In the analysis of categorized data, the tumors were divided into three groups; one group of 12 tumors with the highest expression ratios, another group of 24 tumors with intermediate ratios, and a third group of 12 tumors with the lowest ratios.
In the analysis of exposure categorized in quintiles, regression dilution ratios (RDR) were calculated based on repeated health examinations in 133,820 subjects in the full Me-Can database in order to adjust RRs for random errors in the measurement of exposure variables at baseline [ 27, 28], this process has been described in detail previously [ 13].
Figure 2 illustrates that, in the scenario where the causal variant has an effect on only one sub-phenotype, logistic regression analysis of cases of the specific sub-phenotype against controls is more powerful than multinomial regression analysis of cases categorized according to sub-phenotype, although the difference is minimal (MULTINOMIAL compared with SP1).
However, because the factorial solution resulting from the analysis of categorized OAV items did not markedly differ from the factorial solution of the continuous items, except that the correlations between the latent variables were generally larger, we only report results from those statistical analyses that treated the OAV items as continuous variables.
Our novel segmentation was benchmarked by a retrospective analysis of patients categorized as either 111In-octreotide positive (111In-octreotide or 111In-octreotide negative (111In-octreotide for liver tumours.
In post hoc analysis of patients categorized by serum lithium level, LS mean (SE) change in YMRS total score was −23.6 (0.79) in the ≥6 mEq/L and −21.6 (1.04) in the <6 mEq/L group (p < 0.001 and 0.171, respectively, vs. placebo).
Chi-square analysis was used to perform a responder's analysis of patients categorized as those with 1) at least 30% and 2) at least 20% improvement in pain.
Figure 3 demonstrates that multinomial regression analysis of cases categorized according to sub-phenotype performs well, compared with all other approaches, over a wide range of models in which the causal variant contributes effects to both sub-phenotypes, but not necessarily in the same direction (MULTINOMIAL compared with LOGISTIC, SP1 and SP2).
An analysis of the literature to categorize tweets based on the four aspects of consistency of message, coherency of message, credibility of source and general acceptability as given in the previous section was done.
Further epistasis analysis of WGD pairs categorized by their inferred evolutionary fates demonstrated the utility of these techniques.
