ASA Connect

 View Only

  • 1.  Data collection in an Introductory Statistics Class

    Posted 08-17-2017 13:01
    Dear ASA community,

    I will be collecting data in my Introductory Statistics course which will be used for descriptive and inferential types projects later in the semester. I was wondering what variables do you consider in the data collection as an instructor. Here are some of the variables in my mind:

    1.      Height: Height of students (inch)

    2.      Shoe: Shoe size (U.S.)

    3.      Distance: Dailey one way commuting distance to Miami University (Mile)

    4.      Class: Number of fall, 2017 classes taking at Miami University

    5.      Standing: Class standing – i.e. Freshmen, Sophomore, Junior, Senior

    6.      Hand: Dominant hand i.e. Right or Left

    7.      Sleep: Average sleeping hours in weekday (hours)

    8.      FHeight: Father's height (inch)

    9.      MHeight: Mother's height (inch)


    I would appreciate your ideas.

     

    Sincerely,

    Achut Adhikari



  • 2.  RE: Data collection in an Introductory Statistics Class

    Posted 08-17-2017 15:39
    Hi Achut

    Using student data is a great idea and there are so many variables you could attempt to measure.

    Some additional variables we've collected in the past include:
    • What is the fastest speed you have ever driven a car?
    • How many letters in your official first name?
    • How many pairs of shoes do you own?
    and so many more :-)

    You could also get students to submit data about their or their family pets, including variable such as:
    • Pet name
    • Pet weight
    • Pet type (currently restricted to dog or cat)
    • Pet age
    • Pet cost (to feed per week)
    I also got students to submit a photo of their pet as well (with their pet's permission of course!) so we could make data cards of the pets. You can read more about this project here: teaching.statistics-is-awesome.org/its-raining-cats-and-dogs-hopefully/

    Regards
    Anna

    ------------------------------
    Anna Fergusson
    The University of Auckland

    ------------------------------

    Original Message


  • 3.  RE: Data collection in an Introductory Statistics Class

    Posted 08-18-2017 11:04
      |   view attached

    I have attached our introductory data collection survey.

    Hope this helps,

    Bryan James
    Assistant Professor of Mathematics
    Pennsylvania College of Technology

    This email may contain confidential information about a Pennsylvania College of Technology student. It is intended solely for the use of the recipient. This email may contain information that is considered an "educational record" subject to the protections of the Family Educational Rights and Privacy Act Regulations. The regulations may be found at 34 C.F.R. Part 99 for your reference. The recipient may only use or disclose the information in accordance with the requirements of the Federal Educational Rights and Privacy Act Regulations. If you have received this transmission in error, please notify the sender immediately and permanently delete the email.
    This email may contain confidential information about a Pennsylvania College of Technology student. It is intended solely for the use of the recipient. This email may contain information that is considered an "educational record" subject to the protections of the Family Educational Rights and Privacy Act Regulations. The regulations may be found at 34 C.F.R. Part 99 for your reference. The recipient may only use or disclose the information in accordance with the requirements of the Federal Educational Rights and Privacy Act Regulations. If you have received this transmission in error, please notify the sender immediately and permanently delete the email.



    Attachment(s)

    docx
    Survey Questions S17.docx   18 KB 1 version
    Original Message


  • 4.  RE: Data collection in an Introductory Statistics Class

    Posted 08-18-2017 14:34

    One semester I asked students to come up with their own questions. They were interested in pets, working out, food preferences, housing, sleep (including mattress preference).




    Original Message


  • 5.  RE: Data collection in an Introductory Statistics Class

    Posted 08-19-2017 22:06
    i note that gender is not on the list.  nor age.
    i suppose that gender and age could make the data identifiable, and you probably don't want to do that, but gender alone should be ok.  i expect some correlations to differ by gender, and that in itself is interesting.


    --
    Ellen Hertzmark

    (617) 432-1200 (1635 tremont st--usually wednesdays 1:30-5)



    please call before coming to my office.

    (617) 734-6245 (home -  any time except sundown friday to 1 hour after sundown saturday))



    Original Message


  • 6.  RE: Data collection in an Introductory Statistics Class

    Posted 08-18-2017 03:48
    Hi Achut,

    I think it's a great idea to collect data about your class and there are many possibilities. The two suggestions I would make our first think about what type of inference you want to make. For example comparing males versus females is always interesting for a two sample T Test. I don't think it's necessarily a good idea to collect data on a lot of variables, just a few well-chosen ones.The second thing is I would try to collect data on things that the students would actually be interested in. For example maybe you could look at the type of social media that use or the platform that they used to listen to music. I don't know that students are particularly interested in shoe size and stuff like that. I think dominant hand is interesting if you have a large enough class because then you can test to see if the proportion of left handed students is different than what it is in the general population. A word of advice though. When it comes to students reporting their heights some instructors are reluctant to ask them to do so because very short students could feel singled out. 

    Good luck!
    Matt

    ------------------------------
    Matthew Brenneman
    Instructor of Mathematics & Statistics
    Embry-Riddle Aeronautical University
    ------------------------------

    Original Message


  • 7.  RE: Data collection in an Introductory Statistics Class

    Posted 08-18-2017 09:03
    In addition to a few demos, I also used a 5-item math test that, in addition to being useful for examples, was a pretty good predictor of class performance. I don't still have the test, but the first item was something like 2X + 3 = 15 and the last was log10(100)=? No one in about 45 years of teaching stat ever missed the first item but I got a nice distribution for the others. BTW, no calculators allowed.

    ------------------------------
    Chauncey Dayton
    ------------------------------

    Original Message


  • 8.  RE: Data collection in an Introductory Statistics Class

    Posted 08-18-2017 09:39
    I've used Anna's idea and asked how many pairs of shoes they own.  It's a more surprising question and opens the opportunity to talk about the fact that they will give an answer even if they don't actually know it.  You may get the same opportunity with the parents' heights.  Of course, I was asking the questions in class so there's no opportunity to go check.  I have used the shoe size also because it works so well as qualitative data that looks like quantitative.  Never tried both at once but that could be interesting.

    I'm also not specific about the unit of measure on at least some of the questions.  That gives us the chance to talk about it.  If you have international students, they'll report height in centimeters which is pretty easy to convert.  It's harder to deal with height data when it's given in feet and inches but it drives home the point of needing to ask clear questions to get self-report data.  Distance from campus would be truly messy data because there will be plenty of students who won't know the miles but only the time it takes.

    Love student data collection projects!  It does take forethought if you want to be able to use it throughout the term.  I started with just getting through descriptive statistics and asked questions to generate data that would get used to create various graphs.  Over time, I got better at including questions that also made for good examples in the introduction of various tests too.

    Good luck and have fun.

    ------------------------------
    Beverly Wood
    Assistant Professor
    Embry-Riddle Aeronautical University
    ------------------------------

    Original Message


Related Content