If They Say This About Taguchi Testing Then Run Don’t Walk Away

OK, that title got your attention! What I am talking about? Well, some people promoting Taguchi methods of testing suggest that you can eliminate under performing test runs during the test. Here is a quote from the guy that runs StomperNet’s test software:

Lets say you are running a L18 — this has 18 different landing page recipies. While the test is running you will naturally see a couple of recipies that are doing significantly worse than the others. As this happens you can shut off these recipies. You can keep doing this until you are down to two recipies — i.e. - a split test which will confirm the results from the teguchi test.

Read more

Your Awesome Web 2.0 Graphics Pack

Here is an awesome web 2.o graphics pack to give you a quick start in developing test factors. This is your’s to use as a user of our Taguchi Split Test software.

Here is a look at all of these graphics, giving you a break down of everything you get, along with full size samples… Read more

Installing Taguchi Split Test Software

One feature not mentioned in the video is that the code can be placed on a shopping cart page not on your domain and it will get tracked. This allows you to use the software on any site with an off site shopping cart. You do have to be able to place your code on the cart pages.

The setup loads files for your site in your site’s directory on our server operating in the Amazon EC2 Cloud. Using the Amazon EC2 Cloud allows for a highly reliable server and fast loading of the files by browsers. The number of sites on each of our Amazon EC2 servers is limited in order to maintain performance and allow for at least two years of data storage.

Another advantage of using Amazon EC2 is quick update of the system software as we add new features. It allows us to do the updates without any adverse impact on your site’s tracking and testing.

Easily Create Test Factors

The key to testing is the creation of your test design. With our software, you can create each test factor and its variations or levels using a WYSIWYG editor. This allows the full design to be done without any coding. But you can if you want to, because the editor does have an HTML tab.

You can also change the CSS and apply the change to only the test page or to a defined class across the entire site. This will allow you to change a background color or the font and apply the change across the site so that the visitor gets a consistent presentation.

There is also a Text edit button that allows you to specify a string and its replacement. This can be applied to only a single string or all occurrences of the string on the page.

As you develop test factors with variations, you can preview any combination you wish to by selecting the factor variations and click preview.

You can create several factors with just one variation on each and then use them all in a split test. The split test will create a page with all the variations applied and test it against the control page. Sometimes this is the quickest way to get started because you can generate a new best performing control to take into the Taguchi test.

The WYSIWYG editor makes the whole process friendly and easy.

Easily Place New Optimal Page In Confirmation Test

The confirmation test is important in establishing that the new optimal design will continue to out perform the control. This test tells you the true conversion rate you can expect from the new design.

Also, did you notice the split test feature? Sometimes you may already have a few good ideas on how to improve conversion. You can test these using a split test to create a new control to start with for your Taguchi test.