Displaying and Summarizing Quantitative Data

Module 2 - Section 2

Displaying and Summarizing Quantitative Data

Introduction to Quantitative Data

• Quantitative variables often take many values, exemplified by the prices of walking shoes:

  • Example Prices: 90, 70, 70, 70, 75, 70, 65, 68, 60, 74, 70, 95, 75, 68, 85, 40, 65

• The need for visual representations arises to display the data and illustrate the distribution effectively.

Types of Graphs for Numerical Data

• Categorical Variables:

  • Bar Chart

  • Pie Chart

• Numerical Variables:

  • Dot Plots

  • Stem Plots

  • Histograms

  • Time Plots

  • Box Plots

  • Scatterplots

Dot Plots

• Definition: A dot plot is a graphical display that portrays individual observations.

• Construction Steps:

  1. Draw a horizontal (or vertical) line.

  2. Label the line with the name of the variable and mark the regular values of the variable on it.

  3. For each observation, place a dot above (or next to) its value on the number line.

• Important Notes:

  • The number of dots above a value indicates the frequency of occurrence of that value.

  • Dot plots are more effective for small datasets (n ≤ 50).

Example: Dotplot for Prices of Walking Shoes

• Data for 17 walking shoes:** 90, 70, 70, 70, 75, 70, 65, 68, 60, 74, 70, 95, 75, 68, 85, 40, 65**

• Dotplot created using the data above displays frequency and distribution.

Describing a Distribution

• Important aspects to describe a plot include:

  • Shapes: Determine the nature of the distribution (unimodal, bimodal, multimodal).

  • Modes: Characterization based on the number of humps or peaks in the distribution.

  • Symmetry or Skewness: Aspects related to the balance of the distribution.

  • Deviations or Outliers: Identifying unusual values that deviate from the overall pattern.

  • Center: Refers to the value that divides the data in half, indicating a typical range.

  • Spread: Measures the range of values and the concentration around the center.

Shapes of Distributions

• Unimodal: One peak.

• Bimodal: Two peaks; may indicate two different groups within the data.

• Multimodal: More than two peaks; rarely occurs.

• Uniform: No clear modes (flat distribution).

Skewness in Data

• Symmetric: If a vertical line can divide the graph into mirror images on either side.

• Positively Skewed: Histogram stretches out more to the right; the upper tail is longer.

• Negatively Skewed: Histogram stretches out more to the left; the lower tail is longer.

• Outlier: An observation that falls outside the overall pattern.

Center and Spread of Data

• Center: Value that splits the data in half, indicating typical values within the dataset.

  • Measures of central tendency include mean, median, and mode.

• Spread: Refers to the variation within the data.

  • Important measures include range, standard deviation, and interquartile range (IQR).

Stem-and-Leaf Displays (Stemplots)

• Definition: A stemplot or stem-and-leaf display effectively shows individual observations of quantitative data; suitable for small datasets (n ≤ 50).

• Construction Steps:

  1. Order the data from smallest to largest.

  2. Divide each number into two parts: the stem (leading digits) and the leaf (last digit).

  3. Label the bins using the stem.

  4. List stems in a column and record leaf portions in the corresponding rows.

  5. Provide a key to decode the stemplot.

Example: Stemplot for Prices of Walking Shoes

• Ordered Prices: 40, 60, 65, 65, 68, 68, 70, 70, 70, 70, 70, 74, 75, 75, 85, 90, 95

• Stem and Leaf Representation:

  • Stem: 4, 5, 6, 7, 8, 9

  • Leaves: 0, 0, 5, 5, 8, 8, 0, 0, 0, 0, 0, 4, 5, 5, 5, 0, 5

• Notes that the leaf '5' represents $75.

Back-to-back Stemplot

• Definition: This is effective for comparing the distribution of two groups side by side.

• Construction: Use the same principles as stemplots but position one group's leaves on one side and the other group's leaves on the opposite.

Histogram

• Definition: The most common graph for depicting numerical data which visualizes the distribution of an underlying variable.

• Description: Utilizes bars to represent frequency or relative frequency of measurements falling within specified equal-width intervals (bins).

Constructing a Histogram

• Steps to create:

  1. Decide on intervals of equal length (bins) for data.

  2. Use the left-inclusive method for class intervals; this determines where boundary values fall.

  3. Create a frequency table for intervals.

  4. Mark interval boundaries on the horizontal axis and frequency/relative frequency on the vertical axis.

  5. Draw the bars to represent the class intervals with heights according to frequency or relative frequency.

Example: Histogram for Prices of Walking Shoes

• Data for Analysis: Prices of walking shoes include: 40, 60, 65, 65, 68, 68, 70, 70, 70, 70, 70, 74, 75, 75, 85, 90, 95

• Use a bin width of 10 for the histogram.

• Totals from frequency table reveal distribution:

  • Class Intervals: [40; 50), [50; 60), [60; 70), [70; 80), [80; 90), [90; 100)

  • Frequency values corresponding to each interval.

Relative Frequency and Proportions

• Important calculations:

  • Determine the proportion of walking shoe prices falling on or above $70.

  • Percent of prices falling below $70 calculated using the frequency table derived from histogram.

Frequency Table Example:

Important Notes

• Data values are clearly retained with dot plots and stem-and-leaf plots but are lost in histograms.

• In bar charts (for categorical data), spaces between bars indicate distinct counts of categories.

• Conversely, in histograms, gaps indicate regions without data points, enhancing visualization of distribution gaps.

Conclusion

• Summary of methods to visualize and summarize quantitative data includes dot plots, stem-and-leaf displays, and histograms.

Acknowledgment

• Thank you for watching this video!