Versta Research Blog

Versta Research Blog

About Versta

Versta Research is a marketing research and public opinion polling firm that helps you answer critical questions with customized research and analytical expertise.

Explore Versta

Versta Research Blog

Explore industry trends, research methods, and tips for your own research projects in the Versta Research Blog. All opinions are our own, and some may change over time.

First time reader? Check out the Best of the Blog for the most popular posts from almost 10 years of blogging. We’re glad you’re here.

How Would Hemingway Present Your Research?

How Would Hemingway Present Your Research?

I’m working on a presentation with a research colleague at Wells Fargo for the upcoming ARF (Advertising Research Foundation) Re:Think 2015 conference.  The challenge?  Getting it streamlined and condensed so that we can deliver the whole thing within a strict timeframe.  All the research, all the insights, all the business outcomes from a huge national…

Read the rest of this entry
Stat Testing: A (Too) Easy Crutch

Stat Testing: A (Too) Easy Crutch

Those of us who do a lot of survey research spend tons of time poring over statistics and reading data tables.  And no matter what all the latest clever tools promise, there is no shortcut to reading page after page after page of data or tables or charts, and discerning the patterns or lack thereof.…

Read the rest of this entry
High Response Rates Hurt Data Quality

High Response Rates Hurt Data Quality

An irony of survey researchers’ obsession with high response rates is that higher response rates often hurt data quality.  How can that be?  It happens because aggressive recruiting boosts the participation of people who provide less reliable information.  Two academic articles published in a special issue of Public Opinion Quarterly on “total survey error” nicely…

Read the rest of this entry
A Statistically Significant Cartoon

A Statistically Significant Cartoon

In Turning Data into Stories we pointed out that numbers have no inherent meaning.  There are no essentially big or small or significant numbers, for example—they only become big or small or significant within the context of specific research questions and a range of possible answers. The same is true for p-values by which we…

Read the rest of this entry
Versta Research Post

Testing Your Data for Illusions

Here’s a useful way to think about statistical significance.  When looking at your data, what’s the probability that it looks like something is there, when in fact nothing is there.  Randomness in data (because of sampling) often causes illusions.  So testing for significance is all about measuring whether the patterns we see in our data…

Read the rest of this entry
Scrolling vs. Paging on Mobile Surveys

Scrolling vs. Paging on Mobile Surveys

As more and more people use smartphones and mobile devices to fill out surveys, basic survey design decisions need to be revisited again and again.  How should surveys be laid out visually?  How should answer scales be constructed?  How should people be recruited to take surveys? Some of the latest answers to these questions come…

Read the rest of this entry