Survival analysis: Part I — analysis of time-to-event / 대한마취과학회지

Length of time is a variable often encountered during data analysis. Survival analysis provides simple, intuitive results concerning time-to-event for events of interest, which are not confined to death. This review introduces methods of analyzing time-to-event. The Kaplan-Meier survival analysis, log-rank test, and Cox proportional hazards regression modeling method are described with examples of hypothetical data.

Functional Magnetic Resonance Imaging of Motor Cortex Activation in Schizophrenia

Previous fMRI studies of sensorimotor activation in schizophrenia have found in some cases hypoactivity, no difference, or hyperactivity when comparing patients with controls; similar disagreement exists in studies of motor laterality. In this multi-site fMRI study of a sensorimotor task in individuals with chronic schizophrenia and matched healthy controls, subjects responded with a right-handed finger press to an irregularly flashing visual checker board. The analysis includes eighty-five subjects with schizophrenia diagnosed according to the DSM-IV criteria and eighty-six healthy volunteer subjects. Voxel-wise statistical parametric maps were generated for each subject and analyzed for group differences; the percent Blood Oxygenation Level Dependent (BOLD) signal changes were also calculated over predefined anatomical regions of the primary sensory, motor, and visual cortex. Both healthy controls and subjects with schizophrenia showed strongly lateralized activation in the precentral gyrus, inferior frontal gyrus, and inferior parietal lobule, and strong activations in the visual cortex. There were no significant differences between subjects with schizophrenia and controls in this multi-site fMRI study. Furthermore, there was no significant difference in laterality found between healthy controls and schizophrenic subjects. This study can serve as a baseline measurement of schizophrenic dysfunction in other cognitive processes.

Power Analysis of Association Study Using Single Nucleotide Polymorphism / 신경정신의학

In order to find the disease susceptibility gene in these complex genetic trait, there have been much interests in association study using single nucleotide polymorphism (SNP). Association study can be divided into two approaches candidate gene approach and linkage disequilibrium mapping. Recently, the candidate gene approach also has attracted much attention with the possiblity of whole genome wide scan being widely discussed. In genome wide scan, the amount of information that a locus can provide about the other adjacent loci becomes an important matter. When a locus was found not to be associated with a trait, it is questionable that closely situated adjacent loci can also be excluded as disease susceptible loci. To approach this problem theoretically, this study tried to find a method to calculate power in case-control association study, and aimed to investigate the influence of hypothesized inheritance model to the obtainable power. In addition, this study investigated the implication of negative association results in other adjacent loci. METHOD: The power of associatiation study was calculated applying non-centrality chi-distribution approximated by Poisson distribution. Using this method, the powers in each inheritance model were calculated in candidate gene approach. The power of chi-square test in linkage disequilibrium mapping was also algebraically obtained. This method was applied to simulation data to verify the validity of the method. RESULT: The proportion of phenocopy and the allele frequency of candidate locus exert substantial influence to the power of the study rather than penetrance matrix or inheritance model. The power in linkage disequilibrium mapping exponentially decreased according to the degree of linkage disequilibrium as anticipated, however, the marker allele frequency exert enormous influence to the power. Without any a prior knowledge about which marker allele had linked with disease susceptibility allele, the marker with equal distribution of each allele showed the highest power. CONCLUSION: The implication of negative results obtained in association study can only be determined by power analysis. In linkage disequilibrium mapping, if favorable power had been obtained, exclusion analysis of specific gene segment could be attempted. Taking into account the probable inheritance model and the marker allele frequency in designing association study, more efficient and rigorous study can be possible.

Post-hoc Survey for Power of 119 Negative Results in Korean Journal of Anesthesiology / 대한마취과학회지

BACKGROUND: Statistical type II error has seemed to be ignored commonly by medical researchers. To control and present a power value could be helpful to reduce this type of error and to improve a quality of scientific decision making. We performed the post-hoc survey of the power of the negative results in Korean Journal of Anesthesiology (KJA). METHODS: One Hundred nineteen articles with negative results published in KJA during a year of 1997 were selected. We collected the numbers of the sample size and calculated the power of the given negative result only when applicable. And each author's attitude to negative results was taken by arbitrary criteria. RESULTS: Median sample size of these negative results was 16 12 (median interquartile range). We can calculate the power only in 43 articles of 119 negative results. Median power is 18.0% (interquartile range 26.0). In thirty six articles (83.8% of 43) the powers are proved to be under 80.0%. And 22 articles (51.2% of 43) have the powers even under 20.0%. We couldn't find any author who included either power or effect size in the article, and there was only one article in which its authors considered their inadequate number of sample size. CONCLUSIONS: We conclude that authors of KJA tend to ignore statistical type II error. In 119 negative results published in KJA during 1997, the calculated powers were very low and were not reported in the text.