G*Power is a free power analysis program for a variety of statistical tests. We present extensions and improvements of the version introduced by Faul, Erdfelder, Lang, and Buchner (2007) in the domain of correlation and regression analyses. In the new version, we have added procedures to analyze the power of tests based on (1) single-sample tetrachoric correlations, (2) comparisons of dependent correlations, (3) bivariate linear regression, (4) multiple linear regression based on the random predictor model, (5) logistic regression, and (6) Poisson regression. We describe these new features and provide a brief introduction to their scope and handling.

/pdf/statistical-power-analyses-using-g-power-3-1-tests-for-dnxl4mlxpv.pdf

Statistical power analyses using G*Power 3.1: tests for correlation and regression analyses.

How should ecologists and evolutionary biologists analyze nonnormal data that involve random effects? Nonnormal data such as counts or proportions often defy classical statistical procedures. Generalized linear mixed models (GLMMs) provide a more flexible approach for analyzing nonnormal data when random effects are present. The explosion of research on GLMMs in the last decade has generated considerable uncertainty for practitioners in ecology and evolution. Despite the availability of accurate techniques for estimating GLMM parameters in simple cases, complex GLMMs are challenging to fit and statistical inference such as hypothesis testing remains difficult. We review the use (and misuse) of GLMMs in ecology and evolution, discuss estimation and inference and summarize 'best-practice' data analysis procedures for scientists facing this challenge.

/pdf/generalized-linear-mixed-models-a-practical-guide-for-3gh61pkir0.pdf

Generalized linear mixed models: a practical guide for ecology and evolution

The therapeutic properties of light have been known for thousands of years, but it was only in the last century that photodynamic therapy (PDT) was developed. At present, PDT is being tested in the clinic for use in oncology--to treat cancers of the head and neck, brain, lung, pancreas, intraperitoneal cavity, breast, prostate and skin. How does PDT work, and how can it be used to treat cancer and other diseases?

Photodynamic therapy for cancer

Summary. Recent work by Reiss and Ogden provides a theoretical basis for sometimes preferring restricted maximum likelihood (REML) to generalized cross-validation (GCV) for smoothing parameter selection in semiparametric regression. However, existing REML or marginal likelihood (ML) based methods for semiparametric generalized linear models (GLMs) use iterative REML or ML estimation of the smoothing parameters of working linear approximations to the GLM. Such indirect schemes need not converge and fail to do so in a non-negligible proportion of practical analyses. By contrast, very reliable prediction error criteria smoothing parameter selection methods are available, based on direct optimization of GCV, or related criteria, for the GLM itself. Since such methods directly optimize properly defined functions of the smoothing parameters, they have much more reliable convergence properties. The paper develops the first such method for REML or ML estimation of smoothing parameters. A Laplace approximation is used to obtain an approximate REML or ML for any GLM, which is suitable for efficient direct optimization. This REML or ML criterion requires that Newton–Raphson iteration, rather than Fisher scoring, be used for GLM fitting, and a computationally stable approach to this is proposed. The REML or ML criterion itself is optimized by a Newton method, with the derivatives required obtained by a mixture of implicit differentiation and direct methods. The method will cope with numerical rank deficiency in the fitted model and in fact provides a slight improvement in numerical robustness on the earlier method of Wood for prediction error criteria based smoothness selection. Simulation results suggest that the new REML and ML methods offer some improvement in mean-square error performance relative to GCV or Akaike's information criterion in most cases, without the small number of severe undersmoothing failures to which Akaike's information criterion and GCV are prone. This is achieved at the same computational cost as GCV or Akaike's information criterion. The new approach also eliminates the convergence failures of previous REML- or ML-based approaches for penalized GLMs and usually has lower computational cost than these alternatives. Example applications are presented in adaptive smoothing, scalar on function regression and generalized additive model selection.

/pdf/fast-stable-restricted-maximum-likelihood-and-marginal-4rm5jbnyqs.pdf

Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models

The brms package implements Bayesian multilevel models in R using the probabilistic programming language Stan. A wide range of distributions and link functions are supported, allowing users to fit - among others - linear, robust linear, binomial, Poisson, survival, ordinal, zero-inflated, hurdle, and even non-linear models all in a multilevel context. Further modeling options include autocorrelation of the response variable, user defined covariance structures, censored data, as well as meta-analytic standard errors. Prior specifications are flexible and explicitly encourage users to apply prior distributions that actually reflect their beliefs. In addition, model fit can easily be assessed and compared with the Watanabe-Akaike information criterion and leave-one-out cross-validation.

brms: An R Package for Bayesian Multilevel Models Using Stan

Preface. 1. Introduction: Why Mixed Models? 2. MLE for LME Model. 3. Statistical Properties of the LME Model. 4. Growth Curve Model and Generalizations. 5. Meta--analysis Model. 6. Nonlinear Marginal Model. 7. Generalized Linear Mixed Models. 8. Nonlinear Mixed Effects Model. 9. Diagnostics and Influence Analysis. 10. Tumor Regrowth Curves. 11. Statistical Analysis of Shape. 12. Statistical Image Analysis. 13. Appendix: Useful Facts and Formulas. References. Index.

Mixed Models: Theory and Applications

MicroRNAs (miRNAs) regulate gene expression. It has been suggested that obtaining miRNA expression profiles can improve classification, diagnostic, and prognostic information in oncology. Here, we sought to comprehensively identify the miRNAs that are overexpressed in lung cancer by conducting miRNA microarray expression profiling on normal lung versus adjacent lung cancers from transgenic mice. We found that miR-136, miR-376a, and miR-31 were each prominently overexpressed in murine lung cancers. Real-time RT-PCR and in situ hybridization (ISH) assays confirmed these miRNA expression profiles in paired normal-malignant lung tissues from mice and humans. Engineered knockdown of miR-31, but not other highlighted miRNAs, substantially repressed lung cancer cell growth and tumorigenicity in a dose-dependent manner. Using a bioinformatics approach, we identified miR-31 target mRNAs and independently confirmed them as direct targets in human and mouse lung cancer cell lines. These targets included the tumor-suppressive genes large tumor suppressor 2 (LATS2) and PP2A regulatory subunit B alpha isoform (PPP2R2A), and expression of each was augmented by miR-31 knockdown. Their engineered repression antagonized miR-31-mediated growth inhibition. Notably, miR-31 and these target mRNAs were inversely expressed in mouse and human lung cancers, underscoring their biologic relevance. The clinical relevance of miR-31 expression was further independently and comprehensively validated using an array containing normal and malignant human lung tissues. Together, these findings revealed that miR-31 acts as an oncogenic miRNA (oncomir) in lung cancer by targeting specific tumor suppressors for repression.

/pdf/microrna-31-functions-as-an-oncogenic-microrna-in-mouse-and-wv49bn1f62.pdf

MicroRNA-31 functions as an oncogenic microRNA in mouse and human lung cancer cells by repressing specific tumor suppressors

There is no consensus on the approach to compute the power and sample size with logistic regression. Some authors use the likelihood ratio test; some use the test on proportions; some suggest various approximations to handle the multivariate case. We advocate the use of the Wald test since the Z-score is routinely used for statistical significance testing of regression coefficients. The null-variance formula became popular from early studies, which contradicts modern software, which utilizes the method of maximum likelihood estimation (MLE), when the variance of the MLE is estimated at the MLE, not at the null. We derive general Wald-based power and sample size formulas for logistic regression and then apply them to binary exposure and confounder to obtain a closed-form expression. These formulas are applied to minimize the total sample size in a case-control study to achieve a given power by optimizing the ratio of controls to cases. Approximately, the optimal number of controls to cases is equal to the square root of the alternative odds ratio. Our sample size and power calculations can be carried out online at www.dartmouth.edu/ approximately eugened.

Sample size determination for logistic regression revisited.

BACKGROUND

Although access to cancer care is known to influence patient outcomes, to the authors' knowledge, little is known regarding geographic access to cancer care, and how it may vary by population characteristics. This study estimated travel time to specialized cancer care settings for the continental U.S. population and calculated per capita oncologist supply.



METHODS

The closest travel times were estimated using a network analysis of the road distance weighted by travel speeds from the population or geographic centroid of every ZIP area in the continental U.S. to that of the nearest cancer care setting under consideration: National Cancer Institute (NCI)-designated Cancer Centers, academic medical centers, and oncologists. Alaska and Hawaii were excluded because travel in these states is often not road-based. Population and geographic characteristics including race/ethnicity, income, education, and region were derived from U.S. Census 2000 data and from rural-urban commuting area classifications. Oncologist supply per 100,000 residents in Hospital Referral Regions (pHRRs) was estimated by region.



RESULTS

Travel times of ≤1 hour were estimated for 45.2% of the population to the nearest NCI Cancer Center, 69.4% to the nearest academic-based care, and 91.8% to any specialized cancer care. Native Americans, nonurban dwellers, and residents in the South had the longest travel times to the nearest NCI Cancer Center compared with the overall U.S. population (median [interquartile range (IQR)] in minutes: 155 [62–308], 173 [111–257], and 164 [70–272], vs 78 [27–172], respectively). Travel burdens persisted for Native Americans and nonurban populations across all 3 cancer care settings. For all population strata, travel times markedly increased as the degree of cancer care specialization increased. The median oncologist supply for pHRRs was 2.83 per 100,000 individuals.



CONCLUSIONS

There are population groups with limited access to the most specialized cancer care settings. Cancer 2008. © 2008 American Cancer Society.

https://acsjournals.onlinelibrary.wiley.com/doi/pdf/10.1002/cncr.23229

Geographic access to cancer care in the U.S.

Description: Praise for the First Edition "This book will serve to greatly complement the growing number of texts dealing with mixed models, and I highly recommend including it in one's personal library." Journal of the American Statistical Association Mixed modeling is a crucial area of statistics, enabling the analysis of clustered and longitudinal data. Mixed Models: Theory and Applications with R, Second Edition fills a gap in existing literature between mathematical and applied statistical books by presenting a powerful examination of mixed model theory and application with special attention given to the implementation in R. The new edition provides in–depth mathematical coverage of mixed models' statistical properties and numerical algorithms, as well as nontraditional applications, such as regrowth curves, shapes, and images. The book features the latest topics in statistics including modeling of complex clustered or longitudinal data, modeling data with multiple sources of variation, modeling biological variety and heterogeneity, Healthy Akaike Information Criterion (HAIC), parameter multidimensionality, and statistics of image processing. Mixed Models: Theory and Applications with R, Second Edition features unique applications of mixed model methodology, as well as: Comprehensive theoretical discussions illustrated by examples and figures Over 300 exercises, end–of–section problems, updated data sets, and R subroutines Problems and extended projects requiring simulations in R intended to reinforce material Summaries of major results and general points of discussion at the end of each chapter Open problems in mixed modeling methodology, which can be used as the basis for research or PhD dissertations Ideal for graduate–level courses in mixed statistical modeling, the book is also an excellent reference for professionals in a range of fields, including cancer research, computer science, and engineering.

Eugene Demidenko

Papers

Mixed Models: Theory and Applications

MicroRNA-31 functions as an oncogenic microRNA in mouse and human lung cancer cells by repressing specific tumor suppressors

Sample size determination for logistic regression revisited.

Geographic access to cancer care in the U.S.

Mixed Models: Theory and Applications with R