educational-and-psychological-statistics

Data Sources

 

What if you need some data, either for a presentation, project or other application, but don't happen to have any at hand? There are many good resources for data, univariate or mulitvariate, that may be obtained at no cost from a variety of sources. Here are a few such resources, with a note or two about what each has to offer.

• Data  and  Story  Library  (DASL).  DASL  is  a  resource  maintained  at  Carnegie-­‐Mellon  University   which  has  a  variety  of  data  sets,  some  oriented  toward  a  specific  data  analysis  method,  others   could  be  handled  in  a  variety  of  ways.  Though  the  data  sets  are  numerous,  they  tend  to  be  small,   that  is,  based  on  a  relatively  small  number  of  cases.  The  data  sets  also  tend  to  be  somewhat   dated.  That  doesn't  decrease  their  utility,  however.  Perhaps  the  biggest  deficiency  is  that  there   is  often  little  information  about  the  actual  source  of  the  data,  explanation  of  how  the  data  were   collected,  and,  in  a  few  instances,  the  choice  of  how  the  data  are  quantified.  Some  of  the  data   may  be  fictitious-­‐-­‐drawn  from  text  examples  rather  than  real  data.    

• Australasian  Data  and  Story  Library.  OzDASL  is  similar  to  DASL,  though  the  data  sets  tend  to  be   somewhat  better  documented.    

• National  Center  for  Education  Statistics  (NCES).  NCES  is  the  home  for  all  of  the  data  collected   and  summarized  in  the  "Nation's  Report  Card,"  which  is  based  on  the  National  Assessment  of   Educational  Progress  (NAEP)  test  series.  There  is  much  you  can  find  here;  some  of  which  is  in   summary  form,  and  some  of  which  can  be  obtained  in  raw  form.    

• Inter-­‐university  Consortium  for  Political  and  Social  Research  (ICPSR).  ICPSR  is  a  treasure  trove  of   data  sets,  many  of  which  are  from  very  large  studies,  sometimes  done  longitudinally  over  many   years.  Most  of  the  data  sets  come  from  survey-­‐type  studies,  but  you  should  have  no  problem   finding  something  here.    

• Mississippi  Assessment  and  Accountability  Reporting  System  (MAARS).  MAARS  is  a  convenient   resource  for  school,  district,  and  state-­‐level  information  relative  to  test  performance  of   Mississippi  students  from  elementary  school  through  high  school.  The  basic  retrieval  system  for   MAARS  gives  data  at  a  specific  unit  level  (e.g.,  aggregated  for  a  school,  a  district,  or  the  state),   but  the  Mississippi  Department  of  Education  web  site  also  has  some  larger-­‐level  files  that  can  be   downloaded  as  well.    

• StatSci.Org  list  of  data  sets.  Here's  a  large  list  of  links  to  data  sets,  some  of  which  have  been   listed  above  (like  DASL),  some  from  textbooks,  some  from  elsewhere.  If  you  can't  find  something   from  this  site,  you're  just  not  trying!    

• HUD  USER  data  sets.  From  the  department  of  Housing  and  Urban  Development  comes  a  variety   of  electronically-­‐distributed  data  sets  that  can  be  accessed.  These  are  data  sets  that  have  been   obtained  from  the  Office  of  Policy  Development  and  Research  (PD&R)  at  HUD.    

• Journal  of  Statistics  Education  data  sets.  A  variety  of  data  sets,  usually  larger  than  those  in  DASL,   which  are  submitted  by  authors  to  accompany  their  articles  in  JSE.  Each  data  set  typically  has  a   corresponding  file  with  a  description,  though  you  can  always  consult  the  article.    

• Need  more?  Just  type  "data  set"  into  Google  or  some  other  internet  search  engine,  then  enjoy   the  ride.