Skip all navigation and go to page content

NEO Shop Talk

The blog of the National Network of Libraries of Medicine Evaluation Office

Make 2017 the “Yes-and” Year for Evaluation

20117 (year) with fireworks and "Always Say Yes" written underneath

PSA: New Year’s resolutions are passé.

It’s out with dreary self-betterment goals involving celery and punishing exercise. Instead, the trendiest way to mark the New Year is to pick an inspirational word and make it your annual North Star for self-improvement.  In that spirit, I want to propose a word of the year for the NEO Shop Talk community.

That word is “Yes and.”

Now, some of you are wondering how I passed kindergarten with such poor counting skills. However, If you or anyone you know has taken training in Improv theatre, you know “Yes and” is a word, or, more specifically, a verb.

Improv is a type of theatre in which a team of actors make up scenes on the spot, usually from audience suggestions.  Because performances are unscripted, improv actors train rather than rehearse. Training is built around commonly accepted “rules,” and, arguably, the best known rule of Improv is “Always say Yes and…”   That means that you accept any scene idea your teammate presents and add something to make that idea better. Once novice improvisers experience the upbeat emotional effect of this rule, they soon find themselves “yes-anding” in other parts of their lives. Some even preach about it to others (ahem).  Notice, by the way, I added a hyphen so we can all feel better about “yes-and” as the WORD of the year.

If you can “yes-and” evaluation requirements and responsibilities, it will put you on the road to mastering this rule. Let’s face it, the thought of evaluation does not generate an abundance of enthusiasm. Usually we do evaluation because someone else expects or requires us to do it: upper administration; accreditation boards; funding agencies. We only do evaluation when forced because it’s a lot of work. I compare evaluation to physical exercise. In theory, we know it’s good for us. In practice, we don’t have time for it. “Yes-anding” evaluation may not make you do more evaluation than you’re required to do.  It might, however, make your evaluation responsibilities more enjoyable or, at least, more meaningful to you personally.

For example, if you have to write a proposal for external funding, you often have to pull together assessment information to build a case for your proposed program. Does that mean you have to locate and synthesize lots of data from lots of sources? Yes, and you get to demonstrate all of the great things your library or organization has to offer. You also get to point out areas where you could provide even more awesome services if the funding agency gave you funding to meet your resource needs. (Here’s a NEO Shop Talk blog post on how to use SWOT analysis to synthesize needs assessment data.)

If your proposal includes outreach into a new community, you probably have to collect information from that community.   Do you have to find and conduct key informant interviews with representatives of the community?   Yes, and you also get to initiate relationships with influential community opinion leaders. Listening is a powerful way to build trust and rapport. If you have the opportunity to implement your program, these key informants will be powerful allies when you want to reach out to the broader community. (If you want some tips for finding key informants, check out this blog post.)

You can “yes-and” internally mandated evaluation as well. Your library or organization may require you to track data on an ongoing basis or to submit regular reports. To do this well, do you have to document your daily work, such as keep track of details surrounding reference services, workshop attendance, or facility usage? Yes and, you also get to create a database of motivational information to inspire you and fellow co-workers working on the same objectives and goals. Compile that information monthly or quarterly, and pass it around at staff meetingd.  Celebrate what you’re accomplishing. Figure out where effort is lagging and commit to bolstering activities in that area. Then celebrate your team’s astute use of data for making good program decisions. Yes, and, at reporting time, be sure you present your data so that your upper-level stakeholders notices your hard work.

Maybe your department or office has to set and assess annual objectives or outcomes. Do you have to collect and report data to show program results? Yes, and you also get to demonstrate your value to the organization. Just be sure you don’t hide your candle deep in some organizational online reporting system.  Annual reports are seldom page-turners. Find more compelling ways to communicate your success and contributions to upper administrators and influential users. For some ideas, you might want to check out some of NEO Shop Talk posts on reporting and data visualization.

Another rule of Improv is “There are no mistakes, only opportunities.”  Let’s paraphrase that to “there are no evaluation requirements, only opportunities.”  Here’s to making 2017 the year of “yes-anding” evaluation.

As a post-script, I want to share a NEO Shop Talk success with our readers. Did we post weekly blog entries in 2016? Yes, and you showed up more than ever. NEO Shop Talk visits increased 71% in 2016. Each month, we averaged 259 more visits compared to the same month in the previous year.  Our peak month was February, with 892 visits! Thank you, readers. Please come back and bring your friends!

slide1

2016 Annual NEO Shop Talk Round-up

Top 10 List

Like everyone else, we have an end-of-the-year list.  Here’s our top ten list of the posts we wrote this year, based on number of views:

10. Developing Program Outcomes Using the Kirkpatrick Model – with Vampires

9.  Inspirational Annual Reporting with Appreciative Inquiry

8.  What is a Need?

7.  Designing Surveys: Does the Order of Response Options Matter?

6.  Simply Elegant Evaluation: GMR’s Pilot Assessment of a Chapter Exhibit

5.  A Chart Chooser for Qualitative Data!

4.  W.A.I.T. for Qualitative Interviews

3.  The Zen Trend in Data Visualization

2.  How I Learned to Stop Worrying and Love Logic Models (The Chili Lesson)

1.  Logic Model for a Birthday Party

We put a lot of links to interesting things in our blog posts.  Here are the Top Ten websites that people went to from our blog:

10. The Kirkpatrick Model

9.  Books by Stephanie Evergreen

8.  Tearless Logic Model article in Global Journal of Community Psychology Practice

7.  AEA 365 | A Tip-a-Day by and for Evaluators

6.  Public Libraries, Project Outcome – Looking Back, Looking Forward

5.  Build a Qualitative Dashboard

4.  Nat King Cole, The Christmas Song

3.  The Histomap by John Sparks

2.  Tools: Tearless Logic Model (how-to summary)

1.  Stephanie Evergreen Qualitative Chart Chooser

The NEO wishes you a happy and fulfilling New Year!!

My Favorite Things 2016 (Spoiler Alert: Includes Cats)

Little figurine of Santa standing in snow, holding gifts

During gift-giving season every year, Oprah publishes a list of her favorite things. Well, move over, Oprah, because I also have a list. This is my bag of holiday gifts for our NEO Shop Talk readers.

Art Exhibits

There are two websites with galleries of data visualizations that are really fun to visit. The first,  Information is Beautiful , has wonderful examples of data visualizations, many of which are interactive. My favorites from this site are Who Old Are You?   (put in your birth date to start it) and Common MythConceptions. The other is Tableau Public, Tableau Software Company’s “public commons” for their users to share their work.  My picks are the Endangered Species Safari  and the data visualization of the Simpsons Vizapedia.  And, in case  you’re wondering what happened to your favorite Crayola crayon colors, you can find out here.

Movies

Nancy Duarte’s The Secret Structure of Great Talks is my favorite TEDtalk. Duarte describes the simple messaging structure underlying inspirational speeches. Once you grasp this structure, you will know how to present evaluations findings to advocate for stakeholder support. I love the information in this talk, but that’s not why I listen to it over and over again.  It’s because Duarte says “you have the power to change the world” and, by the end of the talk, I believe her.

Dot plot for a fictional workshop data, titled Participant Self Assessment of their Holiday Skills before and after our holiday survival workshop. Pre/post self-report ratings for four items: Baking without a sugar overdose (pre=3; post-5); Making small talk at the office party (pre=1; post=3); Getting gifts through airport security (pre=2; post-5); Managing road rage in mall parking lots (pre=2; post-4)

I also am a fan of two videos from the Denver Museum of Natural History, which demonstrate how museum user metrics can be surprisingly entertaining. What Do Jelly Beans Have To Do With The Museum? shows demographics with colorful candy and Audience Insights On Parking at the Museum  talks amusingly about a common challenge of urban life.

Crafts

If you want to try your hand at creating snappier charts and graphs, you need to spend some time at Stephanie Evergreen’s blog. For example, she gives you step-by-step instructions on making lollipop charts, dot plots , and overlapping bar charts. Stephanie works exclusively in Excel, so there’s no need to purchase or learn new software. You also might want to learn a few new Excel graphing tricks at Ann Emery’s blog.  For instance, she describes how to label the lines in your graphs or adjust bar chart spacing.

Site Seeing

How about a virtual tour to the UK? I still marvel at the innovative Visualizing Mill Road  project. Researchers collected community data, then shared their findings in street art. This is the only project I know of featuring charts in sidewalk chalk. The web site talks about community members’ reactions to the project, which is also pretty fascinating.

Humor

I left the best for last. This is a gift for our most sophisticated readers, recommended by none other than Paul Gargani, president of the American Evaluation Association. It is a web site for the true connoisseurs of online evaluation resources.  I present to you the Twitter feed for  Eval Cat.  Even the  NEO Shop Talk cats begrudgingly admire it, although no one has invited them to post.

 

Pictures of the four NEO Eval Cats

 

 

 

 

 

 

 

 

 

Here’s wishing you an enjoyable holiday.

Holiday Outcome Planning with Nat King Cole

The holidays can be very stressful. Last minute shopping, traffic, traveling, and talking politics — it’s clearly time to focus on the outcomes we want to see for the holidays, and how we are going to reach them. For help with my planning, I looked to what I think of as the greatest Christmas song of the season, The Christmas Song, most famously sung by Nat King Cole.

Here’s the song in logic model format (I suggest listening to the song at the same time as you read the logic model https://www.youtube.com/watch?v=hwacxSnc4tI):

Logic model of The Christmas Song

 

As with so many things in the holiday season, this song doesn’t really reflect my reality in Gulf Coast Texas (although we do get mistletoe–I had it growing on my oak tree a couple of years ago).  Working from similar outcomes backwards, here’s a different logic model that only applies to me:

Logic Model Showing Karen's Holiday plans

No, I will not attempt to turn it into a song, and you’re even luckier that I’m not going to sing it for you.  But this little process has been really helpful for me in keeping things in perspective for the next couple of weeks.

Thanks Nat King Cole, Bob Wells, and Mel Tormé for a great song and a great planning tool.  What would yours look like?

For more on logic models, select the blog’s Logic Model category, and check out the NEO’s Booklet 2: Planning Outcomes-Based Outreach Projects

‘Tis the Season to Do Some Qualitative Interviewing!

For most of us, the end-of-year festivities are in full swing. We get to enjoy holiday treats. Lift a wine glass with colleagues, friends, and loved ones. Step back from the daily grind and enjoy some light-hearted holiday fun.

Or, we could take these golden holiday social events to work on our qualitative interviewing skills! That’s right.  I want to invite you to participate in another NEO’s holiday challenge: The Qualitative Interview challenge. (You can read about our Appreciative Inquiry challenge here.)

If you are a bit introverted and overwhelmed in holiday situations, this challenge is perfect for you. It will give you a mission: a task to take your mind off that social awkwardness you feel in large crowds. (Please tell me I’m not the only one!) If, on the other hand, you are more of a life-of-the-party guest, this challenge will help you talk less and listen more.  Other party-goers will love you and you might learn something.

Here’s your challenge.  Jot down some good conversational questions that fit typical categories of qualitative interview questions.  Commit a couple questions to memory before you hit a party. Use those questions to fuel conversations with fellow party-goers and see if you get the type of information you were seeking.

To really immerse yourself in this challenge, create a chart with the six categories of questions. (I provided an example below)  When your question is successful (i.e., you get the type of information you wanted), give yourself a star.  Sparkly star stickers are fun, but you can also simply draw stars beside the questions. Your goal is to get at least one star in each category by midnight on December 31.

Holiday challenge chart, There is a holiday border around a table-style chartt with the six categories of questions, the five extra credit techniques, and blank cells for stars

According to qualitative researcher/teacher extraordinaire Michael Q. Patton, there are six general categories of qualitative interview questions.  Here are categories:

  • Experience or behavior questions: Ask people to tell you a story about something they experienced or something they do. For unique experiences, you might say “Describe your best holiday ever.” You could ask about more routine behavior, such as “What traditions do you try to always celebrate during the holidays?”
  • Sensory questions: Sensory questions are similar to experience questions, but they focus on what people see, hear, feel, smell, or taste. Questions about holiday meals or vacation spots will likely elicit sensory answers.
  • Opinion and value questions: If you ask people what they think about something, you will hear their opinions and values. When Charlie Brown asked “What is the true meaning of Christmas?” he was posing a value/opinion question.
  • Emotions questions: Here, you ask people to express their emotional reactions. Emotions questions can be tricky. In my experience, most people are better at expressing opinions than emotions, so be prepared to follow up.  For example, if you ask me “What do you dislike about the holiday season?” I might say “I don’t like gift-shopping.”   “Like” is more of an opinion word than an emotion word. You want me to reach past my brain and into my heart. So you could follow-up with “How do you feel when you’re shopping for holiday gifts?”  I might say “The crowds frustrate and exhaust me” or “I feel stressed out trying to find perfect gifts on a deadline.“ Now I have described my emotions around gift-shopping. Give yourself a star!
  • Knowledge questions: These questions seek factual information. For example, you might ask for tried-and-true advice to make holiday travel easier. If answers include tips for getting through airport security quickly or the location of clean gas station bathrooms on the PA Turnpike, you asked a successful knowledge question.
  • Background and demographic questions: These questions explore how factors such as ethnicity, culture, socio-economic status, occupation, or religion affect one’s experiences and world view. What foods do their immigrant grandparents cook for New Year’s celebrations every year?  What is it like to be single during the holidays? How do religious beliefs or practices affect their approach to the holidays? These are examples of background/demographic questions.

To take this challenge up a notch, try to incorporate the following techniques while practicing interview skills over egg nog.

Ask open-ended questions. Closed-ended questions can be answered with a word or phrase.  “Did you like the movie?”  The answer “Yes” or “No” is a comprehensive response to that question.   An open-ended version of this question might be “Describe  a good movie you saw recently.”  If you phrased your question so that your conversation partner had to string together words or sentences to form an answer, give yourself an extra star.

Pay attention to question sequence:  The easiest questions for people to answer are those that ask them to tell a story. The act of telling a story helps people get in touch with their opinions and feelings about something.  Also, once you have respectfully listened to their story, they will feel more comfortable sharing opinions and feelings with you. So break the ice with experience questions.

Wait for answers:  Sometimes we ask questions, then don’t wait for a response.  Some people have to think through an answer completely before they talk out loud. Those seconds of silence make me want to jump in with a rephrased question. The problem is, you’ll start the clock again as they contemplate the new version of your question. To hold myself back, I try to pay attention to my own breathing while maintaining friendly eye contact.

Connect and support: You get another star if you listened carefully enough to accurately reflect their answers back to them. This is called reflective listening.  If you want a fun tutorial on how to listen, check out Julian Treasure’s TEDtalk.

Some of you are likely thinking “Thanks but no thanks for this holiday challenge.” Maybe it seems too much like work. Maybe you plan to avoid social gatherings like the plague this season.  Fair enough.  All of the tips apply to bona fide qualitative interviews. When planning and conducting qualitative interviews, remember to include questions that target different types of information. Make your questions open-ended and sequence them so they are easy to answer.  Listen carefully and connect with your interviewee by reflecting back what you heard.

Regardless of whether you take up the challenge or not, I wish you happy holidays full of fun and warm conversations.

My source for interview question types and interview techniques was  Patton MQ. Qualitative Research and Evaluation Methods.  4th ed.  Thousand Oaks, CA: Sage, 2015.

Creating Partnerships that Work

Multiracial Businesspeople Stacking Hands

“Five guys on the court working together can achieve more than five talented individuals who come and go as individuals.” Kareem Abdul-Jabbar

When you’re working on an outreach project, you will almost certainly have some kind of partner organizations in the project.  Funders of outreach projects love to see partnerships, and sometimes they even require it.  When everything works like it’s supposed to, a partnership between organizations working on a joint outreach project can spawn better ideas, create a richer program, and improve reach.

But have you ever felt like you’ve made some bad decisions in your choice of partners? (I’m not talking about your sordid relationship history here).  It feels like a disaster when your plans fall apart because your partner organization had a completely different understanding of their role in the project, different priorities, or there were communication problems (okay, maybe I am).

Yesterday I was reviewing our Tools and Resources Guide for a major website update coming next week.  While I was doing that, I re-discovered some great resources for choosing and maintaining partners.

The Community Tool Box from the University of Kansas has a toolkit on Creating and Maintaining Partnerships.  This toolkit is made up of steps for partnering organizations to work through together. Here are some of the main categories, but the descriptions on the website are quite detailed:

  • Describe the problems or goals that have brought partners together in common purpose
  • Outline your partnership’s vision and mission, objectives
  • Re-examine the group’s membership in light of your vision, mission, and objectives
  • Describe potential barriers to your partnership’s success and how you would overcome them
  • Describe how the partnership will function and how responsibilities will be shared among partner organizations
  • Describe how the group will maintain momentum and foster renewal
  • If the partnership is losing momentum, review current barriers to your success
  • If necessary, revisit the plan to identify and recruit new or additional members
  • When maintaining the partnership at its current level is no longer appropriate or feasible, consider other alternatives, including changing focus, adding new members, or even dissolving the partnership

The Urban Indian Health Institute (UIHI) has a Resource Guide: Establishing and Maintaining Effective Partnerships.  It is a one page document with an emphasis on building trust among partners.  Here are some of their characteristics of successful partnerships.

  • A common vision and collective commitment
  • Mutual trust and respect
  • Risks, resources and rewards are shared jointly
  • Opportunities for capacity building through learning exchanges
  • Openness to learning and teaching opportunities
  • Ground rules that create a safe space to address challenges
  • Acknowledgement of the differences between the partners
  • Flexibility

Balancing the emphasis on trust and respect, UIHI also has helpful guides on their Resources for Partnerships page for establishing Memorandums of Understanding (MOUs) so partners clearly understand what’s expected of each other.

You might take a look at these guides and think “they’re asking me to do a lot of work – I just want to do a few health information presentations at the local public library.”  While you may be correct, sometimes a small project grows into something bigger, and then suddenly you find yourselves writing a proposal for a grant from the National Library of Medicine.  When going into a partnership, large or small (or personal), it might be worthwhile to take a look at some of these these guides — even if you don’t do all the steps or complete an MOU, you will find something that can help you make sure your partnership is nourished and successful for as long as it needs to be.

 

The Appreciative Inquiry Holiday Challenge

hand writing something in to the notebook near christmas toys.

The holiday season is upon us, so I want to give our readers a holiday Appreciative Inquiry challenge.  This is a fun way to practice the Appreciative Inquiry interview. It also provides an opportunity for you and your family to plan a better-than-usual holiday season.  Finally, it gives everyone something to talk about other than politics. (You’re welcome.)

During the coming week, ask yourself and your loved ones the following three questions:

  • What was the best holiday experience you’ve ever had?
  • What made that experience so special? What did you value about it?
  • What could happen to make this year’s holiday season exceptional?

Here’s how I would answer the questions.  My favorite holiday was the one I had as a child, traveling to Arizona to spend Christmas with extended family.  For a kid from Western Pennsylvania, Tucson was exotic.  Christmas lights on saguaro cactuses. Luminarias.  Tree ornaments from Mexico. The best part, though, was a trip to the Catalina mountains.

What I valued about that holiday was the differentness of the setting and seeing how those from another part of the country celebrated the holiday. I also liked the bright sunny days outdoors.

It’s a little too late to book a trip to Arizona for the holidays, but I can still seek out places close by that have a different take on holiday decorations. As for enjoying the outdoors, I live in a place that offers lots of opportunity on that front. My husband and I can easily fit in a hike and a trip to Helen, a Bavarian Alpine village in the North Georgia mountains.

Once you’ve talked with your family, make a list of everyone’s ideas for a great holiday and check them off as they happen. You could even do this as a group on a private Facebook page.  Or go old school and put a written list on your refrigerator door.  See if Appreciative Inquiry doesn’t add some sparkle to your holiday season this year.

Happy Thanksgiving, everyone.

 

 

A Chart Chooser for Qualitative Data!

Core Values Word Cloud Concept

When people talk about data visualization, they are usually talking about quantitative data. In a previous post, we explained that data visualizations help people perform three primary functions: exploring, making sense of, and communicating data.  How can we report qualitative data in a way that performs those same functions?

We just got some exciting news from the EvergreenData blog that they have developed a Qualitative Chart Chooser. Seriously–it’s a work of art. Actually two works of art because they have two different chart chooser drafts to choose from.

The way it works is this: you think about the story you want to tell with your data, maybe about how something improved over time because of your awesome project. Then using the chart chooser, you look at the “show change over time” category, and then you could select a timeline, before-and-after “change photos,” or a histomap (what’s a histomap?  Take a look at this one).

This chart chooser is a very cool tool. But I wouldn’t wait until it was time to report findings to use it. One thing that we at the NEO suggest is that when you are first planning your project, you should think about the story or stories you want to tell at the end of your project. Maybe when you’re thinking about the story you want to tell, you could look at all these different qualitative charts in the chart chooser.  Which ones would you like to use? Do you want to tell the story of how your program aligns with the goals of your institution (you could try indicator dots)? Or maybe you want to show how the different parts of your project work together as a whole (a dendrogram might work). By looking at these options before you design your evaluation plan, you can be sure that you are gathering the right data from the beginning. Backing up even further in your planning process, if you are having trouble trying to decide what story or stories you want to tell, this Qualitative Chart Chooser can give you ways to think about that.

Here is some more information on qualitative data visualization and storytelling from NEO Shop Talk:

Qualitative Data Visualization, September 26, 2014

More Qualitative Data Visualization Ideas, December 18, 2014

Telling Good Stories About Good Programs, June 29, 2015

DIY Tool for Program Success Stories, July 2, 2015

 

Participatory Evaluation, NLM Style

Road Sign with directional arrow and "Get Involved" written on it.

This week, I invite you to stop reading and start doing.

Okay, wait. Don’t go yet.  Let me explain. I am challenging you to be a participant-observer in a very important assessment project being conducted by the National Library of Medicine (NLM).

The NEO is part of the National Library of Medicine’s program (The National Network of Libraries of Medicine) that promotes use of NLM’s extensive body of health information resources.  The NLM is devoted to advancing the progress of medicine and improving the public health through access to health information. Whether you’re a librarian, health care provider, public health worker, patient/consumer, researcher, student, educator, or emergency responder fighting health-threatening disasters, the NLM has high quality, open-access health information for you.

Now the NLM is working on a long-range plan to enhance its service to its broad user population.  It is inviting the public to provide input on its future direction and priorities. Readers, you are a stakeholder in the planning process. Here is your chance to contribute to the vision. Just click here to participate.

And, because you are an evaluation-savvy NLM stakeholder, your participation will allow you to experience a strength-based participatory evaluation method in action.  Participatory evaluation refers to evaluation projects that engage a wide swath of stakeholders. Strength-based evaluation approaches are those that focus on getting stakeholders to identify the best of organizations and suggest ways to build on those strengths. Appreciative Inquiry is one of the most widely recognized strength-based approaches. The NEO blog have posts featuring Appreciative Inquiry projects here and here.

While I have no idea if the NLM’s long-range planning team explicitly used Appreciative Inquiry for developing their Request for Information, their questions definitely embody the spirit of strength-based assessment. I’m not going to post all of the question here because I want readers to go to the RFI to see the questions for themselves. But as a teaser, here’s the first question that appears in each area of inquiry addressed in the feedback form:

 “Identify what you consider an audacious goal in this area – a challenge that may be daunting but would represent a huge leap forward were it to be achieved.  Include any proposals for the steps and elements needed to reach that goal. The most important thing NLM does in this area, from your perspective.”

So be an observer: check out the NLM’s Request for Information.  Notice how they constructed a strength-based participant feedback form.

Then be a participant: take a few minutes to post your vision for the future of NLM.

Mean, Median or Mode–What’s the Difference?

Five stars ratings with shadow on white

Last week I taught the class Finding Information in Numbers and Words: Data Analysis for Program Evaluation at the SCC/MLA Annual Meeting in Galveston, TX.  There is a section of the class where we review some math concepts that are frequently used in evaluation, and the discussion of mean, median and mode was more interesting than I expected.  Mean, median and mode are measures of “central tendency,” which is the most representative score in a distribution of scores.  Central tendency is a descriptive statistic, because it is one way to describe a distribution of scores. Since everyone there had run across those concepts before, I asked the group if anyone knew of any clever mnemonics for remembering the difference.  Several people responded, both in class and afterwards (thanks Margaret Vugrin, Julia Crawford and Michelle Malizia!) Here are a couple of memory tools for you:

Mean: Turns out those mean kids are just average (mean = average)

Median: Just like the median in the road: if you line the values up in order, the median is the number “in the middle”

Mode: Mode has an “O” sound, and O is the first letter in “Often.”  It is the value on the list which occurs most often.

Or

Hey diddle diddle, the Median’s the middle; you add and divide for the Mean. The Mode is the one that appears the most, and the Range is the difference between.

Now that you can remember them, which one should you use?  I think a good way to think about it relates to the ratings you see when you’re trying to pick a hotel or restaurant.  I don’t know about you, but when I’m looking at a restaurant score, when I see 4 stars (out of 5), I’m not comfortable with that number without seeing the breakdown.  There’s a big difference between a 4 where the scores are spread out and one where the scores are heavily skewed towards 5.

Let’s say I’m looking at reviews for hotdog restaurants that have around 4.0 stars.  The first one I look at has a distribution of scores spread out relatively evenly from 5 stars (the most number of ratings) to 1 star (the fewest).  A mean (mean kids are just average) works well here.  To do this you add all the scores up and divide the sum by the number of responses to reach a mean of 3.9.

3-9-star-mean

Here is the chart for a similar hotdog restaurant with a slightly higher 4.2 star rating:

4-2-star-median

While the mean adds up to 4.2,  you can see in the chart that the scores are heavily skewed towards 4 and 5 stars, and it seems that 4.2 does not accurately describe the ratings of that restaurant (remember that central tendency is a descriptive statistic). However, if you use a (middle of the road) median with this kind of distribution, the result is a whopping 5.  To determine the median, you line all the results up in order and select the one in the very middle.  You might want to use a median when the distribution looks skewed.

This particular restaurant analogy doesn’t really work with mode. Mode is used for categories, which really cannot be averaged mathematically.  For example, if you want to know what is the most representative type of restaurant in your city, you might find out that your city has more hotdog restaurants than any other kind of restaurant (that would be awesome, right?).

I hope this helps. If you know any other mnemonics for mean, median, or mode, please send me an email at kjvargas@uw.edu and I will add them to the bottom of this post.

 

Last updated on Monday, June 27, 2016

Funded by the National Library of Medicine under Contract No. UG4LM012343 with the University of Washington.