cherry-picking

(verb)

To pick only a part of the whole truth, often in order to support an opinion or personal agenda. In analysis, it is seeing what one wants to see in the data (as opposed to what's there).

Related Terms

Examples of cherry-picking in the following topics:

  • Types of Supporting Materials

    • Because of the small sample, there is a larger chance that it may be unreliable due to cherry-picked or otherwise non-representative samples of typical cases.

  • Analytical Mindset

    • In a world with this much data, maintaining objectivity and refraining from cherry-picking to prove one's opinion is a very important skill.

  • Logical Fallacies

    • Card-stacking, or cherry picking: deliberate action is taken to bias an argument by selective use of facts with opposing evidence being buried or discredited.

  • Types of Transactions

    • A buyer often structures the transaction in order to "cherry-pick" the assets that it wants and leaves out the assets and liabilities that it does not.

  • Basic Concepts

    • Let's say you have a bag with 20 cherries: 14 sweet and 6 sour.If you pick a cherry at random, what is the probability that it will be sweet?
    • There are 20 possible cherries that could be picked, so the number of possible outcomes is 20.
    • Of these 20 possible outcomes, 14 are favorable (sweet), so the probability that the cherry will be sweet is $\frac{14}{20}=\frac{7}{10}$.
    • It must be assumed that the probability of picking any of the cherries is the same as the probability of picking any other.
    • This wouldn't be true if (let us imagine) the sweet cherries are smaller than the sour ones.

  • Foundations for inference

    • Throughout the next few sections we consider a data set called run10, which represents all 16,924 runners who finished the 2012 Cherry Blossom 10 mile run in Washington, DC.
    • These data are special because they include the results for the entire population of runners who finished the 2012 Cherry Blossom Run.
    • Four observations for the run10Samp data set, which represents a simple random sample of 100 runners from the 2012 Cherry Blossom Run.
    • Histograms of time and age for the sample Cherry Blossom Run data.

  • Introduction to variability in estimates

    • We would like to estimate two features of the Cherry Blossom runners using the sample.
    • These questions may be informative for planning the Cherry Blossom Run in future years.

  • Portfolio Risk

    • Three assets (apples, bananas, and cherries) can be thought of as a bowl of fruit.
    • In order to calculate the variance of a portfolio of three assets, we need to know that figure for apples, bananas, and cherries, and we also need to know the co-variance of each.
    • If bananas do great half of the time when cherries do bad and bananas do terrible the other half, their co-variance is zero.
    • Apples may be a substitute for cherries when cherries are expensive.
    • The overall risk of the portfolio would take into account three individual variances and three co-variances (apples-bananas, apples-cherries, and bananas-cherries) and it would reduce the overall portfolio to the degree that they are uncorrelated.

  • Sampling from a small population (special topic)

    • Thus, if you were not picked on the first question, the probability you are again not picked is 13/14.
    • = P(Q1 = not picked, Q2 = not picked, Q3 = not picked. ) = 14/15 × 13/14 × 12/13 = 12/15 = 0.80
    • Each pick is independent, and the probability of not being picked for any individual question is 14/15.
    • P(not picked in 3 questions) = P(Q1 = not picked, Q2 = not picked, Q3 = not picked. ) = 14/15 × 14/15 × 14/15 = 0.813
    • 2.63: The three probabilities we computed were actually one marginal probability, P(Q1=not picked), and two conditional probabilities: P(Q2 = not picked | Q1 = not picked); P(Q3 = not picked | Q1 = not picked, Q2 = not picked) Using the General Multiplication Rule, the product of these three probabilities is the probability of not being picked in 3 questions.

  • Point estimates and standard errors for differences of means

    • We would like to estimate the average difference in run times for men and women using the run10Samp data set, which was a simple random sample of 45 men and 55 women from all runners in the 2012 Cherry Blossom Run.
    • Side-by-side box plots for the sample of 2009 Cherry Blossom Run participants.
    • Summary statistics for the run time of 100 participants in the2009 Cherry Blossom Run.