Selection bias and the cross-validation of regression models for prediction

Strategies are compared for the development of a linear regression model with stochastic (multivariate normal) regressor variables and the subsequent assessment of its predictive ability. Bias and mean squared error of four estimators of predictive performance are evaluated in simulated samples of 32 population correlation matrices. Models including all of the available predictors are compared with those obtained using selected subsets. The subset selection procedures investigated include two stopping rules, C$\sb{\rm p}$ and S$\sb{\rm p}$, each combined with an 'all possible subsets' or 'forward selection' of variables. The estimators of performance utilized include parametric (MSEP$\sb{\rm m}$) and non-parametric (PRESS) assessments in the entire sample, and two data splitting estimates restricted to a random or balanced (Snee's DUPLEX) 'validation' half sample. The simulations were performed as a designed experiment, with population correlation matrices representing a broad range of data structures.^ The techniques examined for subset selection do not generally result in improved predictions relative to the full model. Approaches using 'forward selection' result in slightly smaller prediction errors and less biased estimators of predictive accuracy than 'all possible subsets' approaches but no differences are detected between the performances of C$\sb{\rm p}$ and S$\sb{\rm p}$. In every case, prediction errors of models obtained by subset selection in either of the half splits exceed those obtained using all predictors and the entire sample.^ Only the random split estimator is conditionally (on $\\beta$) unbiased, however MSEP$\sb{\rm m}$ is unbiased on average and PRESS is nearly so in unselected (fixed form) models. When subset selection techniques are used, MSEP$\sb{\rm m}$ and PRESS always underestimate prediction errors, by as much as 27 percent (on average) in small samples. Despite their bias, the mean squared errors (MSE) of these estimators are at least 30 percent less than that of the unbiased random split estimator. The DUPLEX split estimator suffers from large MSE as well as bias, and seems of little value within the context of stochastic regressor variables.^ To maximize predictive accuracy while retaining a reliable estimate of that accuracy, it is recommended that the entire sample be used for model development, and a leave-one-out statistic (e.g. PRESS) be used for assessment. ^

A hybrid method in combining treatment effects from matched and unmatched studies

In the biomedical studies, the general data structures have been the matched (paired) and unmatched designs. Recently, many researchers are interested in Meta-Analysis to obtain a better understanding from several clinical data of a medical treatment. The hybrid design, which is combined two data structures, may create the fundamental question for statistical methods and the challenges for statistical inferences. The applied methods are depending on the underlying distribution. If the outcomes are normally distributed, we would use the classic paired and two independent sample T-tests on the matched and unmatched cases. If not, we can apply Wilcoxon signed rank and rank sum test on each case. ^ To assess an overall treatment effect on a hybrid design, we can apply the inverse variance weight method used in Meta-Analysis. On the nonparametric case, we can use a test statistic which is combined on two Wilcoxon test statistics. However, these two test statistics are not in same scale. We propose the Hybrid Test Statistic based on the Hodges-Lehmann estimates of the treatment effects, which are medians in the same scale.^ To compare the proposed method, we use the classic meta-analysis T-test statistic on the combined the estimates of the treatment effects from two T-test statistics. Theoretically, the efficiency of two unbiased estimators of a parameter is the ratio of their variances. With the concept of Asymptotic Relative Efficiency (ARE) developed by Pitman, we show ARE of the hybrid test statistic relative to classic meta-analysis T-test statistic using the Hodges-Lemann estimators associated with two test statistics.^ From several simulation studies, we calculate the empirical type I error rate and power of the test statistics. The proposed statistic would provide effective tool to evaluate and understand the treatment effect in various public health studies as well as clinical trials.^

Novel Imaging-Based Techniques Reveal a Role for PD-1/PD-L1 in Tumor Immune Surveillance in the Lung

The binding of immune inhibitory receptor Programmed Death 1 (PD-1) on T cells to its ligand PD-L1 has been implicated as a major contributor to tumor induced immune suppression. Clinical trials of PD-L1 blockade have proven effective in unleashing therapeutic anti-tumor immune responses in a subset of patients with advanced melanoma, yet current response rates are low for reasons that remain unclear. Hypothesizing that the PD-1/PD-L1 pathway regulates T cell surveillance within the tumor microenvironment, we employed intravital microscopy to investigate the in vivo impact of PD-L1 blocking antibody upon tumor-associated immune cell migration. However, current analytical methods of intravital dynamic microscopy data lack the ability to identify cellular targets of T cell interactions in vivo, a crucial means for discovering which interactions are modulated by therapeutic intervention. By developing novel imaging techniques that allowed us to better analyze tumor progression and T cell dynamics in the microenvironment; we were able to explore the impact of PD-L1 blockade upon the migratory properties of tumor-associated immune cells, including T cells and antigen presenting cells, in lung tumor progression. Our results demonstrate that early changes in tumor morphology may be indicative of responsiveness to anti-PD-L1 therapy. We show that immune cells in the tumor microenvironment as well as tumors themselves express PD-L1, but immune phenotype alone is not a predictive marker of effective anti-tumor responses. Through a novel method in which we quantify T cell interactions, we show that T cells are largely engaged in interactions with dendritic cells in the tumor microenvironment. Additionally, we show that during PD-L1 blockade, non-activated T cells are recruited in greater numbers into the tumor microenvironment and engage more preferentially with dendritic cells. We further show that during PD-L1 blockade, activated T cells engage in more confined, immune synapse-like interactions with dendritic cells, as opposed to more dynamic, kinapse-like interactions with dendritic cells when PD-L1 is free to bind its receptor. By advancing the contextual analysis of anti-tumor immune surveillance in vivo, this study implicates the interaction between T cells and tumor-associated dendritic cells as a possible modulator in targeting PD-L1 for anti-tumor immunotherapy.

Cryo-electron tomography of Kaposi's sarcoma-associated herpesvirus capsids reveals dynamic scaffolding structures essential to capsid assembly and maturation.

Kaposi's sarcoma-associated herpesvirus (KSHV) is a recently discovered DNA tumor virus that belongs to the gamma-herpesvirus subfamily. Though numerous studies on KSHV and other herpesviruses, in general, have revealed much about their multilayered organization and capsid structure, the herpesvirus capsid assembly and maturation pathway remains poorly understood. Structural variability or irregularity of the capsid internal scaffolding core and the lack of adequate tools to study such structures have presented major hurdles to earlier investigations employing more traditional cryo-electron microscopy (cryoEM) single particle reconstruction. In this study, we used cryo-electron tomography (cryoET) to obtain 3D reconstructions of individual KSHV capsids, allowing direct visualization of the capsid internal structures and systematic comparison of the scaffolding cores for the first time. We show that B-capsids are not a structurally homogenous group; rather, they represent an ensemble of "B-capsid-like" particles whose inner scaffolding is highly variable, possibly representing different intermediates existing during the KSHV capsid assembly and maturation. This information, taken together with previous observations, has allowed us to propose a detailed pathway of herpesvirus capsid assembly and maturation.

Sequential updating via dynamic hierarchical models: A Bayesian approach to longitudinal data analysis

Most statistical analysis, theory and practice, is concerned with static models; models with a proposed set of parameters whose values are fixed across observational units. Static models implicitly assume that the quantified relationships remain the same across the design space of the data. While this is reasonable under many circumstances this can be a dangerous assumption when dealing with sequentially ordered data. The mere passage of time always brings fresh considerations and the interrelationships among parameters, or subsets of parameters, may need to be continually revised. ^ When data are gathered sequentially dynamic interim monitoring may be useful as new subject-specific parameters are introduced with each new observational unit. Sequential imputation via dynamic hierarchical models is an efficient strategy for handling missing data and analyzing longitudinal studies. Dynamic conditional independence models offers a flexible framework that exploits the Bayesian updating scheme for capturing the evolution of both the population and individual effects over time. While static models often describe aggregate information well they often do not reflect conflicts in the information at the individual level. Dynamic models prove advantageous over static models in capturing both individual and aggregate trends. Computations for such models can be carried out via the Gibbs sampler. An application using a small sample repeated measures normally distributed growth curve data is presented. ^