Data Organization in Spreadsheets. Broman, K. W. & Woo, K. H. The American Statistician, 72(1):2–10, Informa UK Limited, sep, 2017.
doi  bibtex   
@Article{Broman2017,
  author    = {Karl W. Broman and Kara H. Woo},
  title     = {Data Organization in Spreadsheets},
  journal   = {The American Statistician},
  year      = {2017},
  volume    = {72},
  number    = {1},
  month     = {sep},
  pages     = {2--10},
  doi       = {10.1080/00031305.2017.1375989},
  comment   = {Do not have mixed info in fields
If numbers, just numbers
If factors, consistent labels
Column names, simple, no spaces (can have a separate spread sheet with more details on each variable if needed)
Be consistent in what is an NA
Do not use 0 for NA, do not use “-“ for NA, do not use a blank for NA… so… actually… just use NA for NA
Do not color code fields (or, if relevant, store said information in some other way and/or use conditional formatting to do it)
Do not have multiple formats in a single worksheet 
1 row per observation, 1 column per variable
No plots in data worksheet
No comments in cells “around” the data


See also:
https://datacarpentry.org/2015-05-03-NDIC/excel-ecology/02-common-mistakes.html

https://analyticsdemystified.com/excel-tips/10-things-you-should-always-do-or-not-do-in-excel/




},
  file      = {:Data Organization in Spreadsheets.pdf:PDF},
  keywords  = {excel, worksheet},
  publisher = {Informa {UK} Limited},
}

Downloads: 0