Traditional latent class analysis (LCA) considers entropy R2 as the only measure of effect size. However, entropy may not always be reliable, a low boundary is not agreed upon, and good separation is limited to values of greater than .80. As applications of LCA grow in popularity, it is imperative to use additional sources to quantify LCA classification accuracy. Greater classification accuracy helps to ensure that the profile of the latent classes reflect the profile of the true underlying subgroups. This Monte Carlo study compared the quantification of classification accuracy and confidence intervals of three effect sizes, entropy R2, I-index, and Cohen’s d. Study conditions included total sample size, number of dichotomous indicators, latent class membership probabilities (γ), conditional item-response probabilities (ρ), variance ratio, sample size ratio, and distribution types for a 2-class model. Overall, entropy R2 and I-index showed the best accuracy and standard error, along with the smallest confidence interval widths. Results showed that I-index only performed well for a few cases.

From the Helichrysum genus 600 species occur in Africa of which 244 species are found in South Africa. The most commonly used Helichrysum species for medicinal purposes are H. cymosum, H. odoratissimum, H. petiolare and H. nudifolium. The medicinal uses include the treatment of coughs, colds, fever, infection, headaches, menstrual pain and are very popular for wound dressing. Previous published research has shown that H. aureonitens has antiviral properties against Herpes simplex virus type 1 (HSV-1). In this study, further investigation into the Helichrysum species was undertaken, to establish the active constituents responsible for anti-HSV activity using a metabolomics approach. The cytotoxicity of 12 Helichrysum species was investigated and ranged from <3.125 μg/ml to 277.8 μg/ml on the vero cell line. The 12 Helichrysum species also showed various levels of antiviral activity against HSV, with both the water-methanol and chloroform extracts of H. adenocarpum subsp. adenocarpum being the most active extract at 25 μg/ml. In this study the activity of Helichrysum species against HIV-1 RT was also investigated. Helichrysum populifolium was the most active extract, inhibiting the HIV-1 RT enzyme by 63.78 % at 200 μg/ml. The bioactivity data and the spectral nuclear magnetic resonance (NMR) data of al the Helichrysum species from this study was analysed using the SIMCA-P software to discriminate between the different species on the basis of their bioactivity and chemical composition. The samples did not group well on Principal Component Analysis (PCA) but did separate well using the Orthogonal Projection to Latent Structure – Discriminate Analysis (OPLS-DA) on the basis of their activity and NMR spectra data. From the OPLS scoring plots analysis, contribution plots were created which indicated regions responsible for the difference between the species, with these regions being investigated to identify the bioactive constituents. It was thus possible to use metabolomics to discriminate between samples on the basis of their activity and show that it could probably be used in future as a tool to identify active ingredients in medicinal plants and accelerate drug discovery. Copyright / Dissertation (MSc)--University of Pretoria, 2009. / Plant Science / unrestricted

The use cases of Information Extraction (IE) are more or less endless, often consisting of a combination of Named Entity Recognition (NER) and Relation Extraction (RE). One use case of IE is the extraction of transaction information from Norwegian insider transaction Press Releases (PRs), where a transaction consists of at most four entities: the name of the owner performing the transaction, the number of shares transferred, the transaction date, and the price of the shares bought or sold. The relationships between the entities define which entity belongs to which transaction, and whether shares were bought or sold. This report has investigated how a pair of supervised NER and RE models extract this information. Since these Norwegian PRs were not labeled, two different approaches to annotating the transaction entities and their associated relations were investigated, and it was found that it is better to annotate only entities that occur in a relation than annotating all occurrences. Furthermore, the number of PRs needed to achieve a satisfactory result in the IE pipeline was investigated. The study shows that training with about 400 PRs is sufficient for the results to converge, at around 0.85 in F1-score. Finally, the report shows that there is not much difference between a complex RE model and a simple rule-based approach, when applied on the studied corpus.