Survey Analytics Updates: Weighting



Happy new year everyone!

The team over at Survey Analytics hope its been a good 2010 for everyone thus far. Every start of the year we're always making new years resolutions. With Survey Analytics we are looking forward to making many more updates and enhancements in 2010.

Here's what's been rolled out in January for Survey Analytics Enterprise Platform that we've been building over the past couple of months. Many of the updates are from a back-end resource/servers standpoint (which I am not going to bother you with) - but there are a few front end updates that you'll find interesting.

The Collaboration options have significantly improved and updated. Collaboration allows you to solicit feedback from stakeholders _about_ your survey. Its a simple way to send out a link to your boss/colleague and see what they think of the survey. Here is the kicker - they can also make _minor_ modifications to the survey (like correct spelling errors etc.) directly as they are taking the survey. All changes are logged for auditing purposes.

The Collaboration tool can be accessed by going to:

Login -> My Survey (Click on the Survey Status link) - Active -> Collaborate

Detailed Help:



Corporate compliance, branding and legal requirements many times require a standard format for all survey that go out of the door. We've added in a quick option that makes it easy to have standard headers and footers across all surveys (across all accounts) - this mitigates the risk of distributing surveys that are not approved from a branding and policy standpoint.

Detailed help on setting this up:



We've added in a new statistical tool for automatic weighting and balancing. At its simplest form, weighting/balancing allows you to adjust the data to account for sample bias. Sample bias occurs when your survey data (from your sample) does not accurately represent your target audience. Lets say for example, you are in the business of selling mens clothing. You also know that males form 80% of your customer base and purchasing decision. If you field a survey, and your survey response has 50% male and 50% female - you have sample bias. The data is leaning towards females, who constitute 50% of the survey data, but only constitute 20% of your customer base.

Detailed Help:



This enhancements came as a result of our friends from Ziff Davis pondering about it. The idea here is, if you have a large (or a subdivided) list of options with categories, visually it makes sense to group items together : Screenshot below:

Survey Software Help ImageSurvey Software Help Image

Detailed Help File:

Comments