Search

Statistics is an inherently collaborative discipline as individuals across academia, government, and industry all rely on data to answer relevant questions and innovate in their fields. As a result, there is a growing body of research regarding how to teach interdisciplinary collaboration skills to statistics students. However, much of this work relies on data that do not objectively assess collaboration. Additionally, prior research lacks detailed evidence of how to assess quality of collaboration skills. In this case study, we compare the statistical collaboration skills of both a team of students and an expert collaborator on two components of effective statistical collaboration: structuring a statistical collaboration meeting and communicating with a domain expert during a statistical collaboration meeting. We find that students can facilitate meetings and communicate comparably well to an expert statistical collaborator, but that expert collaborators may be better able to facilitate meetings and communicate to develop strong relationships with domain experts, an important element for high-quality and long-term statistical collaboration projects. Further work is needed to generalize these findings to a larger population, but these results begin to inform the field regarding effective ways to teach specific statistical collaboration skills.

Serial limiting dilution (SLD) assays are a widely used tool in many areas of public health research to measure the concentration of target entities. This concentration can be estimated via maximum likelihood. Asymptotic as well as exact inference methods have been proposed for hypothesis testing and confidence interval construction in this one-sample problem. However, in many scientific applications, it may be of interest to compare the concentration of target entities between a pair of samples and construct valid confidence intervals for the difference in concentrations. In this paper, an exact, computationally efficient inferential procedure is proposed for hypothesis testing and confidence interval construction in the two-sample SLD assay problem. The proposed exact method is compared to an approach based on asymptotic approximations in simulation studies. The methods are illustrated using data from the University of North Carolina HIV Cure Center.

Accurate power calculations are essential in small studies containing expensive experimental units or high-stakes exposures. Herein, power of the Wilcoxon Mann-Whitney rank-sum test of a continuous outcome is formulated using a Monte Carlo approach and defining [Formula: see text] as a measure of effect size, where [Formula: see text] and [Formula: see text] denote random observations from two distributions hypothesized to be equal under the null. Effect size [Formula: see text] fosters productive communications because researchers understand [Formula: see text] is analogous to a fair coin toss, and [Formula: see text] near 0 or 1 represents a large effect. This approach is feasible even without background data. Simulations were conducted comparing the empirical power approach to existing approaches by Rosner & Glynn, Shieh and colleagues, Noether, and O'Brien-Castelloe. Approximations by Noether and O'Brien-Castelloe are shown to be inaccurate for small sample sizes. The Rosner & Glynn and Shieh, Jan & Randles approaches performed well in many small sample scenarios, though both are restricted to location-shift alternatives and neither approach is theoretically justified for small samples. The empirical method is recommended and available in the R package wmwpow.

OBJECTIVE: To study the contribution of γδ T cells to the persistent HIV reservoir. DESIGN: Fifteen HIV-seropositive individuals on suppressive ART were included. We performed parallel quantitative viral outgrowth assays (QVOA) of resting CD4+ T (rCD4) cells in the presence or absence of γδ T cells. METHODS: Resting αβ+CD4(+) T cells were magnetically isolated from PBMCs using two different custom cocktails, only one kit contained antibodies to deplete γδ T cells, resulting in two populations: rCD4 cells and rCD4 cells depleted of γδ cells. Frequency of infection was analyzed by QVOA and DNA measurements. RESULTS: Recovery of replication competent HIV from cultures of rCD4 cells was similar in 11 individuals despite the presence of γδ T cells. In four donors, HIV recovery was lower when γδ T cells were present. Expression of the cytotoxic marker CD16 on Vδ2 cells was the only variable associated with the lower HIV recovery. Our results highlight the potency of those responses since a mean of 10.000 γδ T cells were present within 2.5million rCD4 cells. However, despite the low frequency of γδ T cells, the presence of cytotoxic Vδ2 cells correlated with lower HIV recovery from cultures of rCD4 cells. CONCLUSIONS: Results of this study show that quantification of the contribution of γδ T cells to the reservoir is challenging due to their low numbers compared to conventional rCD4 cells and highlights the potent antiviral function of γδ T cells and the impact of their presence on the frequency of latent HIV infection.

Serial limiting dilution (SLD) assays are used in many areas of infectious disease related research. This paper presents SLDAssay, a free and publicly available R software package and web tool for analyzing data from SLD assays. SLDAssay computes the maximum likelihood estimate (MLE) for the concentration of target cells, with corresponding exact and asymptotic confidence intervals. Exact and asymptotic goodness of fit p-values, and a bias-corrected (BC) MLE are also provided. No other publicly available software currently implements the BC MLE or the exact methods. For validation of SLDAssay, results from Myers et al. (1994) are replicated. Simulations demonstrate the BC MLE is less biased than the MLE. Additionally, simulations demonstrate that exact methods tend to give better confidence interval coverage and goodness-of-fit tests with lower type I error than the asymptotic methods. Additional advantages of using exact methods are also discussed.