Showing posts with label Correlation. Show all posts
Showing posts with label Correlation. Show all posts

April 15, 2015

The Wrong Way To Test

As educators are pushed to improve students' test scores, sometimes they run afoul.

In Atlanta, 8 former public school educators were sentenced to prison--three were sentenced to as long as seven years--for a conspiracy inflating student scores by "changing answers" to the tests. 

Interestingly, in another article today, we see that not only are students put to the test, but so are job applicants

In fact, "Eight of the top 10 U.S. private employers now administrator pre-hire tests in their job applications."

While testing can certainly show some things, they can also miss the point completely. 

I know some people that test wonderfully--straight A students, 100+ on all exams, 4.0 GPAs--and for the most part, they are wonderful at memorizing and prepping for the test...but sometimes not much else. 

Some of them have no practical knowledge, little critical thinking or creativity, and are even sort of jerky. 

And others who test poorly may be well thought, articulate, hands-on, and good with people--I'd take a million of them. 

"Failing the test" is not necessarily getting it wrong...it may just be errant to the current educational and professional testing system that values memorization and spitting back over insight, innovation, and practical skills. 

The challenge is how do we compare and contrast students and professionals competing for schools and career advancement, if we don't easily have something standardized like a test to rally around. 

Maybe there is no getting away from more holistic assessments--where we look at bona fide life and career experience, a wide range of recommendations from teachers, coaches, and supervisors, hard and soft skills (including communications and interpersonal), professional and personal ethics, genuine interest in the pursuit, and the motivation to work hard and contribute.  

Tests--students cheat, educators game the system, memorization and robotic answers are the name of the game to get the A, and boring homogeneity prevails--but it's often the easy way out to evaluating candidates for a phony success. ;-)

(Source Photo: Andy Blumenthal)
Share/Save/Bookmark

June 29, 2013

Back To The Computer Stone Age

According to Charles Kenny in Bloomberg BusinessWeek (20 June 2013), the Internet is quite a big disappointment--because it "failed to generate much in the way of economic growth."

While on one hand, the author seems to see the impact that the Internet has had--"it sparks uprisings, makes shopping easier, help people find their soul mates, and enables government to collect troves of useful data on potential terrorists;" on the other hand, he pooh-poohs all this and says it hasn't generated prosperity. 


And in a sense, don't the facts seem to support Kenny: GDP is still in the 2-3% range, labor productivity growth is even lower, and unemployment is still elevated at over 7%?


The problem is that the author is making false correlations between our economic conditions and the rise of the Internet, which already Jack Welch pronounced in 2000 as "the single most important event in the U.S. economy since the industrial revolution." 


Kenny seems to think that not only aren't there that many economic benefits to the Internet, but whatever there is we basically squander by becoming Facebook and Youtube junkies.


It's a shame that Bloomberg BusinessWeek decided to publish such a ridiculous article as its "Opening Remarks," blaming the failure of the Internet for economic challenges that have been brewing for decades--with high-levels of debt, low levels of savings, hefty entitlement programs based on empty national trust funds, the global outsourcing of our manufacturing base, elevated political polarization in Washington, and various economic jolts based on runaway technology, real estate, and commodity bubbles.


It's concerning that the author, someone with a masters in International Economics, wouldn't address, let alone mention, any of these other critical factors affecting our national economy--just the Internet! 


Kenny adds insult to injury in his diatribe, when he says that the Internet's "biggest impact" is the delivery of "a form of entertainment more addictive than watching reruns of Friends."


Maybe that's the biggest impact for him, but I think most of us could no longer live seriously without the Internet--whether in how we keep in touch, share, collaborate, inform, innovate, compute, buy and sell, and even entertain (yes, were entitled to some downtime as well). 


Maybe some would like to forget all the benefits of technology and send us back to the Stone Age before computing, but I have a feeling that not only would our economy be a lot worse than it is now, but so would we. :-)


(Source Photo: Andy Blumenthal)



Share/Save/Bookmark

March 27, 2013

Big Data, Correlation Or Causation?

Gordon Crovitz wrote about Big Data in the Wall Street Journal (25 March 2013) this week.

He cites from a book called "Big Data: A Revolution That Will Transform How We Live, Work, and Think," an interesting notion that in processing the massive amounts of data we are capturing today, society will "shed some of its obsession for causality in exchange for simple correlation."

The idea is that in the effort to speed decision processing and making, we will to some extent, or to a great extent, not have the time and resources for the scientific method to actually determine why something is happening, but instead will settle for knowing what is happening--through the massive data pouring in.

While seeing the trends in the data is a big step ahead of just being overwhelmed and possibly drowning in data and not knowing what to make of it, it is still important that we validate what we think we are seeing but scientifically testing it and determining if there is a real reason for what is going on. 

Correlating loads of data can make for interesting conclusions like when Google Flu predicts outbreaks (before the CDC) by reaming through millions of searches for things like cough medicine, but correlations can be spurious when for example, a new cough medicine comes out and people are just looking up information about it--hence, no real outbreak of the flu. (Maybe not the best example, but you get the point). 

Also, just knowing that something is happening like an epidemic, global warming, flight delays or whatever, is helpful in situational awareness, but without knowing why it's happening (i.e. the root cause) how can we really address the issues to fix it?

It is good to know if data is pointing us to a new reality, then at least we can take some action(s) to prevent ourselves from getting sick or having to wait endlessly in the airport, but if we want to cure the disease or fix the airlines then we have to go deeper, find out the cause, and attack it--to make it right. 

Correlation is good for a quick reaction, but correlation is necessary for long-term prevention and improvement. 

Computing resources can be used not just to sift through petabytes of data points (e.g. to come up with neighborhood crime statistics), but to actually help test various causal factors (e.g. socio-economic conditions, community investment, law enforcement efforts, etc.) by processing the results of true scientific testing with proper controls, analysis, and drawn conclusions.


Share/Save/Bookmark