ref.bib

@article{Mahjani20,
title = "Maternal Effects as Causes of Risk for Obsessive-Compulsive Disorder",
journal = "Biological Psychiatry",
volume = "87",
number = "12",
pages = "1045 - 1051",
year = "2020",
note = "Obsessive-Compulsive Disorder and Developmental Disorders",
issn = "0006-3223",
doi = "10.1016/j.biopsych.2020.01.006",
url = "http://www.sciencedirect.com/science/article/pii/S0006322320300123",
author = "Behrang Mahjani and Lambertus Klei and Christina M. Hultman and Henrik Larsson and Bernie Devlin and Joseph D. Buxbaum and Sven Sandin and Dorothy E. Grice",
keywords = "Assortative mating, Direct genetic effects, Heritability, Maternal effects, Obsessive-compulsive disorder, Population based",
abstract = "Background
While genetic variation has a known impact on the risk for obsessive-compulsive disorder (OCD), there is also evidence that there are maternal components to this risk. Here, we partitioned sources of variation, including direct genetic and maternal effects, on risk for OCD.
Methods
The study population consisted of 822,843 individuals from the Swedish Medical Birth Register, born in Sweden between January 1, 1982, and December 31, 1990, and followed for a diagnosis of OCD through December 31, 2013. Diagnostic information about OCD was obtained using the Swedish National Patient Register.
Results
A total of 7184 individuals in the birth cohort (0.87%) were diagnosed with OCD. After exploring various generalized linear mixed models to fit the diagnostic data, genetic maternal effects accounted for 7.6% (95% credible interval: 6.9%–8.3%) of the total variance in risk for OCD for the best model, and direct additive genetics accounted for 35% (95% credible interval: 32.3%–36.9%). These findings were robust under alternative models.
Conclusions
Our results establish genetic maternal effects as influencing risk for OCD in offspring. We also show that additive genetic effects in OCD are overestimated when maternal effects are not modeled."
}

@misc{zhao19,
    title={Missing Value Imputation for Mixed Data via Gaussian Copula},
    author={Yuxuan Zhao and Madeleine Udell},
    year={2019},
    eprint={1910.12845},
    archivePrefix={arXiv},
    primaryClass={stat.ME}
}

@article{Botev17,
author = {Botev, Z. I.},
title = {The normal law under linear restrictions: simulation and estimation via minimax tilting},
journal = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
volume = {79},
number = {1},
pages = {125-148},
keywords = {Exact simulation, Exponential tilting, Linear inequalities, Multivariate normal distribution, Polytope probabilities, Probit posterior simulation},
doi = {10.1111/rssb.12162},
url = {https://rss.onlinelibrary.wiley.com/doi/abs/10.1111/rssb.12162},
eprint = {https://rss.onlinelibrary.wiley.com/doi/pdf/10.1111/rssb.12162},
abstract = {Summary Simulation from the truncated multivariate normal distribution in high dimensions is a recurrent problem in statistical computing and is typically only feasible by using approximate Markov chain Monte Carlo sampling. We propose a minimax tilting method for exact independently and identically distributed data simulation from the truncated multivariate normal distribution. The new methodology provides both a method for simulation and an efficient estimator to hitherto intractable Gaussian integrals. We prove that the estimator has a rare vanishing relative error asymptotic property. Numerical experiments suggest that the scheme proposed is accurate in a wide range of set-ups for which competing estimation schemes fail. We give an application to exact independently and identically distributed data simulation from the Bayesian posterior of the probit regression model.},
year = {2017}
}

@article{Liu17,
author = {Liu, Xing-Rong and Pawitan, Yudi and Clements, Mark S.},
title = {Generalized survival models for correlated time-to-event data},
journal = {Statistics in Medicine},
volume = {36},
number = {29},
pages = {4743-4762},
keywords = {adaptive Gauss-Hermite quadrature, correlated survival data, generalized survival models, link functions, random effects, tensor product},
doi = {10.1002/sim.7451},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/sim.7451},
eprint = {https://onlinelibrary.wiley.com/doi/pdf/10.1002/sim.7451},
abstract = {Our aim is to develop a rich and coherent framework for modeling correlated time-to-event data, including (1) survival regression models with different links and (2) flexible modeling for time-dependent and nonlinear effects with rich postestimation. We extend the class of generalized survival models, which expresses a transformed survival in terms of a linear predictor, by incorporating a shared frailty or random effects for correlated survival data. The proposed approach can include parametric or penalized smooth functions for time, time-dependent effects, nonlinear effects, and their interactions. The maximum (penalized) marginal likelihood method is used to estimate the regression coefficients and the variance for the frailty or random effects. The optimal smoothing parameters for the penalized marginal likelihood estimation can be automatically selected by a likelihood-based cross-validation criterion. For models with normal random effects, Gauss-Hermite quadrature can be used to obtain the cluster-level marginal likelihoods. The Akaike Information Criterion can be used to compare models and select the link function. We have implemented these methods in the R package rstpm2. Simulating for both small and larger clusters, we find that this approach performs well. Through 2 applications, we demonstrate (1) a comparison of proportional hazards and proportional odds models with random effects for clustered survival data and (2) the estimation of time-varying effects on the log-time scale, age-varying effects for a specific treatment, and two-dimensional splines for time and age.},
year = {2017}
}

@article{Kingma15,
  title={Adam: A Method for Stochastic Optimization},
  author={Diederik P. Kingma and Jimmy Ba},
  journal={CoRR},
  year={2015},
  volume={abs/1412.6980}
}

@article{hoff07,
author = "Hoff, Peter D.",
doi = "10.1214/07-AOAS107",
fjournal = "Annals of Applied Statistics",
journal = "Ann. Appl. Stat.",
month = "06",
number = "1",
pages = "265--283",
publisher = "The Institute of Mathematical Statistics",
title = "Extending the rank likelihood for semiparametric copula estimation",
url = "https://doi.org/10.1214/07-AOAS107",
volume = "1",
year = "2007"
}

@article{Pawitan04,
author = {Pawitan, Y. and Reilly, M. and Nilsson, E. and Cnattingius, S. and Lichtenstein, P.},
title = {Estimation of genetic and environmental factors for binary traits using family data},
journal = {Statistics in Medicine},
volume = {23},
number = {3},
pages = {449-465},
keywords = {clustered binary data, GLMM, mixed models, hierarchical likelihood, segregation analysis, pre-eclampsia},
doi = {10.1002/sim.1603},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/sim.1603},
eprint = {https://onlinelibrary.wiley.com/doi/pdf/10.1002/sim.1603},
abstract = {Abstract While the family-based analysis of genetic and environmental contributions to continuous or Gaussian traits is now straightforward using the linear mixed models approach, the corresponding analysis of complex binary traits is still rather limited. In the latter we usually rely on twin studies or pairs of relatives, but these studies often have limited sample size or have difficulties in dealing with the dependence between the pairs. Direct analysis of extended family data can potentially overcome these limitations. In this paper, we will describe various genetic models that can be analysed using an extended family structure. We use the generalized linear mixed model to deal with the family structure and likelihood-based methodology for parameter inference. The method is completely general, accommodating arbitrary family structures and incomplete data. We illustrate the methodology in great detail using the Swedish birth registry data on pre-eclampsia, a hypertensive condition induced by pregnancy. The statistical challenges include the specification of sensible models that contain a relatively large number of variance components compared to standard mixed models. In our illustration the models will account for maternal or foetal genetic effects, environmental effects, or a combination of these and we show how these effects can be readily estimated using family data. Copyright © 2004 John Wiley \& Sons, Ltd.},
year = {2004}
}

@article{Genz02,
author = {Alan Genz and Frank Bretz},
title = {Comparison of Methods for the Computation of Multivariate t Probabilities},
journal = {Journal of Computational and Graphical Statistics},
volume = {11},
number = {4},
pages = {950-971},
year  = {2002},
publisher = {Taylor & Francis},
doi = {10.1198/106186002394},

URL = {
        https://doi.org/10.1198/106186002394

},
eprint = {
        https://doi.org/10.1198/106186002394

}

}

@article{Chlebíková96,
title = {Approximating the maximally balanced connected partition problem in graphs},
journal = {Information Processing Letters},
volume = {60},
number = {5},
pages = {225-230},
year = {1996},
issn = {0020-0190},
doi = {10.1016/S0020-0190(96)00175-5},
url = {https://www.sciencedirect.com/science/article/pii/S0020019096001755},
author = {Janka Chlebíková},
keywords = {Analysis of algorithms, Combinatorial problems, Connected graphs},
abstract = {The approximability of the following optimization problem is investigated: Given a connected graph G = (V, E), find the maximally balanced connected partition for G, i.e. a partition (V1, V2) of V into disjoint sets V1 and V2 such that both subgraphs of G induced by V1 and V2 are connected, and maximize an objective function “balance”, B(V1, V2) = min(¦V1¦, ¦V2¦). We prove that for any ϵ > 0 it is NP-hard (even for bipartite graphs) to approximate the maximum balance of the connected partition for G = (V, E) with an absolute error guarantee of ¦V¦1 − ε. On the other hand, we give a polynomial-time approximation algorithm that solves the problem within 43 even when vertices of G are weighted. The variation of the problem is equivalent to the Maximally Balanced Spanning Tree Problem studied by Galbiati, Maffioli and Morzenti (1995). Our simple polynomial-time algorithm approximates the solution of that problem within 1.072.}
}

@article{Karypis98,
author = {Karypis, George and Kumar, Vipin},
title = {A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs},
journal = {SIAM Journal on Scientific Computing},
volume = {20},
number = {1},
pages = {359-392},
year = {1998},
doi = {10.1137/S1064827595287997},

URL = {
        https://doi.org/10.1137/S1064827595287997

},
eprint = {
        https://doi.org/10.1137/S1064827595287997

}

}

@INPROCEEDINGS{Fiduccia82,
  author={Fiduccia, C.M. and Mattheyses, R.M.},
  booktitle={19th Design Automation Conference},
  title={A Linear-Time Heuristic for Improving Network Partitions},
  year={1982},
  volume={},
  number={},
  pages={175-181},
  doi={10.1109/DAC.1982.1585498}}

@article{Hopcroft73,
author = {Hopcroft, John and Tarjan, Robert},
title = {Algorithm 447: Efficient Algorithms for Graph Manipulation},
year = {1973},
issue_date = {June 1973},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {16},
number = {6},
issn = {0001-0782},
url = {10.1145/362248.362272},
doi = {10.1145/362248.362272},
abstract = {Efficient algorithms are presented for partitioning a graph into connected components, biconnected components and simple paths. The algorithm for partitioning of a graph into simple paths of iterative and each iteration produces a new path between two vertices already on paths. (The start vertex can be specified dynamically.) If V is the number of vertices and E is the number of edges, each algorithm requires time and space proportional to max (V, E) when executed on a random access computer.},
journal = {Commun. ACM},
month = jun,
pages = {372–378},
numpages = {7},
keywords = {graphs, graph manipulation, analysis of algorithms}
}

@ARTICLE{Kernighan70,
  author={Kernighan, B. W. and Lin, S.},
  journal={The Bell System Technical Journal},
  title={An efficient heuristic procedure for partitioning graphs},
  year={1970},
  volume={49},
  number={2},
  pages={291-307},
  doi={10.1002/j.1538-7305.1970.tb01770.x}}