SearcharxivSearch

arXiv subjects

Nicholas Larsen

Publications and source records attributed to Nicholas Larsen.

2 recordsLinked to original sources

The First Four Ground-Level Enhancements in the 1940s: Investigation, Digitisation, and Analysis of Forgotten Data

Intense solar eruptions occasionally accelerate solar energetic particles (SEPs) and can trigger ground-level enhancements (GLEs). Among the 77 known GLEs, the first four GLEs, #1 -- 4 in the 1940s took place before the advent of the standard neutron monitors and were missing from the International GLE Database. This data gap challenged their quantification. To overcome this difficulty, we systematically gathered, digitised, and quantified contemporaneous cosmic-ray records pertaining to these GLEs. These data allow us to reconstruct the temporal evolution, with the 1 -- 15 min resolutions, of these GLEs, and broaden their geographical coverage to a global scale. GLEs #1 and #3 exhibited gradual increases in their rise times, measured at 45 +/- 15 and 105 +/- 15 min, respectively. In contrast, GLEs #2 and #4 both exhibited abrupt increases of 15 +/- 15 min. We also compared integral ionisation increase on the standard ionisation chambers and their local geomagnetic cutoff rigidities Pc to qualitatively compare these GLE's spectral hardness: Our result indicates that their spectra are extremely hard for GLEs #2 and #4 and mildly hard for GLEs #1 and #3. GLE #3 showed the greatest integral ionisations for polar detectors among them.

astro-ph.SR

Statistical Challenges in Online Controlled Experiments: A Review of A/B Testing Methodology

The rise of internet-based services and products in the late 1990's brought about an unprecedented opportunity for online businesses to engage in large scale data-driven decision making. Over the past two decades, organizations such as Airbnb, Alibaba, Amazon, Baidu, Booking, Alphabet's Google, LinkedIn, Lyft, Meta's Facebook, Microsoft, Netflix, Twitter, Uber, and Yandex have invested tremendous resources in online controlled experiments (OCEs) to assess the impact of innovation on their customers and businesses. Running OCEs at scale has presented a host of challenges requiring solutions from many domains. In this paper we review challenges that require new statistical methodologies to address them. In particular, we discuss the practice and culture of online experimentation, as well as its statistics literature, placing the current methodologies within their relevant statistical lineages and providing illustrative examples of OCE applications. Our goal is to raise academic statisticians' awareness of these new research opportunities to increase collaboration between academia and the online industry.

stat.AP