# What Are the Different Types of Histogram Interpretation?

There are many different types of histogram interpretation, determined by the overall shape of the graph. The two main distinctions are symmetrical histograms and asymmetrical histograms. Within those two major distinctions are a number of other distinctions, depending on the distributions of the graph. Understanding the various types of histogram interpretation can let analysts know something about the data at the first glance.

The normal shape of a histogram is known as the bell shape, or the bell curve. The highest number of data points are located near the center of the graph, with increasingly lower amounts of points at each end, moving away from the center. When a line is drawn, roughly using the tops of the bars as reference points, it resembles the shape of a bell. This is the pattern that occurs most often when analyzing things occurring in the natural world.

Two typical variations of the symmetrical histogram interpretation are the non-normal short tailed and the non-normal long tailed. In these cases, the data points tend still be mostly even on either side, but there is some difference in the distribution. In a short-tailed histogram interpretation, the data points tend to bunch up around the center. In a long-tailed interpretation, the data points tend to be more spread out, but still mostly evenly distributed on either side.

Another variation of the symmetric histogram is symmetric with outliers. In this case, there may be significant gaps within the data sets that leave gaps in the histogram. Despite that, the histogram remains relatively symmetrical because the outliers appear on both sides. In some cases, outliers may be thrown out because they are not statistically significant.

The other major type of interpretation for histograms is the asymmetrical interpretation. Like the other major division, asymmetrical histograms can further be broken down into subdivisions. Asymmetrical histograms are also known as skewed histograms, because the data points favor one side of center or the other side. Outliers may also exist in skewed histograms, but usually do not affect the shape or averages, unless they are extreme outliers.

A skewed or asymmetrical histogram interpretation is often difficult to truly accomplish because the data points are heavily favored to one side or the other. Often, averages can mean very little in such data sets because they are so skewed. The average may not be truly in the middle of the histogram, and this tends to reduce its statistical significance.

## Discuss this Article

## Post your comments