The following link leads to an animation that illustrates the effect of a sample size and the
number of classes on a histogram:
http://media.pearsoncmg.com/ph/esm/esm_larson_statlet_questions_2e/Sample_Size_Histogra
m_Statlet/histogram.html
Experiment with the animation, using the:
• Horizontal scrollbar to change the sample size
• Vertical scrollbar to change the number of classes
Respond to this question: “How do you think the sample size and number of classes affect a histogram?”
Subscribe to:
Post Comments (Atom)
Well in a histogram, the horizontal and vertical bars affect the data shown. The horizontal bar is typically quantitative and measures the data values in the histogram. The vertical bar measures the frequencies of the classes in the histogram. Any of the bars that are next to each other need to touch. These bars begin and end at class boundaries instead of limits. The class boundaries are numbers that separate classes without forming gaps between them.
ReplyDeleteEvan-
ReplyDeleteChanging the sample size is going to widen your pool of information or available data. This could allow for a more complete perspective. When changing the number of classes you're creating knowledge of the samples relativeness to that topic. Allowing you to decipher the differences.
Mel Bailey
ReplyDeleteI think even if you increase the sample size and classes the histogram would not be affected, it should still follow the same pattern. (it will just be spread out a little more)
If the survey was conducted correctly, increasing the sample size would not change the results largely; it would only fine-tune and make the results more reliable.
ReplyDeleteAs far as changing the number of classes, it would change only how the information is interpreted. Because a histogram is a visual tool, it must be calibrated to allow for the highest amount of information to be portrayed with the least amount of effort. As such there should be enough classes to properly separate the different areas, but not so many that one gets lost and is unable to interpret any meaning from the graph.
I found that the more sample size is introduced the more uniform the distribution of the histogram. However, the more classes that are represented, the larger the differences between the classes. Less classes mean a more averaged and uniform histrogram.
ReplyDeleteThe number of classes increases the amount of data (distribution) on the chart with the vertical scroll bar.
ReplyDeleteThe sample size seems to be a leveling or sharing of the data across the chart. Sample size affects the symmetry of the data.
“A histogram is used to graphically summarize and display the distribution of a process data set.” (Histogram)
The histogram shows us the most common system responses; the distribution or shape the data has; the symmetry of the data and if it is to the left or right or skewed; and if there are any outliers in the data. (Histogram)
Histogram
By Kerri Simon
Purpose Of A Histogram
http://www.isixsigma.com/library/content/c010527c.asp