Multivariate circular observations, i.e. points on a torus arise frequently in fields where instruments such as compass, protractor, weather vane, sextant or theodolite are used. Multivariate wrapped models are often appropriate to describe data points scattered on p−dimensional torus. However, the statistical inference based on such models is quite complicated since each contribution in the loglikelihood function involves an infinite sum of indices in Z p , where p is the dimension of the data. To overcome this problem, for moderate dimension p, we propose two estimation procedures based on Expectation-Maximisation and Classification Expectation-Maximisation algorithms. We study the performance of the proposed techniques on a Monte Carlo simulation and further illustrate the advantages of the new procedures on three real-world data sets.

Academic conferences offer scientists the opportunity to share their findings and knowledge with other researchers. However, the number of conferences is rapidly increasing globally and many unsolicited e-mails are received from conference organizers. These e-mails take time for researchers to read and ascertain their legitimacy. Because not every conference is of high quality, there is a need for young researchers and scholars to recognize the so-called “predatory conferences” which make a profit from unsuspecting researchers without the core purpose of advancing science or collaboration. Unlike journals that possess accreditation indices, there is no appropriate accreditation for international conferences. Here, a bibliometric measure is proposed that enables scholars to evaluate conference quality before attending.

No abstract

Background Neuropathological studies, based on small samples, suggest that symptoms of Parkinson's disease (PD) emerge when dopamine/nigrostriatal loss is around 50–80%. Functional neuroimaging can be applied in larger numbers during life, which allows analysis of the extent of dopamine loss more directly. Objective To quantify dopamine transporter (DaT) activity by neuroimaging in early PD. Methods Systematic review and novel analysis of DaT imaging studies in early PD. Results In our systematic review, in 423 unique cases from 27 studies with disease duration of less than 6 years, mean age 58.0 (SD 11.5) years, and mean disease duration 1.8 (SD 1.2) years, striatal loss was 43.5% (95% CI 41.6, 45.4) contralaterally, and 36.0% (95% CI 33.6, 38.3) ipsilaterally. For unilateral PD, in 436 unique cases, mean age 57.5 (SD 10.2) years, and mean disease duration 1.8 (SD 1.4) years, striatal loss was 40.6% (95% CI 38.8, 42.4) contralaterally, and 31.6% (95% CI 29.4, 33.8) ipsilaterally. In our novel analysis of the Parkinson's Progressive Marker Initiative study, 413 cases had 1436 scans performed. For a disease duration of less than 1 year, age was 61.8 (SD 9.8) years, and striatal loss was 51.2% (95% CI 49.1, 53.3) contralaterally and 39.5% (36.9, 42.1) ipsilaterally, giving an overall striatal loss of 45.3% (43.0, 47.6). Conclusions Loss of striatal DaT activity in early PD is less at 35–45%, rather than the 50–80% striatal dopamine loss estimated to be present at the time of symptom onset, based on backwards extrapolation from autopsy studies.

No abstract