 |
|
|||
JAQM Volume 13, Issue 2 - June 30, 2018
Contents
The Quality of Influenza-Related Romanian Websites – Are They Any Better than Seven Years Ago?
Septimiu Daniel POPESCU, Alex Otniel POPESCU, Mihaela DĂNILĂ, Rareş PĂROIU, Septimiu VOIDĂZAN, Valentin NĂDĂŞAN
The proportion of people browsing the Internet for health-related purposes keeps growing and the quality of information users find may have a profound impact on the outcome of their medical decisions. The goal of this study was to observe changes in the quality of the Romanian language influenza-related websites for the general public over a period of seven years. The 2011, baseline sample and the 2018, follow-up sample, included 20 websites each, selected from Google’s search results pages using “gripa” (influenza, in Romanian) as a search term. Two independent evaluators followed a common set of detailed instructions and rated the websites for credibility, completeness, and accuracy on a numeric scale going from 0 to 10 points. A number of 16 (80%) of the websites in the baseline sample remained accessible in 2018 but most of them had a major decline in their Google ranking (> 100 positions down). The baseline sample had a mean credibility score of 3.9 points (SD 2.2), a mean completeness scores of 5.8 points (SD 2.8), and a mean accuracy score of 7.5 points (SD 1.2). The follow-up sample had a mean credibility score of 4.1 points (SD 2.6), a mean completeness score of 6.4 points (SD 1.8), and a mean accuracy score of 6.0 points (SD 0.9). Timewise comparison tests detected no change in credibility scores (p>0.05), and completeness scores (p>0.05). Accuracy scores recorded a statistically significant drop (p<0.0001), but considering that the mean difference between the 2011 and 2018 accuracy scores was only 1.5 points, the practical implications of this finding should be interpreted with caution. However, observing these low quality scores and no improvement over such a long period of time, should be a reason for concern for public health professionals. In corroboration with the results of other similar studies, the observed lack of improvement in online health-related information quality should prompt the implementation of interventions aiming to improve the quality of sources used by online health-seekers.
Analyzing Factorial Experiments with a Single Common Control Group
Soner YIĞIT, Corrado DIMAURO, Mehmet MENDEŞ
Researchers generally put a common control group into their experiments in order to determine how effective the treatments are or to compare the effect of their treatments with a baseline. In this study, classical statistical analysis of factorial experiments and a solution way which has been proposed by Winer et al. (1991) have been compared in terms of type I error rate and test power under different experimental conditions. Results of 100,000 simulation study revealed that performing Winer et al. (1991) test is more appropriate in terms of getting reliable results when there is a single common control group in factorial experiments.
The Poisson-Weighted Akash Distribution and its Applications
Rama SHANKER, Kamlesh Kumar SHUKLA
A Poisson-Weighted Akash distribution which includes Poisson-Akash distribution has been proposed. Its moments and moments based statistical constants have been derived and studied. Maximum likelihood estimation has been discussed for estimating the parameters of the distribution. Finally, applications of the proposed distribution have been explained through two count datasets and the goodness of fit has been compared with other discrete distributions.
Tests for Equality of Variances between Two Samples which Contain Both Paired Observations and Independent Observations
Ben DERRICK, Annalise RUCK, Deirdre TOHER, Paul WHITE
Tests for equality of variances between two samples which contain both paired observations and independent observations are explored using simulation. New solutions which make use of all of the available data are put forward. These new approaches are compared against standard approaches that discard either the paired observations or the independent observations. The approaches are assessed under equal variances and unequal variances, for two samples taken from the same distribution. The results show that the newly proposed solutions offer Type I error robust alternatives for the comparison of variances, when both samples are taken from the same distribution.
Non-Formal Education in Romania – an Analysis in European Context
Andreea MIRICĂ
Non-formal education is an important component in adults’ education. The current study aims to analyse the status quo of non-formal education in Europe, based on most recently available data. The research will focus on Romania. Furthermore, the paper contains an analysis of the higher education area in this country and recommendations for using non-formal education in order to bring value-added to this sector.