• Lyrics © 2015 by Larry Lesser, music by Larry Lesser and Dominic Dousa

    Nominal, ordinal, interval, ratio are levels of measurement.
    Let's show that progression with examples that we present.

    With a variable that's nominal, values are just like names.
    So ordering or averaging religions would really be a shame!

    A variable that's ordinal sorts values like a chain,
    But don't assume with Likert scales each jump would mean the same!

    With a variable that's interval, differences are sound,
    But Fahrenheit ratios would only just confound.

    With a variable that's ratio, zero means there's none.
    And when it comes to incomes, two's twice as much as one!

    Examples help us learn what measurement levels are!
    An acronym recalls them:
    It's the French word NOIR!

  • If it is not possible to state unequivocally 'how much is enough,' it should be possible to assert with confidence how much, on an average, is too little.

    Mollie Orshansky (1915 – 2006)

  • Q: Who ranks professions by prestige?
    A: Status-ticians!
    Larry Lesser

  • We have to remember that what we observe is not nature herself, but nature exposed to our method of questioning.

    Werner Heisenberg (1901 - 1976)

  • Failing the possibility of measuring that which you desire, the lust for measurement may, for example, merely result in your measuring something else - and perhaps forgetting the difference - or in your ignoring some things because they cannot be measured.

    George Udny Yule (1871 - 1951)


  • by Larry Lesser

    Suppose 50 people are randomly chosen
    and asked "Do you fancy yogurt that's frozen?"
    That 50 is viewed as the size of our sample;
    not a variable's value, just for example.
    What's one guy's answer? That's not rhetorical;
    It's a variable that's categorical.

    The way to view it, the way you can know:
    Each person we surveyed says 'yes' or a 'no'.
    Of course, you could tally each label's amounts
    For a summ'ry statistic from each of the counts,
    But that doesn't make the variable numerical
    Each value's a category whose tallies are clerical.

    So, a variable can be very able
    To yield useful data in a nice table,
    But we must assert categorically
    Variable type is important, you see,
    To know what sum'ries and tools you can use
    So bar graphs and histograms won't be confused.

  • Every careful measurement in science is always given with the probable error... every observer admits that he is likely wrong, and knows about how much wrong he is likely to be.

    Bertrand A.W. Russell (1872 - 1970)

  • If you can't measure it, I'm not interested.

    Laurence J. Peter (1919 - 1990)

  • It is easy to lie with statistics, but it is easier to lie without them.

    Frederick Mosteller (1916 - 2006)