Guest Author: Teresa Tallman, "The MEAN lady"
Statistics for kids? Yes. Elliot Schrage, vice president of communications at Facebook, argues that our kids should study “statistics, because the ability to understand data will be the most powerful skill in the twenty-first century.”
Rebecca Nichols, American Statistical Association’s Director of Education, said: “Sound statistical thinking and reasoning takes time to develop. As mathematical thinking is developed over years of study starting in the early grades, so should statistical thinking.”
This means that children should be introduced to statistics concepts along with other math concepts…at ages 3, 4, 5… Impossible? Not at all.
First, let’s understand why teachers and parents don’t talk statistics to kids.
· Parents may be unfamiliar with statistical concepts themselves.
· Teachers are familiar with statistics and do not like it.
· Children are too young to hear complicated terms.
· Children do not have the math skills necessary for statistics.
Many people are afraid of statistics. I get that. My first introduction to statistics was in tenth grade math (I hate to think how long ago that was!). We were doing probability by flipping coins. I did not plan on gambling so I didn’t understand the point of probability. I couldn’t relate at all. I became traumatized by the term statistics.
When I began my career as a manufacturing engineer, my company put me through a six week, eight hour a day applied statistics class. I figured out pretty quickly that using statistical techniques in data analysis was important to this company and if I wanted to succeed, I’d better figure it out.
My factory made pressure sensitive adhesive tape for diapers, microwaves, cars, labels and highways. Let me tell you, there is a lot of designing that goes into that little tab of sticky stuff. It has to be engineered regarding what it sticks to, how long it adheres, how you get it off and what temperatures and humidity and stress it has to endure. From the manufacturing line, data is collected on temperatures, speeds, humidity, pressures, and that is paired with quality test data of raw material inputs and outputs. The data may be collected every few seconds. That’s a lot of numbers to wrestle with.
A big part of a manufacturing engineer’s job is to track the data generated and confirm that the process is steady state. It’s consistent. Don’t you hate it when you buy something at the store and you really liked it and you buy again, and it’s not what you bought before? It’s the same thing in manufacturing. A customer wants a product they can depend on. No one likes surprises.
One tool that an engineer uses is something called a control chart. It’s a picture of the data over time. On a control chart, points go up and down but you can pretty easily see if there is a trend. Limits based on normal variability help you decide when to make an adjustment to the process so a consistent product is produced. (We’ll talk about the fundamental role of variation in a future blog.) The tool of statistical process control turns all of that data into information so people can make decisions.
Today, most factories use statistical process control to manage their operations. Factory by factory…what if statistical process control proliferated through a country? That’s just what happened to Japan after WWII thanks to the efforts of W. Edwards Deming.
Deming's teachings and philosophy are clearly illustrated by examining the results they produced after they were adopted by Japanese industry, as the following example shows. Ford Motor Co. was simultaneously manufacturing a car model with transmissions made in Japan and the United States. Soon after the car model was on the market, Ford customers were requesting the model with Japanese transmission over the US-made transmission, and they were willing to wait for the Japanese model. As both transmissions were made to the same specifications, Ford engineers could not understand the customer preference for the model with a Japanese transmission. Finally, Ford engineers decided to take apart the two different transmissions. The American-made car parts were all within specified tolerance levels. On the other hand, the Japanese car parts were virtually identical to each other, and much closer to the nominal values for the parts—e.g., if a part was supposed to be one foot long, plus or minus 1/8 of an inch—then the Japanese parts were all within 1/16 of an inch, less variation. This made the Japanese cars run more smoothly and customers experienced fewer problems.
Many in Japan credit Deming as one of the inspirations for what has become known as the Japanese post war miracle of 1950 to 1960, when Japan rose from the ashes of war on the road to becoming the second largest economy in the world. (Wikipedia)
That’s the power of statistics.
Statistical thinking needs to be integrated with math and science concepts throughout the learning years. I want kids to avoid my initial experience. It should be presented in a fun environment around projects that kids are interested in. And believe it or not, we can introduce the concepts of mean, variability and other terms to preschoolers without using numbers. In the future, I’ll be sharing how to go about doing that!
Remember, STATISTICS is FUN.
Author: Teresa Tallman
"The MEAN lady"