A likelihood ratio test for the homogeneity of between-study variance in network meta-analysis

Background Network meta-analysis (NMA) is a statistical method used to combine results from several clinical trials and simultaneously compare multiple treatments using direct and indirect evidence. Statistical heterogeneity is a characteristic describing the variability in the intervention effects being evaluated in the different studies in network meta-analysis. One approach to dealing with statistical heterogeneity is to perform a random effects network meta-analysis that incorporates a between-study variance into the statistical model. A common assumption in the random effects model for network meta-analysis is the homogeneity of between-study variance across all interventions. However, there are applications of NMA where the single between-study assumption is potentially incorrect and instead the model should incorporate more than one between-study variances. Methods In this paper, we develop an approach to testing the homogeneity of between-study variance assumption based on a likelihood ratio test. A simulation study was conducted to assess the type I error and power of the proposed test. This method is then applied to a network meta-analysis of antibiotic treatments for Bovine respiratory disease (BRD). Results The type I error rate was well controlled in the Monte Carlo simulation. We found statistical evidence (p value = 0.052) against the homogeneous between-study variance assumption in the network meta-analysis BRD. The point estimate and confidence interval of relative effect sizes are strongly influenced by this assumption. Conclusions Since homogeneous between-study variance assumption is a strong assumption, it is crucial to test the validity of this assumption before conducting a network meta-analysis. Here we propose and validate a method for testing this single between-study variance assumption which is widely used for many NMA.

Testing significance of random effects for the Wiener degradation model

This paper considers the Wiener degradation model with random effects. Random-effect models take into account the unit-to-unit variability of the degradation index. It is assumed that a random parameter has a truncated normal distribution. During the research, the expression for the maximum likelihood estimates and the reliability function has been obtained. Two statistical tests have been proposed to reveal the existence of random effects in degradation data corresponding to the Wiener degradation model. The first test is a well-known likelihood ratio test, and the second one is based on the variance estimate of the random parameter. These tests have been compared in terms of power with the Monte-Carlo simulation method. The result of the research has shown that the criterion based on the variance estimate of the random parameter is more powerful than the likelihood ratio test in the case of the considered pairs of competing hypotheses. An example of the analysis using the proposed tests for the turbofan engine degradation data has been considered. The data set includes the measurements recorded from 18 sensors for 100 engines. Before constructing the degradation model, the single degradation index has been obtained using the principal component method. The hypothesis of the random effect insignificance in the model has been rejected for both tests. It has been shown that the random-effect Wiener degradation model describes the failure time distribution more accurately than the fixed-effect Wiener degradation model.

Hubungan Tingkat Pengetahuan dengan Sikap dan Tindakan terhadap Human Immunodeficiency Virus/ Acquired Immunodeficiency Syndrome pada Remaja

Background: Human immunodeficiency virus/acquired immunodeficiency syndrome (HIV/AIDS) is one of the diseases with high mortality rate, but we can prevent its transmission. People with good knowledge about HIV/AIDS should have the positive attitude and action on HIV/AIDS. Objective: The aim of this study was to investigate the correlation between knowledge level about HIV/AIDS and the attitude and action on HIV/AIDS in high school students. Methods: This cross-sectional study of 96 teenagers (aged 15-19 years old) was performed at SMA Swasta HKBP Sidorame Medan. The knowledge, attitude, and action on HIV/AIDS were evaluated with questionnaire. Knowledge level was categorized to good, fair, and bad. Attitude was categorized to positive and negative attitude. Action was categorized to risk and no risk action. Likelihood-ratio test was performed to evaluate the correlation between knowledge with attitude and action on HIV/AIDS because chi-square test criteria was not met. Results: This study showed that about 57.3% of students have bad knowledge about HIV/AIDS, 62.5% have positif attitude on HIV/AIDS, and 86.5% did no risky action on HIV/AIDS. Likelihood-ratio test showed that there was a significant correlation between knowledge about HIV/AIDS with attitude on HIV/AIDS (p= 0.000), and with the action on HIV/AIDS (p= 0.009). Conclusion: The knowledge level about HIV/AIDS correlates with attitude and action on HIV/AIDS.

A Likelihood-Ratio Test for Lumpability of Phylogenetic Data: Is the Markovian Property of an Evolutionary Process Retained in Recoded DNA?

In molecular phylogenetics, it is typically assumed that the evolutionary process for DNA can be approximated by independent and identically distributed Markovian processes at the variable sites and that these processes diverge over the edges of a rooted bifurcating tree. Sometimes the nucleotides are transformed from a 4-state alphabet to a 3- or 2-state alphabet by a procedure that is called recoding, lumping, or grouping of states. Here, we introduce a likelihood-ratio test for lumpability for DNA that has diverged under different Markovian conditions, which assesses the assumption that the Markovian property of the evolutionary process over each edge is retained after recoding of the nucleotides. The test is derived and validated numerically on simulated data. To demonstrate the insights that can be gained by using the test, we assessed two published data sets, one of mitochondrial DNA from a phylogenetic study of the ratites and the other of nuclear DNA from a phylogenetic study of yeast. Our analysis of these data sets revealed that recoding of the DNA eliminated some of the compositional heterogeneity detected over the sequences. However, the Markovian property of the original evolutionary process was not retained by the recoding, leading to some significant distortions of edge lengths in reconstructed trees.[Evolutionary processes; likelihood-ratio test; lumpability; Markovian processes; Markov models; phylogeny; recoding of nucleotides.]

Which Divergent Thinking Index Is More Associated With Problem Finding Ability? The Role of Flexibility and Task Nature

Problem finding (PF) and divergent thinking (DT) are considered to be indicators of creative potential. Previous studies, with different goals, suggest a positive correlation between PF and DT. However, none of these works have explicitly examined which index of DT is more associated with PF. The current investigation examined the association between PF and three main indexes of DT: fluency, flexibility, and originality. It also tested whether such a relation differs based on task nature (verbal vs. figural). The sample consisted of 90 sixth graders who completed three tests: (a) a verbal DT test, (b) a figural DT test, and (c) a PF test. Correlational analysis showed that flexibility was highly correlated with PF in the verbal DT test, whereas originality was significantly correlated with PF in the figural test. Results of the path analysis confirmed the results from correlational analyses and showed that verbal flexibility strongly predicted PF fluency, flexibility, and originality more than any other variable. Likelihood ratio test showed that using 1 or 3% cutoff for scoring originality did not significantly altered the results in both figural and verbal DT (vs. PF), while the likelihood ratio test showed significant differences between the figural and verbal DT. Finally, predictor variables in the verbal DT accounted for 40–58% of the variance in PF skills, whereas predictor variables in the figural DT accounted for 28–37% of the variance in PF skills. As suggested by experts in the field of PF, the role of flexibility in PF is a fertile area to be considered in future studies.

Bartlett-corrected tests for varying precision beta regressions with application to environmental biometrics

Beta regressions are commonly used with responses that assume values in the standard unit interval, such as rates, proportions and concentration indices. Hypothesis testing inferences on the model parameters are typically performed using the likelihood ratio test. It delivers accurate inferences when the sample size is large, but can otherwise lead to unreliable conclusions. It is thus important to develop alternative tests with superior finite sample behavior. We derive the Bartlett correction to the likelihood ratio test under the more general formulation of the beta regression model, i.e. under varying precision. The model contains two submodels, one for the mean response and a separate one for the precision parameter. Our interest lies in performing testing inferences on the parameters that index both submodels. We use three Bartlett-corrected likelihood ratio test statistics that are expected to yield superior performance when the sample size is small. We present Monte Carlo simulation evidence on the finite sample behavior of the Bartlett-corrected tests relative to the standard likelihood ratio test and to two improved tests that are based on an alternative approach. The numerical evidence shows that one of the Bartlett-corrected typically delivers accurate inferences even when the sample is quite small. An empirical application related to behavioral biometrics is presented and discussed.