More Like this

1. Online control of the familywise error rate

   https://doi.org/10.1177/0962280220983381  

   Tian, Jinjin; Ramdas, Aaditya (April 2021, Statistical Methods in Medical Research)

   null (Ed.)

   Biological research often involves testing a growing number of null hypotheses as new data are accumulated over time. We study the problem of online control of the familywise error rate, that is testing an a priori unbounded sequence of hypotheses ( p-values) one by one over time without knowing the future, such that with high probability there are no false discoveries in the entire sequence. This paper unifies algorithmic concepts developed for offline (single batch) familywise error rate control and online false discovery rate control to develop novel online familywise error rate control methods. Though many offline familywise error rate methods (e.g., Bonferroni, fallback procedures and Sidak’s method) can trivially be extended to the online setting, our main contribution is the design of new, powerful, adaptive online algorithms that control the familywise error rate when the p-values are independent or locally dependent in time. Our numerical experiments demonstrate substantial gains in power, that are also formally proved in an idealized Gaussian sequence model. A promising application to the International Mouse Phenotyping Consortium is described. 

   more » « less
2. Algorithmic Pulsar Timing

   https://doi.org/10.3847/1538-3881/ac403e  

   Phillips, Camryn; Ransom, Scott (January 2022, The Astronomical Journal)

   Abstract Pulsar timing is a process of iteratively fitting pulse arrival times to constrain the spindown, astrometric, and possibly binary parameters of a pulsar, by enforcing integer numbers of pulsar rotations between the arrival times. Phase connection is the process of unambiguously determining those rotation numbers between the times of arrival while determining a pulsar timing solution. Pulsar timing currently requires a manual process of step-by-step phase connection performed by individuals. In an effort to quantify and streamline this process, we created the Algorithmic Pulsar Timer (APT), an algorithm that can accurately phase connect and time isolate pulsars. Using the statistical F-test and knowledge of parameter uncertainties and covariances, the algorithm decides what new data to include in a fit, when to add additional timing parameters, and which model to attempt in subsequent iterations. Using these tools, the algorithm can phase-connect timing data that previously required substantial manual effort. We tested the algorithm on 100 simulated systems, with a 99% success rate. APT combines statistical tests and techniques with a logical decision-making process, very similar to the manual one used by pulsar astronomers for decades, and some computational brute force, to automate the often tricky process of isolated pulsar phase connection, setting the foundation for automated fitting of binary pulsar systems. 

   more » « less
3. The impact of drifting substorm-injected electrons on pulsating aurora initiation and intensification

   https://doi.org/10.3389/fspas.2024.1335562  

   Momberg, John C; Jaynes, Allison N; Chepuri, Sanjay_N F; Leali, Alexis; Karl, Juliana A; Troyer, Riley N (March 2024, Frontiers in Astronomy and Space Sciences)

   Pulsating aurora, which consists of diffuse patches blinking on and off, is caused by pitch angle scattering of radiation belt electrons into the loss cone by lower-band chorus waves. Understanding the drivers of pulsating aurora is important as it is a long-lasting and widespread phenomenon, accounting for significant energy transfer from the solar wind into the ionosphere. Substorm injections, which transport electrons from the magnetotail into the inner magnetosphere, are one source of electrons in this region. Injections have been observed simultaneously with pulsating aurora during conjunctions between ground cameras and satellites. In addition, previous work has also shown that substorms can enhance chorus activity (the fundamental process that produces pulsating aurora), providing a mechanism linking substorms to pulsating aurora. To further study this connection, we used the Van Allen Probes and all-sky cameras to look at events where pulsating aurora and substorm injections were observed at different locations in Magnetic Local Time (MLT), rather than focusing only on conjunctions. To make this comparison, we calculated the drift rate of electrons originating from observed injections and projected their motion forward in time until their Magnetic Local Time was the same as the ground camera. When the electrons are located at the same MLT as the ground camera, the pulsating aurora they cause would most likely occur in the field of view of the camera. We compared the time drifting substorm-injected particles arrived at the MLT of the camera to when pulsating aurora was observed. We found several instances where the initiation or intensification of pulsating aurora was accompanied by the arrival of substorm-injected electrons. This observation gives further evidence that pulsating aurora can be enhanced by or occur after substorm injections. 

   more » « less
4. A heterogeneous single changepoint software reliability growth model framework

   https://doi.org/10.1002/stvr.1717  

   Nagaraju, Vidhyashree; Fiondella, Lance; Wandji, Thierry (December 2019, Software Testing, Verification and Reliability)

   Summary Many non‐homogeneous Poisson process software reliability growth models (SRGM) are characterized by a single continuous curve. However, failures are driven by factors such as the testing strategy and environment, integration testing and resource allocation, which can introduce one or more changepoint into the fault detection process. Some researchers have proposed non‐homogeneous Poisson process SRGM, but only consider a common failure distribution before and after changepoints. This paper proposes a heterogeneous single changepoint framework for SRGM, which can exhibit different failure distributions before and after the changepoint. Combinations of two simple and distinct curves including an exponential and S‐shaped curve are employed to illustrate the concept. Ten data sets are used to compare these heterogeneous models against their homogeneous counterparts. Experimental results indicate that heterogeneous changepoint models achieve better goodness‐of‐fit measures on 60% and 80% of the data sets with respect to the Akaike information criterion and predictive sum of squares measures. 

   more » « less
5. Characterization of Additively Manufactured Metals from ADDERE Printing

   Foster, J.; Kumpaty, S.; Coen, L.; Perkins, A.; Gengler, M.; Woida, S. (November 2022, ASME International Mechanical Engineering Congress and Exposition)

   IMECE2022-88299 Midwest Engineered Systems Inc. has created a novel laser wire metal deposition process, ADDere manufacturing. ADDere has a much higher deposition rate than powder bed fusion, making it ideal for large components. In this project, the mechanical properties of ADDere printed materials were tested and compared to typical values found in ASM publications to show the quality of materials manufactured by the ADDere printing process. A detailed material analysis was performed on samples made from Ti-6Al-4V and 17-4 PH stainless steel. This work builds upon an earlier study of samples made from 17-4 PH that were produced using a single direction pattern. In this project, the 17-4 PH samples were printed in a cross hatched pattern, and testing results were compared to existing data from single direction samples of the previous research. The Ti-6Al-4V samples were created in two builds. One using the uni-directional method and the other with the crossed pattern. Testing specimens were removed from the samples using a water jet cutter and further machined into ASTM tensile bars and metallurgic mounts to perform a thorough material evaluation. The Ti-6Al-4V sample met the expected values in the ASM literature, and the cross hatched 17-4 PH exhibited a higher hardness and better microstructure than the single direction samples from the previous work. It was also observed that when the Ti64 samples were manufactured in the cross hatched pattern, the properties indicated slight improvement and more homogeneity than those printed in single layer direction. The obtained results indicate that ADDere’s printing process can produce highly refined materials that are customizable with their expected uses. This work showcases an excellent industry collaboration of an undergraduate research experience. 

   more » « less