Before we board the jet at Data Designation Gate 1, we will need to obtain a clear understanding of the value of data, how data is compiled and how it will be assessed.

Value of Data:

Any effective business plan contains correctly compiled and analyzed data. Good market research and resulting data can send a company in a new and more profitable direction. Great marketing plans, based on solid business plans incorporate data as its cornerstone. Pre- and Post- Advertising campaigns rely on data to keep score on the effectiveness of the ad campaigns, expenditures, tag lines, ROI and more.

Data as an Asset Class:

As of March 2011, some companies are transforming data into a “data asset class” model: Excerpt from the Institute For the Future:

“ At this year's World Economic Forum, as the Wallstreet Journal reports, "executives and academics gathered to discuss how to turn personal data into an "asset class" by giving people the right to manage and sell it on their own behalf." And this discussion isn't just theoretical.  Startups like I-Allow and Personal are allowing people to essentially gain a share of the profits that company's currently receive for selling their data.

In addition, the data designation asset class is also being used by companies as a non-profit “donation vehicle”, replacing monetary contributions.

In effect, not only is data valuable for your business, but data is also a viable asset that justifies monetary value.

Compiling Data: All Data is Not Equal:

Have you ever noticed a situation whereby the application of compiled data did not yield the desired results?  In cases such as these, the problem more than likely arose from data not being gathered correctly.

Weighted and Ascripted Data:

Weighted data generally means that the most common type of average for the data points is utilized instead of each of the data points contributing equally to the final average, with some data points contributing more than others.

A basic example of a weighted scheme can be seen within a rudimentary demographic survey.

Example 1:

A survey company targets two thousand adult respondents, aged 25 – 54, homeowners, whose income levels exceed $150,000 annually. The target respondents are divided equally between the men and woman, i.e., one thousand for each respondent group. The survey is conducted by phone and must be completed in 90 days. Upon reaching the 90-day time limit, only 750 respondent answers were gathered from male respondents, as opposed to 975 respondent answers compiled from female respondents.

The survey company decides to drop 225 of the answers obtained from the women to make the survey appear to be equal -750 males and females each. The question becomes, which two hundred and twenty five women respondent answers get dropped? The answers listed above seven hundred and fifty, or the answers listed from first two hundred and twenty five?

This approach can be dangerous when a means average is applied to the overall number as the actual positive numbers are replaced by a negative trend. Be aware of how a survey company weights and/or ascripts data.

Many statisticians believe that the mainstream public should be informed of the counter-intuitive results in statistics such as Simpson's Paradox.

In probability and statistics, Simpson's Paradox (or the Yule–Simpson effect) paradox in which a correlation present in different groups is reversed when the groups are combined.

An example of Simpson’s Paradox:

“A real-life example is the passage of the Civil Rights Act of 1964 in the United States. Overall, a larger fraction of Republican legislators voted in favor of the Act than Democrats.

However, when the congressional delegations from the northern and southern States are considered separately, a larger fraction of Democrats voted in favor of the act in both regions. This arose because regional affiliation is a very strong indicator of how a congressman or senator voted, but party affiliation is a weak indicator.”

Data Ascription:

MatterMax Media is of the opinion that this method of gathering data is questionable and should be avoided like the plague. When the ascription rule is applied to our example of the 2,000 adult respondents, aged 25-54, the men’s respondent level is raised to nine hundred and seventy five to match the women’s respondent level.

When you extrapolate and add 225 five male respondent answers to the overall respondent pool, you are now flirting with a possible 23% disparity among the men respondents and thus the outcome becomes skewed.

A Data Ascription Example:

Among the major U.S. syndicated readership studies, MRI is the most prominent user of ascription. MRI’s approach to ascription is called “Donor-Recipient.” Each respondent who does not return a PIB is matched up with one who did and the entire PIB is copied over. The primary basis for the matching process is usually demographics. MRI establishes criteria and compares recipients against potential donors to identify the closest possible match. In recent years, as MRI’s completion rates for the PIB have declined, it has become necessary to ascribe data for a growing proportion of the sample. This has caused worry in a number of sectors within the research and data user communities.

Assessing the Data:

Once you have successfully and effectively acquired your data, the task of assessing the data and deciding how you would most likely use it is the main priority.

The most efficient way to understand or assess your data is with a spreadsheet using tables. Many survey companies provide you with a statistical spreadsheet so you can optimize the impact of the data at a glance. Obviously the more complex the data survey, the more time it will take to grasp all the moving parts.

MatterMax Media recommends that you get familiar with surveys, how to construct them, how to read them, and more importantly how to create strategies based on survey results.

Survey Flight 411 is ready to board and please have your survey documents ready for business travel.

Next week, MatterMax Media’s, Today’s Marketing Blog will put forward Step two of the series, “Flying High - Data Crunch & Munch, Ground Level Check-In.” Understanding data is critical to all your business and marketing initiatives.

MatterMax Media is a full service integrated marketing agency located in Stone Mountain, Georgia. MatterMax Media provides strategy, technology, marketing and training for individuals, businesses and government. Today’s Marketing Blog focuses on Entrepreneurship, Marketing and Web Matters. When you require assistance with your branding/marketing strategy, feel free to contact us.