The graph on the left is not meaningful because the bars are nearly the same height. This scale makes it difficult to see any trends or changes from month to month.  However, the graph on the right is much easier to read because the scale does not begin with zero. It begins with the lowest value in the range.  The intervals are also different in this scale. An interval is the amount from one tick mark to the next on that axis.  The intervals on the y-axis in the first graph are 10, while the intervals in the second graph are two.

 

Logarithmic Scale

 

Sometimes it is necessary to use a logarithmic scale. A Logarithmic scale is used when there is a large range of values, and when the degree of change within that range in values depends on the size of the change in proportion to the value itself.  For example, when the difference between 1 and 10 is as important as the difference between 10 and 100 you use a log scale, when the difference between 1 and 10 is as important as the difference between 10 and 20 you use a normal scale.  Presentation of data on a logarithmic scale can be helpful when the data covers a large range of values because the logarithm reduces the data to a more manageable range.

Knowing Which Graph To Use

Drawing in Word:

There is help with drawing in word so you can put your concept map or thinking map into the Virtual Vee Map Template.  Go to the help with drawing in word file.

 

Knowing which Graph to Use:

Ann Marshall (2008) has written some instruction for using EXCEL for use by students or teachers.  Begin by looking at the data sets and decide which one(s) you would like to investigate (In Excel, highlight the data you want to put into graphical form and click on the graph icon at the top).  What relationships or comparisons are you interested in making?  What hypothesis would you like to test?  Know your questions and the general characteristics of your data first, Then decide which type of graph would best illustrate your data. 

 

Scatter (XY) plots – Scatter plots are used for examining relationships between two types of data.  If you know that one of the types of data depends on the other (for example, waves depend on wind), the dependent variable (effect) goes on the y-axis (vertical left) and the independent variable (cause) goes on the x-axis (bottom).  The dots are not normally connected in a scatter plot, though a ‘best-fit’ or regression line may be drawn through the points to illustrate the relationship.  The dots are connected ONLY if you expect that a measurement taken between the two x values would yield a y value midway between their associated two y values.  Go to the “Creating XY Scatter Plots” file

 

Bar (column) graphs – Bar graphs are used for making comparisons between discrete cases or to look for trends (usually over space or time).  Bar graphs are appropriately used when one of the axes (usually the x) is discontinuous - evenly spaced (e.g., dates) or non-numeric (e.g., station codes).   Excel uses the term ‘column’ for a bar chart where the x-axis (independent variable) is the one which is discontinuous and ‘bar’ for a bar chart where the y-axis is discontinuous. There are four sub-types of the bar graph. They are explained below. Go to the “Creating a Bar Graph” page to create a bar graph or any of the sub-types.

 

Clustered column (bar) graph – A clustered bar graph is used to simultaneously depict several series on one graph.  This is the same as putting multiple series on a scatter plot or multiple lines on a line plot.  Go to the “Creating a Bar Graph” file to create a bar graph or any of the sub-types.

 

Stacked bar (column) – Really a combination of two or more bar graphs into a single image.  This should be used only where the sum of the series has meaning.  For example, graphing particulate carbon for one series and dissolved carbon for a second series (which add to total carbon) is appropriate; adding temperature plus oxygen would not be appropriate because the total bar height would have no independent meaning.  Go to the “Creating a Bar Graph” file to create a bar graph or any of the sub-types.

 

Broken stick graph (100% stacked bar) – When comparing a two sets of percentage data, typically two pie charts side-by-side are used to illustrate the comparison.  However, in comparing multiple sets, a broken stick graph is more typical.  Like the individual pie charts, each column of the broken stick chart represents 100% subdivided into pieces.  Go to the “Creating a Bar Graph” file to create a bar graph or any of the sub-types.

 

       A 3-D Column is used to simultaneously compare 3 data sets which are believed to be simultaneously related.  The x-axis (horizontal) is used for the independent variable, the z-axis (vertical) is used for the dependent variable; the variable graphed along the y-axis (depth) may be a second independent variable or also dependent on x.  For example, if you make the hypothesis that wave height depends on both wind speed and water depth, you might graph wind speed (independent) on the x-axis, water depth (also independent) on the y-axis, and wave height on the z-axis.  Go to the “Creating a Bar Graph” page to create a bar graph or any of the sub-types.

 

Surface plot – a surface plot is similar to a 3-D column but should only be used for continuous data. Go to the “Creating a Bar Graph” file to create a bar graph or any of the sub-types.

 

Creating a Bar (Column) Graph with Multiple Independent Variables – Bar graphs are used for making comparisons between discrete cases or to look for trends (usually over space or time).  Bar graphs are appropriately used when one of the axes (usually the x) is discontinuous - evenly spaced (e.g., dates) or non-numeric (e.g., station codes).   Excel uses the term ‘column’ for a bar chart where the x-axis (independent variable) is the one which is discontinuous and ‘bar’ for a bar chart where the y-axis is discontinuous. There are four sub-types of the bar graph. They are explained below. Go to the “Creating a Bar Graph with Multiple Variables” file to create a bar graph or any of the sub-types.

 

 

Line Graphs – Line graphs are a hybrid of the scatter plot and bar graph.  They are used for looking at the relationship between two continuous types of data.  They are appropriately used when the independent variable is evenly spaced (e.g., whole numbers) or non-numeric (e.g., station codes) AND the information is expected to be continuous (e.g., you might reasonably expect that if you look at a station between these two geographically you would find an intermediate y value).  The points are connected in a line graph.  Go to the “Creating a Line Graph” file to create a line graph.

 

Pie charts – Pie charts are used to depict data indicating fractions (percentages) of a whole.  Go to the “Creating a Pie Chart” file to create a pie chart.

 

Excel offers many additional advanced graphing options; however, most of these have specific uses and should not be employed unless you understand their appropriate use.  For example, the donut graph which may look like a cool version of the pie chart is appropriately used only for cases where the series are all related (for example, they all depend on the same independent variable). 

 

Excel also offers many options for graphing which give a 3-D visual effect to bars graphs and pie charts.  These generally add nothing to the meaning, and may be visually misleading; for example, the ‘pieces’ to the forward edge of a 3-D pie chart appear larger than those to the rear because of the inclusion of the ‘edge’.  Always consider whether these visual effects add to or detract from the meaning and readability of your graph before using them.

 

Don’t worry if you are not positive you have the right type at first.  Excel makes it easy to change your mind if you decide after looking at your first graph that a different type would be more appropriate.

 

Scale

 

Scale is very important on a graph and must be formatted according to the range of values being represented. For example, look at the graphs below. Both graphs below contain exactly the same information the only difference is the scale of the y-axis.

Here are a few examples:

 

This examples below has the depth on the x-axis and the temperature and dissolved oxygen on the y-axis. It is testing the hypothesis that temperature and oxygen are each dependent on depth and comparing the relationship between temperature and depth with the relationship between oxygen and depth.  The one of the left shows both variables together on the left hand side.  The graph on the right shows the variables separated with the dissolved oxygen on the left and the temperature on the right.

This example below has the temperature and dissolved oxygen on the x-axis and the depth on the y-axis. Notice the y-axis has been reversed with the 0 at the top. This represents the water column.  This type of graph is referred to as a hydrograph and used almost exclusively by limnologists and oceanographers.  The graph is turned solely because it is easier to visually interpret depth when it is depicted this way.  Depth is still considered to be the independent variable in a hydrograph.

 

You can also use a bar graph for single data points, especially in cases where the independent variables (in this case station numbers) cannot be logically ordered. This is shown below with Secchi data.

You could also graph data over time.  Below is an example an x-y plot was used to test whether there was a relationship between temperature and depth and whether there was a relationship between dissolved oxygen and depth as well as to compare those two relationships.  A clustered column would also be appropriate since the data are evenly spaced.  A 3D column would be used only if you were also interested in the relationship between temperature and dissolved oxygen (or thought that dissolved oxygen might also depend on temperature as well as on date.  If you believe that the data are continuous and that, for example, the temperature on 5/28/2005 was 8^oC, then you could connect the dots or use a line graph.