psy291

Stem-and-Leaf Display

  • Definition: A stem-and-leaf display is a method of organizing numerical data that separates each score in a distribution into two parts: a 'stem' and a 'leaf'.

  • Components of Stem-and-Leaf Display:

    • Stem: The stem represents the leading digit(s) of the numbers in the data set. It essentially groups the numbers into larger intervals.

    • Leaf: The leaf represents the trailing digit(s) of the numbers, providing finer detail within each stem group.

  • Purpose: This display is used to provide a visual representation of quantitative data and to facilitate the understanding of the distribution of scores.

  • How to Create a Stem-and-Leaf Display:

    1. Organize the Data: Arrange the data in ascending order to clearly identify stems and leaves.

    2. Determine Stems: Identify the appropriate level of digits to use as the stem, generally the leading digit(s) based on the range of data.

    3. Assign Leaves: For each data point, take the trailing digit(s) as the leaves corresponding to the appropriate stem.

    4. Format the Display: List each stem in one column, and align the corresponding leaves in the row next to it, generally in increasing order.

  • Example:

    • Given the data set: 23, 25, 27, 30, 31, 32

    • Stems: 2 (for 20s), 3 (for 30s)

    • Corresponding Leaves: 3, 5, 7 (for stem "2") and 0, 1, 2 (for stem "3")

    • Stem-and-Leaf Display:

    • 2 | 3 5 7

    • 3 | 0 1 2

  • Characteristics:

    • It retains the actual data values in the display. Every number can be reconstructed from its stem and leaf, preserving information integrity.

    • It is a compact way to visualize a data set that allows for easy identification of the shape, spread, and central tendency of the data without the data loss that can occur with data binning.

  • Applications: Commonly used in statistics for exploratory data analysis, particularly when analyzing small to moderate-sized data sets. Facilitates understanding of data distributions, including identifying modes, outliers, and gaps in the data.

  • Advantages:

    • Combines features of both a histogram and a list.

    • Easy to derive summary statistics like median and mode directly from the display.

  • Limitations:

    • Can become unwieldy with large datasets.

    • Might be less intuitive for individuals unfamiliar with the format compared to other graphical representations such as histograms or box plots.