Determination of Urinary Cotinine Cut-Off Concentrations for Pregnant Women in the Japan Environment and Children’s Study (JECS)

Few studies have assessed the accuracy of self-reported questionnaires to determine smoking habits relative to urinary biomarkers. This study investigated urinary cotinine cut-off concentrations distinguishing active, passive and non-smokers among pregnant women who participated in the Japan Environment and Children’s Study, a nationwide birth cohort study. Pregnant participants with measured urinary cotinine concentrations (UCCs) and who completed self-reported questionnaires on smoking status were included (n = 89,895). The cut-off values (COVs) for active and passive smokers were calculated by fitting mixed normal distribution functions to UCCs. The sensitivity and specificity of the questionnaires were subsequently evaluated. The median (interquartile range) UCC was 0.24 (0.083–0.96) µg/g-creatinine, with the detection rate of 89%. The COV for distinguishing active smokers from passive and non-smokers was 36.8 µg/g-creatinine. When this COV was considered to represent the true condition, the questionnaire had a sensitivity of 0.523, a specificity of 0.998, a positive predictive value (PPV) of 0.967 and a negative predictive value (NPV) of 0.957. The COV for distinguishing passive smokers from non-smokers was 0.31 µg/g-creatinine, with the questionnaire having a sensitivity of 0.222, a specificity of 0.977, a PPV of 0.868 and an NPV of 0.644. As many as 78% of passive smokers might be misclassified as non-smokers.

MIXED NORMAL INFERENCE ON MULTICOINTEGRATION

Asymptotic likelihood analysis of cointegration in I (2) models (see Johansen, 1997, 2006; Boswijk, 2000; Paruolo, 2000) has shown that inference on most parameters is mixed normal, implying hypothesis test statistics with an asymptotic χ2 null distribution. The asymptotic distribution of the multicointegration parameter estimator so far has been characterized by a Brownian motion functional, which has been conjectured to have a mixed normal distribution, based on simulations. The present note proves this conjecture.

Estimating the False Discovery Rate Using Mixed Normal Distribution for Identifying Differentially Expressed Genes in Microarray Data Analysis

The recent development of DNA microarray technology allows us to measure simultaneously the expression levels of thousands of genes and to identify truly correlated genes with anticancer drug response (differentially expressed genes) from many candidate genes. Significance Analysis of Microarray (SAM) is often used to estimate the false discovery rate (FDR), which is an index for optimizing the identifiability of differentially expressed genes, while the accuracy of the estimated FDR by SAM is not necessarily confirmed. We propose a new method for estimating the FDR assuming a mixed normal distribution on the test statistic and examine the performance of the proposed method and SAM using simulated data. The simulation results indicate that the accuracy of the estimated FDR by the proposed method and SAM, varied depending on the experimental conditions. We applied both methods to actual data comprised of expression levels of 12,625 genes of 10 responders and 14 non-responders to docetaxel for breast cancer. The proposed method identified 280 differentially expressed genes correlated with docetaxel response using a cut-off value for achieving FDR <0.01 to prevent false-positive genes, although 92 genes were previously thought to be correlated with docetaxel response ones.

Nonparametric Competitors to the Two-Way ANOVA

The ANOVA F and several nonparametric competitors for two-way designs were compared for empirical α and power. Simulation of 2 × 2, 2 × 4, and 4 × 4 designs was done with cell sizes of 5 and 10 when sampling from normal, exponential, and mixed normal distributions. Conservatism of both α and power in the presence of other nonnull effects was seen in the tests due to Puri and Sen (1985) and, to a lesser degree, in the rank transform tests ( Conover & Iman, 1981 ). Tests by McSweeney (1967) and Hettmansperger (1984) had liberal α for some designs and distributions, especially for small n. The ANOVA F suffers from conservative α and power for the mixed normal distribution, but it is generally recommended.