Authors: Ilija Barukčić
Comments: 37 pages. Copyright © 2018 by Ilija Barukčić, Horandstrasse, Jever, Germany. Published by:
Objective: Accumulating evidence indicates that the gut microbiome has an increas-ingly important role in human disease and health. Fusobacterium nucleatum has been identified in several studies as the leading gut bacterium which is present in colorectal cancer (CRC). Still it is not clear if Fusobacterium plays a causal role.
Methods: To explore the cause-effect relationship between Fusobacterium nucleatum and colorectal cancer, a systematic review and re-analysis of studies published was performed. The method of the conditio sine qua non relationship was used to proof the hypothesis without Fusobacterium nucleatum infection no colorectal cancer. The mathematical formula of the causal relationship k was used to proof the hypothesis, whether there is a cause effect relationship between Fusobacterium nucleatum and colorectal cancer. Significance was indicated by a p-value of less than 0.05
Result: The data analyzed support the Null-hypothesis that without Fusobacterium nucleatum infection no colorectal cancer. In the same respect, the studies analyzed provide highly significant cause effect relationship between Fusobacterium nucleatum and colorectal cancer.
Conclusion: The findings of this study suggest that Fusobacterium (nucleatum) is the cause of colorectal cancer.
Authors: Robert Bennett
Comments: 14 Pages.
Biased statistics can arise from computational errors, belief in non-existent or unproven correlations ...or acceptance of premises proven invalid scientifically.
It is the latter that will be examined here for the case of human life expectancy, whose values are well-known...and virtually never challenged as to their basic assumptions.
Whether the false premises are accidental, a case of overlooking the obvious...or if they may be deliberate distortions serving a subliminal agenda.... is beyond the scope of this analysis.
Authors: Jason Hou-Liu
Latent Dirichlet Allocation (LDA) is a generative model describing the observed data as being composed of a mixture of underlying unobserved topics, as introduced by Blei et al. (2003). A key hyperparameter of LDA is the number of underlying topics k, which must be estimated empirically in practice. Selecting the appropriate value of k is essentially selecting the correct model to represent the data; an important issue concerning the goodness of fit. We examine in the current work a series of metrics from literature on a quantitative basis by performing benchmarks against a generated dataset with a known value of k and evaluate the ability of each metric to recover the true value, varying over multiple levels of topic resolution in the Dirichlet prior distributions. Finally, we introduce a new metric and heuristic for estimating kand demonstrate improved performance over existing metrics from the literature on several benchmarks.