Archive for January, 2012

A debatable question: Should healthy people take cholesterol drugs?

At my annual physical before my heart attack in December of 2004 I was advised that, although the cholesterol came in a bit high, it would not be necessary to go on medicine to reduce this.  Would I have been spared if I had?  This sort of speculation really does nothing for me but it underscores a big question that is debated in today’s Wall Street Journal: Should Healthy People Take Cholesterol Drugs to Prevent Heart Disease.

You be the judge whether the answer is yes or no—it is far too problematic for me to say.  However, here are two points I want to make on the WSJ debate:

  • I am not so sanguine as the proponent for healthy patients taking cholesterol-reducing drugs (statins, in particular), Dr. Roger S. Blumenthal—Director of the Johns Hopkins Ciccarone Center for the Prevention of Heart Disease, when he says in regards to meta-analysis that “the sum of the trials flushes out bias and reduces statistical uncertainty.”  This does not sway me from wanting a proper experimental study.
  • I agree with the opponent, Dr. Rita Redberg—director of women’s cardiovascular service at the University of California, who advises that
  • “we need clinical trials that actually follow healthy people treated with statins for the long term to see if treatment really results in lower mortality.”

    I remain very skeptical of “experiments” comprised in a metamorphic manner by happenstance, as opposed to being truly controlled from start to finish and done double-blind (if possible).

    No Comments

    Good bees and bad bees

    People in my home state believe in a high degree of politeness which we deem Minnesota Nice.  Thus it should be no surprise that entomologist Marla Spivak, who runs the Bee Lab at the University, has developed a trait for bees that she calls Minnesota Hygienic.  These bees have been bred to detect and remove damaging diseases and parasites from the hive, thus lessening the likelihood of colony collapses that have confounded keepers nationwide.  Spivak’s work came to my attention in this recent Washington Post article featuring beekeepers in nearby Maryland who get $165 for queens whose offspring do not tolerate parasitic mites and, hopefully, this zombie fly.

    This concern over keeping bees healthy is not shared by everyone.  For example, see this horrifying report from Florida (where I happen to be at the moment).  If you fear bees (apiphobia), do not watch the video.

    No Comments

    Favorite posts from three rings in the 2011 Management Improvement Blog Carnival (3 of 3)

    For the final blog review of the 2011 Management Improvement Blog Carnival I have chosen to review NOOP.NL, a blog about Agile software development and management by Dutch author (among other things) Jurgen Appelo. Being a software developer myself, this blog caught my eye. For those unfamiliar with Agile development, it is a method of software development that focuses on small, short iterations (called Sprints).

    The first post that I want to share is actually not about Agile specifically – The Feedback Door is a clever method of getting feedback after a presentation or course. You put sticky notes on or near the door and ask people to stick their feedback directly on the door. Since the attendees need to pass through the door to leave, it’s difficult to ignore! Jorgen combines the feedback door idea with a “Happiness Index” (expanded on in this post) as a simple way to get quantitative feedback as well. It’s called, naturally, the Happiness Door.

    Many of the posts in the blog are of a more philosophical bent (such as The Purpose of a Business is NOT Customer Value, and It takes Complexity to Handle Complexity). However, 21 Concrete Practices for Agile Managers stands out as a great collection of practical suggestions for Agile practitioners.

    Finally, I liked this short and to the point post about the necessity of measures. It’s true that you can’t improve something without measuring some aspect of it. However as a commenter pointed out, you have to be careful what you measure. If you emphasize the wrong metric as a manager you may be encouraging the wrong behavior. A classic example in software is using lines of code (LOC) as a metric. This rewards sloppy and verbose coding and penalizes concise and elegant solutions to problems.

    No Comments

    Extracting Sunbeams from Cucumbers

    With this intriguing title Richard Feinberg and Howard Wainer draw readers of Volume 20, Number 4 into what might have been a dry discourse: How contributors to The Journal of Computational and Graphical Statistics rely mainly on tables to display data.  Given that “Graphical” is in the title of this publication, it begs the question on whether this method of for presenting statistics really works.

    When working on the committee that developed the ASTM 1169-07 Standard Practice for Conducting Ruggedness Tests, I introduced the half-normal plot for selecting effects from two-level factorial experiments.  Most of the committee favored this, but one individual – a professor emeritus from a top school of statistics – resisted the introduction of this graphical tool.  He believed that only numerical methods, specifically analysis of variance (ANOVA) tables, could support objective decisions for model selection.  My comeback was to dodge the issue by simply using graphs and tables – this need not be an either/or choice.  Why not do both, or merge them by putting number on to graphs – the best of both worlds?

    “A heavy bank of figures is grievously wearisome to the eye, and the popular mind is as incapable of drawing any useful lessons from it as of extracting sunbeams from cucumbers.”

    — Economists (brothers) Farquhar and Farquhar (1891)

    In their article which can be seen here Feinberg and Wainer take a different tack (path of least resistance?): Make tables look more like graphs.  Here are some of their suggestions for doing so:

    • Round data to 3 digits or less.
    • Line up comparable numbers by column, not row.
    • Provide summary statistics, in particular medians.
    • Don’t default to alphabetical or some other arbitrary order: Stratify by size or some other meaningful attribute.
    • Call out data that demands attention by making it bold and/or bigger and/or boxing it.
    • Insert extra space between rows or columns of data where they change greatly (gap).

    Check out the remodeled table on arms transfers which makes it clear that, unlike the uptight USA, the laissez faire French will sell to anyone.  It would be hard to dig that nugget out of the original data compilation.

    No Comments