Workshopping project proposals

Lecture 6

Aidan Combs

Duke University
SOCIOL 333 - Summer Term 1 2023

2023-05-25

Today

  • Fit between research questions and data
  • Workshop your research questions

Fit between research questions and data

  • Is the sample generalizable to the target population?
  • Does it contain the necessary variables to answer the research question?

This is a problem if you want to estimate mental health in the population

But not if you’re interested in the social media/mental health relationship

Interactions are a problem for studying relationships

Research questions and variables

  • EADA data
glimpse(sports)
Rows: 2,311
Columns: 10
$ school       <chr> "Duke", "Duke", "Duke", "Duke", "Duke", "Duke", "Duke", "…
$ year         <dbl> 2003, 2003, 2003, 2003, 2003, 2003, 2003, 2003, 2003, 200…
$ division     <chr> "NCAA Division I-A", "NCAA Division I-A", "NCAA Division …
$ teamgender   <chr> "men", "men", "men", "men", "men", "men", "men", "men", "…
$ sport        <chr> "Baseball", "Basketball", "Football", "Golf", "Lacrosse",…
$ coachgender  <chr> "men", "men", "men", "men", "men", "men", "women", "men",…
$ coachlevel   <chr> "assistant", "assistant", "assistant", "assistant", "assi…
$ assignstatus <chr> "FT", "FT", "FT", "PT", "PT", "PT", "PT", "FT", "FT", "FT…
$ ncoaches     <dbl> 2, 3, 9, 1, 2, 2, 1, 1, 1, 1, 2, 2, 1, 3, 6, 1, 3, 2, 9, …
$ nplayers     <dbl> 33, 15, 81, 12, 45, 23, 32, 11, 50, 50, 35, 35, 35, 30, 1…

Would these research questions work? What variables would they use?

  • How does the number of assistant coaches assigned to teams vary by university?
glimpse(sports)
Rows: 2,311
Columns: 10
$ school       <chr> "Duke", "Duke", "Duke", "Duke", "Duke", "Duke", "Duke", "…
$ year         <dbl> 2003, 2003, 2003, 2003, 2003, 2003, 2003, 2003, 2003, 200…
$ division     <chr> "NCAA Division I-A", "NCAA Division I-A", "NCAA Division …
$ teamgender   <chr> "men", "men", "men", "men", "men", "men", "men", "men", "…
$ sport        <chr> "Baseball", "Basketball", "Football", "Golf", "Lacrosse",…
$ coachgender  <chr> "men", "men", "men", "men", "men", "men", "women", "men",…
$ coachlevel   <chr> "assistant", "assistant", "assistant", "assistant", "assi…
$ assignstatus <chr> "FT", "FT", "FT", "PT", "PT", "PT", "PT", "FT", "FT", "FT…
$ ncoaches     <dbl> 2, 3, 9, 1, 2, 2, 1, 1, 1, 1, 2, 2, 1, 3, 6, 1, 3, 2, 9, …
$ nplayers     <dbl> 33, 15, 81, 12, 45, 23, 32, 11, 50, 50, 35, 35, 35, 30, 1…

Would these research questions work? What variables would they use?

  • How does the number of coaches assigned to basketball teams vary by gender of the team?
glimpse(sports)
Rows: 2,311
Columns: 10
$ school       <chr> "Duke", "Duke", "Duke", "Duke", "Duke", "Duke", "Duke", "…
$ year         <dbl> 2003, 2003, 2003, 2003, 2003, 2003, 2003, 2003, 2003, 200…
$ division     <chr> "NCAA Division I-A", "NCAA Division I-A", "NCAA Division …
$ teamgender   <chr> "men", "men", "men", "men", "men", "men", "men", "men", "…
$ sport        <chr> "Baseball", "Basketball", "Football", "Golf", "Lacrosse",…
$ coachgender  <chr> "men", "men", "men", "men", "men", "men", "women", "men",…
$ coachlevel   <chr> "assistant", "assistant", "assistant", "assistant", "assi…
$ assignstatus <chr> "FT", "FT", "FT", "PT", "PT", "PT", "PT", "FT", "FT", "FT…
$ ncoaches     <dbl> 2, 3, 9, 1, 2, 2, 1, 1, 1, 1, 2, 2, 1, 3, 6, 1, 3, 2, 9, …
$ nplayers     <dbl> 33, 15, 81, 12, 45, 23, 32, 11, 50, 50, 35, 35, 35, 30, 1…

Would these research questions work? What variables would they use?

  • How is the number of games a team wins related to the number of coaches it has?
glimpse(sports)
Rows: 2,311
Columns: 10
$ school       <chr> "Duke", "Duke", "Duke", "Duke", "Duke", "Duke", "Duke", "…
$ year         <dbl> 2003, 2003, 2003, 2003, 2003, 2003, 2003, 2003, 2003, 200…
$ division     <chr> "NCAA Division I-A", "NCAA Division I-A", "NCAA Division …
$ teamgender   <chr> "men", "men", "men", "men", "men", "men", "men", "men", "…
$ sport        <chr> "Baseball", "Basketball", "Football", "Golf", "Lacrosse",…
$ coachgender  <chr> "men", "men", "men", "men", "men", "men", "women", "men",…
$ coachlevel   <chr> "assistant", "assistant", "assistant", "assistant", "assi…
$ assignstatus <chr> "FT", "FT", "FT", "PT", "PT", "PT", "PT", "FT", "FT", "FT…
$ ncoaches     <dbl> 2, 3, 9, 1, 2, 2, 1, 1, 1, 1, 2, 2, 1, 3, 6, 1, 3, 2, 9, …
$ nplayers     <dbl> 33, 15, 81, 12, 45, 23, 32, 11, 50, 50, 35, 35, 35, 30, 1…

Workshopping

  • Groups of 3

    • You have access to each others’ github repos

  • Read your group members’ submissions

  • Answer some questions about their work

    • Make your feedback a GitHub issue: copy/paste template from project instructions; fill out
    • 10-15 min/person
    • Goal is improvement–how can they make their work better?

  • Talk through your thoughts on each group member’s proposal and their choice of question (5-10 minutes each)

  • Was this helpful?
  • Do you feel like you’re on a good path with your project?
  • How is learning our computing workflow going?
  • Suggestions for me for next time? Questions you’d like me to address?

🔗 https://soc333-sum23.github.io/