Archive for category Uncategorized

Scroll sawers put blades to the statistical test by cutting out ducks

Years ago I helped Quality Assurance Manager John Engler solve a tricky issue at Robinson Rubber via design of experiments (DOE). He contacted me last fall to help him apply DOE to a nagging question about scroll sawing: Does it pay to buy pricier blades?

We worked together to design a simple-comparative randomized-block experiment on 10 competitive blades. John enlisted 20 fellow hobbyists in his NorthStar Scrollers club to cut out a duck from pine (see pattern below) using the selected blades (such as the one taped on the board) in a random order.

They then rated the results on a 1 to 9 scale—higher the better—for speed of cut, blade jumpiness, fuzzies (undesirable!), edge smoothness, burns and line following.

Scroll saw ready to cut out a duck

The blades differed significantly by all attributes at p < 0.0001 other than the line following (p = 0.3419). For the most critical measure—speed of cut, blades 3, 8 and 9 stood above all others on average.

The power of doing 21 replicates—widely spread as indicated by the red dots—and, furthermore, blocking out the scroller-to-scroller differences, is seen by the narrowness of the least significant differences (based on a p of 0.05).

Accounting for all the attributes via Stat-Ease software’s multiple response optimization these three blades held up overall with number 3 being the winner by costing less than the other two.

After I reported my findings to the group, John laid out a number of mitigating factors:

  • Experience of the scroll sawers
  • Type of wood, e.g., something a lot harder
  • The life of the blades (important to consider for the cost)

But all-in-all, this planned experiment proved to be a big hit with the NorthStar Scroller hobbyists. What impressed me was their depth of knowledge on scroll-saw blades and why we observed such significant differences due to the patterns and orientation of their teeth, etc. I was also struck by how some individuals could tell right away which blades worked best—even before seeing the entire set of data. This reinforces my feeling that laying out and analyzing experiments works best by combining the know-how of a DOE expert (like me) with subject matter experts (not me in this case—far from it!).

“This went much better for me than I thought it might and I learned some things about blades along the way. This was fun!”

–Helen (a NorthStar Scroller blade-tester)

No Comments

Chance discovery on random walk in Utrecht

Last week I taught a class on design of experiments to a biotech company in Leiden, Netherlands. Afterwards I spent a few days in Utrecht with some friends from Germany. Imagine my excitement (nerd alert!) when on my first walk from our hotel to the city center just a few hundred feet down the sidewalk I encountered this mural featuring a differential equation.

Not being a physicist, I did not immediately grasp the formula’s importance, nor the clue provided by the fellow high-stepping down a street. It turns out this fellow is a drunk whose walk has become random. The mural, as explained by Utrecht University, pays homage to their famous professor Leonard Ornstein who, in the early 1900s along with another physicist—George Uhlenbeck—developed an important variant of the “random walk”—a term introduced by pioneering statistician Karl Pearson. The Ornstein-Uhlenbeck process is used to derive models from “big” financial data, including inflation rates, commodity prices and stock values.

I did not expect to gain an education on a vacation expedition.

Very cool!

PS: I thought about asking my colleague Martin Bezener, a PhD statistician, for his opinion on the chances of coming across something so relevant to our mission at Stat-Ease while on a random walk. But I will not bother, because I already know what he would say: “One-hundred percent: It already happened”.

No Comments

Data detectives keep science honest

An article in Wall Street Journal last week* drew my attention to a growing number of scientists who moonlight as data detectives sleuthing out fraudulent studies. Thanks to their work the number of faulty papers retracted increased from 119 in 2002 to 5,500 last year. These statistics come from Retraction Watch who provide a better, graphical, perspective on the increase based on percent retractions per annual science and engineering (SE) publication–not nearly as dramatic given the explosion in publications over the last 20 years, but still very alarming.

“If you take the sleuths out of the equation it’s very difficult to see how most of these retractions would have happened.”

Ivan Oransky, co-founder of Data Colada –a  blog dedicated to investigative analysis and replication of academic research.

Coincidentally, I just received this new cartoon from Professor Nadeem Irfan Bukhari. (See my all-time favorite from him in the April 27, 2007 StatsMadeEasy blog Cartoon quantifies commitment issue.)

It depicts statistics as the proverbial camel allowed to put its nose in the tent occupied by science disciplines until it become completely entrenched.

Thank goodness for scientists like Nadeem who embrace statistical tools for design and analysis of experiments. And kudos to those who guard against faulty or outright fraudulent scientific publications.

*The Band of Debunkers Busting Bad Scientists, Nidhi Subbaraman, 9/24/23

No Comments

Hurricane season off to a hot start with great uncertainty ahead

After narrowly dodging Ian’s devastating blow last fall—predicted the day before landfall to hit just a few blocks from my southwest Florida winter home, I am keeping a close watch on this year’s storms.

Just prior to 2024 season on June 1, the National Oceanic and Atmospheric Administration (NOAA) predicted it would be near normal. The NOAA forecasters figure on the winds from the Pacific’s El Nino counteracting the storm inducing temperatures in the Atlantic.

A clash of the titans lies ahead as developing El Niño and notable warmth in the Tropical Atlantic go toe-to-toe.

Ryan Truchelut—the Weather Tiger’s Atlantic Hurricane Season Outlook for May 2023

The Weather Tiger (quoted above) calculated Florida landfall odds this year at slightly above 50/50 for at least 1 hurricane. That was before Tropical Storm Cindy formed behind Tropical Storm Bret in June, creating the first case of two storms in the tropical Atlantic in June since record keeping began in 1851–an alarmingly aggressive start to the season.

Based on these forecasts and the history of USA hurricanes, it seems certain to me that, before 2023 is over, our home will come into harm’s way. Therefore, I keep a close watch on NOAA’s graphical forecasts that display cones showing the probable track of the center of every tropical cyclone. These cones create a great deal of consternation and confusion due to difficulties comprehending probabilities, overly high expectations in the accuracy and precision of forecasting models, and other issues.

While admiring the continuing advancements in meteorology, including this year’s extension to 7 days for hurricane forecasts, I believe (but only half seriously) that if a weather forecast one-day ahead puts me at the bullseye of an oncoming storm, then it will be a miss. This worked for Hurricane Ian. But to hedge my bets, I greatly reinforced our home over the winter to resist wind, rain and flooding—bringing it all up to current hurricane codes and beyond.

Best be safe!

No Comments

Hard-boiled Easter eggs not a-peeling

One of my daughters provided me with half a dozen hard-boiled eggs left over from Easter. However, so far I have not cracked (pun intended) the process for peeling of their shells without also taking off much of the albumen (the white part on the outside). That leaves a very raggedy yolk with white bits hanging off. You could say that the yoke is on me (sorry, cannot resist). Even this supposedly “genius” hack (literally—using a spoon) failed miserably.

Unfortunately, my wife ate up the remaining stock before I could try more eggs-periments. She also experienced difficulties peeling them, which made me feel better (my dexterity falling fall short of hers). Should un-a-peeling eggs be encountered again, here are my other possible remedies:

Any other ideas for easy and reliable egg peeling are welcome!

No Comments

Major League Baseball’s grand-slam experiment to pick up its pace

It’s Opening Day today for Major League Baseball (MLB), when hopes for a championship season hit a peak before reality sets in for most of our teams. Excitement runs higher than usual this year because trial runs at lower levels emboldened Major League Baseball (MLB) into implementing drastic rule changes aimed at speeding up the game. The biggest impacts will come from a new pitch clock, a ban on the infield shift and limits on pickoff throws.

Results from MLB’s spring training—wrapping up this weekend—look very promising: The average time per game dropped to about 2.5 hours—down 26 minutes from last year. That will keep me, a Minnesota Twins season-ticket holder, in the game—no more bailing out in the later innings and listening to the finish on the radio during my half-hour drive home from Target Field.

Another likely effect of the MLB rule changes will be more attempts to steal bases, increased this spring by almost 50% from 2.1 to 3.1 per 100 plate appearances with a success rate of 77.2 percent—up from year’s 71.3.* Let’s go!

These new rules for 2023 augment one adopted in 2020 to limit overtime games—the placement of a “ghost runner” at second base beginning in the 10th inning. The October issues of Significance magazine** reports remarkable agreement of actual results versus predictions generated by a natural experiment on this rule—a reduction of about 15 minutes per game. Even better!

“This is the game we all want to see — get the ball, pitch the ball, keep the defense on their toes.”

Actor Bryan Cranston speaking on behalf of MLB

PS It’s hard to argue with the efficacy of natural experiments based on this MLB example and the methodology being awarded the 2021 Nobel Prize in Economic Sciences.*** However, if at all possible from an ethical, practical and political perspective, a planned experiment laid out in randomized fashion remains the ‘gold standard’ for predictive modeling. Why not take over a baseball league or a specific team, preferably the lowest level possible, and run a designed experiment? I did so successfully for my softball squad. See how and the results in this 2007 StatsMadeEasy blog.

*Statistics on game time and stolen bases from Tyler Kepner, The New York Times, 2023 MLB Season Preview, 3/27/23.

**“Baseball’s natural experiment,” Lee Kennedy-Shaffer.

***Natural experiments help answer important questions

No Comments

Going all out to save the birds

Last summer a cute little bird smacked into our patio door. It stood stunned long enough for me to get this closeup.

I see lots of cardinals (my favorite!), finches, sparrows and other backyard birds all year round. Others—robins and the like—come only when the weather warms up. However, I don’t recall ever seeing one in pretty pastels of brown and yellow. This beautifully colored creature does not pop out for me as one of the 23 most common birds in Minnesota. What could it be? Google Lens provides a clue by identifying it as a warbler. Along this line, based on what’s pictured on internet (even narrowed to warblers, many appearing similar), I’m going with this being a female (juvenile?) common yellowthroat. Do you agree?

Happily, this cute little yellow-throated bird flew off soon after its stunning encounter with our house and never came back to knock on our door. However, from time to time a bright-red male cardinal takes issue with its rival staring back from our bay windows. I’ve tried to ward these aggressors off by taping CDs shiny-side-out to the middle of the glass. However, that never works. Now, thanks to a heads-up from New York Times,* I know why: This new study by College of William & Mary biologists shows that window films increase avoidance of collisions by birds but only when applied externally.

“Bird collisions with windows kill more than a billion birds per year.”

Professor John Swaddle, lead scientist of first experimental study to compare the effectiveness of window films when applied to internal versus external surfaces of double-glazed windows

The researchers randomly divided 72 zebra finches into 4 groups via a two-factor, two-level factorial that varied type of film—BirdShades (not commercially available yet) vs Haverkamp—and location on the glass surface—interior vs exterior. No worries—their ingenious flight-testing facility featured a net that prevented window-bound birds from head-on collision.

By the way, in this interview by W&M News (check out the picture of his student showing the “proper technique for holding a zebra finch”), Swaddle says that “silhouettes of animals or birds don’t tend to work in part because they’re generally too spaced out.” So, when our windows again come under attack by angry birds, I will use many CDs (putting a plentiful pile of unused and obsolete media to good use)—not just one—and duct tape them to the outside—not the inside. I just hope that the neighbors don’t complain about the blast of solar radiation going back their way.

*“Those Window Stickers to Prevent Bird Strikes? There’s a Catch.”, Catrin Einhorn, Feb. 2, 2023 (Updated Feb. 7)

No Comments

Smoot points about measurements

Does it really matter that the calendar turned over from December 2022 to January 2023? From where I sit nothing much changed from one day—12/31/22—to the next—1/1/23. It’s just as cold here in Minnesota—below freezing (32 F or 0 C: Take your pick). Must we pay any attention to an irrelevant measure of time passing by? Of course, the answer is “yes” for everyone to party on a timely basis for the New Year, birthdays, and anniversaries. However, I feel badly for my niece’s daughter born on Leap Day 2020—no 1st birthday until 2024. That’s a measurement failure. Anyways, Happy New Year!

Also, why do we continue to favor English versus metric units here in the USA? That is a huge waste! Let’s begin the conversion by expanding the football fields to 100 meters. The players won’t even notice the 10 percent increase in required effort. My feeling is that this will be the breakthrough to the far more sensible and scientific metric system—a movement that seemed certain to succeed when Congress passed the Metric Conversion Act in 1975. Unfortunately, this became a political football when folks here in the Midwest resisted being told to post their distances in kilometers rather than miles.

The silliness of the archaic English anthropometric measures, such as height in feet and quantities of spices in pinches, came to a head in 1958 when frat brothers from MIT flipped a pledge named Oliver Smoot over-and-over the length of the Mass. Ave. bridge for a total of 364.4 Smoots (plus “one ear”*). In 2016, the MIT Alumni magazine published this April Fool’s joke that the Institute planned to recalibrate the Smoot to its namesakes current height (presumably a bit shrunken by the decades). What I find most interesting is that Smoot later served as chairman of the American National Standards Institute and president of the International Organization for Standardization. He went all out, literally, for the sake of measurements!

By way, it snowed 4 and 3/16ths of an inch yesterday according to my double Helix measuring ‘stick’. For my own purposes, I always use the metric side of this ruler—much preferring its decimal system (m/cm/mm, etc.) over the cumbersome fractions of inches. But to keep things simple, I pay the teenager next door by the inch.

PS It snowed another 6 inches overnight, bringing the total to 25 cm or so (deliberately mixing measurement scales to make my point). In any case, I need a taller ruler!

*Per Smoot in this 1995 interview. I first heard of him from the November 21st Wall Street Journal review of “Beyond Measure: The Hidden History of Measurement from Cubits to Quantum Constants.” For details and reader ratings (assuming you like accurate measurements!) of this new book, I recommend you go to this Goodreads site.

No Comments

Age vs happiness—some ups and downs

The “mid-life crisis” provides endless amusement from over-the-hill fellows trying to hold on to their youth via frivolous purchases (e.g., a sportscar) and foolish escapades (e.g., young women). A few years ago, economist David Blanchflower pinpointed 47.2 as the age when unhappiness reaches this minimum.* However, my re-analysis of his data indicate a very plausible complication to this picture: A late 20s dip creating a double “U” in the happiness curve.

Life satisfaction versus age

After importing Blanchflower’s life-satisfaction data** into Stat-Ease software, I applied a 6th order polynomial model—not just the 2nd order quadratic typically used for simplification. This more sophisticated analysis reveals an initial dip at 24.1 years before the ‘mid-life crisis’ coming at 50.9 years of age.

Of course, all of us differ individually in our happiness throughout our lives, but it is interesting to see how we compare to the average person in this regard. Although I would not mind a rejuvenation to my mid-20s physical fitness, it really is great to be well past the unhappiness of those youthful days and the subsequent stress that comes at mid-life. Old guys really do rule for happiness by my reckoning.

Cheers!

*Research Shows People Become Increasingly Unhappy Until Age 47.2, Inc., 1/30/20.

**Figure 2: “US Gallup Daily Tracker Cantril’s 11-step life satisfaction ladder, 2008-2018, no control curve”, Is happiness U-shaped everywhere? Age and subjective well-being in 145 countries, David G. Blanchflower, Journal of Population Economics, v34, pp 575–624, 9/9/20.

No Comments

Embrace coincidences to shore up your well-being

Being a believer in the power of positivity, I am always on the lookout for the bright side of life. For example, while out for a very chilly walk this morning, I was delighted to see a dozen or so bluebirds perched along a fence next to the sidewalk. I embraced this happy coincidence!

Professor David Hand, former Chair in Statistics at Imperial College, London, made a case that these little miracles occur daily.* You just need to be pay attention. I got some great reinforcement for collecting coincidences from a report last week by Wall Street Journal columnist Elizabeth Anne Bernstein.** She provided a great example of a fortuitous series of events that led to a wonderful meeting with a friend of her father, who passed away earlier this year.

“Surprising concurrent events can help us reach decisions, soothe us in grief and tighten our connections to others.

Elizabeth Anne Bernstein

Although some people believe in divine causes for coincidences such as Elizabeth’s,*** I think they occur at random and get selectively noticed due to personal biases. In any case, I am happy for anyone who gains comfort from them.

PS For an excellent breakdown of coincidence by serendipity (“happy accidents”) versus synchronicity (an acausal “falling together in time” see this 2021 Psychology Today explanation by Bernard D. Beitman, M.D. of Meaningful Coincidences.

PPS On a related, more humorous note, check out this ‘heads-up’ on the Baader-Meinhof Phenomenon. Eery!

*See my 2014 blog explaining why Laws of nature lead to rare events that really ought not surprise anyone

**The Hidden Power of Coincidences

***For example, many believed in a heavenly arrangement for the simultaneous deaths of Thomas Jefferson and John Adams on July 4, 1826—exactly 50 years after each had signed the Declaration of Independence.

No Comments