Exercise 10: Histograms in Prism

Go to parent GraphPad Prism statistical analyses

We go back to the table (created in the section on entering your own data).

Suppose we want to calculate the mode of each of the two Y-columns. The Y columns contain unranked categorical data, numbers representing the predominant method of transmission of a disease in a dry and a humid climate. This means that the mode is the only descriptive statistic for the center of the data that you are allowed to calculate. Remember the mode is the value that appears most often in a data set and may be calculated for all types of data.

The easiest way of calculate the mode in Prism is to calculate the frequency distribution table and see which data value has the highest frequency. The frequency distribution is a table that shows for each column the frequency of each data value (the number of times it occurs in that column).

Calculate the frequency distribution of the Y-columns.
Calculating the frequency distribution is a statistical analysis: Click Analyze in the Analysis section of the top toolbar Select to perform a Frequency distribution from the Column analyses section on both Y-columns Click OK Explanation of the parameters. Use the default parameters for our example and click OK. The analysis returns the following Results table:

The frequency distribution table shows that the dry climate column has two modes: 4 and 5, both occurring thrice whereas the humid climate column has one single mode: 5.

Frequency distributions are graphically represented by histograms: the frequency is plotted along the Y-axis, while the X-axis displays the bins.

Look at the corresponding frequency distribution histograms.
Click the Histogram graph:

Frequency distributions and histograms are by definition discrete:

• For discrete data values, the bins correspond to the values as is the case in our example here. The numbers in the Y columns represent methods of disease transmission so they are discrete numbers.
• For continous data values, discrete intervals or bins will be created:
  e.g. bin with center = 1 and width = 1 then all data values between 0.5 and 1.5 belong in this bin and the frequencies of all members of a bin are added to calculate and plot the bin frequency.

The labels on the X-axis are messy. Instead of showing the centers of the bins as labels on the X-axis, Prism repeats the names of the two columns (Dry climate and Humid climate) that are already included in the legend. This is because we plotted two histograms on one graph. You will see that the labels are plotted correctly if you repeat the analysis on a single column.

Create an individual frequency distribution histogram of column Dry climate.
Proceed in exactly the same way as for both columns except in the Analyze data window you have to deselect column Humid climate and start the bins of the histogram at value 1: The histogram that is generated now looks better with data values used to label the bin centers on the X-axis: