View Only
  • 1.  IMPACT in Action #1a - Show Me the Data!

    Posted 03-04-2021 08:44:00
    Edited by Karen Gaines 03-04-2021 08:47:23

    Students often find "real" data sets engaging. But sometimes as instructors we struggle to find relevant and engaging data sets that are also manageable (not too large, not too "messy"). 

    Where do you find good data? How do you handle messy/cumbersome data sets that may be troublesome for students? Feel free to include a specific site/source even if you just found one useful set of data there.

    Mark Earley
    Assistant Professor
    Columbus State CC
    Columbus OH

  • 2.  RE: IMPACT in Action #1a - Show Me the Data!

    Posted 03-06-2021 21:09:00
    One website I like when I need a quick data set is Andrew Luttrell's Data Generator: 
    As I said, it's quick, and you can get summary statistics, graphs, and the actual data for sample sizes you select. The data are random, so abnormalities may appear depending on the parameters you set. Still, it's fun to play with!

    Mark Earley
    Assistant Professor
    Columbus State CC
    Columbus OH

  • 3.  RE: IMPACT in Action #1a - Show Me the Data!

    Posted 03-08-2021 12:14:00
    I like to use the ASA Census at Schools data site . It's easy to use, is interesting for students, and has many opportunities to discuss the need for data "cleaning".  It is great to use when starting the course.  I also give students an assignment to find a data set they're interested in.  I've been surprised how, with just a little guidance, students are able to find interesting data sets.  Then I use their data sets in class, when possible, for examples.

    Rebecca Wong
    West Valley College
    Saratoga CA

  • 4.  RE: IMPACT in Action #1a - Show Me the Data!

    Posted 03-08-2021 13:26:00
    I use data from one of the many city portals.  For example, the City of Chicago portal has data on salaries, taxi rides, red light cameras for traffic violations and more.  Much of the data requires a cleanse for missing observations, typos, and strange results (such as $30,000 taxi rides paid in cash).  This data may be used throughout the semester to illustrate virtually all concepts taught in Intro Stats.

    Michael Sullivan
    Sullivan Texts; Joliet Junior College
    Joliet IL

  • 5.  RE: IMPACT in Action #1a - Show Me the Data!

    Posted 03-11-2021 00:00:00

    Thanks Mike, Rebecca, and Mark.  Those are great ideas for sources of data.  A couple years ago, some committee members compiled a list of some places where they found data sets and posted it to the Classroom Resources page on the Statistics Resources Webpage (the second bullet from the top on this page: ).  Does anyone else have any places where you find good data that you could share with us?

    Julie Hanson
    Professor of Mathematics and Statistics
    Clinton CC
    Plattsburgh NY

  • 6.  RE: IMPACT in Action #1a - Show Me the Data!

    Posted 03-11-2021 06:52:00
    I often look at "Data is Plural" ( which the creator describes as "a weekly newsletter of curious/useful datasets." Another source is which organizes the datasets by domain, e.g., biology, education, sports, etc.

    Donna LaLonde
    American Statistical Association
    Alexandria VA

  • 7.  RE: IMPACT in Action #1a - Show Me the Data!

    Posted 03-14-2021 22:14:00
    Sometimes I find data from NYTimes, which has a learning center. In Fall, with the data for Covid cases, I was able to create a quiz for College Algebra with questions regarding the function (number of daily infections or deaths) increasing, decreasing or having a relative maximum/minimum. Questions asking for cumulative infections/deaths required students to think beyond simply reading graph numbers. Covid cases quiz has been added to the library.
    The worldometer site is one that I use for various types of demographic data.

    Manisha Ranade
    Santa Fe College
    Gainesville FL

  • 8.  RE: IMPACT in Action #1a - Show Me the Data!

    Posted 03-15-2021 23:51:00
      |   view attached
    I have worked with the Maryland Sex Offenders Registry before which allows to filter data by zip code, state, city, name and more. Once you get to the individual name of a person, variables such as weight, age, height, race, ethnicity and residency become available. The link to the national sex offender public website is .
    Another interesting site is the Baltimore Neighborhood Indicator Alliance (BNIA) which provides meaningful, accurate and open data at the community level. From the open data portal under Quick Links you can access the Vital Signs Open Data Portal concentrating on census demographics, community development, children and family health, crime and safety, education and youth, and much more. I have used graphs from that site and have contrasted and compared different neighborhoods with each other. 
    And last, I have used data from a study on Maryland College Students at Public Institutions that produced about 1400 data points with over 20 variables and very interesting information about our students. The file has received over 3000 views in StatCrunch, so some of you may have seen this already. In StatCrunch it can be accessed in the data search box under the name "MD College Students". I have also attached the file for your convenience.
    Happy analyzing!

    Barbara Leitherer
    Professor of Mathematics
    CC of Baltimore County - Essex
    Baltimore MD


  • 9.  RE: IMPACT in Action #1a - Show Me the Data!

    Posted 03-24-2021 21:34:00
    I have asked students to answer a few questions at the beginning of the semester. We analyze that data, and the question, "How old are you?" is always a fun one. You have answers like "22", "45yrs old", and "I will be 21 on June 19". This gives students the opportunity to see:

    1.) Real world data is messy.
    2.) If you do not define your questions clearly, you can expect some unexpected answers.
    3.) Cleaning data is a very important part of data analysis.
    4.) For some questions, you may want to have some data validation techniques employed such as giving an error if the answer is not an integer.

    Teaching of Statistics in Health Sciences

    ICPSR - ICPSR advances and expands social and behavioral research, acting as a global leader in data stewardship and providing rich data resources and responsive educational opportunities for present and future generations.

    Cengage Data set hub

    Pearson's Shared Data Sets

    Salary Data for State Employees - This is always a fun one for department meetings.

    SAT and ACT results by District

    Tuition and Fees of Universities

    US News and World Report - 100 Best Jobs in America

    Keisha Brown
    Assistant Professor
    Georgia State University Perimeter College - Dunwoody
    Dunwoody GA