Comparison between Maximum Likelihood and Bayesian Estimation in Structural Equation Modelling and Effects of Informative Priors

The aims of this study are to compare the maximum likelihood and Bayesian methods for estimation in structural equation modelling in real large data sets with different degrees of multivariate non-normality and to investigate the effects of non-informative and informative priors on parameter estimates in Bayesian structural equation modelling. Two data sets from the British Household Panel Survey are taken for the analyses, with total respondents of 6,522 and 7,150. In each of them, eighteen questions are drawn to be indicators for seven latent variables. In this dissertation, three separate hypothesised models are constructed in order to increase a variety of multivariate non-normality degrees; these are Models A, B and C. The research findings provided from classical structural equation modelling show that Model A and Model B are well fitted with a non-significant chi-square statistic at a bootstrap probability of more than 0.05, while Model C is also reasonably fitted with a significant chi-square statistic at a bootstrap probability of just below 0.05. The comparative fit indices in all models illustrate very high values; additionally, the root mean square error of approximation values are rather low. Furthermore, all estimated parameters are significant at a p-value of 0.001 and there are no zero values lying between their bootstrap confidence intervals. Under the multivariate non-normal condition, maximum likelihood estimators seem to lose their efficiency property, but not by much, and are robust to violation due to the large sample size. As for the findings from Bayesian structural equation modelling, all the estimated parameters of the three models are also significant. When incorporated with non-informative priors, the estimates and their standard errors are equivalent to the ones yielded by classical structural equation modelling. On the other hand, the parameters generated with informative priors vary according to the prior means but the standard errors are diminished consistently for all estimates, in comparison with the ones provided from classical structural equation modelling and Bayesian structural equation modelling with non-informative priors. The posterior distributions after being updated by the informative priors appear to be more normal owing to a decrease in skewness and kurtosis; moreover, the ones produced from Model B, which has the highest non-normality, are most affected by the informative priors according to the change in skewness and kurtosis.

A review of the Mutillidae (Hymenoptera) of Turkey

Sixty five species in 21 genera are recorded from Turkey. The new species, Skorikovia anatolica Lelej, sp. nov. (Turkey), is described and illustrated. The hitherto unknown male is recognized for Pseudophotopsis schachruda (Skorikov). A new synonymy is proposed for Pseudophotopsis schachruda (Skorikov 1935) = Ephutomma schachruda var. robusta Skorikov 1935, syn. nov., E. mavromoustakisi Suárez 1959, syn. nov. A new status is proposed for Krombeinella gaullei (Invrea). The status is resurrected for Pseudophotopsis schachruda (Skorikov) and Dentilla erronea (André). Nine species are recorded for the first time from Turkey: Pseudophotopsis syriaca (André), Myrmilla anopla Skorikov, Tropidotilla semirufa (André), Mutilla richterae Lelej, Skorikovia radoszkovskii (Skorikov), S. transcaucasica (Lelej), Smicromyrme azerbaidzhanicus Lelej, S. novaki Invrea, and S. rufipes (Fabricius). Krombeinella gaullei (Invrea) is recorded for the first time from Bulgaria. Eleven species and one subspecies are excluded from the list of Turkish fauna. A key to five Palaearctic species of Skorikovia is given. A tabular checklist for the mutillid fauna of Turkey, Greece, Armenia, Azerbaijan, and Georgia includes 106 species and four subspecies. A cluster analysis of faunal similarities among these countries for Mutillidae produce two major clusters (index similarity 0.4): Turkey and Greece (bootstrap probability 95 %), and Armenia, Azerbaijan, and Georgia (bootstrap probability 90 %), and demonstrates the important boundary between two large biogeographical subregions of Palaearctic: Mediterranean and Euro-Siberian. The Turkish fauna, especially its eastern part, is the transitional zone between these subregions. The mutillid fauna of Turkey consists of widely distributed in the Mediterranean (21), East Mediterranean (28), widely distributed in the Palaearctic (three) and Anatolian-Armenian (13) species, including five endemic species. The highest number of species is known from the Anatolian biogeographical province of Turkey: 55.

Molecular characterization of whitefly, Bemisia tabaci (Hemiptera: Aleyrodidae) populations infesting cassava

Bemisia tabaci (Gennadius) populations, collected from cassava and other plants in major cassava-cultivation areas of Sub-saharan Africa and from elsewhere around the world, were studied to determine their biotype status and genetic variation. Random amplified polymorphic DNA–polymerase chain reaction (RAPD–PCR) markers were used to examine the genetic structure of the populations. The dendogram obtained using the neighbour joining method (NJ) split the cassava-associated populations from the non-cassava types with a 100% bootstrap probability. Analysis of molecular variance (AMOVA) of the RAPD fragments revealed that 63.2% of the total variation was attributable to differences among populations, while the differences among groups (host) and within populations accounted for 27.1 and 9.8% respectively. Analysis of the internally transcribed spacer region I (ITS 1) of the ribosomal DNA confirmed that the cassava populations of B. tabaci populations were distinct from non-cassava populations. Experiments to establish whitefly populations on various host plants revealed that cassava-associated populations were restricted to cassava only, whereas B. tabaci from other hosts were polyphagous but did not colonize cassava. Hence, populations of B. tabaci from cassava in Africa represent a distinct group.

Sequence analysis of vasotocin cDNAs of the lamprey, Lampetra japonica, and the hagfish, Eptatretus burgeri: evolution of cyclostome vasotocin precursors

ABSTRACT We determined the nucleotide sequences of cDNAs encoding precursors of vasotocin (VT) from two cyclostomes, the lamprey Lampetra japonica and the hagfish Eptatretus burgeri, for estimation of their phylogenetic relationships. Although only 47% similarity was found between the VT cDNAs, the predicted VT precursors of the lamprey and the hagfish were both composed of a signal peptide, VT, Gly-Lys-Arg and a neurophysin, as has been shown for precursors of vasopressin (VP) family hormones, including VP, VT and molluscan conopressin. The central region of the lamprey neurophysin was very similar to those of previously characterized gnathostome neurophysins. Conspicuously, all the positions of 14 Cys residues were conserved in the lamprey neurophysin. The C-terminal region did not have a distinctive Leu-rich core segment, which is always found in the glycopeptide (copeptin) moiety of VP precursors. In contrast, the hagfish neurophysin showed at least two insertions and one deletion in the conserved central region including 14 Cys residues, but contained a potential N-linked glycosylation site and had a high proportion of Leu residues in the C-terminal region, like the neurophysin of another hagfish, Eptatretus stouti. The evolutionary relationships of the precursors of VP family hormones among the lamprey, hagfish, gnathostomes and a mollusc were estimated by a maximum likelihood method. The phylogenetic tree with the highest bootstrap probability showed that the lamprey VT precursor is more closely related to the gnathostome VT and VP precursors than to the hagfish VT precursors.