- Compare data sets by describing their shapes, centers, spreads, and outliers
Which one should I use?
We used two types of graphs to analyze the distribution of a quantitative variable: histograms and dotplots.
- Some observations about histograms:
- Individual variable values are not visible.
- Grouping individuals into bins of equal-sized intervals is particularly useful when analyzing large data sets.
- We can easily use percentages, also called relative frequencies, to describe the distribution.
- Descriptions of shape, center, and spread are affected by how the bins are defined.
- Histograms can make it easier to identify skewness and modality (i.e., whether the distribution is symmetric, skewed, unimodal, bimodal, etc.), particularly for large data sets.
- Outliers may not be as apparent in histograms, especially if the bin width is too large, which can mask the variability in the data.
- Some observations about dotplots:
- Individual variable values are visible, particularly when the data set is small.
- Descriptions of shape, center, and spread are not affected by how the dotplot is constructed.
- We can accurately calculate the overall range (largest value – smallest value).
- Dotplots can make it easier to identify outliers and gaps within the data due to the visibility of individual data points.
- Dotplots are most effective for smaller datasets, as they can become cluttered and less informative with larger datasets.
How do we decide when to use a dotplot and when to use a histogram?
There are no rules here. Each type of graph can highlight different aspects of the data.
- Size of the Dataset: The choice between a dotplot and a histogram often depends on the size of the dataset. Dotplots work well for small to moderately sized datasets, while histograms are better suited for larger datasets.
- Detail Required: Dotplots provide detail at the individual data point level, which can be useful for in-depth analysis, whereas histograms provide a summary view, which can be useful for identifying general patterns.