How Much Data Is Enough? or, To Be or Not To Be: Is Data the Answer?

Seems public relations and social media measurement has gone from not enough data to too much data in the blink of an eye. On this subject, two more-or-less antipodal posts arrived in the in-box today. David Brooks likes data, especially when it proves common knowledge wrong. Thomas Tunquz, on the other hand, argues that too much data can be debilitating.

Mr. Brooks, columnist for The New York Times, keeps an eye on research in the social sciences. Today he asked in "The Philosophy of Data": "In what situations should we rely on intuitive pattern recognition and in which situations should we ignore intuition and follow the data?”

In his post he relates several interesting instances in which the data proves intuition wrong:

• Basketball players do not have “hot streaks.”
• Political elections that are well-financed do not benefit from increased TV ad spends.
• There is no evidence to support the intuitive sense that students have different learning styles.

Meanwhile, venture capitalist Thomas Tunguz argues against too much data in his post "How to Optimize Every Decision in Your Life and Accomplish Nothing": “...the byproduct of the relentless pursuit of the ‘best’ can be debilitation.”

He relates the story of Richard Feynman and Ralph Leighton’s data-driven restaurant menu decisions. They developed a formula to determine how many different dishes they should order from a menu before settling upon a favorite. I know you can't wait to find out, so here it is:

The number of dishes to try = √2(Meals remaining at restaurant+1) - 1

--Bill Paarlberg, editor

Thanks to Let's Graph for the illustration!