% =============================================================================
% BIS 527 -- shared bibliography for scribe notes.
%
% Add the references you actually cite. Keep the keys descriptive
% (author-year-word) so the file stays readable as it grows across the
% semester. Entries below are the ones used by the two example scribe notes.
%
% One key per work. If you find two keys for the same work, merge them --
% duplicates are how a citation quietly ends up pointing at the wrong entry.
% =============================================================================

% --- What data science is: history and framing -------------------------------

@book{graunt1662observations,
  author    = {Graunt, John},
  title     = {Natural and Political Observations Made upon the Bills of Mortality},
  publisher = {Thomas Roycroft},
  address   = {London},
  year      = {1662}
}

@book{taisbak2003euclid,
  author    = {Taisbak, Christian Marinus},
  title     = {Euclid's {Data}: The Importance of Being Given},
  publisher = {Museum Tusculanum Press},
  address   = {Copenhagen},
  year      = {2003}
}

@book{popper1959logic,
  author    = {Popper, Karl R.},
  title     = {The Logic of Scientific Discovery},
  publisher = {Hutchinson},
  address   = {London},
  year      = {1959}
}

@book{fisher1935design,
  author    = {Fisher, Ronald A.},
  title     = {The Design of Experiments},
  publisher = {Oliver and Boyd},
  address   = {Edinburgh},
  year      = {1935}
}

@book{stigler2016pillars,
  author    = {Stigler, Stephen M.},
  title     = {The Seven Pillars of Statistical Wisdom},
  publisher = {Harvard University Press},
  address   = {Cambridge, MA},
  year      = {2016}
}

@article{tukey1962future,
  author  = {Tukey, John W.},
  title   = {The Future of Data Analysis},
  journal = {The Annals of Mathematical Statistics},
  volume  = {33},
  number  = {1},
  pages   = {1--67},
  year    = {1962}
}

@book{naur1974survey,
  author    = {Naur, Peter},
  title     = {Concise Survey of Computer Methods},
  publisher = {Studentlitteratur},
  address   = {Lund, Sweden},
  year      = {1974}
}

@article{cleveland2001datascience,
  author  = {Cleveland, William S.},
  title   = {Data Science: An Action Plan for Expanding the Technical Areas of
             the Field of Statistics},
  journal = {International Statistical Review},
  volume  = {69},
  number  = {1},
  pages   = {21--26},
  year    = {2001}
}

@article{davenport2012sexiest,
  author  = {Davenport, Thomas H. and Patil, D. J.},
  title   = {Data Scientist: The Sexiest Job of the 21st Century},
  journal = {Harvard Business Review},
  volume  = {90},
  number  = {10},
  pages   = {70--76},
  year    = {2012}
}

@article{breiman2001cultures,
  author  = {Breiman, Leo},
  title   = {Statistical Modeling: The Two Cultures},
  journal = {Statistical Science},
  volume  = {16},
  number  = {3},
  pages   = {199--231},
  year    = {2001}
}

@article{donoho201750years,
  author  = {Donoho, David},
  title   = {50 Years of Data Science},
  journal = {Journal of Computational and Graphical Statistics},
  volume  = {26},
  number  = {4},
  pages   = {745--766},
  year    = {2017}
}

@book{gitelman2013rawdata,
  editor    = {Gitelman, Lisa},
  title     = {``Raw Data'' Is an Oxymoron},
  publisher = {MIT Press},
  address   = {Cambridge, MA},
  year      = {2013}
}

@article{lazer2014googleflu,
  author  = {Lazer, David and Kennedy, Ryan and King, Gary and
             Vespignani, Alessandro},
  title   = {The Parable of {Google Flu}: Traps in Big Data Analysis},
  journal = {Science},
  volume  = {343},
  number  = {6176},
  pages   = {1203--1205},
  year    = {2014}
}

@article{wing2006computational,
  author  = {Wing, Jeannette M.},
  title   = {Computational Thinking},
  journal = {Communications of the ACM},
  volume  = {49},
  number  = {3},
  pages   = {33--35},
  year    = {2006}
}

@article{obermeyer2019dissecting,
  author  = {Obermeyer, Ziad and Powers, Brian and Vogeli, Christine and
             Mullainathan, Sendhil},
  title   = {Dissecting Racial Bias in an Algorithm Used to Manage the Health
             of Populations},
  journal = {Science},
  volume  = {366},
  number  = {6464},
  pages   = {447--453},
  year    = {2019}
}

% --- Computing: what a procedure is, and what machines now write -------------

@book{knuth1997fundamental,
  author    = {Knuth, Donald E.},
  title     = {The Art of Computer Programming, Volume 1: Fundamental Algorithms},
  edition   = {3rd},
  publisher = {Addison-Wesley},
  address   = {Reading, MA},
  year      = {1997},
  note      = {Section~1.1 discusses the derivation of the word ``algorithm''.}
}

@article{turing1936computable,
  author  = {Turing, Alan M.},
  title   = {On Computable Numbers, with an Application to the
             {Entscheidungsproblem}},
  journal = {Proceedings of the London Mathematical Society},
  volume  = {s2-42},
  number  = {1},
  pages   = {230--265},
  year    = {1936},
  note    = {Issue published 1937; conventionally cited as 1936.}
}

@article{good1979turing,
  author  = {Good, Irving J.},
  title   = {Studies in the History of Probability and Statistics. {XXXVII}:
             {A. M. Turing's} Statistical Work in {World War II}},
  journal = {Biometrika},
  volume  = {66},
  number  = {2},
  pages   = {393--396},
  year    = {1979}
}

@article{turing1950computing,
  author  = {Turing, Alan M.},
  title   = {Computing Machinery and Intelligence},
  journal = {Mind},
  volume  = {59},
  number  = {236},
  pages   = {433--460},
  year    = {1950}
}

@article{bommasani2021foundation,
  author  = {Bommasani, Rishi and Hudson, Drew A. and Adeli, Ehsan and others},
  title   = {On the Opportunities and Risks of Foundation Models},
  journal = {arXiv preprint arXiv:2108.07258},
  year    = {2021}
}

@article{shumailov2024collapse,
  author  = {Shumailov, Ilia and Shumaylov, Zakhar and Zhao, Yiren and
             Papernot, Nicolas and Anderson, Ross and Gal, Yarin},
  title   = {{AI} Models Collapse When Trained on Recursively Generated Data},
  journal = {Nature},
  volume  = {631},
  pages   = {755--759},
  year    = {2024}
}

% --- Causal inference --------------------------------------------------------

@article{neyman1923application,
  author  = {Splawa-Neyman, Jerzy},
  title   = {On the Application of Probability Theory to Agricultural
             Experiments. Essay on Principles. Section 9},
  journal = {Statistical Science},
  volume  = {5},
  number  = {4},
  pages   = {465--472},
  year    = {1990},
  note    = {Translated and edited by D.~M. Dabrowska and T.~P. Speed from the
             Polish original in \emph{Roczniki Nauk Rolniczych} X (1923), 1--51.}
}

@article{rubin1974estimating,
  author  = {Rubin, Donald B.},
  title   = {Estimating Causal Effects of Treatments in Randomized and
             Nonrandomized Studies},
  journal = {Journal of Educational Psychology},
  volume  = {66},
  number  = {5},
  pages   = {688--701},
  year    = {1974}
}

@book{pearl2009causality,
  author    = {Pearl, Judea},
  title     = {Causality: Models, Reasoning, and Inference},
  edition   = {2nd},
  publisher = {Cambridge University Press},
  address   = {Cambridge, UK},
  year      = {2009}
}

@book{pearl2018bookofwhy,
  author    = {Pearl, Judea and Mackenzie, Dana},
  title     = {The Book of Why: The New Science of Cause and Effect},
  publisher = {Basic Books},
  address   = {New York},
  year      = {2018}
}

% --- Snow and the 1854 outbreak ----------------------------------------------

@book{snow1855cholera,
  author    = {Snow, John},
  title     = {On the Mode of Communication of Cholera},
  edition   = {2nd},
  publisher = {John Churchill},
  address   = {London},
  year      = {1855}
}

@incollection{snow1855report,
  author    = {Snow, John},
  title     = {Dr.\ {Snow's} Report},
  booktitle = {Report on the Cholera Outbreak in the Parish of St.\ James,
               Westminster, during the Autumn of 1854},
  publisher = {Cholera Inquiry Committee, J. Churchill},
  address   = {London},
  pages     = {97--120},
  year      = {1855}
}

@article{freedman1991shoe,
  author  = {Freedman, David A.},
  title   = {Statistical Models and Shoe Leather},
  journal = {Sociological Methodology},
  volume  = {21},
  pages   = {291--313},
  year    = {1991}
}

% --- Complexity, sorting, and searching --------------------------------------

@book{clrs2022,
  author    = {Cormen, Thomas H. and Leiserson, Charles E. and
               Rivest, Ronald L. and Stein, Clifford},
  title     = {Introduction to Algorithms},
  edition   = {4th},
  publisher = {MIT Press},
  address   = {Cambridge, MA},
  year      = {2022}
}

@book{knuth1998sorting,
  author    = {Knuth, Donald E.},
  title     = {The Art of Computer Programming, Volume 3: Sorting and Searching},
  edition   = {2nd},
  publisher = {Addison-Wesley},
  address   = {Reading, MA},
  year      = {1998}
}

@article{hoare1962quicksort,
  author  = {Hoare, C. A. R.},
  title   = {Quicksort},
  journal = {The Computer Journal},
  volume  = {5},
  number  = {1},
  pages   = {10--16},
  year    = {1962}
}

@book{sedgewick2011algorithms,
  author    = {Sedgewick, Robert and Wayne, Kevin},
  title     = {Algorithms},
  edition   = {4th},
  publisher = {Addison-Wesley},
  address   = {Upper Saddle River, NJ},
  year      = {2011}
}

@book{bentley2000pearls,
  author    = {Bentley, Jon},
  title     = {Programming Pearls},
  edition   = {2nd},
  publisher = {ACM Press / Addison-Wesley},
  address   = {Reading, MA},
  year      = {2000}
}

@article{musser1997introsort,
  author  = {Musser, David R.},
  title   = {Introspective Sorting and Selection Algorithms},
  journal = {Software: Practice and Experience},
  volume  = {27},
  number  = {8},
  pages   = {983--993},
  year    = {1997}
}

@misc{peters2002timsort,
  author       = {Peters, Tim},
  title        = {\texttt{listsort.txt}: Description of Python's List Sort},
  howpublished = {CPython source distribution, \texttt{Objects/listsort.txt}},
  year         = {2002}
}

% --- Added for Lecture 1 (2026-09-06). Checked against primary sources. ------

@article{student1908probable,
  author  = {{Student}},
  title   = {The Probable Error of a Mean},
  journal = {Biometrika},
  volume  = {6},
  number  = {1},
  pages   = {1--25},
  year    = {1908},
  note    = {Pseudonym of William Sealy Gosset}
}

@book{pearson1990student,
  author    = {Pearson, Egon S.},
  title     = {`{Student}': A Statistical Biography of William Sealy Gosset},
  note      = {Edited and augmented by R. L. Plackett, with the assistance of
               G. A. Barnard},
  publisher = {Clarendon Press},
  address   = {Oxford},
  year      = {1990}
}

@article{wild1999statistical,
  author  = {Wild, Chris J. and Pfannkuch, Maxine},
  title   = {Statistical Thinking in Empirical Enquiry},
  journal = {International Statistical Review},
  volume  = {67},
  number  = {3},
  pages   = {223--248},
  year    = {1999}
}

@inproceedings{parikh2022credence,
  author    = {Parikh, Harsh and Varjao, Carlos and Xu, Louise and
               Tchetgen Tchetgen, Eric},
  title     = {Validating Causal Inference Methods},
  booktitle = {Proceedings of the 39th International Conference on Machine
               Learning},
  series    = {Proceedings of Machine Learning Research},
  volume    = {162},
  pages     = {17346--17358},
  publisher = {PMLR},
  year      = {2022}
}

@misc{zhang2026causalmix,
  author       = {Zhang, Qi and Parikh, Harsh and Naimi, Ashley and
                  Nabi, Razieh and Kim, Christopher and Lash, Timothy},
  title        = {Controllable Generative Sandbox for Causal Inference},
  howpublished = {arXiv preprint arXiv:2603.03587},
  year         = {2026},
  note         = {Preprint; not peer reviewed}
}

@inproceedings{cheng2023gpt4,
  author    = {Cheng, Liying and Li, Xingxuan and Bing, Lidong},
  title     = {Is {GPT-4} a Good Data Analyst?},
  booktitle = {Findings of the Association for Computational Linguistics:
               EMNLP 2023},
  pages     = {9496--9514},
  publisher = {Association for Computational Linguistics},
  address   = {Singapore},
  year      = {2023}
}

@article{noy2023experimental,
  author  = {Noy, Shakked and Zhang, Whitney},
  title   = {Experimental Evidence on the Productivity Effects of Generative
             Artificial Intelligence},
  journal = {Science},
  volume  = {381},
  number  = {6654},
  pages   = {187--192},
  year    = {2023}
}

@techreport{dellacqua2023jagged,
  author      = {Dell'Acqua, Fabrizio and McFowland III, Edward and
                 Mollick, Ethan R. and Lifshitz-Assaf, Hila and
                 Kellogg, Katherine and Rajendran, Saran and Krayer, Lisa and
                 Candelon, Fran\c{c}ois and Lakhani, Karim R.},
  title       = {Navigating the Jagged Technological Frontier: Field
                 Experimental Evidence of the Effects of Artificial
                 Intelligence on Knowledge Worker Productivity and Quality},
  institution = {Harvard Business School},
  type        = {Technology and Operations Management Unit Working Paper},
  number      = {24-013},
  year        = {2023}
}

@article{fisher1922foundations,
  author  = {Fisher, Ronald A.},
  title   = {On the Mathematical Foundations of Theoretical Statistics},
  journal = {Philosophical Transactions of the Royal Society of London,
             Series A},
  volume  = {222},
  pages   = {309--368},
  year    = {1922}
}

% --- Added for Lecture 2 (2026-09-06). Checked against primary sources. ------
% Title, author, journal, pages and year from the Duke Scholars catalogue
% record; volume, number and DOI from the ACM Digital Library listing.

@article{astrachan2003bubble,
  author  = {Astrachan, Owen},
  title   = {Bubble Sort: An Archaeological Algorithmic Analysis},
  journal = {ACM SIGCSE Bulletin},
  volume  = {35},
  number  = {1},
  pages   = {1--5},
  year    = {2003},
  doi     = {10.1145/792548.611918}
}