Thomas Scheike

IT University of Copenhagen, København, Capital Region, Denmark

Are you Thomas Scheike?

Claim your profile

Publications (137)489.52 Total impact

  • Cancer Epidemiology Biomarkers & Prevention 11/2015; DOI:10.1158/1055-9965.EPI-15-0913 · 4.13 Impact Factor
  • Torben Martinussen · Klaus K Holst · Thomas H Scheike ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Missing covariate values is a common problem in survival analysis. In this paper we propose a novel method for the Cox regression model that is close to maximum likelihood but avoids the use of the EM-algorithm. It exploits that the observed hazard function is multiplicative in the baseline hazard function with the idea being to profile out this function before carrying out the estimation of the parameter of interest. In this step one uses a Breslow type estimator to estimate the cumulative baseline hazard function. We focus on the situation where the observed covariates are categorical which allows us to calculate estimators without having to assume anything about the distribution of the covariates. We show that the proposed estimator is consistent and asymptotically normal, and derive a consistent estimator of the variance-covariance matrix that does not involve any choice of a perturbation parameter. Moderate sample size performance of the estimators is investigated via simulation and by application to a real data example.
    Lifetime Data Analysis 10/2015; DOI:10.1007/s10985-015-9351-y · 0.65 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Context: Testosterone levels (T) have been associated with mortality, but controversy exists. Objective: To investigate associations between serum levels of total testosterone, SHBG, free testosterone, estradiol, LH and FSH, and subsequent mortality with up to 30 years of follow-up. Design: A prospective cohort study consisting of men participating in four independent population-based surveys (MONICA I-III and Inter99) from 1982 to 2001 and followed until December 2012 with complete registry follow-up. Setting and participants: 5,350 randomly selected men from the general population aged 30, 40, 50, 60 or 70 years at baseline. Main outcome measures: All-cause mortality, cardiovascular disease (CVD) mortality and cancer mortality. Results: 1,533 men died during the follow-up period; 428 from CVD and 480 from cancer. Cox proportional hazard models revealed that men in highest LH quartile had an increased all-cause mortality compared to lowest quartile (HR=1.32, 95%CI: 1.14 to 1.53). Likewise, increased quartiles of LH/T and estradiol increased the risk of all-cause mortality (HR=1.23, 95%CI: 1.06 to 1.43, HR=1.23, 95%CI: 1.06 to 1.43). No association to testosterone levels was found. Higher LH levels were associated with increased cancer mortality (HR=1.42, 95%CI: 1.10 to 1.84) independently of smoking status. Lower CVD mortality was seen for men with testosterone in the highest quartile compared to lowest (HR=0.72, 95%CI: 0.53 to 0.98). Furthermore, negative trends were seen for SHBG and free testosterone in relation to CVD mortality, however insignificant. Conclusion: The observed positive association of LH and LH/T, but not testosterone, with all-cause mortality suggests that a compensated impaired Leydig cell function may be a risk factor for death by all causes in men. Our findings underpin the clinical importance of including LH measurement in the diagnostic work-up of male patients seeking help for possible androgen insufficiency.
    The Journal of Clinical Endocrinology and Metabolism 10/2015; DOI:10.1210/jc.2015-2460 · 6.21 Impact Factor
  • Thomas H Scheike · Jacob B Hjelmborg · Klaus K Holst ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Twin and family data provide a key source for evaluating inheritance of specific diseases. A standard analysis of such data typically involves the computation of prevalences and different concordance measures such as the casewise concordance, that is the probability that one twin has the disease given that the co-twin has the disease. Most diseases have a varying age-of-onset that will lead to age-specific prevalence. Typically, this aspect is not considered, and this may lead to severe bias as well as make it very unclear exactly what population quantities that we are estimating. In addition, one will typically need to deal with censoring in the data, that is the fact that we for some subjects only know that they are alive at a specific age without having the disease. These subjects needs to be considered age specifically, and clearly if they are young there is still a risk that they will develop the disease. The aim of this contribution is to show that the standard casewise concordance and standard prevalence estimators do not work in general for age-of-onset data. We show how one can in fact do something easy and simple even with censored data. The key is to take age into account when analysing such data.
    Behavior Genetics 07/2015; 45(5). DOI:10.1007/s10519-015-9729-3 · 3.21 Impact Factor
  • Peng He · Frank Eriksson · Thomas H. Scheike · Mei‐Jie Zhang ·
    [Show abstract] [Hide abstract]
    ABSTRACT: With competing risks data, one often needs to assess the treatment and covariate effects on the cumulative incidence function. Fine and Gray proposed a proportional hazards regression model for the subdistribution of a competing risk with the assumption that the censoring distribution and the covariates are independent. Covariate-dependent censoring sometimes occurs in medical studies. In this paper, we study the proportional hazards regression model for the subdistribution of a competing risk with proper adjustments for covariate-dependent censoring. We consider a covariate-adjusted weight function by fitting the Cox model for the censoring distribution and using the predictive probability for each individual. Our simulation study shows that the covariate-adjusted weight estimator is basically unbiased when the censoring time depends on the covariates, and the covariate-adjusted weight approach works well for the variance estimator as well. We illustrate our methods with bone marrow transplant data from the Center for International Blood and Marrow Transplant Research. Here, cancer relapse and death in complete remission are two competing risks.
    Scandinavian Journal of Statistics 06/2015; DOI:10.1111/sjos.12167 · 0.87 Impact Factor
  • Frank Eriksson · Thomas Scheike ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Epidemiological studies of related individuals are often complicated by the fact that follow-up on the event type of interest is incomplete due to the occurrence of other events. We suggest a class of frailty models with cause-specific hazards for correlated competing events in related individuals. The frailties are based on sums of gamma distributed variables and offer closed form expressions for the observed intensities. An inference procedure with a recursive baseline estimator is proposed, and its large sample properties are established. The estimator readily handles cluster left-truncation as occurring in the Nordic twin registers. The performance in finite samples is investigated by simulations and an example on prostate cancer in twins is provided for illustration. © 2015, The International Biometric Society.
    Biometrics 06/2015; 71(3). DOI:10.1111/biom.12326 · 1.57 Impact Factor
  • Zahra Mansourvar · Torben Martinussen · Thomas H. Scheike ·
    [Show abstract] [Hide abstract]
    ABSTRACT: A mean residual life function (MRLF) is the remaining life expectancy of a subject who has survived to a certain time point. In the presence of covariates, regression models are needed to study the association between the MRLFs and covariates. If the survival time tends to be too long or the tail is not observed, the restricted mean residual life must be considered. In this paper, we propose the proportional restricted mean residual life model for fitting survival data under right censoring. For inference on the model parameters, martingale estimating equations are developed, and the asymptotic properties of the proposed estimators are established. In addition, a class of goodness-of-fit test is presented to assess the adequacy of the model. The finite sample behavior of the proposed estimators is evaluated through simulation studies, and the approach is applied to a set of real life data collected from a randomized clinical trial.
    Journal of Applied Statistics 05/2015; DOI:10.1080/02664763.2015.1043871 · 0.42 Impact Factor
  • Frank Eriksson · Jianing Li · Thomas Scheike · Mei‐Jie Zhang ·
    [Show abstract] [Hide abstract]
    ABSTRACT: We suggest an estimator for the proportional odds cumulative incidence model for competing risks data. The key advantage of this model is that the regression parameters have the simple and useful odds ratio interpretation. The model has been considered by many authors, but it is rarely used in practice due to the lack of reliable estimation procedures. We suggest such procedures and show that their performance improve considerably on existing methods. We also suggest a goodness-of-fit test for the proportional odds assumption. We derive the large sample properties and provide estimators of the asymptotic variance. The method is illustrated by an application in a bone marrow transplant study and the finite-sample properties are assessed by simulations. © 2015, The International Biometric Society.
    Biometrics 05/2015; 71(3). DOI:10.1111/biom.12330 · 1.57 Impact Factor
  • Frank Eriksson · Torben Martinussen · Thomas H. Scheike ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Left-truncation occurs frequently in survival studies, and it is well known how to deal with this for univariate survival times. However, there are few results on how to estimate dependence parameters and regression effects in semiparametric models for clustered survival data with delayed entry. Surprisingly, existing methods only deal with special cases. In this paper, we clarify different kinds of left-truncation and suggest estimators for semiparametric survival models under specific truncation schemes. The large-sample properties of the estimators are established. Small-sample properties are investigated via simulation studies, and the suggested estimators are used in a study of prostate cancer based on the Finnish twin cohort where a twin pair is included only if both twins were alive in 1974.
    Scandinavian Journal of Statistics 04/2015; DOI:10.1111/sjos.12157 · 0.87 Impact Factor
  • Jianing Li · Thomas H Scheike · Mei-Jie Zhang ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Recently, Fine and Gray (J Am Stat Assoc 94:496-509, 1999) proposed a semi-parametric proportional regression model for the subdistribution hazard function which has been used extensively for analyzing competing risks data. However, failure of model adequacy could lead to severe bias in parameter estimation, and only a limited contribution has been made to check the model assumptions. In this paper, we present a class of analytical methods and graphical approaches for checking the assumptions of Fine and Gray's model. The proposed goodness-of-fit test procedures are based on the cumulative sums of residuals, which validate the model in three aspects: (1) proportionality of hazard ratio, (2) the linear functional form and (3) the link function. For each assumption testing, we provide a [Formula: see text]-values and a visualized plot against the null hypothesis using a simulation-based approach. We also consider an omnibus test for overall evaluation against any model misspecification. The proposed tests perform well in simulation studies and are illustrated with two real data examples.
    Lifetime Data Analysis 11/2014; 21(2). DOI:10.1007/s10985-014-9313-9 · 0.65 Impact Factor
  • Thomas H Scheike · Klaus K Holst · Jacob B Hjelmborg ·
    [Show abstract] [Hide abstract]
    ABSTRACT: We consider data from the Danish twin registry and aim to study in detail how lifetimes for twin-pairs are correlated. We consider models where we specify the marginals using a regression structure, here Cox's regression model or the additive hazards model. The best known such model is the Clayton-Oakes model. This model can be extended in several directions. One extension is to allow the dependence parameter to depend on covariates. Another extension is to model dependence via piecewise constant cross-hazard ratio models. We show how both these models can be implemented for large sample data, and suggest a computational solution for obtaining standard errors for such models for large registry data. In addition we consider alternative models that have some computational advantages and with different dependence parameters based on odds ratios of the survival function using the Plackett distribution. We also suggest a way of assessing how and if the dependence is changing over time, by considering either truncated or right-censored versions of the data to measure late or early dependence. This can be used for formally testing if the dependence is constant, or decreasing/increasing. The proposed procedures are applied to Danish twin data to describe dependence in the lifetimes of the twins. Here we show that the early deaths are more correlated than the later deaths, and by comparing MZ and DZ associations we suggest that early deaths might be more driven by genetic factors. This conclusion requires models that are able to look at more local dependence measures. We further show that the dependence differs for MZ and DZ twins and appears to be the same for males and females, and that there are indications that the dependence increases over calendar time.
    Lifetime Data Analysis 09/2014; 21(2). DOI:10.1007/s10985-014-9309-5 · 0.65 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Context: Human exposure to polychlorinated biphenyls (PCBs) has been associated to type 2 diabetes in adults. Objectives: To determine whether concurrent serum PCB concentration was associated with markers of glucose metabolism in healthy children. Design: Cross-sectional study. Settings and participants: A total of 771 healthy Danish third grade school children aged 8-10 years in the municipality of Odense were recruited in 1997 through a two-stage cluster sampling from 25 different schools stratified according to location and socioeconomic character; 509 (9.7±0.8 years, 53% girls) had adequate amounts available for PCB and analyses. Main outcome measures: Fasting plasma glucose and serum insulin were measured and a homeostasis assessment model of insulin resistance (HOMA-IR) and β-cell function (HOMA-B) calculated. Serum PCB congeners and other persistent compounds were measured and ΣPCB calculated. Results: PCBs were present in serum at low concentrations, median 0.19μ g/g lipid (interquartile range, IQR: 0.12-0.31). After adjustment for putative confounding factors, the second, third, fourth and fifth quintiles of total PCB were significantly inversely associated with serum insulin (-14.6%, -21.7%, -18.9%, -23.1%, p-trend<0.01), compared to the first quintile, but not with plasma glucose (p=0.45). HOMA-IR and HOMA-B were affected in the same direction due to the declining insulin levels with increasing PCB exposure. Similar results were found for individual PCB congeners, for βHCB and pp-DDE. Conclusion: A strong inverse association between serum insulin and PCB exposure was found while fasting plasma glucose remained within the expected narrow range. Our findings suggest that PCB may not exert effect through decreased peripheral insulin sensitivity, as seen in obese and low fit children, but rather through a toxicity to β-cells. It remains to be shown if lower HOMA-B is caused by destruction of β-cell reducing peripheral insulin resistance and thereby increase fasting plasma glucose as previously found.
    Journal of Clinical Endocrinology &amp Metabolism 08/2014; 99(12):jc20141683. DOI:10.1210/jc.2014-1683 · 6.21 Impact Factor
  • Source
    Klaus K. Holst · Thomas H. Scheike · Jacob B. Hjelmborg ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Family studies provide an important tool for understanding etiology of diseases, with the key aim of discovering evidence of family aggregation and to determine if such aggregation can be attributed to genetic components. Heritability and concordance estimates are routinely calculated in twin studies of diseases, as a way of quantifying such genetic contribution. The endpoint in these studies are typically defined as occurrence of a disease versus death without the disease. However, a large fraction of the subjects may still be alive at the time of follow-up without having experienced the disease thus still being at risk. Ignoring this right-censoring can lead to severely biased estimates. We propose to extend the classical liability threshold model with inverse probability of censoring weighting of complete observations. This leads to a flexible way of modeling twin concordance and obtaining consistent estimates of heritability. We apply the method in simulations and to data from the population based Danish twin cohort where we describe the dependence in prostate cancer occurrence in twins.
    Computational Statistics & Data Analysis 07/2014; 93. DOI:10.1016/j.csda.2015.01.014 · 1.40 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Background: Prostate cancer is thought to be the most heritable cancer, although little is known about how this genetic contribution varies across age. Methods: To address this question, we undertook the world's largest prospective study in the Nordic Twin Study of Cancer cohort, including 18,680 monozygotic and 30,054 dizygotic same sex male twin pairs. We incorporated time-to-event analyses to estimate the risk concordance and heritability while accounting for censoring and competing risks of death, essential sources of biases that have not been accounted for in previous twin studies modeling cancer risk and liability. Results: The cumulative risk of prostate cancer was similar to that of the background population. The cumulative risk for twins whose co-twin was diagnosed with prostate cancer was greater for MZ than for DZ twins across all ages. Among concordantly affected pairs, the time between diagnoses was significantly shorter for MZ than DZ pairs (median 3.8 versus 6.5 years, respectively). Genetic differences contributed substantially to variation in both the risk and the liability (heritability=58% (95% CI 52%-63%) of developing prostate cancer. The relative contribution of genetic factors was constant across age through late life with substantial genetic heterogeneity even when diagnosis and screening procedures vary. Conclusions: Results from the population based twin cohort, indicate a greater genetic contribution to the risk of developing prostate cancer when addressing sources of bias. The role of genetic factors is consistently high across age Impact: Findings impact the search for genetic and epigenetic markers and frame prevention efforts.
    Cancer Epidemiology Biomarkers & Prevention 05/2014; 23(11). DOI:10.1158/1055-9965.EPI-13-0568 · 4.13 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Objective: Our objective was to explore whether childhood exposure to perfluorinated and polyfluorinated compounds (PFCs), widely used stain- and grease-repellent chemicals, is associated with adiposity and markers of glycemic control. Materials and methods: Body mass index, skinfold thickness, waist circumference, leptin, adiponectin, insulin, glucose, and triglyceride concentrations were assessed in 8- to 10-year-old children in 1997 in a subset of the European Youth Heart Study, Danish component. Plasma PFC concentrations were available from 499 children. Linear regression models were performed to determine the association between PFC exposure and indicators of adiposity and markers of glycemic control. Results: There was no association between PFC exposures and adiposity or markers of glycemic control in normal-weight children. Among overweight children, an increase of 10 ng perfluorooctane sulfonic acid/mL plasma was associated with 16.2% (95% confidence interval [CI], 5.2%-28.3%) higher insulin concentration, 12.0% (95% CI, 2.4%-22.4%) higher β-cell activity, 17.6% (95% CI, 5.8%-30.8%) higher insulin resistance, and 8.6% (95% CI, 1.2%-16.5%) higher triglyceride concentrations, and an increase of 10 ng perfluorooctanoic acid/mL plasma was associated with 71.6% (95% CI, 2.4%-187.5%) higher insulin concentration, 67.5% (95% CI, 5.5%-166.0%) higher β-cell function, 73.9% (95% CI, 0.2%-202.0%) higher insulin resistance, and 76.2% (95% CI, 22.8%-153.0%) higher triglyceride concentrations. Discussion: Increased PFC exposure in overweight 8- to 10-year-old children was associated with higher insulin and triglyceride concentrations. Chance findings may explain some of our results, and due to the cross-sectional design, reverse causation cannot be excluded. The findings therefore need to be confirmed in longitudinal studies.
    The Journal of Clinical Endocrinology and Metabolism 02/2014; 99(4):jc20133460. DOI:10.1210/jc.2013-3460 · 6.21 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Objective: The aim of this study was to evaluate overall survival (OS) after treatment of metastatic renal cell carcinoma (mRCC) following the introduction of tyrosine kinase inhibitors (TKIs) and mammalian target of rapamycin (mTOR) inhibitors. Material and methods: One-hundred and forty-three consecutive mRCC patients were given immunotherapy (n = 59), TKIs (n = 49) or sequential therapy (IMM → TKI group; n = 35). The TKI group included patients with higher age (p < 0.001), worse performance status (p = 0.005) and higher risk profile (p < 0.001) than the other two treatment groups. Number of metastases and sites and tumour histology did not differ between groups. Results: First line immunotherapy gave a median OS of 16.3 months and first line TKIs 10.9 months (p = 0.003). Survival longer than 5 years was limited to immunotherapy. Sarcomatoid component, metastatic sites, papillary histology, stage, performance status and white cell blood count were related to poor OS. Using multivariate analyses to adjust for risk predictors the difference in OS disappeared. Median OS before and after introduction of TKIs was 16 months and 14 months, respectively (p = 0.189). Memorial Sloan Kettering Cancer Center (MSKCC) risk groups were related to OS (p < 0.001). Heng's prognostic criteria appeared slightly more predictive than MSKCC (p = 0.12). Metastasectomy (n = 42) may improve OS [surgery: median OS 18.8 months, 95% confidence interval (CI) 12.3-48.5; no surgery: median OS 15 months, 95% CI 10.4-16.5; p = 0.07]. Conclusions: MSKCC and Heng's prognostic algorithms were valid for prognostication and can be used for individual planning of treatment and follow-up. Surgical removal of metastases may improve OS.
    Scandinavian Journal of Urology 02/2014; 48(4). DOI:10.3109/21681805.2013.876550 · 1.25 Impact Factor
  • Thomas H Scheike · Klaus K Holst · Jacob B Hjelmborg ·
    [Show abstract] [Hide abstract]
    ABSTRACT: For twin time-to-event data, we consider different concordance probabilities, such as the casewise concordance that are routinely computed as a measure of the lifetime dependence/correlation for specific diseases. The concordance probability here is the probability that both twins have experienced the event of interest. Under the assumption that both twins are censored at the same time, we show how to estimate this probability in the presence of right censoring, and as a consequence, we can then estimate the casewise twin concordance. In addition, we can model the magnitude of within pair dependence over time, and covariates may be further influential on the marginal risk and dependence structure. We establish the estimators large sample properties and suggest various tests, for example, for inferring familial influence. The method is demonstrated and motivated by specific twin data on cancer events with the competing risk death. We thus aim to quantify the degree of dependence through the casewise concordance function and show a significant genetic component. Copyright © 2013 John Wiley & Sons, Ltd.
    Statistics in Medicine 10/2013; 33(7). DOI:10.1002/sim.6016 · 1.83 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Do birthweight (BW) and co-twin sex influence the age at menarche in twins? BW, but not co-twin sex, was associated with age at menarche in twins. However, BW was not associated with age at menarche after controlling for genetics and shared rearing environment. Nutritional deprivation during critical developmental periods can trigger long-term effects on health. A small size at birth has been associated with early age at menarche in singletons. However, the relative influence of genetics and environmental factors on this association remains unresolved. In total, 2505 twin pairs were included in this cohort study. All participants were recruited from the Danish Twin Register. Data on the age at menarche were collected by questionnaire and combined with data on BW, birth length (BL) and gestational age (GA) from the Danish Medical Birth register. The BW for GA standard deviation score (BW-SDS) was calculated. BW-SDS [hazard ratio (HR) 0.96; 95% confidence interval (CI): 0.93-0.00], P = 0.04], but not BW, BL or GA (P ≥ 0.15), was positively associated with age at menarche in all twins after adjustment for zygosity and year of birth. However, BW-SDS was not associated with menarcheal age within twin pairs (HR 1.01; 95% CI: 0.91-1.12, P = 0.88). No differences were found in the age at menarche or birth size between twin girls from same sex and twin girls from opposite-sex pregnancies. Heritability of menarcheal age and BW were estimated to be 0.61 (95% CI: 0.38-0.84) and 0.27 (95% CI: 0.18-0.38), respectively. Both BW and menarcheal age were influenced by genetic and environmental factors. A limitation of this study is recall bias on the age at menarche. It is also not clear how these results should be extrapolated to the non-twin population. lower BW for GA is associated with earlier age at menarche in twin girls. However, the lack of within-pair differences in menarcheal age between even markedly BW-discordant twins indicates that this association is governed by environmental or genetic factors shared by both twins. Thus, within-pair differences in intrauterine nutritional factors leading to discordant growth do not seem to influence timing of menarche. The authors have nothing to declare. Departmental funds were used to support all authors during the study period and preparation.
    Human Reproduction 08/2013; 28(10). DOI:10.1093/humrep/det283 · 4.57 Impact Factor
  • Thomas H Scheike · Klaus K Holst · Jacob B Hjelmborg ·
    [Show abstract] [Hide abstract]
    ABSTRACT: There has been considerable interest in studying the magnitude and type of inheritance of specific diseases. This is typically derived from family or twin studies, where the basic idea is to compare the correlation for different pairs that share different amount of genes. We here consider data from the Danish twin registry and discuss how to define heritability for cancer occurrence. The key point is that this should be done taking censoring as well as competing risks due to e.g. death into account. We describe the dependence between twins on the probability scale and show that various models can be used to achieve sensible estimates of the dependence within monozygotic and dizygotic twin pairs that may vary over time. These dependence measures can subsequently be decomposed into a genetic and environmental component using random effects models. We here present several novel models that in essence describe the association in terms of the concordance probability, i.e., the probability that both twins experience the event, in the competing risks setting. We also discuss how to deal with the left truncation present in the Nordic twin registries, due to sampling only of twin pairs where both twins are alive at the initiation of the registries.
    Lifetime Data Analysis 02/2013; 20(2). DOI:10.1007/s10985-013-9244-x · 0.65 Impact Factor
  • Source
    Thomas A Gerds · Thomas H Scheike · Per K Andersen ·
    [Show abstract] [Hide abstract]
    ABSTRACT: In survival analysis with competing risks, the transformation model allows different functions between the outcome and explanatory variables. However, the model's prediction accuracy and the interpretation of parameters may be sensitive to the choice of link function. We review the practical implications of different link functions for regression of the absolute risk (or cumulative incidence) of an event. Specifically, we consider models in which the regression coefficients β have the following interpretation: The probability of dying from cause D during the next t years changes with a factor exp(β) for a one unit change of the corresponding predictor variable, given fixed values for the other predictor variables. The models have a direct interpretation for the predictive ability of the risk factors. We propose some tools to justify the models in comparison with traditional approaches that combine a series of cause-specific Cox regression models or use the Fine-Gray model. We illustrate the methods with the use of bone marrow transplant data. Copyright © 2012 John Wiley & Sons, Ltd.
    Statistics in Medicine 12/2012; 31(29). DOI:10.1002/sim.5459 · 1.83 Impact Factor

Publication Stats

5k Citations
489.52 Total Impact Points


  • 1992-2015
    • IT University of Copenhagen
      København, Capital Region, Denmark
  • 2014
    • University of Southern Denmark
      • Institute of Public Health
      Odense, South Denmark, Denmark
  • 2009
    • National Institute for Medical Research (NIMR)
      Dār es Salām, Dar es Salaam, Tanzania
  • 2002
    • Aalborg University
      • Department of Mathematical Sciences
      Ålborg, North Denmark, Denmark
  • 2000
    • Odense University Hospital
      Odense, South Denmark, Denmark
  • 1993-1994
    • University of California, Berkeley
      • Department of Statistics
      Berkeley, California, United States