# Get More Information From Your Data With Tableau's Analytics Functions

The analytics functions of Tableau are some of its least utilised tools. This blog will give you a brief overview of the whole analytics pane, showing the amount of extra information that you can bring to a graph with a simple drag and drop. To get to the Analytics pane, you need to click the "Analytics" tab in the top left corner of the screen.

Once there, you will have access to a lot of different reference lines and other analytics tools. These can be applied to a whole table, each pane of the table or even to each cell, as well either of the two axes (chart dependant). These can give simple averages or constant lines to the graphs, complex box plots or forecasts for the future. There are a lot of options to choose from, so it's important to have in mind exactly what you want to show and only then find the option that suits your needs.

### Breakdown of the analytics tab

Below is a brief description of everything in the analytics tab in Tableau:

**Summarize****Constant Line -**A line with the value that is input.**Average Line -**A line showing the average summed up to the level specified.**Median with Quartiles -**The middle number and the lines which contain 25% and 75% of the values.**Box Plot -**The same as above but with more lines and at different values.**Totals -**Gives the totals for a table.**Model****Average with 95% CI -**Gives the average and a customisable confidence level line.**Trend Line -**Finds the trend of your points (the line closest to the most points).**Forecast -**Forecasts your data for the future.**Custom****Reference Line -**Plots a line based on any measure in the visualisation.**Reference Band -**Maps a box between two customisable lines.**Distribution Band -**Same as above but with percentages of values.**Box Plot -**The same as a box plot but with the custom menu open by default.

### Use cases of common Analytics Functions

My personal advice is to test and learn to see what works for you. It is always important to know what you want to show before you start using the Analytics pane, as it will allow you to do things which aren't best practice. It's very easy to confuse an average line with a median line, for example, unless it is labelled well.

To avoid clutter, only add items from the Analytics pane when they are entirely needed, but be careful not to leave out important information. For example, an average line can make it easier for users to understand a graph that contains a lot of data points.

**1. Average Line**

In the graph below, you can see the difference between applying an average line to the Pane as opposed to a table. When applied to the table it would give one average line that would be the same for both sections of the bar chart. By applying the average line to the pane instead, it is split by team. You could also apply the line to the cells which would give each bar its own average line (not that this would be useful in most situations). In this situation, it would make more sense to apply the average line to the panes as it clearly shows the differences between the two teams. If, however, we wanted to see who performed better than average out of both teams, a combined average line would be the way to do this.

**2. Constant Line**

The constant line can be really useful for a quick analysis when calculations or a more robust solution aren't needed. This works similarly to the average line, but with a specified value instead. I found this very useful in the Tableau certification where the aim is arriving at the correct answer quickly, not creating fully functioning dashboards.

**3. Trend Lines**

Trend Lines allow users to easily see the general trends in data, which is especially useful when viewing a scatter chart like the one below, based on Sales and Profit for EU Superstores.

When using the trend lines, choose the correct option for your graph: Linear, Quadratic, Exponential or Polynomial, as they can show drastically different things. The linear option shows the most insight quickly as humans are better at judging straight lines. For example, in the graph above you can instantly realise that the greater the sales the greater the profits (generally). Meanwhile, the graph below illustrates how the application of an incorrect trend line that is ill-fitting to the data could lead to incorrect assumptions. Figure 4 can mislead people into thinking that profit could skyrocket if they manage to get past a certain sales threshold.

**4. The Undo Function**

The Undo function (Ctrl + Z) is very useful because it can be difficult to remove the reference lines by clicking on them or dragging them off, as the line might be hidden behind data points.

**5. Editing a Reference Line**

After clicking on a reference line, it is also possible to edit it with custom text, change the line type or change where the line is applied to.

Given the myriad of features available and how hard it is to find a perfect option that would show everything you need, it's important to know what you want to see before finding the best way of showing it.

## Tim Day

### About the author

Tim Day is a Graduate BI Developer at Concentra. After graduating from Warwick with a bachelor's degree in Mechanical Engineering, he wanted to continue working where he would have the freedom to create something visually appealing. Having started at Concentra as an intern, he loves the data visualisation part of the job and has also grown to love the data warehousing side. He especially likes providing insights into sports events, as this data is often not shown in a captivating way.