controversy is an opportunity for learning

Every now and then I have one of these days when I know that my students truly understand and apply what they’ve been taught. At those moments, teaching is incredibly rewarding.

I am not one to shy away from controversial topics in the classroom. It is important for students to learn how to approach tough topics using OR and numbers, rather than by flinging personal attacks. In my intro to statistics course this semester, I used Larry Summers to make a point about the importance of variance. Originally, it was reported that Summers claimed that there might be some evidence that men were innately “better” than math than women. Naturally, I was offended when I read the original stories. But I don’t like to judge someone without knowing all of the facts. When the transcript of his controversial speech was posted online, I read it. Aside from one paragraph that would have made me cringe unless it was delivered in the perfect tone (and supposedly it wasn’t), I couldn’t find anything about Summers suggesting that men were innately better than women in math. The controversial comments were about variability in math scores, not average math scores. Apparently, it has been well documented that there is more variability in boys’ math scores, but no one knows to what extent it is nature or nurture.

After illustrating this point in class by drawing a couple of bell curves with the same means but different variances, I couldn’t tell if my students were lost or offended.

Weeks passed. Surprisingly, I found out that my students were neither lost nor offended. Two of my students not only understood what I was teaching, but they were able to teach the concepts to others (one of the highest forms of learning!). These two students are taking a class on women’s health. The topic of Larry Summers came up, and my students walked the class of mostly non-technical majors through the basic concepts, by drawing bell curves and correcting the misconceptions. The professor was so impressed that she emailed me about it. And now here I am, brimming with pride over my “kids.” It’s days like this that remind me how much fun teaching can be.

Links:

• The Anita Borg Institute chronicles the controversy
• Marginal Revolution explains what nearly all of the articles about the controversy got wrong much better than I could. More than three years after the controversy, we finally started seeing articles start to get some of the details right.

Related post:

• Are there more women in OR?

score one for OR!

I saw a recent press release about one of Sheldon Jacobson’s projects that investigates vaccination issues for H1N1. What is interesting about the press release is that it  actually promotes the field of operations research. Maybe the grassroots efforts to promote OR are working!  You can read the press release for yourself, but check out the plug for OR:

Jacobson’s field is Operations Research (OR for short). OR is a combination of a multitude of tools, including aspects of engineering, computer science, mathematical modeling and algorithms, and statistical analysis. It also utilizes tactics like probability theory, game theory, decision analysis, and simulation to find optimal solutions to complex problems. OR’s countless applications have led Jacobson to conduct research in areas as far-flung as aviation security, automobile fuel consumption, NCAA basketball tournaments, and predictions for presidential elections… “When one does research, it is an opportunistic situation. You are constantly bombarded with challenges in life and society, and there are wonderful problems that can be addressed by using engineering, computer science, and specifically, operations research.”

Hopefully, this is part of a trend that helps increase the awareness of our field.

Link: press release.

Using OR for good

Margaret Brandeau gave the first WORMS keynote address entitled “From Venn Diagrams to Public Health Policy: An OR Journey” This is my third blog post about the INFORMS Annual meeting.

Dr. Brandeau’s excellent talk chronicled her journey from an undergraduate math student at MIT to a OR superstar.  She could recall the exact day when she decided to become an operations researcher.  This day was one of the first days of an applied math class, when her professor outlined several real applications of math.  This opened Dr. Brandeau’s eyes to the many things that math could do.  Prior to this, Dr. Brandeau enjoyed math but wasn’t sure it could make a difference.

Over the years, Dr. Brandeau worked on many projects, such as subway system design, ambulance deployment, optimal hospital patient mixture (using linear programming), facility location, and component sharing and manufacturing (using integer programming and heuristics).  She stressed the importance of designing practical planning tools for implementing OR tools in the real world, since policy makers do not like our theoretical OR papers as much as we do.

Dr. Brandeau’s story about her work on HIV treatment and prevention was interesting.  It all started in 1985, when one of her MS students was interested in using her engineering degree to address needs in the HIV epidemic.  She and Dr. Brandeau worked on a proposal, and were funded to address numerous resource allocation issues associated with HIV.  They tried to analytically determine which HIV prevention and treatment programs to invest in, as well as how to balance resources between both treatment and prevention.  Dr. Brandeau’s engineering colleagues were skeptical at the time, but were soon won over.

Dr. Brandeau’s research journey started with traditional OR tools, but she chose to work on cutting edge application areas.  Dr. Brandeau advised those in attendance to work on interesting problems, even if they seem like they do not fit within the traditional bounds of OR.  The left turns she took in research (like starting work on HIV) all started from unique opportunities that arise.  She took advantage of these opportunities (rather than shying away from the potential riskiness) to put together an interesting research portfolio over the years.  Although Dr. Brandeau was extremely modest, I found her courage to be different inspiring.

My favorite part of the keynote was when Dr. Brandeau recalled seeing so few women at her first ORSA/TIMS meeting (ORSA/TIMS became INFORMS).  She felt a little conspicuous.  The other women in attendance felt the same way, so they decided to have an impromptu brown bag lunch together.  The chance meeting of these women turned into WORMS.  I am grateful that they started the first WORMS lunch.

Incidentally, the highlight of my first INFORMS conference was also the WORMS lunch.  The lunch is when the Award for the Advancement of Women in OR/MS is awarded.  It is not to be missed!  Approximately 200 people attended this year’s lunch, the largest turnout to date.

I truly enjoyed the first WORMS keynote.  I hope this is a sign of good things to come.

Link:  The Forum on Women in OR/MS. Become a member today!

 

OR and H1N1

This is the second of three posts about the INFORMS Annual Meeting.

I enjoyed a talk by Dr. Richard Larson of MIT about the timely topic of H1N1 and operations research.  I tuned out much of the alarmist news prior to the conference (to keep my sanity) and instead adopted a rigorous handwashing regimen.  Larson’s talk highlighted the many opportunities for addressing H1N1 issues using operations research, including:

• Queuing for vaccinations.
• Reneging on vaccinations (some health care workers are refusing required vaccinations).
• Timing the vaccinations (before the prevalence peaks) is important for reducing risks, since youths are particularly susceptible to dying from H1N1..
• Locating facilities to manage surge capacity when the epidemic hits.
• Correctly diagnosing and isolating cases of H1N1.
• Supply chains for vaccinations.

Larson and his collaborator Dr. Stan Finkelstein takes a different kind of focus, looking at personal choices, such as hand washing, coughing into sleeves, avoiding handshakes, and avoiding crowds.  They examine this issue through non-pharmaceutical interventions.  Someone infected with H1N1 infects about 1.5 people in the next 24 hours (on average).  This value is the mean of a random variable, which depends on personal choices (like handwashing).  He examines the conditions under which the average number of infections decreases below 1.0, when the virus essentially dies out (Similar to my reasoning on vampire populations).

Finkelstein, a medical doctor, discussed some of the policy results.  Initial reports suggested that H1N1 has a fatality rate of about 50% (Spanish flu has a FR of 3%).  After an initial panic, flu fatigue set in.  And the first wave of H1N1 resemble seasonal rather than pandemic flu.  But after the recent panicking, many of us simply have not been motivated to improve our personal choices to reduce H1N1 transmission.  Case in point, elbow bumping pictured below (instead of hand shaking) did not catch on at the conference as I had hoped. And the anti-bacterial hand gel was not located in useful places at the conference, so I used my own personal stash of anti-bacterial lotion after shaking hands.

I hope some of this research is used to lessen the impact of H1N1 this year before I am transformed into a germ-a-phobe.

Link:  Flu101@MIT

Karima Nigmatulina, after successfully defending the first PhD thesis on our flu research project, bumps congratulatory elbows with advisor Richard Larson.

criminal background checks

This is the first of three posts about the INFORMS Annual Meeting.  Check back in the next few days for the other two posts.

I thoroughly enjoyed the Threats to Life and Limb session.  Thanks to Arnie Barnett for organizing a great session!

In this session, Al Blumstein gave a provocative talk about criminal recidivism.  His research is motivated by employe background checks.  Since most records are electronic, arrest records from the distant past survive.  In many cases, a reformed individual could be denied employment for a minor indiscretion committed decades previously.  The data indicates that more than 50% of the population will have a non-traffic related arrest at some time in their lifetime, making this a huge problem.  However, most of these arrests are for youthful indiscretions.

Blumstein proposes developing hazard curves (based on age of first arrest and type of crime committed).  The hazard rates quantifies the likelihood of someone being arrested for the first time after a given amount of time has passed.  Blumstein uses these hazard rates to determine when a distant, initial arrest should be ignored after someone has been clean long enough.  Blumstein’s research assumes that being “clean” means not being arrested, since background checks only see if arrests have occurred (not whether someone is committing crimes that are undetected).

Blumstein’s results are provocative and generated quite a stir within the session.   Based on the age of first arrest and the type of crime, it takes about 4-8 years of a “clean” record to have a hazard rate similar to the general population.   Since many employers ignore criminal records older than seven years, and they would be on track.

The general population, however, contains many criminals that we probably don’t want to hire.  A better solution may be to compare those with a criminal record to a law-abiding population instead (those who have never been arrested).  The probability of being arrested in a given year is about 10% for the general population and about 1% for those who have never had a prior arrest.  Of course, a former criminal has to stay clean much longer to be “good as new.”  In fact, the hazard functions of the former criminals and the never arrested never overlap.  You can compare the two hazard rates when they get “close enough.”  The confidence intervals here are pretty wide, but Blumstein’s results suggest 10-20 years of being clean.

Blumstein’s research will hopefully be used to create guidelines for employer background checks (in terms of when they can ignore distant arrests).  Criminal justice needs good OR.

Related posts:

• Criminal justice loves OR!
• Murder and the operations researcher
• Sense in sentencing

WORMS at INFORMS

I am getting ready for the INFORMS Annual Meeting.  Stop by and say hi if you see me there.  I will be blogging about the conference during and after the conference.  As the WORMS VP of meetings, I must publicize the WORMS events, most of which occur on Tuesday:

• Sunday @6:15 Business meeting in the Hilton
• Tuesday @8am Panel Discussion:  Challenges and Opportunities for Women in Academia
• Tuesday @11 Keynote address by Margaret Brandeau
• Tuesday @12:30 Luncheon (buy tickets in advance).  This is always my favorite INFORMS event.
• Tuesday @2:45 Panel Discussion: What I Wish I Had Known: Ph.D. Years and Beyond

FYI, you can follow the conference twitter feed.

The status of P=NP? Still open.

Mike Trick’s post on the status of P=NP is required reading.  He writes about a new review paper on the status of P=NP (by Lance Fortnow at Northwestern) and its corresponding New York Times article.  I had not heard about either.  There have been a few recent developments on the P=NP front (check out the blog Godel’s Lost Letter and P=NP for updates).  I have trouble keeping track of all of the news and had always felt like a review article was needed.  I am thrilled that one now exists, along with the newspaper article to explain the concept more clearly to non-experts.  I will be using both in some of my classes.  For more info, please check out Mike Trick’s blog post.

Bulgarian lottery – what are the odds?

The same six winning lottery numbers turned up in two consecutive drawings in the Bulgaria lottery earlier in the month (1 chance in 5.2 million).  Carl Bialik in the WSJ writes about the odds of this happening.  He notes that “With so many numbers colliding each week, the lottery might be the ideal proving ground for something that statisticians have long recognized: Given enough opportunities, the seemingly impossible becomes plausible.”  He explores several lottery issues in more detail in the Numbers Guy blog.  Statistician David Smith also blogged about the Bulgarian lottery.

Although the lottery is random, the people who play it are not.  I had always intuitively known this, but the picture below illustrates this quite nicely.  Apparently, people making lottery picks based on birthdays, for example, skews the picks toward smaller numbers.

Lottery numbers as chosen by lottery players are far from random

The lotteries are designed such that the expected winnings are negative when accounting for the price of the ticket, since the probability of winning is so low (E[winnings] = P(win)*Jackpot – Ticket Price). When the jackpot grows large enough, the “average” lottery player can come out ahead (although there really is no one at the average – there are a couple of winners who really skew the average). In March 1992, the Virginia lottery almost guaranteed a true winner. It offered a jackpot of $27M to a single winner whereas it cost $7.5M to purchase all Choose(44, 6) combinations of possible tickets (by piacking six of 44 numbers). Of course, this strategy could backfire if there were many winners. However, a group of 2500 people accepted this challenge and pooled their resources. They ended up being the single winner, and after a legal struggle, they were awarded the jackpot. The Virginia lottery was subsequently changed to be less lucrative.

Do you play the lottery?

Emily Stoll on using math/OR in the real world

Emily Stoll from Johns Hopkins Applied Physics Laboratory gave  a talk on balancing life and work as part of the Women in Math program.  She offered several lessons that she has learned along the way.

Stoll has a degree in civil engineering, a degree in applied math, and an MBA.  She talked about all of the different things you can do with an applied math degree.  Most of her work involves homeland security applications.  As a mathematical analyst, she analyzed submarine data using the Chi-squared test, Kolmogorov-Smirnov test, Fault tree analysis, and other statistical tests.    She used design of experiments as well as modeling and simulation to improve port security.  Her research on receiver operating (ROC) curves for IED detection was featured in the TSA’s blog.

One of the more interesting projects Stoll was involved with is the US Navy “Marine Mammals” program. She helped to optimize the location of dolphins and sea lions to interdict dangerous materials (such as mines) and for swimmer defense.  Amazingly, the US Navy has been using the marine mammals program since the Vietnam War era.

All of Stoll’s work requires the use of statistics.  It’s nice to know that the tools I teach students in STAT 541 (an introductory statistics course for engineers) are widely used in industry, even by mathematicians and engineers who don’t consider themselves to be statisticians.

Stoll’s excellent life lessons include:

• Take your time to think about a job offer before accepting
• Know what you want before you go after it.
• Build and use your network.
• Very few decisions in life are Life Decisions.
• Sometimes you have to take a risk.
• You can do it all, just not at the same time.
• Do what works for you.
• Realize that it can be done.
• Realize that you will need help.
• Realize that almost every other woman in your position are struggling with the same decisions.
• Figure out what is important to you and make that your priority.

green construction

The VCU STS initiative sponsored an e-Festival Sustainability Symposium.  I had the pleasure of attending Ramana Pidaparti’s talk on recycled materials for sustainable housing applications.  Green engineering has never been hotter.  And it has a huge impact on energy usage.  The US Green Building Council (2001) reports that 37% of total energy consumption in the US is due to housing.  Since we spend nearly five times as much on renovation than on new construction, there are many opportunities for making green buildings that save energy, reduce carbon emissions, and reduce waste.

Efficient design was cutting edge in the 19^th century whereas maintenance was trendy in the 20^th century.  The latest trend is to minimize waste in the end of the life cycle.  I recommend reading Cradle to Cradle for more about this concept.  Dr. Pidaparti talked about several materials for green construction, including

• Insulated wall and roof panels
• Insulated concrete form (for walls and foundation)
• Wheatboard and formaldehyde-free plywood
• Optimized manufacturing methods (such as prefabricated construction)
• Recycled materials (wood flooring, sheetrock, steel, concrete, glass, furnishings)

His research group minimally processed aluminum cans (i.e., by cutting and pasting) to construct aluminum-wood composite laminate.  It reminded me of the weather sensors used in the movie Twister, except this is real.  He is hoping to use these designs in a coffee bistro for Monroe Park, a park in the middle of VCU’s campus in need of a facelift.

Dr. Pidaparti also mentioned that cost does not capture all important attributes in green constructions, since the consumer does not absorb all costs (such as the implications of waste).  It sounds like there may be opportunities for decision analysis to take these other attributes into account.

The 18^th Annual Future City Competition for middle school children will examine affordable sustainable housing this year.  Perhaps the winning competition will use OR?

Read GreenOR for more about, well, green OR.