Katie Jager:

Senior statistics instructor, College of Science.

Years at OSU: Nine.

City of Residence: Corvallis.

With years of experience in online education, Katie Jager knew she was well positioned for Oregon State’s transition to remote instruction in the face of COVID-19.

But she also knew that around 95% of the 20-person statistics faculty was somewhat less ready.

So she jumped in to help.

“I volunteered to be the remote-teaching liaison for our department because many of our faculty members understandably like to teach the way they’ve always taught,” Jager said. “I just approached it like, ‘OK, what are you doing now and how can we translate that quickly to remote teaching so you don’t feel like you have to change everything.’”

In addition to working with colleagues one on one, Jager set up a Canvas page specific to the needs of their department.

“The university is giving a lot of information, but sometimes it’s just too much,” Jager said. “Sometimes, someone just needs to ask, ‘I want to do this one thing – how do I do that?’ I’m trying to make it so every faculty member feels like they have a handle on this and can be successful.”

Jager said promoting a sense of community was a major goal – allowing people to have a discussion about the way they want to teach their classes and then coming up with ways they can do that via remote delivery.

“Before we shut down,” she said, “I talked to other faculty and said, ‘What is your plan for actual lecture time – what do you feel comfortable doing, what is best for students, what’s realistic with what you have at home to do this?’

“We’re used to getting feedback from students to know if they’re getting it, and we were worried we were going to lose that, so we had conversations about how to keep the class actively learning. We came up with a number of ways to do that.”

For the 100 students she’s personally teaching – in ST314, statistics for engineers – she provided a beginning-of-term survey asking, basically, what success in the class would look like to them, and what might hinder them.

“I got to learn so much about how people are dealing with this, being home and not necessarily with all of the resources you need to be going to school,” she said. “A lot of them have, like I do, children at home, or others at home who might be sort of distracting for them. I got to identify with students on a deeper level and let them know we’re all in this together.”

Associate Professor Lisa Ganio, head of the Department of Statistics and Jager’s unsung hero nominator, said faculty could not get all of their critical work done without Jager’s assistance.

Of the nomination, Jager said: “I feel a little odd being called a hero, especially in a time when people are actually saving lives and stepping up in amazing ways. It's tough for me to consider what I do as heroic, but I appreciate the sentiment.”

This story is a part of an OSU series called "Unsung Heroes," highlighting faculty, staff and students who are going above and beyond to assist with the pandemic response in their roles at OSU or in their communities from Corvallis to Bend to Newport and throughout the state. To read more stories like this, go here.

The 5th Stan Conference will take place at Oregon State University on August 11-14, 2020. The four-day conference will include two days of tutorials followed by an exciting scientific program comprising talks, posters, open discussions and statistical modeling.

Registration for Stan 2020 is now open. Researchers, students and professionals are encouraged to register for the conference which includes all tutorials. The conference is also soliciting session proposals, contributed talks and posters. Deadlines and other information can be found here.

Stan is a freedom-respecting, open-source software that has had an extensive and far-reaching impact on Bayesian computations for a broad range of applied statistics and data science problems.

The conference typically draws 300 attendees from academia, industry and government agencies. The conference offers a great opportunity for students and other participants to learn about Bayesian computation. Previous Stan Conferences were held at Columbia University, New York, and Cambridge University, U.K., among other places.

Plenary speakers at Stan 2020 are Elizabeth Wolkovich from the University of British Columbia and Adrian Rafftery, a member of the National Academy of Sciences, from the University of Washington, Seattle.

Debashis Mondal, associate professor in the Department of Statistics at OSU, is a co-organizer of Stan 2020. The other organizers of Stan 2020 are Susana Marquez, The Rockefeller Foundation; Eric J. Ward, Northwest Fisheries Science Center (NOAA); Yi Zhang, Metrum Research Group; and Daniel Lee, Generable.

Follow Stan on Twitter.

How can we better understand how devastating plant diseases are spread? Is there a better statistical model to predict HIV prevalence in a city? Is there a way we can detect toxic algae blooms in freshwater and marine ecosystems before they occur? And of the hundreds of thousands of different metal-organic frameworks (MOFs) in the world, how can we can better find the ones that are most useful for storing and separating gases, like CO2 from industrial plants?

Curiosity is critical for discovery. Asking the questions above led five faculty members to receive College of Science Research and Innovation Seed (SciRIS-II) and Betty Wang Discovery Fund awards this February to pursue answers over the course of the next year. Their proposals all showed transformative potential and progress toward new frontiers of science and aimed to strengthen collaboration with external research partners. Below is more detail about each of their proposals.

Mathematics Professor Vrushali Bokil was awarded $8,000 to use modeling techniques to understand the spread and control of plant diseases caused by coinfecting viruses. She will focus on Maize Lethal Necrosis (MLN), an emerging disease in Kenya and other parts of Africa that is caused by coinfecting viruses and spread by insects called Thrips, as a test case. Her team’s goals are to use stochastic models and optimal control theory to understand the mechanisms that drive patterns of coinfection in plant populations and effective techniques for controlling the spread of disease in crops and natural grasslands.

In collaboration with the Centers for Disease Control and Prevention (CDC), Statistics Assistant Professor Katherine McLaughlin received $10,000 to explore the use of new statistical methodologies to estimate the number of people who inject drugs in metropolitan areas. The research project, supported by the privately-funded Disease Mechanism & Prevention Fund at the OSU Foundation, has a goal of refining current methods to produce improved population-level demographic, behavioral, disease prevalence and population size estimations. This will aid the CDC in their efforts to contain or slow the rate of HIV in metropolitan areas across the U.S.

Microbiologist Kimberly Halsey was awarded $10,000 to examine the potential for real-time, automated volatile organic compound (VOC) detection as early-warning signals of toxic harmful algal blooms (HABs) in freshwater and marine ecosystems. HABs are increasing in intensity and severity due to climate change and nutrient loading from agriculture and other human-related activities. Some HABs can become toxic to humans and animals. Halsey will use data integration to merge aquatic microbiome data with environmental properties and VOC signatures to identify determinants and trajectory of the annual toxic HAB at Upper Klamath Lake, Oregon.

Physicist David Roundy was also awarded $10,000 to develop new flat histogram Monte Carlo molecular simulation methods to accelerate the discovery of metal-organic frameworks (MOFs) for applications in storing and separating gases. MOFs are crystalline materials that harbor nano-sized pores that have the potential to be used in a variety of clean energy applications, from hydrogen and natural gas storage to capturing carbon dioxide from coal-fired power plant flues. His study aims to enable scientists to accurately predict the absorption properties of hundreds of thousands of MOFs and accelerate the rate of MOF discovery for clean energy applications.

In addition, chemistry professors Kyriakos Stylianou and May Nyman, along with Todd Miller from the Advanced Technology and Manufacturing Institute (ATAMI), received $30,000 from the Betty Wang Discovery Fund to purchase a microwave reactor to integrate on the continuous flow reactor to accelerate the discovery and production of inorganic materials like MOFs. The Betty Wang Discovery Fund supports equipment acquisitions and laboratory infrastructure improvements to advance fundamental discoveries in science. Microwave heating has recently emerged as a powerful method for the preparation of inorganic materials at the laboratory scale, reducing synthesis time down to a few minutes without affecting the product quality or reaction yield. The new machinery will allow the team to investigate the potential of new MOFs to capture carbon in laboratory and industrial applications.

The projects will run for one year, ending next February 2021.The SciRIS program provides funding in three stages for high impact collaborative proposals that build teams, pursue fundamental discoveries and create societal impact. The awards range from $10,000 to $125,000 for various stages of the program and are supported in part by generous alumni and friends, and grants from the U.S. Department of Defense and National Institutes of Health.

The College of Science celebrated its 2020 Winter Teaching and Advising Awards with faculty, advisors and students on February 13 to recognize exceptional teaching and advising, both areas of distinction in the College. Committed and effective teaching, advising and mentorship are at the very heart of the College of Science’s identity as a robust and thriving community of students and scholars.

The awards ceremony included an engaging presentation by the Learning Assistants program, which puts high-achieving undergraduate assistants in large enrollment, often first-and second-year STEM classrooms to facilitate and strengthen undergraduate learning. Over the past five years, the LA program in the College of Science has reduced the drop-fail-withdrawal (DFW) rate in several key courses by half, and has now become a model for other colleges in the university.

“Our faculty are not only leaders here at OSU, but also across the nation and around the world. We celebrate our award recipients today for the incredible difference they have made in students’ lives,” said Dean Roy Haggerty, emcee for the ceremony, in his opening remarks.

Dean Haggerty recognized two faculty members at the beginning of the ceremony. Virginia Weis, Head of the Department of Integrative Biology and OSU Distinguished Professor, was named the new Dr. Russ and Dolores Gorman Faculty Scholar. The three-year rotating award recognizes faculty who bring distinction to the College of Science, connect with industry, and have a strong record of innovative research with practical impact. He also announced Elisar Barbar as the new head of the Department of Biochemistry and Biophysics and thanked Andy Karplus for his service as department head from 2007 to 2011, and then again from 2015 to January 2020.

Congratulations to all the nominees and especially to the award winners. The award recipients exemplify deep commitment, skill and effectiveness in mentoring and advising to ensure student learning and success within and beyond the classroom.

Associate Professor of statistics Lisa Madsen and statisticians from the United States Geological Survey (USGS) have come together to develop methodology to estimate the total mortality of bats, birds and other small creatures on wind farms and solar facilities. The Endangered Species Act requires that wind farms pay particular attention to endangered or threatened species such as golden eagles, brown pelicans, whooping cranes, condors and Indiana bats, which are killed when they accidentally collide with turbine blades.

“We want to keep track of our natural resources. We don’t want to end up depleting them, because we can’t tell we are taking too much.”

Monitoring fatalities at wind energy facilities can help government agencies, such as the U.S. Fish & Wildlife Service and the Bureau of Land Management, make better decisions about species management. Developing statistically accurate fatality prediction and estimation tools and monitoring protocols can also help agencies ensure that renewable energy facilities developers design operations to minimize the impact to wildlife, thus reducing environmental damage. “Fundamentally, what people want to know is ‘how many?’. This idea of keeping count and our desire to know ‘how many’ are important for conservation,” Madsen said. “We want to keep track of our natural resources. We don’t want to end up depleting them, because we can’t tell we are taking too much.”

How many? The missing bats and birds

Madsen’s collaborators, Manuela Huso and Dan Dalthorp, from the USGS Forest and Rangeland Ecosystem Science Center in Corvallis are contributing new statistical models, estimators and software tools to improve bird and bat fatality estimates at solar and wind power facilities. Huso initiated the research 10 years ago to come up with improved models and methods of estimating the count of carcasses. Dalthorp joined her shortly thereafter; Madsen began collaborating with the USGS team in a more substantial capacity during her sabbatical two years ago.

Last year, the team along with collaborators from consulting firm, Western EcoSystems Technology, Inc, data science lab DAPPER Stats, the Swiss Ornithological Institute, and Duke University developed a software package called GenEst (a generalized estimator of mortality) — a suite of statistical models and software tools specifically designed for estimating the total number of creatures arriving in an area during a specific time period when their detection probability is unknown but estimable. The latter can also be used more generally to estimate the size of open populations with imperfect detection probabilities.

However, as Madsen’s research on fatalities at wind farms shows, estimating an accurate count is anything but a straightforward process. In the case of wildlife fatalities due to collision with wind turbines or solar panels, carcasses invariably go missing, carried away by scavengers or fall in areas inaccessible to searchers. Therefore, simple counts of carcasses found at wind farms do not reflect the actual number of fatalities.

Madsen and her colleagues have developed complex statistical tools that estimate the actual number of carcasses when they are undetectable for any reason by taking into account a host of predictor variables such as searcher efficiency, variations in plot sizes and location of inaccessible areas.

Madsen developed a model to use data from field trials to estimate searcher efficiency. This model is incorporated into the larger GenEst model framework. “My collaborators are working on other aspects of the problem: getting a count of missing carcasses by estimating the amount of time a carcass is likely to stay before getting carried away by a predator. It is a highly involved project, where we put all the pieces of the puzzle together along with the uncertainty associated with all of these aspects,” explained Madsen.

“I think that non-statisticians could benefit from learning some statistical principles such as the concept of uncertainty, collecting useful data, and applying appropriate data analysis tools in a given situation.”

The software package, created by the team, will be utilized by government agencies as well as Western EcoSystems Technology, Inc., which has already begun to implement the software to assist their clients. The project has also attracted attention from environmental and government agencies in Canada, South Africa, Portugal and Scotland among others. In addition, the USGS statisticians have conducted workshops demonstrating how to use the software to estimate animal mortality at wind and solar energy facilities. “The methodology is generally applicable to any situation where you want to count something where the detection is not perfect,” said Madsen.

The path to ecological statistics

After graduating from the University of Oregon with a master’s degree in mathematics, Madsen taught mathematics in a community college in New York. She wanted to get a doctorate in math education because she enjoyed teaching the subject. But she quickly discovered it wasn’t an ideal academic match for her. In the meantime, her husband suggested she try a statistics course. Madsen enjoyed the experience and switched to the Ph.D. program in statistics at Cornell University.

She also obtained a minor in natural resources at Cornell, which inspired her to apply statistics to ecological problems. In recent years, Madsen has also worked on numerical models of geological data to estimate the risk of environmental disasters such as leaking oil wells and other phenomena.

Madsen excels at teaching courses on statistical methods to non-statistics students at the graduate and undergraduate levels. She enjoys helping her students develop a statistical mindset as they learn about extending statistical methods to different disciplines.

“I think that non-statisticians could benefit from learning some statistical principles such as the concept of uncertainty, collecting useful data, and applying appropriate data analysis tools in a given situation,” Madsen remarked.

The College of Science welcomes Lisa Ganio as the new Department of Statistics Head effective December 1, 2018. Ganio is a tenured Associate Professor in the Department of Forest Ecosystems and Society within the College of Forestry at OSU.

Ganio also serves as director of her department’s graduate program, associate director for the Forestry Computing Resources and director of the College of Forestry’s Statistical Consulting program, which she has led for 20 years. She is also an adjunct professor of statistics.

Ginny Lesser, current head of the department of statistics, announced this summer that she would step down from her post, which she has held since 2011. She will return to her teaching and research responsibilities and continue in her role as Director of the Survey Research Center.

“I want to thank Ginny for her excellent leadership as Statistics Department Head,” said Roy Haggerty, dean of the College of Science. “Ginny grew the department to its largest size since 1977, hiring six new faculty, and increased its diversity.” The statistics department is 45% women and 45% Asian with two Hispanics.

A few of Lesser’s notable accomplishments include growing enrollment and revenue in all online statistics courses, doubling the number of funded graduate students from 21 to 41 and graduating twice as many master’s and Ph.D. students. Under her leadership, the department made significant improvements to its Statistics 201 course that decreased D/F/W rates by more than 60% and launched the College’s first online degree: a master’s degree in data analytics as well as a graduate certificate.

“I would also like to thank the search committee and the committee chair, Bill Bogley, for running a smooth search and for their dedication to filling this important leadership position,” said Haggerty.

“I look forward to Lisa join the College of Science. She brings deep expertise in the application of statistics to applied problems and has a clear vision for the department that’s well aligned with the college and university strategic plans,” said Haggerty. “Her experience with graduate programs and research will be useful additions to our excellent Department of Statistics.”

Ganio brings more than 25 years of experience as an educator and as a consulting statistician. She has collaborated with academic researchers as well as worked with private, state, non-profit and federal natural resource management agencies as well as. With deep expertise in the application of statistics to applied problems, Ganio’s work emphasizes appropriate use of research design and technical quantitative tools applied to pressing ecological questions. Specifically, her areas of interest involve the interaction of natural resources research and quantitative science and statistics; critical thinking, study design and scientific inference in research; and statistical consulting and methods for multi-scaled temporal and spatial natural resources data.

Prior to her academic appointment at OSU, Ganio worked as a Senior Scientist for Mantech Environment at the Environmental Protection Agency Research Lab in Corvallis where she a provided research design and analysis.

Ganio is an exceptional scholar and teacher. Her experience in the College of Forestry’s graduate programs and research will be instrumental in building on existing research projects in the department of statistics. She received the Dean’s Award for Outstanding Achievement in Advising, Mentoring and Instruction in the College of Forestry in 2003 and 2008. Ganio has demonstrated a strong, long-standing commitment to diversity and inclusion and views it as crucial to the success not only of colleges but also of the university.

She received her bachelor’s degree in botany and zoology at Humboldt State University in California and both her MS and Ph.D. in statistics from Oregon State.

The more people a city has and the more organized its residents’ movement patterns, the longer its flu season is apt to last, according to population biologist Benjamin Dalziel.

The findings, published today in Science, are an important step toward predicting outbreak trends for a viral infection that each year in the United States sickens millions of people, sends hundreds of thousands to the hospital and kills tens of thousands.

Dalziel, the corresponding author of the new study, worked with an international collaboration to analyze weekly flu incidence data from 603 cities of varying size and “structure” – that is, patterns people follow in where they live and work.

The other factor the researchers looked at was the role a key weather metric – specific humidity – played in flu epidemics.

Flu is transmitted by virus-bearing moisture droplets that people exhale, cough out or sneeze out, creating a “cloud of risk” that emanates from an infected person and is breathed in by those around him or her.

“As specific humidity decreases, the virus remains viable in the air for longer, effectively expanding that cloud,” Dalziel said. “However, if an infected person is right beside you, it matters less what the specific humidity is.”

Which is where city size and structure come in – if there are lots of people, and transportation patterns frequently draw them together, it helps flu viruses find new hosts even when climatic conditions aren’t at their most favorable for transmission.

For the full story, click here.

The College of Science welcomes James Molyneux, who joined the Department of Statistics as an assistant professor in Fall 2018. Molyneux joined the department from UCLA, where he completed his dissertation on earthquake forecasting models based on statistical and computational methods.

In his new role, Molyneux teaches a wide variety of undergraduate and graduate courses, including online courses, to both statistics students and those from majors in engineering and biological sciences in the areas of data analytics, statistical methods and theory.

In addition to research on statistical seismology, Molyneux brings deep expertise in statistics pedagogy and education to OSU. As a doctoral student, he collaborated with his professors, high school educators, and other graduate students to create a project on statistics education funded by the National Science Foundation. The result is an innovative Introduction to Data Science (IDS) curriculum, which introduces high school students to data and statistics.

Part of a math-science partnership grant between UCLA and the Los Angeles Unified School District, IDS has been designated as a core math course and has been implemented in 14 southern California high school districts with further plans of scaling it to other school districts in the United States and even abroad.

A revolutionary approach to 21^st-century mathematical learning, the year-long course engages students with real data, introducing statistical, computational and graphical tools for reasoning about the world.

Molyneux is excited about exploring the possibility of introducing Oregon high school students to data, statistics and coding through IDS. He had an opportunity to introduce the IDS program to the Oregon Department of Education during a Math Pathways seminar in December.

“There has been a lot of interest in changing how mathematics is taught in high schools in Oregon,” observed Molyneux. “What if we didn’t make every student learn calculus, and introduced them to data science instead?”

In recent times, educators have begun to question the longstanding tradition of high school mathematics curriculum, whose mainstays have been the much-feared algebra II and calculus courses, arguing in favor of multiple math pathways towards graduation and college, which would include new courses in data science, statistics and programming.

“I think students find a lot of utility and value in being shown how to type instructions to a computer in a coding language, hit enter and have something happen based on what they are writing. It teaches them a lot of fundamental statistical ideas and how to be a good citizen by learning to evaluate data critically and detect misrepresented graphs and data,” said Molyneux.

Molyneux eagerly looks forward to utilizing his experiences and background in statistics pedagogy in the classroom. His teaching is also guided by his own experience of transformation.

An indifferent student of mathematics during his undergraduate years at California State University, Fullerton, Molyneux’s academic interests underwent a radical metamorphosis when he crossed paths with a brilliant teacher in a calculus II class.

“I had barely passed calculus I, but my teacher — Kathy Lewis — changed everything for me. That’s when I thought for the first time math is for me.” The realization prompted him to add a major in mathematics along with his major in economics, which eventually led to several classes in statistics and a Ph.D. in statistics.

“Having come from a place where I did not initially like math, I really want to expose people to this field I fell in love with and why they may like it too. You can do powerful things with statistics; it has real-life applications. Enabling students to find meaning in statistics has a lot of value for me,” said Molyneux.

He is excited to collaborate with statistics colleagues and others on campus on several new projects. Some of these include creating software for hydrologists and joining forces with OSU’s Center for Genomics Research and Biotechnology to fashion a data science program for students from rural communities in Oregon, which will impart skills in data analytics and statistical applications in natural resources and agriculture.

“I am delighted to be here. The department has a data analytics program which is growing fast and it’s very fulfilling to be a part of it. The statistics faculty are incredible teachers and researchers. It has definitely been a highlight to get to do statistics with so many talented people,” said Molyneux.

A native of La Habra, California, Molyneux enjoys hiking, cycling and discovering the restaurants in Salem, Ore., where he resides. He harbors a dream to reach the summits of all the mountains in Oregon.

The College of Science is launching a transformative program to support and strengthen innovation and entrepreneurship that will enable us to better identify, validate, and develop the commercial impact of basic research. Innovation Days will bring together faculty, faculty research assistants and research associates to discuss and learn about moving basic research ideas and discoveries from the lab to commercial applications and practical solutions.

Co-hosted by the College of Science and the Office of Commercialization and Corporate Development (OCCD), Innovation Days will host its first session on January 7, 2019, 2:30-5 pm followed by a reception from 5-6 p.m. The deadline to register is December 14, 2018. Additional sessions to follow on February 4, April 1 and April 29.

Innovation Days is designed to build awareness and engagement with experts who will help advance and propel the OSU innovation enterprise. Workshop participants will learn about resources to:

• Leverage basic research and research funding opportunities toward application
• Increase the impact of basic research through patents and commercialization
• Validate broader impacts of research projects to enhance proposal success
• Connect with local innovation ecosystem and identify pathways to translate research to application
• Create opportunities with industry
• Integrate invention disclosures, patent applications, and company formation into day-to-day work to advance your career

Facilitators represent and support the many pathways available to successfully transfer technology and commercialize scientific research. The workshop series includes: Berry Treat, director of OCCD, who will provide an overview of his office and how it supports the research to industry pathway; Joe Christison, senior intellectual property and licensing manager at OCCD, who will introduce participants to technology transfer at OSU; Katie Pettinger, commercialization catalyst at OSU Advantage Accelerator, who will discuss startup support available to OSU researchers; chemistry professor Rich Carter, who will share his success story as an inventor; and Chris Stoner, senior industry contracts manager, OCCD, who will discuss the development of appropriate and effective research agreements with companies.

New research shows that a big earthquake can not only cause other quakes, but large ones, and on the opposite side of the Earth.

The findings, published Aug. 2 in Nature Scientific Reports, are an important step toward improved short-term earthquake forecasting and risk assessment.

Statistician Debashis Mondal, collaborating with Robert O'Malley and Michael Behrenfeld of the College of Agricultural Sciences and Chris Goldfinger of the College of Earth, Ocean and Atmospheric Sciences, looked at 44 years of seismic data and found clear evidence that temblors of magnitude 6.5 or larger trigger other quakes of magnitude 5.0 or larger.

It had been thought that aftershocks – smaller magnitude quakes that occur in the same region as the initial quake as the surrounding crust adjusts after the fault perturbation – and smaller earthquakes at great distances – were the main global effects of very large earthquakes.

But the OSU analysis of seismic data from 1973 through 2016 – an analysis that excluded data from aftershock zones – using larger time windows than in previous studies, provided discernible evidence that in the three days following one large quake, other earthquakes were more likely to occur.

“The test cases showed a clearly detectable increase over background rates,” said the study’s corresponding author, Robert O’Malley. “Earthquakes are part of a cycle of tectonic stress buildup and release. As fault zones near the end of this seismic cycle, tipping points may be reached and triggering can occur.”

The higher the magnitude, the more likely a quake is to trigger another quake. Higher-magnitude quakes, which have been happening with more frequency in recent years, also seem to be triggered more often than lower-magnitude ones.

For the full story, click here.