A simulation study using the hybrid statistic and the meta-analysis t-test for data with matched and unmatched subjects in the interim analysis of clinical trials

An interim analysis is usually applied in later phase II or phase III trials to find convincing evidence of a significant treatment difference that may lead to trial termination at an earlier point than planned at the beginning. This can result in the saving of patient resources and shortening of drug development and approval time. In addition, ethics and economics are also the reasons to stop a trial earlier. In clinical trials of eyes, ears, knees, arms, kidneys, lungs, and other clustered treatments, data may include distribution-free random variables with matched and unmatched subjects in one study. It is important to properly include both subjects in the interim and the final analyses so that the maximum efficiency of statistical and clinical inferences can be obtained at different stages of the trials. So far, no publication has applied a statistical method for distribution-free data with matched and unmatched subjects in the interim analysis of clinical trials. In this simulation study, the hybrid statistic was used to estimate the empirical powers and the empirical type I errors among the simulated datasets with different sample sizes, different effect sizes, different correlation coefficients for matched pairs, and different data distributions, respectively, in the interim and final analysis with 4 different group sequential methods. Empirical powers and empirical type I errors were also compared to those estimated by using the meta-analysis t-test among the same simulated datasets. Results from this simulation study show that, compared to the meta-analysis t-test commonly used for data with normally distributed observations, the hybrid statistic has a greater power for data observed from normally, log-normally, and multinomially distributed random variables with matched and unmatched subjects and with outliers. Powers rose with the increase in sample size, effect size, and correlation coefficient for the matched pairs. In addition, lower type I errors were observed estimated by using the hybrid statistic, which indicates that this test is also conservative for data with outliers in the interim analysis of clinical trials.^

Bayesian estimation of multilevel item response model with missing data

This study proposed a novel statistical method that modeled the multiple outcomes and missing data process jointly using item response theory. This method follows the "intent-to-treat" principle in clinical trials and accounts for the correlation between outcomes and missing data process. This method may provide a good solution to chronic mental disorder study. ^ The simulation study demonstrated that if the true model is the proposed model with moderate or strong correlation, ignoring the within correlation may lead to overestimate of the treatment effect and result in more type I error than specified level. Even if the within correlation is small, the performance of proposed model is as good as naïve response model. Thus, the proposed model is robust for different correlation settings if the data is generated by the proposed model.^

Network-based analysis of genome-wide scans of natural selection

The genomic era brought by recent advances in the next-generation sequencing technology makes the genome-wide scans of natural selection a reality. Currently, almost all the statistical tests and analytical methods for identifying genes under selection was performed on the individual gene basis. Although these methods have the power of identifying gene subject to strong selection, they have limited power in discovering genes targeted by moderate or weak selection forces, which are crucial for understanding the molecular mechanisms of complex phenotypes and diseases. Recent availability and rapid completeness of many gene network and protein-protein interaction databases accompanying the genomic era open the avenues of exploring the possibility of enhancing the power of discovering genes under natural selection. The aim of the thesis is to explore and develop normal mixture model based methods for leveraging gene network information to enhance the power of natural selection target gene discovery. The results show that the developed statistical method, which combines the posterior log odds of the standard normal mixture model and the Guilt-By-Association score of the gene network in a naïve Bayes framework, has the power to discover moderate/weak selection gene which bridges the genes under strong selection and it helps our understanding the biology under complex diseases and related natural selection phenotypes.^

Decomposition of $\rm R\times C$ contingency table chi -square: Application to binned DNA fragment size data and population structure analysis

The purpose of this research is to develop a new statistical method to determine the minimum set of rows (R) in a R x C contingency table of discrete data that explains the dependence of observations. The statistical power of the method will be empirically determined by computer simulation to judge its efficiency over the presently existing methods. The method will be applied to data on DNA fragment length variation at six VNTR loci in over 72 populations from five major racial groups of human (total sample size is over 15,000 individuals; each sample having at least 50 individuals). DNA fragment lengths grouped in bins will form the basis of studying inter-population DNA variation within the racial groups are significant, will provide a rigorous re-binning procedure for forensic computation of DNA profile frequencies that takes into account intra-racial DNA variation among populations. ^

A comparison between multi-proxy and historical data of drift-ice conditions on the East Greenland shelf

The reduction in sea ice along the SE Greenland coast during the last century has severely impacted ice-rafting to this area. In order to reconstruct ice-rafting and oceanographic conditions in the area of Denmark Strait during the last ~150 years, we conducted a multiproxy study on three short (20 cm) sediment cores from outer Kangerdlugssuaq Trough (~300 m water depth). The proxy-based data obtained have been compared with historical and instrumental data to gain a better understanding of the ice sheet-ocean interactions in the area. A robust chronology has been developed based on 210Pb and 137Cs measurements on core PO175GKC#9 (~66.2°N, 32°W) and expanded to the two adjacent cores based on correlations between calcite weight percent records. Our proxy records include sea-ice and phytoplankton biomarkers, and a variety of mineralogical determinations based on the <2 mm sediment fraction, including identification with quantitative x-ray diffraction, ice-rafted debris counts on the 63-150 µm sand fraction, and source identifications based on the composition of Fe oxides in the 45-250 µm fraction. A multivariate statistical analysis indicated significant correlations between our proxy records and historical data, especially with the mean annual temperature data from Stykkishólmur (Iceland) and the storis index (historical observations of sea-ice export via the East Greenland Current). In particular, the biological proxies (calcite weight percent, IP25, and total organic carbon %) showed significant linkage with the storis index. Our records show two distinct intervals in the recent history of the SE Greenland coast. The first of these (ad 1850-1910) shows predominantly perennial sea-ice conditions in the area, while the second (ad 1910-1990) shows more seasonally open water conditions.

(Table 1) Sediment descriptions and age at DSDP Legs 5 and 63 Holes

Sediments from immediately above basalt basement and from between sections of basalt recovered from Deep Sea Drilling Project Legs 5 and 63 were analyzed by atomic absorption spectroscopy for Mg, Al, Si, Ca, Mn, Fe, Co, Ni, Cu, Zn, and Ba. All of these sediments showed enrichment in Fe and Mn over values typical of detritus supplied to the northeastern Pacific Ocean. X-ray diffractometry and differential chemical leaching indicate that up to 50% of the sediment, by weight, is in amorphous phases and that these phases are rich in Mn, Co, Cu, Ni, and Zn. Multivariate statistical analysis and normative partitioning of the chemical data indicate that much of the excess Fe and other transition elements in the sediment originate from hydrothermal sources.

Características palinológicas de mieles de eucalipto (Eucalyptus sp.) y tréboles (Trifolium sp.) provenientes de la Provincia Fitogeográfica Pampeana Argentina

El objetivo de este trabajo fue estudiar el perfil polínico de mieles de tréboles y de eucalipto de la Provincia Fitogeográfica Pampeana Argentina, con el fin de contribuir a su caracterización palinológica. Se realizó un análisis polínico cualitativo y se aplicaron técnicas estadísticas descriptivas y multivariadas, para conocer la distribución de frecuencia de los pólenes y caracterizar cada origen floral, según los pólenes acompañantes y los años de cosecha. Se analizaron 81 muestras de miel, de cuatro cosechas diferentes. Se encontraron 41 tipos morfológicos de polen, cuya variación por muestra osciló entre dos y ocho. El taxón presente en más del 80% de las mieles fue Eucalyptus sp. Los principales pólenes acompañantes encontrados pertenecieron a los tipos Helianthus annuus y Carduus sp., para ambos orígenes florales estudiados, y a la familia de las Brassicaceae, para las mieles de tréboles. Los años de cosecha estudiados mostraron diferentes espectros polínicos.

Grain entrainment and transport rates of magnetic minerals of coastal sediment samples from the Bay of Plenty, New Zealand

Heavy (magnetic & non-magnetic) minerals are found concentrated by natural processes in many fluvial, estuarine, coastal and shelf environments with a potential to form economic placer deposits. Understanding the processes of heavy mineral transport and enrichment is prerequisite to interpret sediment magnetic properties in terms of hydro- and sediment dynamics. In this study, we combine rock magnetic and sedimentological laboratory measurements with numerical 3D discrete element models to investigate differential grain entrainment and transport rates of magnetic minerals in a range of coastal environments (riverbed, mouth, estuary, beach and near-shore). We analyzed grain-size distributions of representative bulk samples and their magnetic mineral fractions to relate grain-size modes to respective transport modes (traction, saltation, suspension). Rock magnetic measurements showed that distribution shapes, population sizes and grain-size offsets of bulk and magnetic mineral fractions hold information on the transport conditions and enrichment process in each depositional environment. A downstream decrease in magnetite grain size and an increase in magnetite concentration was observed from riverine source to marine sink environments. Lower flow velocities permit differential settling of light and heavy mineral grains creating heavy mineral enriched zones in estuary settings, while lighter minerals are washed out further into the sea. Numerical model results showed that higher heavy mineral concentrations in the bed increased the erosion rate and enhancing heavy mineral enrichment. In beach environments where sediments contained light and heavy mineral grains of equivalent grain sizes, the bed was found to be more stable with negligible amount of erosion compared to other bed compositions. Heavy mineral transport rates calculated for four different bed compositions showed that increasing heavy mineral content in the bed decreased the transport rate. There is always a lag in transport between light and heavy minerals which increases with higher heavy mineral concentration in all tested bed compositions. The results of laboratory experiments were validated by numerical models and showed good agreement. We demonstrate that the presented approach bears the potential to investigate heavy mineral enrichment processes in a wide range of sedimentary settings.

Geochemistry and isotopes at DSDP Leg 80 Holes

Thirty-eight samples from DSDP Sites 549 to 551 were analyzed for major and minor components and trace element abundances. Multivariate statistical analysis of geochemical data groups the samples into two major classes: an organic-carbon- rich group (> 1% TOC) containing high levels of marine organic matter and certain trace elements (Cu, Zn, V, Ni, Co, Ba, and Cr) and an organic-carbon-lean group depleted in these components. The greatest organic and trace metal enrichments occur in the uppermost Albian to Turanian sections of Sites 549 to 551. Carbon-isotopic values of bulk carbonate for the middle Cenomanian section of Site 550 (2.35 to 2.70 per mil) and the upper Cenomanian-Turonian sections of Sites 549 (3.35 to 4.47 per mil) and 551 (3.13 to 3.72 per mil) are similar to coeval values reported elsewhere in the region. The relatively heavy d13C values from Sites 549 and 551 indicate that this interval was deposited during the global "oceanic anoxic event" that occurred at the Cenomanian/Turonian boundary. Variation in the d18O of bulk carbonate for Section 550B-18-1 of middle Cenomanian age suggests that paleosalinity and/or paleotemperature variations may have occurred concurrently with periodic anoxia at this site. Climatically controlled increases in surface-water runoff may have caused surface waters to periodically freshen, resulting in stable salinity stratification

Cenozoic oxygen isotopic values for benthic foraminifera from DSDP and ODP low and high latitude marine sediment cores

The climate during the Cenozoic era changed in several steps from ice-free poles and warm conditions to ice-covered poles and cold conditions. Since the 1950s, a body of information on ice volume and temperature changes has been built up predominantly on the basis of measurements of the oxygen isotopic composition of shells of benthic foraminifera collected from marine sediment cores. The statistical methodology of time series analysis has also evolved, allowing more information to be extracted from these records. Here we provide a comprehensive view of Cenozoic climate evolution by means of a coherent and systematic application of time series analytical tools to each record from a compilation spanning the interval from 4 to 61 Myr ago. We quantitatively describe several prominent features of the oxygen isotope record, taking into account the various sources of uncertainty (including measurement, proxy noise, and dating errors). The estimated transition times and amplitudes allow us to assess causal climatological-tectonic influences on the following known features of the Cenozoic oxygen isotopic record: Paleocene-Eocene Thermal Maximum, Eocene-Oligocene Transition, Oligocene-Miocene Boundary, and the Middle Miocene Climate Optimum. We further describe and causally interpret the following features: Paleocene-Eocene warming trend, the two-step, long-term Eocene cooling, and the changes within the most recent interval (Miocene-Pliocene). We review the scope and methods of constructing Cenozoic stacks of benthic oxygen isotope records and present two new latitudinal stacks, which capture besides global ice volume also bottom water temperatures at low (less than 30°) and high latitudes. This review concludes with an identification of future directions for data collection, statistical method development, and climate modeling.

Chemical composition of surficial bottom sediments from the Chukchi Sea and adjacent part of the Arctic Ocean

This paper presents data on chemical composition of bottom sediments from the Chukchi Sea and the adjacent Arctic Ocean. Multivariate statistical techniques were used for analysis of the data set and revealed that grain size fractionation of the original terrigenous component during sedimentation was the major factor of clustering of the samples in study. Secondary factors include accumulation of biogenic siliceous and carbonate material and chemogenic or biochemical accumulation of iron, manganese, and some trace elements. The latter factor was significant in areas of tectonic activity within the graben-rift system of the Chukchi Sea.

Phytoplankton niches estimated from CPR data in the North Atlantic

We combine phytoplankton occurrence data for 119 species from the continuous plankton recorder with climatological environmental variables in the North Atlantic to obtain ecological response functions of each species using the MaxEnt statistical method. These response functions describe how the probability of occurrence of each species changes as a function of environmental conditions and can be reduced to a simple description of phytoplankton realized niches using the mean and standard deviation of each environmental variable, weighted by its response function. Although there was substantial variation in the realized niche among species within groups, the envelope of the realized niches of North Atlantic diatoms and dinoflagellates are mostly separate in niche space.

Planktic foraminiferal flux and faunal composition of sediment trap L1_K276 in the northeastern Atlantic

Planktic foraminiferal (PF) flux and faunal composition from three sediment trap time series of 2002-2004 in the northeastern Atlantic show pronounced year-to-year variations despite similar sea surface temperature (SST). The averaged fauna of the in 2002/2003 is dominated by the species Globigerinita glutinata, whereas in 2003/2004 the averaged fauna is dominated by Globigerinoides ruber. We show that PF species respond primarily to productivity, triggered by the seasonal dynamics of vertical stratification of the upper water column. Multivariate statistical analysis reveals three distinct species groups, linked to bulk particle flux, to chlorophyll concentrations and to summer/fall oligotrophy with high SST and stratification. We speculate that the distinct nutrition strategies of strictly asymbiontic, facultatively symbiontic, and symbiontic species may play a key role in explaining their abundances and temporal succession. Advection of water masses within the Azores Current and species expatriation result in a highly diverse PF assemblage. The Azores Frontal Zone may have influenced the trap site in 2002, indicated by subsurface water cooling, by highest PF flux and high flux of the deep-dwelling species Globorotalia scitula. Similarity analyses with core top samples from the global ocean including 746 sites from the Atlantic suggest that the trap faunas have only poor analogs in the surface sediments. These differences have to be taken into account when estimating past oceanic properties from sediment PF data in the eastern subtropical North Atlantic.

Planktic and benthic 14C reservoir ages, calibrated by a suite of 14C plateaus in the glacial-to-deglacial Suigetsu atmospheric 14C record

We here present a compilation of planktic and benthic 14C reservoir ages for the Last Glacial Maximum (LGM) and early deglacial from 11 key sites of global ocean circulation in the Atlantic and Indo-Pacific Ocean. The ages were obtained by 14C plateau tuning, a robust technique to derive both an absolute chronology for marine sediment records and a high-resolution record of changing reservoir/ventilation ages (Delta14C values) for surface and deep waters by comparing the suite of planktic 14C plateaus of a sediment record with that of the atmospheric 14C record (Sarnthein et al., 2007, doi:10.1029/173GM13). Results published thus far used as atmospheric 14C reference U/Th-dated corals, the Cariaco planktic record, and speleothems (Fairbanks et al., 2005, doi:10.1016/j.quascirev.2005.04.007; Hughen et al., 2006, doi:10.1016/j.quascirev.2006.03.014; Beck et al., 2001, doi:10.1023/A:1008175728826). We have now used the varve-counted atmospheric 14C record of Lake Suigetsu terrestrial macrofossils (Ramsey et al., 2012, doi:10.1126/science.1226660) to recalibrate the boundary ages and reservoir ages of the seven published records directly to an atmospheric 14C record. In addition, the results for four new cores and further planktic results for four published records are given. Main conclusions from the new compilation are: (1) The Suigetsu atmospheric 14C record on its varve counted time scale reflects all 14C plateaus, their internal structures and relative length previously identified, but implies a rise in the average 14C plateau age by 200-700 14C yr during LGM and early deglacial times. (2) Based on different 14C ages of coeval atmospheric and planktic 14C plateaus, marine surface water Delta14C may have temporarily dropped to an equivalent of ~0 yr in low-latitude lagoon waters, but reached >2500 14C yr both in stratified subpolar waters and in upwelled waters such as in the South China Sea. These values differ significantly from a widely assumed constant global planktic Delta14C value of 400 yr. (3) Suites of deglacial planktic Delta14C values are closely reproducible in 14C records measured at neighboring core sites. (4) Apparent deep-water 14C ventilation ages (equivalents of benthic Delta14C), deduced from the sum of planktic Delta14C and coeval benthic-planktic 14C differences, vary from 500 up to >5000 yr in LGM and deglacial ocean basins.