Webinar: How to Run Discrete Choice Conjoint Analysis

May 15, 2012 By Leave a Comment

Steps

Editor’s Note: Today’s post was originally published on the Survey Analytics blog.

Discrete choice conjoint analysis is a popular marketing research technique that helps you determine the optimal mix of features in a new product or service.

Survey Analytics invites you to a complimentary one-hour webinar, “How to Run Discrete Choice Conjoint Analysis.” The webinar is on Tuesday, May 22nd at 10am Pacific Time / 1pm Eastern Time / 6pm Greenwich Mean Time.

Click this link to register for the webinar.

The basics of discrete choice conjoint analysis are not hard to understand. In just one hour, you will gain an understanding of how to design, conduct and analyze a discrete choice conjoint analysis project.

This webinar will help you understand:

  • What discrete choice conjoint analysis is
  • The theory and logic behind discrete choice conjoint analysis
  • When to use discrete choice conjoint in your research
  • Specific case studies of how others have used discrete choice conjoint
  • How to design a discrete choice conjoint project
  • How to write a discrete choice conjoint questionnaire
  • How to analyze the results of a discrete choice conjoint project

The webinar will feature Survey Analytics’ Enterprise Research Platform, with a newly enhanced discrete choice conjoint module, including such features as integrated d-optimal design generation, design import and upgraded part-worth calculations using maximum likelihood estimates.

The webinar will be conducted by Andrew Jeavons, President of Survey Analytics.

Anyone who attends the webinar or downloads the video and slides afterward will get one complimentary month of Survey Analytics’ discrete choice conjoint capability.

Click this link to register for the webinar.

Filed Under: Events, How-To, Market Research Tagged With:

5 Awesome Free Online Data Tools from the U.S. Census

May 11, 2012 By Leave a Comment

Too often in the day to day business of research, we forget that there’s an astounding set of data resources provided by the U.S. Census Bureau. Doubtless other U.S. federal agencies and statistical agencies in other countries have some nice data goodies for us, but the U.S. Census Bureau is the treasure trove.

Here are 5 of my favorite free online data tools provided by the U.S. Census Bureau.

1) The American FactFinder

http://factfinder2.census.gov/faces/nav/jsf/pages/index.xhtml

The American Fact Finder is often the best place to start on the Census Bureau website. It is a user-friendly front-end to a vast amount of information made available by multiple Census Bureau initiatives, including the Decennial Census, the American Community Survey, and a number of economic surveys.

There is a helpful search interface that allows you to narrow down data by topic (people, housing, business, year, etc.), geography, race and ethnic group, and industry codes.

Or you can use the Quick Start search box to find data using just a few criteria – sort of like using the “I’m feeling lucky” button on Google.

You can also search your own (or any) street address to find out lots of relevant information, including county, town, block, census tract, metropolitan statistical area, congressional district, state legislative district, school district and more.

The American Fact Finder

The American Fact Finder

2) The 2010 Census Interactive Population Map

http://2010.census.gov/2010census/popmap/

This is an interactive visualization of data from the 2010 decennial census.

You can interactively drill down on the map in order to see a map visualization of a particular community on a number of criteria, including total population, race, ethnicity, age, sex, and household characteristics.

The map shows various geographic levels, from states down to census tracts, color coded on criteria from dark (most populous) to light (least populous).

You can also choose up to 5 locations to compare them on the same criteria, and you can even embed the interactive data you select on a website.

2010 Census Interactive Population Map

2010 Census Interactive Population Map

3) County Business and Demographics Map

http://www.census.gov/cbdmap/

The County Business and Demographics Map is very similar to the Census Interactive Population map, except it depicts business data rather than population data.

The County Business and Demographics Map

The County Business and Demographics Map

4) DataFerrett

http://dataferrett.census.gov/

DataFerrett

DataFerrett

In true federal style, the Ferrett in DataFerrett is an acronym (for Federated Electronic Research, Review and Extraction & Tabulation Tool). Coincidentially, it helps you ferret out the right data.

DataFerrett helps you identify, extract and recode data across federal, state and local surveys and statistical data, including both one-off and longitudinal datasets.

With DataFerrett you can search for the right variables and put them in something called a Data Basket.  From the Data Basket you can create spreadsheets, graphs, maps, PDFs and more right within the tool. And of course, you can download the data.

5) Censtats Databases

http://censtats.census.gov/

Looking to skip the bells and whistles and go straight for some of the most commonly requested data? The Censtats databases may be the place to look.

The Censtats databases are a good place to find quick tables on things like state and county population and business data. With the Censtats databases you can run these simple searches, and you can also download the relevant data files.

The Censtats databases also include information such as building permits, international trade data and housing data.

What about you? What are your favorite places to get data from the U.S. Census? How about from other agencies in the U.S. or other countries? What cool data tools can you point us to?

Filed Under: Government, How-To

5 Ways to Avoid Creating Dead Robot Respondents

May 10, 2012 By Leave a Comment

Dead Robots“When the individual’s behavior and consciousness get hooked to a routine sequence of external actions, he is a dead robot, and it is time for him to die and be reborn. Time to ‘drop out,’ ‘turn on,’ and ‘tune in.’

- Dr. Timothy Leary

OK, it’s no longer the 1960s, but the words of Dr. Timothy Leary are eerily prescient about the current state of survey research.

Allow me to explain.

When we expect respondents to take the same old boring surveys, when we misuse their time, and when we treat them with less than full respect, we cannot expect them to feel good about what they are doing.

However enthusiastic they may be about helping us help our clients, they eventually, understandably, become “dead robots,” responding in a rote fashion until they just can’t take it anymore.

Naturally, “dead robot” respondents provide lesser quality data, and, they are much more likely to drop out of our surveys.

We could all use tips and reminders about how to keep respondents “turned on” and “tuned in.” Here are 5 suggestions for you to consider using in your surveys.

And no, I’m not suggesting using any of Dr. Leary’s preferred methods.

Note: Ivana Taylor at the QuestionPro Blog recently had an excellent post with a couple of suggestions for minimizing drop-outs, which I will borrow as suggestions 1) and 2).

1) Allow Respondents to Save and Continue Later

Your respondent is halfway done with your questionnaire, and the phone and doorbell ring simultaneously.

Why not give the respondent the option to save their progress and continue taking the survey at a more convenient time? If you don’t allow this option, you’re encouraging people to close their browser and say, “oh, forget it.”

2) Set a Time Limit and Provide a Timer

If you set a time limit for the completion of a survey, along with a built-in timer, you are encouraging the respondent to give a higher level of focus on the task.

Think about it, if you are trying to finish the survey within 10 minutes, you are concentrating and working hard. You don’t want to drop out because you are in a race with yourself and you want to see if you can meet the challenge.

And now, here are three more suggestions:

3) Keep Your Survey Short

Write your survey. Cut it in half. Then cut it in half again. Then maybe, just maybe, you can add a few questions back in.

For years I’ve been hearing people talk about the importance of keeping surveys short. With the advent of mobile surveys, that advice is even more important. Yet I keep hearing horror stories about 30-minute, 40-minute or even longer questionnaires.

Stand up for your respondents by cruelly and efficiently cutting out all the fat, and maybe even some bone.

If you’re asking respondents to fill out a questionnaire, ask yourself, “Would I do this survey?” I think the answer may be revealing.

4) Provide a Progress Bar

A progress bar is a merciful thing. And it’s a smart thing. Without it, respondents are left guessing how much longer they will be completing your questionnaire.

Without a progress bar, a respondent could drop out just a few questions from the end of the survey. With a progress bar, respondents at least have a sense of the task at hand. Honesty is appreciated and goes a long way to engendering loyalty.

If your survey software offers a progress bar option, use it. If it doesn’t, consider looking for new survey software.

5) Make the Survey Convenient

If you make the survey convenient for the respondent, they will reward you with their responses and with quality data.

First and foremost, for online surveys your default assumption should be to offer the questionnaire on a traditional desktop/laptop web browser, and offer a mobile option.

Of course, this can backfire if your survey has not been properly tested and is thus terrible looking, or even completely messed up, on a mobile device. Depending on your audience, you should also consider offering offline options as well.

These are just a few options to consider for keeping your respondents “turned on” and “tuned in.” Fundamentally, it boils down to putting yourself in the respondents’ shoes and creating a questionnaire that you yourself would realistically complete.

Please share your ideas for keeping respondents engaged in your survey in the comments section below.

Filed Under: How-To, Market Research Tagged With: ,

How to Do TURF Analysis

April 25, 2012 By Leave a Comment

TURF AnalysisSpringtime is here! What better time to dust off your tools, including a nifty but underutilized method called TURF Analysis?

No, I’m not talking about something in your yard or garden.

I’m talking about the market research analytical technique called TURF Analysis. TURF is an acronym which stands for “Total Unduplicated Reach and Frequency.”

TURF Analysis is a somewhat fancy term for a pretty simple concept and associated analytical technique (but we researchers love fancy words, don’t we?).

What is TURF Analysis?

TURF Analysis is a technique that allows you to assess which combination of products and services will allow you to appeal to the greatest number of customers.

It is a simple improvement on the most common analytical technique, which is a simple frequency analysis.

Reach is a term derived from media research. It means how many people you contact.

Frequency, of course, means how often you are in contact with the people you reach.

When Do I Use TURF Analysis?

Have you ever asked:

  • Which combination of products or services would sell the best?
  • How do I determine which marketing and placement campaigns are driving consumers?
  • What is the best way to spend marketing dollars on a limited budget?

When you ask these questions, it’s time to conduct TURF Analysis.

How Do I Conduct TURF Analysis?

Several survey software packages include TURF Analysis capabilities. Here is a hypothetical example of how to run TURF Analysis using Survey Analytics software.

A bank is looking to offer credit cards to customers, and it asks a survey question about the credit cards consumers use: Visa, Mastercard, Amex or Discover.

Here are the results using simple frequency analysis:

Credit Card Frequency

What matters is not which credit card is used by the most consumers, represented by the frequency table. What matters is which combination of credit cards offers the greatest total reach. Because if a consumer holds both a MasterCard and a Visa, you can reach them by either means.

The software allows you to look at the reach of various combinations of cards.

Total Unduplicated Reach

The result of this calculation will be the percentage of consumers that have either MasterCard or Visa.

Of course, it would be tedious to look at every combination by hand. The “simulator” feature allows you to look at every combination under a specific count. In other words, you can look at every combination of 2 cards, then every combination of 3 cards, etc.

Simulator

And now you can see the unduplicated market share for each combination of 2 cards, like so:

Simulator Output

Of course, different options have different costs of implementation. The cards will not cost the bank the same amount to implement. So they are faced with a trade off between cost and opportunity.

The price modeling function of the TURF Analysis simulator allows for looking at different price scenarios, allowing you as the researcher to look at a balance between cost and opportunity. Here is a snapshot of the output.

TURF Analysis Price Modeling

Finally, the line optimization function allows you to set a minimum reach, then see which combinations get you above that threshold.

I hope this brief explanation of TURF Analysis has been useful, and I hope it’s helped you cover new ground. Enjoy TURFing!

 

Filed Under: How-To Tagged With: ,

Think Beyond iPad for Tablet Surveys

February 24, 2012 By 1 Comment

OSLogosResearchers, when you read about companies equipping their employees with iPads, I know you’re dreaming about beautiful, feature-rich, touch-based surveys for the B2B market.  In fact, this type of tablet-based survey is already being done today by the likes of SurveyPocket and others.

You need to start thinking beyond just the iPad, though.  The corporate market for tablets is up for grabs, according to a report by the Financial Times.

The report notes recent research by the NPD group indicating that 68% of company-supplied tablets are iPads.  However, it indicated that companies are taking a “wait-and-see” attitude when it comes to tablets, with Android presenting some security concerns, and with Microsoft not having yet launched its Windows 8 product, which is expected to be touch- and app-friendly.

The stakes couldn’t be higher. iPad has the first-mover advantage, but the market is growing fast.

Globally in Q4 2011 the tablet market grew dramatically; iPad’s market share was still dominant at 57%, but that figure was down from 64% in the prior quarter.

In addition to security and functionality, price has got to be a big factor moving forward.  I’ve got to believe that corporate purchasing departments will take notice of the iPad’s price tag, which is approximately double those of its competitors.

I have an iPad and am a huge fan of Apple products.  But double the price is a huge hurdle to overcome, especially in the corporate budgeting environment.

Sorry to make your job more complicated, but you need to start testing your tablet surveys on more than just the iPad.  To complete your survey coverage, you need to be thinking about Android, Blackberry and Windows.

Filed Under: How-To, Market Research, Mobile Tagged With: , , , , , ,

What is “Big Data,” and What Can I Do About It?

February 16, 2012 By Leave a Comment

Big DataThere are a lot of buzzwords out there in market research, and Big Data is one of them. I’ve been hearing that term everywhere.

I’m proud to announce that Research Access is partnering with GreenBook to bring you a webinar to help you understand Big Data.

This is the first in a series of webinars to be brought to you in 2012 in an exciting partnership between Research Access and GreenBook.

The webinar is entitled, “Turning Big Data from a Headache to a Competitive Advantage,” and it will be held on Tuesday, February 21 at 1pm EST / 10am PST.

Click This Link to Register

We’ve assembled a panel of experts to help you understand Big Data and, more importantly, give you practical tips for how to analyze it and turn it to your advantage.

I will be moderating the session, and joining me will be four expert panelists:

Sign up for the webinar today, and when you attend, tweet your questions to the hashtag #mrxideas.

Filed Under: Events, Featured, How-To, Market Research Tagged With: , ,

The ABCs of CSAT

January 31, 2012 By Leave a Comment

CustomerSatisfactionLoyaltyLater this week I’ll be attending the Net Promoter Conference in San Francisco.  I’m really looking covering this event for Research Access.

Customer satisfaction (or CSAT) measurement is a highly specialized, but vitally important, part of the research world.  

Yet I think there are many researchers and marketers who aren’t terribly familiar with the ins and outs of customer satisfaction and loyalty measurement.

Here is a quick ABC guide to what you need to know about CSAT.

S

Satmetrix 

Satmetrix, known as the Net Promoter Company, is the firm that administers the Net Promoter methodology.

A

ACSI

The ACSI (American Customer Satisfaction Index) is a methodology for measuring customer satisfaction.  It factors in the following variables:  customer expectations, perceived quality, perceived value, customer complaints and customer loyalty.

T

Tracking

Customer satisfaction and loyalty are fluid; therefore, most measurement programs involve tracking scores consistently over time.

I

Indicator

Customer satisfaction is a leading indicator of business success; that’s why it’s so important to understand it and take action based on it.

S

SCI

The Secure Customer Index is a customer satisfaction measurement methodology developed by D. Randall Brandt.  The SCI combines three elements – overall satisfaction, likelihood to continue using the service, and likelihood to recommend.

F

Future

The purpose of customer satisfaction research is to assess current attitudes toward a company in order to predict purchase behavior in the future.

A

Answering the Ultimate Question

Answering the Ultimate Question is a book by Fred Reichheld which outlines the Net Promoter methodology.

C

Calculating Your Net Promoter Score

The Net Promoter score is just what the name implies – the net of customers who are “promoters” minus those who are “detractors.”  The core Net Promoter question asks on a scale of 0 to 10 how likely a customer is to recommend the company to a colleague or friend.  The NPS is calculated by subtracting the percentage of customers who give a score of 0 through 6 (“Detractors”) from the percentage who give a score of 9 or 10 (“Promoters”).

T

Truth

Like all research, customer satisfaction research is a search for truth.  There are different approaches, but the search for truth must continue unabated.

I

Index

Most customer satisfaction methodologies yield an index; a single score which is easy for an organization to understand, and, importantly, can be the basis for positive action.

O

Out of Luck

Firms that ignore customer satisfaction altogether will soon find themselves out of luck.

N

Net Promoter

Net Promoter is a customer satisfaction measurement methodology, developed by  Satmetrix, Bain & Company, and Fred Reichheld.  The Net Promoter Score is obtained by asking customers about their likelihood to recommend a company to a friend or colleague.

You can use this link to get a discount if you’d like to join me at the Net Promoter Conference in San Francisco, February 1-3, 2012.

I hope to see you there!

Filed Under: Essay, Featured, How-To, Market Research Tagged With:

A Primer on the 4 Data Types You Can Collect in Your Market Research

January 18, 2012 By Leave a Comment

CalculatorMaking a business research questionnaire is no big deal, but making one that successfully derives the information that is actually required by the business to improve its practices is something not every person can do. One of the things that help make an online survey more effective is the understanding of the different types of data that is required out of survey respondents and of the different ways to measure the response. Different situations demand the use of different types of data. Remember, different scales have to be designed to derive these different types of data.

The feedback of survey respondents can be categorized into two basic forms of data – non-parametric and parametric.

Non-Parametric Data

The sort of data that does not have any direction and cannot be divided is called non-parametric data. Usually histograms are used to analyze non-parametric data. There are two basic types of non-parametric data.

Nominal Data

Nominal data refers to alphabetical or numeric data that is used to name people or objects for symbolic purposes and has no mathematical value.

For example, a questionnaire may ask the respondents to name the brand of shampoo they use. Numeric data too can also be included in the category of nominal data such as numbers written on the backs of sportsmen.

Ordinal Data

Ordinal data refers to numeric data that indicates only the relative ranking of different items, without representing the intensity of the mathematical value or the distance between the values. For example, respondents to an online survey may be asked to rank different brands of shampoo.  Hence, the ranking of different shampoo brands will inform researchers the relative preference of survey respondents but will not inform them about the intensity of the difference of preference of one shampoo brand from another.

Parametric Data

Numeric data that has direction is called parametric data. It can be used to analyze the difference the different responses and can also be at times divided. There are two different types of parametric data.

Interval Data

The collection of internal data is done on a scale on which all points are equidistant from the ones next to them. Scales measuring interval data do not have zero because of the nature of thing being measured. For example, respondents can be asked to rate their happiness on a scale of 1 through 10. Interval data cannot be divided because of the non-absolute nature of the data.

Ratio Data

Ratio data is the most absolute form of numeric data collected from respondents. It can be divided and altered in different ways to derive more meaning. All absolute mathematical values can be called ratio data such as income, age, sales, market share, etc.

Although ratio data may seem the most usable form of data and researchers may feel tempted to ask their survey respondents to answer all the questions in ratio form, it is either not practically possible to do so or isn’t the best form of data because of the objective of the research being conducted. An effective online survey questionnaire contains questions that derive the sort of data that will come handy in getting better insight into the respondents’ minds.

The QuestionPro and Survey Analytics online survey platforms allow you to collect all of these forms of data.  The trick is knowing which type to choose to get the best information that you can use in order to make a decision.

Filed Under: How-To Tagged With:

Survey Tip: Pay Attention to the Details

January 13, 2012 By Leave a Comment

blueprintWhy survey creators need to pay more attention to the details of wording, question types and other matters that not only affect results but also how customers view the company. A recent survey from Sage Software had quite a few issues, and gives me the opportunity to share some pointers.

The survey was for follow up satisfaction after some time with a new version of ACT! Call me a dinosaur, but after experiments with various online services, I still prefer a standalone CRM. Still, this post isn’t really about ACT! – I’m just giving a little background to set the stage.

  • The survey title is ACT! Pro 2012 Customer Satisfaction Survey. Yet one of the questions asks the survey taker to compare ACT 2011 with previous versions. How dumb does this look?

  • This same question has a text box for additional comments. The box is too small to be of much use, but also the box can’t be filled with text. All the text boxes in the survey have the the same problem.

  • If you have a question that should be multiple choice, set it up correctly.

Some survey tools may use radio buttons for multiple choice (not a good idea), but this isn’t one of them. This question should either be reworded along the lines of “Which of these is the most important social networking site you use“, or – probably better – use a multiple choice question type.

  • Keep up to date.

What happened to Quickbooks 2008, or more recent versions? It would have been better to simply have Quickbooks as an option (none of the other products had versions). If the version of Quickbooks was important (I know that integration with Quickbooks is a focus for Sage) then a follow up with the date/version would work, and would make the main question shorter.

There were a couple of questions about importance and performance for various features. I could nitpick the importance question (more explanation about the features or an option something like “I don’t know what this is” would have been nice), but my real issue is with the performance question. 20 different features were included in both importance and performance. That’s a lot to keep in mind, so it’s good to try to make the survey taker’s life easier by keeping the order consistent between importance and performance. The problem was that the order of the performance list didn’t match the first. I thought at first that the lists were both randomized separately, instead of randomizing the first list and using the same order for the second. This is a common mistake, and sometimes the survey software doesn’t support doing it the right way. But after trying the survey again, I discovered the problem was that both lists were fixed orders, different between importance and performance. Be consistent. Note, if your scales are short enough, and if you don’t have a problem with the survey taker adjusting their responses as they think about performance and importance together (that’s a topic of debate among researchers) you might consider showing importance and performance together for each option. QuestionPro and Survey Analytics have a special question type just for this.

  • Keep up to date – really! The survey asked whether I used a mobile computing device such as a smartphone. But the next question asked about the operating system for the smartphone without including Android. Unbelievable!

There were a few other problems that I noted, but they are more related to my knowledge of the product and Sage’s stated directions. But similar issues to those above occur on a wide variety of surveys. Overall, I score this survey 5 out of 10.

These issues make me as a customer wonder about the competence of the people at Sage. A satisfaction survey is designed to learn about customers, but should also create the opportunity to make the customers feel better about the product and the company. However, if you don’t pay attention to the details you may do more harm than good.

Idiosyncratically,
Mike Pritchard

[Editor's Note:  This post was originally published on 5circles.com]

Photo Credit

Filed Under: Featured, How-To, Market Research Tagged With: , ,

Measuring the Effectiveness of Your Blog

December 13, 2011 By 1 Comment

After you’ve been blogging for a few months, it’s a good idea to take a step back, examine what’s worked, and refine your blogging strategy. Especially if you have only recently begun blogging, it’s important to frequently review your strategy and successes, to make sure that you are progressing toward your goals. This can be hard to do if you aren’t sure how to go about measuring your blog accurately, or how to draw the correct judgement out of your information. Let’s examine one methodology to review your blog’s analytics and determine successes. To get started, log into whatever analytics platform that you prefer for your blog, be it Google Analytics, HubSpot, or whatever else is available to you.

Once you’ve signed into your blog, gather all of your blog’s data and export it to a spreadsheet so that you can slice it up and look at it from different angles. Your blog software can usually provide you with this general data, including the author name for each of your posts. If not, you may need to combine data from different systems. This way, you can easily build averages for each of your blog authors for how many views their posts get, or other criteria that you’re interested in. Depending on what data your blog can export, you have many options here – If it exports the tags for each post for example, you could also cut across the tags and see which of your blog’s tags generates the most views, tweets, or conversions on a regular basis.

Break Down Your Post Success By Author

Begin reviewing your blog’s performance by looking at clear breakdowns of your posts, such as by the author. This is an easy to access piece of data, and can show you who your real star authors are. Here is a Google Doc that can help you visualize how to break down your blog analytics by author. If you’d like to use it to get started, you should download it or save it on your own.

While the left contains the raw data from some sample blog analytics, the right hand side breaks down blog post performance by author. In this example, you can see that the average post by Kurt just isn’t performing as well as the other authors. This sheet can’t divine why Kurt’s posts aren’t performing as well, but it can point out the trends that you need to make your own observations. You can take this spreadsheet with you for your analysis – Just paste in your own blog’s data for post title, date, views, and authors into the left, and then fill in the right with the name of each blogger who writes for you regularly.

Look At Other Variables

This process works just as well if if you replace the content of Column D with another attribute that you know – For example, the post category, time of day, or other information. For example, you can do some surface-level research very easily into what times of day are most successful for your blog if you’ve previously tried out publishing posts at different times of the day. Go through your last two months of blog posts and categorize them into rough times of day, like “Morning”, “Afternoon”, “Evening” and “Weekend”. That way, you can break down the post averages by when you post them and see if different times of day lead to more successful posts for you. If you haven’t tried this out yet, spend a month varying up your posting times for your posts, and then check out if there are any consistent patterns.

Consider Your Business Goals

Finally, consider the business goals for your blog. Are you trying to generate conversions or leads? Or establish a presence as an authority on a subject? Review what metric you are trying to change by having a blog, and then look at how you can bring this into the analysis. Remember that the most important part of blogging is how it plays into moving your goals as a business organization. Do not just blog for the sake of doing it; if something is not working in your strategy, or if your marketing analytics show that your hard work is not translating into success, change things up until you find something that makes you successful.

Filed Under: Featured, How-To, Marketing, Social Media Tagged With: , , , ,
« Older Posts