Correct and logical causal inference for binary and time-to-event outcomes in randomized controlled trials.

Targeted therapies tend to have biomarker defined subgroups that derive differential efficacy from treatments. This article corrects three prevailing oversights in stratified analyses comparing treatments in randomized controlled trials (RCTs) with binary and time-to-event outcomes: 1.Using efficacy measures such as odds ratio (OR) and hazard ratio (HR) can make a prognostic biomarker appear predictive, targeting wrong patients, because the inference is affected by a confounding/covert factor even with ignorable treatment assignment in an RCT. As shown analytically and with real immunotherapy patient level data, OR and HR cannot meet the causal Estimand requirement of ICH E9R1. 2.Mixing efficacy in subgroups by prevalence, the prevailing practice, can give misleading results also, for any efficacy measured as a ratio. However, mixing relative response (RR) and ratio of median (RoM) survival times by the prognostic effect, the confounding/covert factor hiding in plain sight, will give causal inference in an RCT. 3.Effects in subgroups should not be mixed on the logarithmic scale, because it creates an artificial Estimand for the whole population which changes depending on how the population is divided into subgroups. Current computer package implementations contain all these oversights. Probabilities, including survival curve probabilities, naturally average within each treatment arm by prevalence. The subgroup mixable estimation (SME) principle fixes the oversights by first averaging probabilities (not their logarithms) within each treatment arm, then computing simultaneous confidence intervals for ratio efficacy in subgroups and their mixtures based on rigorous mathematical derivation, to finally provide causal inference in the form of apps.

Importance of the efficiency of double-stranded DNA formation in cDNA synthesis for the imprecision of microarray expression analysis.

BACKGROUND: The causes of imprecision in microarray expression analysis are poorly understood, limiting the use of this technology in molecular diagnostics. Two-dimensional strandness-dependent electrophoresis (2D-SDE) separates nucleic acid molecules on the basis of length and strandness, i.e., double-stranded DNA (dsDNA), single-stranded DNA (ssDNA), and RNA·DNA hybrids. METHODS: We used 2D-SDE to measure the efficiency of cDNA synthesis and its importance for the imprecision of an in vitro transcription-based microarray expression analysis. RESULTS: The relative amount of double-stranded cDNA formed in replicate experiments that used the same RNA sample template was highly variable, ranging between 0% and 72% of the total DNA. Microarray experiments showed an inverse relationship between the difference between sample pairs in probe variance and the relative amount of dsDNA. Approximately 15% of probes showed between-sample variation (P < 0.05) when the dsDNA percentage was between 12% and 35%. In contrast, only 3% of probes showed between-sample variation when the dsDNA percentage was 69% and 72%. Replication experiments of the 35% dsDNA and 72% dsDNA samples were used to separate sample variation from probe replication variation. The estimated SD of the sample-to-sample variation and of the probe replicates was lower in 72% dsDNA samples than in 35% dsDNA samples. CONCLUSIONS: Variation in the relative amount of double-stranded cDNA synthesized can be an important component of the imprecision in T7 RNA polymerase-based microarray expression analysis.