Frequency Distribution Chart
Overview
Note: this chart is available with an Enterprise Services subscription only.
The Frequency Distribution Chart allows you to examine probabilistic results from simple returns (the default) or from any script that you can think of. The chart forms part of the statistical module that we are building in Optuma. Our goal is to take complex statistical concepts and present them in an easy to use way to give our clients the edge.
The default case is looking at weekly returns from a security. We can then see how likely we are to achieve the required returns. If the average returns were 0.5%, then we would not want to use a strategy that required us to obtain 2% returns. We need to be able to examine all the historical results (and possibly filter the outliers) so that we know what our probabilities are.
The chart is built by taking the range of possible returns and splitting that up into “bins”. A bin is simply a range of values. eg 1.0% to 1.1%. Anytime we get a result that falls into the range of the bin, we increment the count for that bin. Statistics 101 would tell us that we should see the highest counts (frequency) around the average. When we don’t, we need to explore the data to find out why.
There are four “moments” that describe a distribution plot.
1. Mean - The average of all the results.
2. Standard Deviation - The spread of the results around the average. We want it as small as possible.
3. Skewness - Is the peak of the curve, skewed to one side? It is calculated as the distance between the Mean and the Mode. A positive value means it is skewed to the left. Negative to the right. Negative skew is good for us when measuring returns.
4. Kurtosis - This describes the shape of the curve. A value of 3 is a normal Gaussian curve. Higher numbers means the curve is high and tight (this is good).
Remember the Mode is the bin with the highest count. It is not always the mean as outliers can effect the Mean.
To open a new Frequency Distribution Chart, click the New menu, expand the Single Code Chart section and left click Frequency Distribution Chart. The security selector will open, double click the code, or enter in the code you want to open and press Enter.
Actions & Properties
Actions
Clone Chart: Makes a carbon copy of the source chart alongside the original.
Print Chart: Creates a PDF file of the chart which can then be sent to a printer.
Restore Default Settings: Click this action if you have adjusted the default settings of the chart, and wish to return to the standard properties originally installed with Optuma.
Save Settings as Default: If you have adjusted any of the chart’s properties (such as the Colour Scheme or bar thickness, for example) you can save the adjustments as your new default setting. Each time you open a new chart it will display using the new settings.
Send To: Allows you to send the chart to an image file, or if you have the Publishing module to MS Word, Powerpoint, etc.
Properties
Date Range:** Set to Last Year by default, allows you to adjust the amount of historical data you can scroll back through on the chart (via the history slider).
Auto Scale: Allows you to set how the scale of the Frequency Chart is calculated (Current Values, Historical Min / Max, or Manually).
Script: Allows you to set the script the Frequency Chart uses in its calculation. By default it will be Change() however you can use any script which returns a numerical value (not designed to work with True / False scripts).
Bins: Allows you to select how many columns the Frequency Chart is split into. By default 20 bins will be used but this can be increased / decreased.
Log Normal: Switches the Frequency Chart to display values in a Log scale.
Remove Outliers: Removes the Top and Bottom 3% of results from the Frequency Chart.
Currency: Allows you to adjust the currency of the underlying symbol being used to build the Frequency Chart.
Bar Colour: Allows you to adjust the colour of the bars displayed on the Frequency Chart (green by default).
Bars on Screen: Sets how many bars from the underlying symbol are used to calculate the Frequency Chart. By default 250 is used, however this can be adjusted, either via this property, or via the history slider along the top of the Frequency Chart.
Show Normal Curve: Adds a curved line to the Frequency Chart which represents what the frequency distribution would look like if they were perfectly normal (ie fit the normal standard distribution given their mean and standard deviation).
Scales Font Size: Allows you to increase or decease the font size of the text labels in the Frequency Charts scales.
Show History Slider: Allows you to hide / display the history slider along the top of the Frequency Chart.