When would I use this?
Error bars are a representation of data variability or uncertainty often displayed with graph results. They are a simple way to provide a general idea of how far the true value might be from the displayed value. Error bars are not standardised so the measure of the error bar should be stated in the graph or supporting text. It is often represented by one standard deviation above and below the value given.
It is included in most analyzing tools and will usually be made available if the user would like to include them. Error bars provide a very simple way of gauging whether there is a significant difference between groups.
Error bars are good indicators of difference in general, but can not identify statistically significant differences.
An example is provided here to evaluate the correlation of temperature measured by temperature probes 1, 2 and 3. This dataset includes the temperature of 20 patients. A separate column with random data generated for three artificial probes is also produced. Both graphs can be produced with error bars, showing variability in their data respectively.
Download above example excel file ‘Error Bars for Multiple Variables Correlation’.
- A file is provided as an example
- A total of three columns are present, with one representing the temperature of each probe
- Open rBiostatistics >> Correlation >> Multiple variables >> ↬ Analyze
- Browse and upload the Excel file
- Note that you must choose file type (.xlsx or .csv) as appropriate
- .csv files also need you to define your separator
- Select the variables that you would like to include in your analysis
- In this situation, we want to include all three (Probes 1, 2 and 3)
- Various tabs are available to view the statistical output on the top
- ‘Table’ tab displays the dataset itself
- ‘Cronbach alpha’ tab provides the results
- ‘Plot ‘ tab shows the correlation plots as a matrix (3x3 matrix for 3 variables, 4x4 for 4 variables, etc)
Written by Ka Siu Fan and Ka Hay Fan