Journal of Data Science

Many believe that use of generative AI as a private tutor has the potential to shrink access and achievement gaps between students and schools with abundant resources versus those with fewer resources. Shrinking the gap is possible only if paid and free versions of the platforms perform with the same accuracy. In this experiment, we investigate the performance of GPT versions 3.5, 4.0, and 4o-mini on the same 16-question statistics exam given to a class of first-year graduate students. While we do not advocate using any generative AI platform to complete an exam, the use of exam questions allows us to explore aspects of ChatGPT’s responses to typical questions that students might encounter in a statistics course. Results on accuracy indicate that GPT 3.5 would fail the exam, GPT4 would perform well, and GPT4o-mini would perform somewhere in between. While we acknowledge the existence of other Generative AI/LLMs, our discussion concerns only ChatGPT because it is the most widely used platform on college campuses at this time. We further investigate differences among the AI platforms in the answers for each problem using methods developed for text analytics, such as reading level evaluation and topic modeling. Results indicate that GPT3.5 and 4o-mini have characteristics that are more similar than either of them have with GPT4.

This paper introduces flowthrough centrality, a node centrality measure determined from the hierarchical maximum concurrent flow problem (HMCFP). Based upon the extent to which a node is acting as a hub within a network, this centrality measure is defined to be the fraction of the flow passing through the node to the total flow capacity of the node. Flowthrough centrality is compared to the commonly-used centralities of closeness centrality, betweenness centrality, and flow betweenness centrality, as well as to stable betweenness centrality to measure the stability (i.e., accuracy) of the centralities when knowledge of the network topology is incomplete or in transition. Perturbations do not alter the flowthrough centrality values of nodes that are based upon flow as much as they do other types of centrality values that are based upon geodesics. The flowthrough centrality measure overcomes the problem of overstating or understating the roles that significant actors play in social networks. The flowthrough centrality is canonical in that it is determined from a natural, realized flow universally applicable to all networks.

Abstract: The rule of three gives 3/n as the upper 95% bound for the success rate of the zero-numerator problems. However, this bound is usu ally conservative although it is useful in practice. Some Bayesian methods with beta distributions as priors have been studied. However, choosing the parameters for the priors is subjective and can severely impact the corre sponding posterior distributions. In this paper, some hierarchical models are proposed, which provide practitioners other options for those zero-numerator problems.