Social media analytics for YouTube comments: potential and limitations

The need to elicit public opinion about predefined topics is widespread in the social sciences, government and business. Traditional survey-based methods are being partly replaced by social media data mining but their potential and limitations are poorly understood. This article investigates this issue by introducing and critically evaluating a systematic social media analytics strategy to gain insights about a topic from YouTube. The results of an investigation into sets of dance style videos show that it is possible to identify plausible patterns of subtopic difference, gender and sentiment. The analysis also points to the generic limitations of social media analytics that derive from their fundamentally exploratory multi-method nature.     

Government Sanctioned “Tight” and “Loose” Slot Machines: How Having Multiple Versions of the Same Slot Machine Game May Impact Problem Gambling

In Ontario, Canada, the regulator approves identical looking slot machine games with different payback percentages. We gained access to the design documents (called PAR Sheets) used to program these different versions of the same slots game and ran Gambler’s Ruin simulations of 2,000 first-time players who each arrived with a $100 bankroll and played either the 85 or 98% version of the same game until broke. Simulations revealed that the typical (median) player’s experience did not differ significantly between versions. However the payback percentage affected the experience of players in the upper tails of the distributions with those in the 98% version having dramatically more total spins, winning spins, entries into the “bonus mode”, and “hand pays” (a win of $100 bankroll and played either the 85 or 98% version of the same game until broke. Simulations revealed that the typical (median) player’s experience did not differ significantly between versions. However the payback percentage affected the experience of players in the upper tails of the distributions with those in the 98% version having dramatically more total spins, winning spins, entries into the “bonus mode”, and “hand pays” (a win of 125 or more on a given spin). Most importantly, the number of simulated players who had a maximum peak balance in excess of $1,000 rose tenfold—from 5 in the 85% version to 54 in the 98% version. The results are discussed in terms of the Pathways Model of Problem and Pathological Gambling especially in terms of behavioural conditioning, cognitive beliefs, and early big wins. It may well be that those machines that are on the surface the “fairest” to the gambler, actually pose the most risk for ensuing gambling problems.     

Life and death decisions

It has recently been suggested 1 that many clinical trials should have a data monitoring and ethics committee, and that on this committee should be a statistician. Such committees are attached to individual trials and are distinct from local ethics committees, which are not required to have a statistician and are not concerned solely with trials. Given the plethora of trials, there will be increasing demand for statisticians to sit on these committees. Although it is both an honour and a privilege, Mike Campbell warns that membership should not be undertaken lightly.     

Missing data: Discussion points from the PSI missing data expert group

The Points to Consider Document on Missing Data was adopted by the Committee of Health and Medicinal Products (CHMP) in December 2001. In September 2007 the CHMP issued a recommendation to review the document, with particular emphasis on summarizing and critically appraising the pattern of drop‐outs, explaining the role and limitations of the ‘last observation carried forward’ method and describing the CHMP's cautionary stance on the use of mixed models. In preparation for the release of the updated guidance document, statisticians in the Pharmaceutical Industry held a one‐day expert group meeting in September 2008. Topics that were debated included minimizing the extent of missing data and understanding the missing data mechanism, defining the principles for handling missing data and understanding the assumptions underlying different analysis methods. A clear message from the meeting was that at present, biostatisticians tend only to react to missing data. Limited pro‐active planning is undertaken when designing clinical trials. Missing data mechanisms for a trial need to be considered during the planning phase and the impact on the objectives assessed. Another area for improvement is in the understanding of the pattern of missing data observed during a trial and thus the missing data mechanism via the plotting of data; for example, use of Kaplan–Meier curves looking at time to withdrawal. Copyright © 2009 John Wiley & Sons, Ltd.     

Recommendations on the statistical analysis of the Comet assay

In 2010, the Statisticians in the Pharmaceutical Industry (PSI) Toxicology Special Interest Group met to discuss the design and analysis of the Comet assay. The Comet assay is one potential component of the package of safety studies required by regulatory bodies. As these studies usually involve a three-way nested experimental design and as the distribution of the measured response is usually either lognormal or lognormal plus a point mass at zero, the analysis is not straightforward. This has led to many different types of analysis being proposed in the literature, with several different methods applied within the pharmaceutical industry itself. This article summarises the PSI Toxicology Group's discussions and recommendations around these issues.     

Blocking in two-level non-regular fractional factorial designs

In this paper we consider screening experiments where a two-level fractional factorial design is to be used to identify significant factors in an experimental process and where the runs in the experiment are to occur in blocks of equal size. A simple method based on the foldover technique is given for constructing resolution IV orthogonal and non-orthogonal blocked designs and examples are given to illustrate the process.     

On the optimality of chemical balance weighing designs

In this paper we consider the problem of optimally weighing n objects with N weighings on a chemical balance. Several previously known results are generalized. In particular, the designs shown by Ehlich (1964a) and Payne (1974) to be D-optimal in various classes of weighing designs where N≡2 (mod4) are shown to be optimal with respect to any optimality criterion of Type I as defined in Cheng (1980). Several results on the E-optimality of weighing designs are also given.     

Researching non-profit organisational effectiveness: A comment on Herman and Heimovics

Conclusions This brief paper has both welcomed the work of Herman and Heimovics on the criteria of organisational effectiveness of VNPOs, and provided a critique of it. In doing this it has presented an alternative approach developed from the work of these authors and situated it within the evolving critiques of the rationalist tradition of organisation management. The intention, however, has not been to provide a final codification of organisational effectiveness. Rather, it has been to stimulate further debate on this important issue. Only through such a dialogue can we hope to develop truly representative and robust frameworks within which to situate the evaluation of the organisational effectiveness of VNPOs and its definition by key stakeholders. The alternative approach offered eschews normative propositions about the implicit or assumed effectiveness of VNPOs and rejects a wholly quantitative approach to its analysis. Instead, it provides a framework within which to situate and debate the differing criteria, perceptions and loci of effectiveness within such organisations.