@article{borer2009,
    title = {Some Simple Guidelines for Effective Data Management},
    volume = {90},
    issn = {0012-9623},
    url = {http://www.esajournals.org/doi/full/10.1890/0012-9623-90.2.205},
    doi = {10.1890/0012-9623-90.2.205},
    number = {2},
    urldate = {2013-12-11},
    journal = {Bulletin of the Ecological Society of America},
    author = {Borer, E. T. and Seabloom, E. W. and Jones, M. B. and Schildhauer, M.},
    month = apr,
    year = {2009},
    pages = {205--214}
}

@misc{datacarpentry2016,
    title = {Spreadsheets for Ecology},
    url = {http://www.datacarpentry.org/spreadsheet-ecology-lesson/},
    urldate = {2016-08-08},
    author = {{Data Carpentry}}
}

@misc{leek2016,
    title = {How to share data with a statistician},
    url = {https://github.com/jtleek/datasharing},
    abstract = {datasharing - The Leek group guide to data sharing},
    urldate = {2016-08-08},
    journal = {GitHub},
    author = {J. Leek}
}

@article{white2013,
    title = {Nine simple ways to make it easier to (re)use your data},
    volume = {6},
    issn = {1918-3178},
    url = {http://ojs.library.queensu.ca/index.php/IEE/article/view/4608},
    doi = {10.4033/iee.v6i2.4608},
    number = {2},
    journal = {Ideas in Ecology and Evolution},
    author = {White, E. P. and Baldridge, E. and Brym, Z. T. and Locey, K. J. and McGlinn, D. J. and Supp, S. R.},
    month = Aug,
    year = {2013}
}

@article{wickham2014,
   author = {H. Wickham},
   title = {Tidy Data},
   journal = {Journal of Statistical Software},
   volume = {59},
   year = {2014},
   keywords = {},
   abstract = {A huge amount of effort is spent cleaning data to get it ready for analysis, but there has been little research on how to make data cleaning as easy and effective as possible. This paper tackles a small, but important, component of data cleaning: data tidying. Tidy datasets are easy to manipulate, model and visualize, and have a specific structure: each variable is a column, each observation is a row, and each type of observational unit is a table. This framework makes it easy to tidy messy datasets because only a small set of tools are needed to deal with a wide range of un-tidy datasets. This structure also makes it easier to develop tidy tools for data analysis, tools that both input and output tidy datasets. The advantages of a consistent data structure and matching tools are demonstrated with a case study free from mundane data manipulation chores.},
   issn = {1548-7660},
   pages = {1--23},
   doi = {10.18637/jss.v059.i10},
   url = {https://www.jstatsoft.org/index.php/jss/article/view/v059i10}
}

@article{zeeberg2004,
    title = {Mistaken identifiers: gene name errors can be introduced inadvertently when using {Excel} in bioinformatics},
    volume = {5},
    issn = {1471-2105},
    shorttitle = {Mistaken identifiers},
    doi = {10.1186/1471-2105-5-80},
    abstract = {BACKGROUND: When processing microarray data sets, we recently noticed that some gene names were being changed inadvertently to non-gene names.
RESULTS: A little detective work traced the problem to default date format conversions and floating-point format conversions in the very useful Excel program package. The date conversions affect at least 30 gene names; the floating-point conversions affect at least 2,000 if Riken identifiers are included. These conversions are irreversible; the original gene names cannot be recovered.
CONCLUSIONS: Users of Excel for analyses involving gene names should be aware of this problem, which can cause genes, including medically important ones, to be lost from view and which has contaminated even carefully curated public databases. We provide work-arounds and scripts for circumventing the problem.},
    language = {eng},
    journal = {BMC Bioinformatics},
    author = {Zeeberg, B. R. and Riss, J. and Kane, D. W. and Bussey, K. J. and Uchio, E. and Linehan, W. M. and Barrett, J. C. and Weinstein, J. N.},
    month = jun,
    year = {2004},
    pmid = {15214961},
    pmcid = {PMC459209},
    keywords = {Animals, Computational Biology, Genes, Humans, Mice, Oligonucleotide Array Sequence Analysis, Research Design, Software},
    pages = {80}
}

@article{casimir1992,
    title = {Real Programmers Don't Use Spreadsheets},
    volume = {27},
    issn = {0362-1340},
    url = {http://doi.acm.org/10.1145/130981.130982},
    doi = {10.1145/130981.130982},
    number = {6},
    urldate = {2016-08-21},
    journal = {SIGPLAN Not.},
    author = {Casimir, R. J.},
    month = jun,
    year = {1992},
    pages = {10--16}
}

@incollection{wagner2006,
    series = {{INFORMS} Tutorials in Operations Research},
    title = {Enhance Your Own Research Productivity Using Spreadsheets},
    isbn = {978-1-877640-20-9},
    url = {http://pubsonline.informs.org/doi/abs/10.1287/educ.1063.0028},
    doi = {10.1287/educ.1063.0028},
    urldate = {2016-08-21},
    booktitle = {Models, Methods, and Applications for Innovative Decision Making},
    publisher = {INFORMS},
    author = {J. M. Wagner and J. Keisler},
    month = sep,
    year = {2006},
    pages = {148--162}
}

@incollection{chadwick2003,
    series = {{IFIP} — The International Federation for Information Processing},
    title = {Stop That Subversive Spreadsheet!},
    copyright = {©2003 Springer Science+Business Media New York},
    isbn = {978-1-4757-5535-0 978-0-387-35693-8},
    url = {http://link.springer.com/chapter/10.1007/978-0-387-35693-8_13},
    abstract = {This paper documents the formation of the European Spreadsheet Risks Interest Group (EuSpRIG http://​www.​eusprig.​org) and outlines some of the research undertaken and reported upon by interested parties in EuSpRIG publications.},
    language = {en},
    number = {124},
    urldate = {2016-08-21},
    booktitle = {Integrity and Internal Control in Information Systems V},
    publisher = {Springer US},
    author = {Chadwick, D.},
    editor = {Gertz, M.},
    year = {2003},
    note = {DOI: 10.1007/978-0-387-35693-8\_13},
    keywords = {Accounting/Auditing, engineering, eusprig, Information Systems Applications (incl. Internet), integrity, Management of Computing and Information Systems, risks, spreadsheet, Theory of Computation},
    pages = {205--211}
}

@article{brown1987,
    title = {An Experimental Study of People Creating Spreadsheets},
    volume = {5},
    issn = {1046-8188},
    url = {http://doi.acm.org/10.1145/27641.28058},
    doi = {10.1145/27641.28058},
    abstract = {Nine experienced users of electronic spreadsheets each created three spreadsheets. Although participants were quite confident that their spreadsheets were accurate, 44 percent of the spreadsheets contained user-generated programming errors. With regard to the spreadsheet creation process, we found that experienced spreadsheet users spend a large percentage of their time using the cursor keys, primarily for the purpose of moving the cursor around the spreadsheet. Users did not spend a lot of time planning before launching into spreadsheet creation, nor did they spend much time in a separate, systematic debugging stage. Participants spent 21 percent of their time pausing, presumably reading and/or thinking, prior to the initial keystrokes of spreadsheet creation episodes.},
    number = {3},
    urldate = {2016-08-21},
    journal = {ACM Trans. Inf. Syst.},
    author = {Brown, P. S. and Gould, J. D.},
    month = jul,
    year = {1987},
    pages = {258--272}
}

@inproceedings{panko1996,
    title = {Spreadsheets on trial: a survey of research on spreadsheet risks},
    volume = {2},
    shorttitle = {Spreadsheets on trial},
    doi = {10.1109/HICSS.1996.495416},
    abstract = {Even the earliest writers in end user computing remarked on the potential dangers of end user spreadsheet development. Until recently, there was only anecdotal evidence to support their concerns. Now, there is considerable evidence from experiments, field audits, and surveys of end users and organizations that early concerns were well-founded. The paper presents a framework for risks in spreadsheeting and organizes selected research findings in terms of this framework},
    booktitle = {Proceedings of the Twenty-Ninth Hawaii International Conference on System Sciences, 1996},
    author = {Panko, R. R. and Halverson, R. P.},
    month = jan,
    year = {1996},
    keywords = {administrative data processing, Books, Costs, Debugging, Degradation, end user computing, end user spreadsheet development, Error analysis, Error correction, errors, experiments, field audits, Laboratories, Logic, office automation, personal computing, reviews, risk management, software engineering, spreadsheet programs, spreadsheet risks, surveys, systems analysis, Taxonomy},
    pages = {326--335 vol.2}
}

@misc{panko2008,
    title = {What We Know About Spreadsheet Errors},
    url = {http://panko.shidler.hawaii.edu/SSR/Mypapers/whatknow.htm},
    urldate = {2016-08-21},
    author = {Panko, R.},
    year = {2008},
    file = {What We Know About Spreadsheet Errors:/Users/Kara/Library/Application Support/Zotero/Profiles/cqr2h477.default/zotero/storage/C6R5FIU7/whatknow.html:text/html}
}

@article{powell2008,
    title = {A critical review of the literature on spreadsheet errors},
    volume = {46},
    issn = {0167-9236},
    url = {http://www.sciencedirect.com/science/article/pii/S0167923608001127},
    doi = {10.1016/j.dss.2008.06.001},
    abstract = {Among those who study spreadsheet use, it is widely accepted that errors are prevalent in operational spreadsheets and that errors can lead to poor decisions and cost millions of dollars. However, relatively little is known about what types of errors actually occur, how they were created, how they can be detected, and how they can be avoided or minimized. This paper summarizes and critiques the research literature on spreadsheet errors from the viewpoint of a manager who wishes to improve operational spreadsheet quality. We also offer suggestions for future research directions that can improve the state of knowledge about spreadsheet errors and mitigate spreadsheet risks.},
    number = {1},
    urldate = {2016-08-21},
    journal = {Decision Support Systems},
    author = {Powell, S. G. and Baker, K. R. and Lawson, B.},
    month = dec,
    year = {2008},
    keywords = {Decision support, End-user computing, Error classification, Spreadsheets},
    pages = {128--138}
}

@misc{woo2014,
    title = {Abandon all hope, ye who enter dates in {Excel}},
    url = {https://datapub.cdlib.org/2014/04/09/abandon-all-hope-ye-who-enter-dates-in-excel/},
    abstract = {Big thanks to Kara Woo of Washington State University for this guest blog post! Update: The XLConnect package has been updated to fix the problem described below; however, other R packages for inte…},
    urldate = {2016-08-21},
    journal = {Data Pub},
    author = {Woo, K. H.},
    month = apr,
    year = {2014},
    file = {Snapshot:/Users/Kara/Library/Application Support/Zotero/Profiles/cqr2h477.default/zotero/storage/7IRRZUJ3/abandon-all-hope-ye-who-enter-dates-in-excel.html:text/html}
}

@article{milne2015,
    title = {Spreadsheets and the Violence of Forms: Tracking Organisational and Domestic Use},
    volume = {18},
    copyright = {Copyright (c) 2015 Esther Milne},
    issn = {14412616},
    shorttitle = {Spreadsheets and the Violence of Forms},
    url = {http://www.journal.media-culture.org.au/index.php/mcjournal/article/view/1023},
    language = {en},
    number = {5},
    urldate = {2016-08-22},
    journal = {M/C Journal},
    author = {Milne, E.},
    month = aug,
    year = {2015}
}

@misc{eusprig2016,
    title = {European Spreadsheet Risks Interest Group - spreadsheet risk management and solutions conference},
    url = {http://www.eusprig.org/horror-stories.htm},
    urldate = {2016-08-22},
    file = {European Spreadsheet Risks Interest Group - spreadsheet risk management and solutions conference:/Users/Kara/Library/Application Support/Zotero/Profiles/cqr2h477.default/zotero/storage/VGWSIAA3/horror-stories.html:text/html}
}

@article{ziemann2016,
    title = {Gene name errors are widespread in the scientific literature},
    volume = {17},
    issn = {1474-760X},
    url = {http://dx.doi.org/10.1186/s13059-016-1044-7},
    doi = {10.1186/s13059-016-1044-7},
    abstract = {The spreadsheet software Microsoft Excel, when used with default settings, is known to convert gene names to dates and floating-point numbers. A programmatic scan of leading genomics journals reveals that approximately one-fifth of papers with supplementary Excel gene lists contain erroneous gene name conversions.},
    urldate = {2016-09-27},
    journal = {Genome Biology},
    author = {Ziemann, M. and Eren, Y. and El-Osta, A.},
    year = {2016},
    keywords = {Gene symbol, Microsoft Excel, Supplementary data},
    pages = {177},
    annote = {Pages 1-3 in PDF},
    file = {Full Text PDF:/Users/Kara/Library/Application Support/Zotero/Profiles/cqr2h477.default/zotero/storage/3HUHEKIR/Ziemann et al. - 2016 - Gene name errors are widespread in the scientific .pdf:application/pdf;Snapshot:/Users/Kara/Library/Application Support/Zotero/Profiles/cqr2h477.default/zotero/storage/A92592VF/s13059-016-1044-7.html:text/html}
}

@incollection{murrell2013,
    title = {Data intended for human consumption, not machine consumption},
    author = {P. Murrell},
    bookauthor = {Q. E. MacCallum},
    booktitle = {Bad Data Handbook},
    publisher = {O'Reilly Media},
    address = {Sebastopol, CA},
    year = {2013},
    pages = {31--51},
    chapter = {3}
}


@misc{briney2017,
    title = {Two strategies for working with dates in {E}xcel},
    author = {K. Briney},
    year = {2017},
    date = {2017-07-27},
    url = {http://dataabinitio.com/?p=798}
}