematic review was performed to provide an overview of studies (2005-2020) on the effectiveness of antimicrobial therapy that used propensity score methods. A quality assessment tool and a standardized quality score were developed to evaluate a subset of studies in which antibacterial therapy was investigated in detail. The scale of this standardized score ranges between 0 (lowest quality) and 100 (excellent).Results: A total of 437 studies were included. The absolute number of studies that investigated the effectiveness of antimicrobial therapy and that used propensity score methods increased 15-fold between the periods 2005-2009 and 2015-2019. Propensity score matching was the most frequently applied technique (65%), followed by propensity score-adjusted multivariable regression (25%). A subset of 108 studies was evaluated in detail. The median standardized quality score per year ranged between 53 and 61 (overall range: 33-88) and remained constant over the years.Conclusions: The quality of conduct and reporting of propensity score methods in research on the effectiveness of antimicrobial therapy needs substantial improvement. The quality assessment instrument that was developed in this study may serve to help investigators improve the conduct and reporting of propensity score methods.
|
|
| 7. |
- Gabriel, Erin E., et al.
(författare)
-
Inverse probability of treatment weighting with generalized linear outcome models for doubly robust estimation
- 2024
-
Ingår i: Statistics in Medicine. - : John Wiley & Sons. - 0277-6715 .- 1097-0258. ; 43:3, s. 534-547
-
Tidskriftsartikel (refereegranskat)abstract
- There are now many options for doubly robust estimation; however, there is a concerning trend in the applied literature to believe that the combination of a propensity score and an adjusted outcome model automatically results in a doubly robust estimator and/or to misuse more complex established doubly robust estimators. A simple alternative, canonical link generalized linear models (GLM) fit via inverse probability of treatment (propensity score) weighted maximum likelihood estimation followed by standardization (the g-formula) for the average causal effect, is a doubly robust estimation method. Our aim is for the reader not just to be able to use this method, which we refer to as IPTW GLM, for doubly robust estimation, but to fully understand why it has the doubly robust property. For this reason, we define clearly, and in multiple ways, all concepts needed to understand the method and why it is doubly robust. In addition, we want to make very clear that the mere combination of propensity score weighting and an adjusted outcome model does not generally result in a doubly robust estimator. Finally, we hope to dispel the misconception that one can adjust for residual confounding remaining after propensity score weighting by adjusting in the outcome model for what remains ‘unbalanced’ even when using doubly robust estimators. We provide R code for our simulations and real open-source data examples that can be followed step-by-step to use and hopefully understand the IPTW GLM method. We also compare to a much better-known but still simple doubly robust estimator.
|
|
| 8. |
- Gabriel, Erin E., et al.
(författare)
-
Propensity weighting plus adjustment in proportional hazards model is not doubly robust
- 2024
-
Ingår i: Biometrics. - : Oxford University Press. - 0006-341X .- 1541-0420. ; 80:3
-
Tidskriftsartikel (refereegranskat)abstract
- Recently, it has become common for applied works to combine commonly used survival analysis modelingmethods, such as the multivariable Cox model and propensity score weighting, with the intention of forming a doublyrobust estimator of an exposure effect hazard ratio that is unbiased in large samples when either the Cox model orthe propensity score model is correctly specified. This combination does not, in general, produce a doubly robustestimator, even after regression standardization, when there is truly a causal effect. We demonstrate via simulationthis lack of double robustness for the semiparametric Cox model, the Weibull proportional hazards model, and asimple proportional hazards flexible parametric model, with both the latter models fit via maximum likelihood. Weprovide a novel proof that the combination of propensity score weighting and a proportional hazards survival model,fit either via full or partial likelihood, is consistent under the null of no causal effect of the exposure on the outcomeunder particular censoring mechanisms if either the propensity score or the outcome model is correctly specified andcontains all confounders. Given our results suggesting that double robustness only exists under the null, we outlinetwo simple alternative estimators that are doubly robust for the survival difference at a given time point (in the abovesense), provided the censoring mechanism can be correctly modeled, and one doubly robust method of estimationfor the full survival curve. We provide R code to use these estimators for estimation and inference in the supporting information.
|
|
| 9. |
- Goetghebeur, Els, et al.
(författare)
-
Formulating causal questions and principled statistical answers
- 2020
-
Ingår i: Statistics in Medicine. - : WILEY. - 0277-6715 .- 1097-0258. ; 39:30, s. 4922-4948
-
Tidskriftsartikel (refereegranskat)abstract
- Although review papers on causal inference methods are now available, there is a lack of introductory overviews onwhatthey can render and on the guiding criteria for choosing one particular method. This tutorial gives an overview in situations where an exposure of interest is set at a chosen baseline ("point exposure") and the target outcome arises at a later time point. We first phrase relevant causal questions and make a case for being specific about the possible exposure levels involved and the populations for which the question is relevant. Using the potential outcomes framework, we describe principled definitions of causal effects and of estimation approaches classified according to whether they invoke the no unmeasured confounding assumption (including outcome regression and propensity score-based methods) or an instrumental variable with added assumptions. We mainly focus on continuous outcomes and causal average treatment effects. We discuss interpretation, challenges, and potential pitfalls and illustrate application using a "simulation learner," that mimics the effect of various breastfeeding interventions on a child's later development. This involves a typical simulation component with generated exposure, covariate, and outcome data inspired by a randomized intervention study. The simulation learner further generates various (linked) exposure types with a set of possible values per observation unit, from which observed as well as potential outcome data are generated. It thus provides true values of several causal effects. R code for data generation and analysis is available on , where SAS and Stata code for analysis is also provided.
|
|
| 10. |
- Gorbach, Tetiana, 1991-, et al.
(författare)
-
Contrasting Identifying Assumptions of Average Causal Effects : Robustness and Semiparametric Efficiency
- 2023
-
Ingår i: Journal of machine learning research. - : Microtome Publishing. - 1532-4435 .- 1533-7928. ; 24:197, s. 1-65
-
Tidskriftsartikel (refereegranskat)abstract
- Semiparametric inference on average causal effects from observational data is based on assumptions yielding identification of the effects. In practice, several distinct identifying assumptions may be plausible; an analyst has to make a delicate choice between these models. In this paper, we study three identifying assumptions based on the potential outcome framework: the back-door assumption, which uses pre-treatment covariates, the front-door assumption, which uses mediators, and the two-door assumption using pre-treatment covariates and mediators simultaneously. We provide the efficient influence functions and the corresponding semiparametric efficiency bounds that hold under these assumptions, and their combinations. We demonstrate that neither of the identification models provides uniformly the most efficient estimation and give conditions under which some bounds are lower than others. We show when semiparametric estimating equation estimators based on influence functions attain the bounds, and study the robustness of the estimators to misspecification of the nuisance models. The theory is complemented with simulation experiments on the finite sample behavior of the estimators. The results obtained are relevant for an analyst facing a choice between several plausible identifying assumptions and corresponding estimators. Our results show that this choice implies a trade-off between efficiency and robustness to misspecification of the nuisance models.
|
|
| 11. |
- Hedström, Erik, et al.
(författare)
-
Incidence of fractures among children and adolescents in rural and urban communities : analysis based on 9,965 fracture events
- 2014
-
Ingår i: Injury Epidemiology. - : Springer Science and Business Media LLC. - 2197-1714. ; 1
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Previous work has explored the significance of residence on injuries. A number of articles reported higher rates of injury in rural as compared to urban settings. This study aimed to evaluate the importance of residency on the occurrence of fractures among children and adolescents within a region in northern Sweden.Methods: In a population based study with data from an injury surveillance registry at a regional hospital, we have investigated the importance of sex, age and place of residency for the incidence of fractures among children and adolescents 0-19 years of age using a Poisson logistic regression analysis. Data was collected between 1998 and 2011.Results: The dataset included 9,965 cases. Children and adolescents growing up in the most rural communities appeared to sustain fewer fractures than their peers in an urban municipality, risk ratio 0.81 (0.76-0.86). Further comparisons of fracture rates in the urban and rural municipalities revealed that differences were most pronounced for sports related fractures and activities in school in the second decade of life.Conclusion: Results indicate that fracture incidence among children and adolescents is affected by place of residency. Differences were associated with activity at injury and therefore we have discussed the possibility that this effect was due to the influence of place on activity patterns.The results suggest it is of interest to explore how geographic and demographic variables affect the injury pattern further.
|
|
| 12. |
|
|
| 13. |
- Hedström, Erik, 1977-, et al.
(författare)
-
Socioeconomic variables and fracture risk in children and adolescents : A population-based study from northern Sweden
- 2021
-
Ingår i: BMJ Open. - : BMJ Publishing Group Ltd. - 2044-6055. ; 11:10
-
Tidskriftsartikel (refereegranskat)abstract
- Objectives: Previous studies have investigated the association between socioeconomic characteristics and fractures among children, producing different results. In a population-based study, we previously found an increased risk of fractures among children living in an urban municipality compared with rural municipalities. This study aimed to evaluate the importance of socioeconomic variables for the incidence of fractures among 0-17 year olds.Setting, design and outcome measure: We present a longitudinal, observational study of a population 0-17 years of age. Data from an injury database were linked with additional socioeconomic data for the population at risk. These were 55 758 individuals residing within the primary catchment area of a regional hospital in northern Sweden. Using the number of fractures as the outcome, we fitted a generalised linear mixed model for a Poisson response with socioeconomic variables at the family level as independent variables while controlling for age, sex and place of residence.Results: We found a significant association between higher levels of family income and the risk of fracture, rate ratio 1.40 (1.28-1.52) p<0.001 when comparing the highest income quintile to the lowest as well as the number of siblings and the risk of fracture. Children with one or two siblings had a rate ratio of 1.28 (1.19-1.38) p<0.001 when compared with children with no siblings. Parents' educational level and having a single parent showed no significant association with fractures. The previously observed association between municipalities and fracture risk was less pronounced when taking family-level socioeconomic variables into account.Conclusion: Our results indicate that children from families with higher income and with siblings are at greater risk of sustaining fractures.
|
|
| 14. |
- Källberg, David, 1982-, et al.
(författare)
-
Large sample properties of entropy balancing estimators of average causal effects
- 2023
-
Ingår i: Econometrics and Statistics. - : Elsevier. - 2452-3062.
-
Tidskriftsartikel (refereegranskat)abstract
- Weighting methods are used in observational studies to adjust for covariate imbalances between treatment and control groups. Entropy balancing (EB) is an alternative to inverse probability weighting with an estimated propensity score. The EB weights are constructed to satisfy balance constraints and optimized towards stability. Large sample properties of EB estimators of the average causal treatment effect, based on the Kullback-Leibler and quadratic Rényi relative entropies, are described. Additionally, estimators of their asymptotic variances are proposed. Even though the objective of EB is to reduce model dependence, the estimators are generally not consistent unless implicit parametric assumptions for the propensity score or conditional outcomes are met. The finite sample properties of the estimators are investigated through a simulation study. The average causal effect of smoking on blood lead levels is estimated using data from the National Health and Nutrition Examination Survey.
|
|
| 15. |
|
|
| 16. |
- Olarte Parra, Camila, et al.
(författare)
-
Trial emulation and survival analysis for disease incidence registers : A case study on the causal effect of pre-emptive kidney transplantation
- 2022
-
Ingår i: Statistics in Medicine. - : John Wiley & Sons. - 0277-6715 .- 1097-0258. ; 41:21, s. 4176-4199
-
Tidskriftsartikel (refereegranskat)abstract
- When drawing causal inference from observed data, failure time outcomes present additional challenges of censoring often combined with other missing data patterns. In this article, we follow incident cases of end-stage renal disease to examine the effect on all-cause mortality of starting treatment with transplant, so-called pre-emptive kidney transplantation, vs starting with dialysis possibly followed by delayed transplantation. The question is relatively simple: which start-off treatment is expected to bring the best survival for a target population? To address it, we emulate a target trial drawing on the long term Swedish Renal Registry, where a growing common set of baseline covariates was measured nationwide. Several lessons are learned which pertain to long term disease registers more generally. With characteristics of cases and versions of treatment evolving over time, informative censoring is already introduced in unadjusted Kaplan-Meier curves. This leads to misrepresented survival chances in observed treatment groups. The resulting biased treatment association may be aggravated upon implementing IPW for treatment. Aware of additional challenges, we further recall how similar studies to date have selected patients into treatment groups based on events occurring post treatment initiation. Our study reveals the dramatic impact of resulting immortal time bias combined with other typical features of long-term incident disease registers, including missing covariates during the early phases of the register. We discuss feasible ways of accommodating these features when targeting relevant estimands, and demonstrate how more than one causal question can be answered relying on the no unmeasured baseline confounders assumption.
|
|
| 17. |
- Pazzagli, Laura, et al.
(författare)
-
Marginal structural model to evaluate the joint effect of socioeconomic exposures on the risk of developing end-stage renal disease in patients with type 1 diabetes : a longitudinal study based on data from the Swedish Childhood Diabetes Study Group
- 2017
-
Ingår i: Annals of Epidemiology. - New York : Elsevier. - 1047-2797 .- 1873-2585. ; 27:8, s. 479-484
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: Diabetic nephropathy is a severe complication of type 1 diabetes (T1D) that may lead to renal failure and end-stage renal disease (ESRD) demanding dialysis and transplantation. The aetiology of diabetic nephropathy is multifactorial and both genes and environmental and life style related factors are involved. In this study we investigate the effect of the socioeconomic exposures unemployment and receiving income support on the development of ESRD in T1D patients, using a marginal structural model in comparison with standard logistic regression models.Methods: The study is based on the Swedish Childhood Diabetes Register which in 1977 started to register patients developing T1D before 15 years of age. In the analyses we include patients born between 1965 and 1979, developing diabetes between 1977 and 1994, followed until 2013 (n=4034). A marginal structural model (MSM) was fitted to adjust for both baseline and time-varying confounders.Results: The main results of the analysis indicate that being unemployed for more than one year and receiving income support are risk factors for the development of ESRD. Multiple exposure over time to these risk factors increases the risk associated with the disease.Conclusions: Using a MSM is an advanced method well suited to investigate the effect of exposures on the risk of complications of a chronic disease with longitudinal data. The results show that socioeconomic disadvantage increases the risk of developing ESRD in patients with type 1 diabetes.
|
|
| 18. |
- Persson, Emma, 1981-, et al.
(författare)
-
Estimating a marginal causal odds ratio in a case-control design : analyzing the effect of low birth weight on the risk of type 1 diabetes mellitus
- 2013
-
Ingår i: Statistics in Medicine. - : Wiley. - 0277-6715 .- 1097-0258. ; 32:14, s. 2500-2512
-
Tidskriftsartikel (refereegranskat)abstract
- Estimation of marginal causal effects from case-control data has two complications: (i) confounding due to the fact that the exposure under study is not randomized, and (ii) bias from the case-control sampling scheme. In this paper, we study estimators of the marginal causal odds ratio, addressing these issues for matched and unmatched case-control designs when utilizing the knowledge of the known prevalence of being a case. The estimators are implemented in simulations where their finite sample properties are studied and approximations of their variances are derived with the delta method. Also, we illustrate the methods by analyzing the effect of low birth weight on the risk of type 1 diabetes mellitus using data from the Swedish Childhood Diabetes Register, a nationwide population-based incidence register.
|
|
| 19. |
- Petrauskiene, V, et al.
(författare)
-
The risk of venous thromboembolism is markedly elevated in patients with diabetes
- 2005
-
Ingår i: Diabetologia. ; 48, s. 1017–1021-
-
Tidskriftsartikel (refereegranskat)abstract
- OBJECTIVE: To survey unnatural deaths among teenagers in northern Sweden and to suggest preventive measures. SETTING: The four northernmost counties (908,000 inhabitants, 1991), forming 55% of the area of Sweden. MATERIAL AND METHODS: All unnatural teenager deaths from 1981 through 2000 were identified in the databases of the Department of Forensic Medicine in Umea, National Board of Forensic Medicine. Police reports and autopsy findings were always studied, social and hospital records if present. RESULTS: Three hundred and fifty-five deaths were found, of which 267 (75%) were males and 88 (25%) females. Ninety out of 327 (28%) tested positive for alcohol. Two hundred and forty-eight (70%) were unintentional and 102 (30%) were intentional deaths, and five (1%) were categorized as undetermined manner of death. Unintentional deaths decreased while the incidence of intentional deaths remained unaffected by time. CONCLUSIONS: Injury-reducing measures have been effective concerning unintentional deaths and the fall in young licensed drivers due to the economical recess have probably also contributed to the decrease. However, there were no signs of decreasing numbers of suicides during the study period, which calls for resources to be allocated to suicide prevention.
|
|
| 20. |
- Sjölander, Arvid, et al.
(författare)
-
Improved sensitivity bounds for mediation under unmeasured mediator-outcome confounding
- 2024
-
Ingår i: Journal of Causal Inference. - : Walter de Gruyter. - 2193-3677 .- 2193-3685. ; 12:1
-
Tidskriftsartikel (refereegranskat)abstract
- It is often of interest to decompose a total effect into an indirect effect, relayed through a particular mediator, and a direct effect. However, these effect components are not identified if there are unmeasured confounding of the mediator and the outcome. We derive nonparametric bounds on the natural direct and indirect effects, and Cornfield inequalities that the unmeasured confounders must satisfy to explain away an “observed” effect. We demonstrate, analytically and by simulation, that these bounds and Cornfield inequalities are sharper than those previously proposed in the literature. We illustrate the methods with an application to cholestyramine treatment for coronary heart disease.
|
|
| 21. |
- Skog, Frida, 1979-, et al.
(författare)
-
Effects of spacing and sibship size on adult earnings : Results from a propensity score analysis on a population-based cohort
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Research has shown that the sibling constellation impacts on adult life chances. The outcomes commonly investigated are education and various forms of psychological factors such as cognitive ability. In this study we investigate an outcome relatively few have studied before – adult earnings. Three different sibling constellations are in focus: 1) being an only child, 2) having many siblings, and 3) close birth spacing between siblings. The national context is Sweden, and the study is based on administrative data, including all individuals born in the country in 1973. The outcome variable is mean labour market earnings from age 33 to 35. Using propensity score matching, we show that individuals having grown up with more than two siblings have substantially lower earnings in adulthood than those with fewer siblings. However, no significant difference was found between individuals having a closely spaced sibling and those who do not have closely spaced siblings. We also could not find any differences between only children and children with siblings.
|
|
| 22. |
|
|
| 23. |
- Toppe, Cecilia, et al.
(författare)
-
Decreasing cumulative incidence of end-stage renal disease in young patients with type 1 diabetes in Sweden : A 38-year prospective nationwide study
- 2019
-
Ingår i: Diabetes Care. - : American Diabetes Association. - 0149-5992 .- 1935-5548. ; 42:1, s. 27-31
-
Tidskriftsartikel (refereegranskat)abstract
- OBJECTIVE Diabetic nephropathy is a serious complication of type 1 diabetes. Recent studies indicate that end-stage renal disease (ESRD) incidence has decreased or that the onset of ESRD has been postponed; therefore, we wanted to analyze the incidence and time trends of ESRD in Sweden. RESEARCH DESIGN AND METHODS In this study, patients with duration of type 1 diabetes >14 years and age at onset of diabetes 0–34 years were included. Three national diabetes registers were used: the Swedish Childhood Diabetes Register, the Diabetes Incidence Study in Sweden, and the National Diabetes Register. The Swedish Renal Registry, a national register on renal replacement therapy, was used to identify patients who developed ESRD. RESULTS We found that the cumulative incidence of ESRD in Sweden was low after up to 38 years of diabetes duration (5.6%). The incidence of ESRD was lower in patients with type 1 diabetes onset in 1991–2001 compared with onset in 1977–1984 and 1985–1990, independent of diabetes duration. CONCLUSIONS The risk of developing ESRD in Sweden in this population is still low and also seems to decrease with time.
|
|
| 24. |
- Waernbaum, Ingeborg, 1972-
(författare)
-
Covariate selection and propensity score specification in causal inference
- 2008
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis makes contributions to the statistical research field of causal inference in observational studies. The results obtained are directly applicable in many scientific fields where effects of treatments are investigated and yet controlled experiments are difficult or impossible to implement. In the first paper we define a partially specified directed acyclic graph (DAG) describing the independence structure of the variables under study. Using the DAG we show that given that unconfoundedness holds we can use the observed data to select minimal sets of covariates to control for. General covariate selection algorithms are proposed to target the defined minimal subsets. The results of the first paper are generalized in Paper II to include the presence of unobserved covariates. Morevoer, the identification assumptions from the first paper are relaxed. To implement the covariate selection without parametric assumptions we propose in the third paper the use of a model-free variable selection method from the framework of sufficient dimension reduction. By simulation the performance of the proposed selection methods are investigated. Additionally, we study finite sample properties of treatment effect estimators based on the selected covariate sets. In paper IV we investigate misspecifications of parametric models of a scalar summary of the covariates, the propensity score. Motivated by common model specification strategies we describe misspecifications of parametric models for which unbiased estimators of the treatment effect are available. Consequences of the misspecification for the efficiency of treatment effect estimators are also studied.
|
|
| 25. |
- Waernbaum, Ingeborg, 1972-, et al.
(författare)
-
Low mean temperature rather than few sunshine hours are associated with an increased incidence of type 1 diabetes in children
- 2016
-
Ingår i: European Journal of Epidemiology. - : Springer. - 0393-2990 .- 1573-7284. ; 31:1, s. 61-65
-
Tidskriftsartikel (refereegranskat)abstract
- The well-known north-south gradient and the seasonal variability in incidence of childhood type1 diabetes indicate climatological factors to have an effect on the onset. Both sunshine hours and a low temperature may be responsible. In the present study we tried to disentangle these effects that tend to be strongly connected.Exposure data were sunshine hours and mean temperature respectively obtained from eleven meteorological stations in Sweden which were linked to incidence data from geographically matched areas. Incident cases during 1983-2008 were retrieved from the population based Swedish childhood diabetes register. We used generalized additive models to analyze the incidence as a function of mean temperature and hours of sun adjusted for the time trend, age and sex.In our data set the correlation between sun hours and temperature was weak (r=0.36) implying that it was possible to estimate the effect of these variables in a regression model. We fit a general additive model with a smoothing term for the time trend. In the model with sun hours we found no significant effect on T1 incidence (p=0.17) whereas the model with temperature as predictor was significant (p=0.05) when adjusting for the time trend, sex and age. Adding sun hours in the model where mean temperature was already present did not change the effect of temperature.There is an association with incidence of type1 diabetes in children and low mean temperature independent of a possible effect of sunshine hours after adjustment for age, sex and time trend. The findings may mirror the cold effect on insulin resistance and accords with the hypothesis that overload of an already ongoing beta cell destruction may accelerate disease onset.
|
|
