VizWiz

Launch, grow, and unlock your career in data
Showing posts with label standard deviation. Show all posts

June 4, 2024

Find Red Flags in Your Data in ONLY 5 MINUTES with Control Charts

, , , , , , , , , , , , , No comments
If you like this video, you'll love learning from me 4 hours per week in Next-Level Tableau. Join here.

Control charts are one of the best charts you can use for identifying outliers in a series of measurement. So what are they?

Control charts are used to monitor whether a process is performing consistently over time. It's basically a line graph that tracks data points collected at specific intervals, but with three key additions:

1. 𝗔𝘃𝗲𝗿𝗮𝗴𝗲 𝗹𝗶𝗻𝗲: This horizontal line represents the average performance of the process based on historical data.
2. 𝗖𝗼𝗻𝘁𝗿𝗼𝗹 𝗹𝗶𝗺𝗶𝘁𝘀: These are two additional horizontal lines, one above and one below the center line. They are typically 2-3 standard deviations from the average, but can be whatever number of standard deviations work for your situation. These limits reflect your "stable" range.
3. 𝗢𝘂𝘁𝗹𝗶𝗲𝗿 𝗶𝗱𝗲𝗻𝘁𝗶𝗳𝗶𝗰𝗮𝘁𝗶𝗼𝗻: Color-coding the outlier marks helps you more easily identify the problems.

The line chart you create will help you see if measurements fall within the control limits. 

- If they do, it suggests the process is in control. 
- If they fall outside the control limits, it indicates a potential problem that needs additional analysis.

Control charts are widely used for quality control purposes (especially in manufacturing), but they can be applied to any process where you want to track performance over time. 

Download the workbook here.

April 13, 2021

How to Calculate a Z-Score

, , , , , , , , , , , , No comments
A Z-score is a numerical measurement that describes a value's relationship to the mean of a group of values. Z-score is measured in terms of standard deviations from the mean. 

  • If a Z-score is 0, it indicates that the data point's score is identical to the mean score. 
  • A Z-score of 1.0 would indicate a value that is one standard deviation from the mean. 
  • Z-scores may be positive or negative, with a positive value indicating the score is above the mean and a negative score indicating it is below the mean. 

The calculation you need is Tableau is: 

( SUM([Profit]) - WINDOW_AVG(SUM([Profit])) ) 
 / 
WINDOW_STDEV(SUM([Profit])) 

Replace the SUM([Profit]) with whichever measure you'd like to use at the aggregation that makes sense in your data. 

Get the data used in the video here - https://data.world/vizwiz/car-sales-mock-data

March 9, 2021

How to Create a Control Chart

, , , , , , , , , , , , , , No comments
Control charts are used to monitor the stability and control of measurements over a period of time. There are four elements to make an effective control chart. 

  1.  A control chart is a time series graph.
  2. A line across the time series that represents the mean of all of the measurements in the graph. 
  3. Upper and lower control limits (UCL and LCL) that are displayed as a reference band across the view at a specified number of standard deviations from the mean. 
  4. Indicators to show which measurements are "out of control". 

Typically, any measurements that are more than three standard deviations from the mean are considered unlikely and therefore outside the control limits. However, it is also common to consider measurements that are more than 1 or 2 standard deviations from the mean as a form of analysis. 

In this video, I show you how to create a control chart that allows the user to specify the number of standard deviations at which to plot the upper and lower control limits.

April 19, 2017

Workout Wednesday: Bollinger Bands and Tableau Stock

, , , , , No comments
Emma had a cheeky grin on her face today when I asked her about Workout Wednesday. I'm fairly sure she was convinced that she had something tricky up her sleeve for me because, well, we're a bit competitive.

This week she challenged us to build a Bollinger Band chart based on Tableau's stock performance.
Fortunately for me I had already done nearly this exact chart back in 2014 as a tip here and as a video here. Heck, it was even based on Tableau's stock! How convenient is that!

Emma threw in a couple nice nuggets in her tooltips that required a couple calcs, but nothing overly complex. The trickiest bits are the table calcs you need for the lower and upper bounds. Mostly everything else is formatting the view.

Thanks for the challenge Emma! I'll be extra mean next week because you seemed excited about that.

Subscribe to: Posts ( Atom )