# Datasaurus dozen > Mediated Wiki article. Canonical URL: https://mediated.wiki/source/Datasaurus_dozen > Markdown URL: https://mediated.wiki/source/Datasaurus_dozen.md > Source: https://en.wikipedia.org/wiki/Datasaurus_dozen > Source revision: 1353914246 > License: Creative Commons Attribution-ShareAlike 4.0 International (https://creativecommons.org/licenses/by-sa/4.0/) {{Short description|Collection of statistical data sets}} {{Data Visualization}} The '''Datasaurus dozen''' comprises [thirteen](/source/Baker's_dozen) [data set](/source/data_set)s that have nearly identical simple [descriptive statistics](/source/descriptive_statistics) to two decimal places, yet have very different [distributions](/source/Probability_distribution) and appear very different when [graphed](/source/Plot_(graphics)).{{Cite book |last1=Matejka |first1=Justin |last2=Fitzmaurice |first2=George |chapter=Same Stats, Different Graphs: Generating Datasets with Varied Appearance and Identical Statistics through Simulated Annealing |date=2017-05-02 |title=Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems |chapter-url=https://doi.org/10.1145/3025453.3025912 |series=CHI '17 |location=New York, NY, USA |publisher=Association for Computing Machinery |pages=1290–1294 |doi=10.1145/3025453.3025912 |isbn=978-1-4503-4655-9 |archive-url=https://research.autodesk.com/app/uploads/2023/03/same-stats-different-graphs.pdf_rec2hRjLLGgM7Cn2T.pdf |archive-date=2017-05-02}} It was inspired by the smaller [Anscombe's quartet](/source/Anscombe's_quartet) that was created in 1973. == Data == The following table contains summary statistics for all thirteen data sets. {| class="wikitable" !Property !Value !Accuracy |- |Number of elements |142 |exact |- |[Mean](/source/Mean) of ''x'' |54.26 |to 2 decimal places |- |Sample [variance](/source/variance) of ''x'': ''s''{{supsub|2|''x''}} |16.76 |to 2 decimal places |- |Mean of ''y'' |47.83 |to 2 decimal places |- |Sample variance of ''y'': ''s''{{supsub|2|''y''}} |26.93 |to 2 decimal places |- |[Correlation](/source/Correlation) between ''x'' and ''y'' | −0.06 |to 3 decimal places |- |[Linear regression](/source/Linear_regression) line |''y'' = 53 − 0.1''x'' |to 0 and 1 decimal places, respectively |- |[Coefficient of determination](/source/Coefficient_of_determination) of the linear regression: R^2 |0.004 |to 3 decimal places |} alt=thirteen graphs of the datasets in the Datasaurus Dozen, visualized graphically and also summarized numerically to show their statistical summaries are similar, while their graphical representations are not similar|thumb|318x318px|The thirteen data sets in the Datasaurus Dozen, visualized and summarized The thirteen data sets were labeled as the following: {{div col|colwidth=8em}} * away * bullseye * circle * dino * dots * h_lines * high_lines * slant_down * slant_up * star * v_line * wide_lines * x_shape {{div col end}} Similar to [Anscombe's quartet](/source/Anscombe's_quartet), the Datasaurus dozen was designed to further illustrate the importance of looking at a set of data graphically before starting to analyze according to a particular type of relationship, and the inadequacy of basic statistic properties for describing realistic data sets.{{cite book |last=Elert |first=Glenn |year=2021 |chapter=Linear Regression - Practice |chapter-url=http://physics.info/linear-regression/practice.shtml#4 |title=The Physics Hypertextbook}}{{cite book |last=Janert |first=Philipp K. |url=https://archive.org/details/isbn_9780596802356/page/65 |title=Data Analysis with Open Source Tools |publisher=[O'Reilly Media](/source/O'Reilly_Media) |year=2010 |isbn=978-0-596-80235-6 |pages=[https://archive.org/details/isbn_9780596802356/page/65 65–66]}}{{cite book |last1=Chatterjee |first1=Samprit |title=Regression Analysis by Example |last2=Hadi |first2=Ali S. |publisher=John Wiley and Sons |year=2006 |isbn=0-471-74696-7 |page=91}}{{cite book |last1=Saville |first1=David J. |title=Statistical Methods: The geometric approach |last2=Wood |first2=Graham R. |publisher=[Springer](/source/Springer_Science%2BBusiness_Media) |year=1991 |isbn=0-387-97517-9 |page=418}}{{cite book |last=Tufte |first=Edward R. |url=https://archive.org/details/visualdisplayofq00tuft |title=The Visual Display of Quantitative Information |publisher=Graphics Press |year=2001 |isbn=0-9613921-4-2 |edition=2nd |location=Cheshire, CT |authorlink=Edward Tufte}} == Creation == [[File:Datasaurus.png|thumb|The dinosaur data set created by [Alberto Cairo](/source/Alberto_Cairo) that inspired the creation of the Datasaurus Dozen]]The first data set, in the shape of a [Tyrannosaurus](/source/Tyrannosaurus), that inspired the rest of the "datasaurus" data set was constructed in 2016 by [Alberto Cairo](/source/Alberto_Cairo).{{Cite web |last=Cairo |first=Alberto |title=Download the Datasaurus: Never trust summary statistics alone; always visualize your data |url=http://www.thefunctionalart.com/2016/08/download-datasaurus-never-trust-summary.html |access-date=2024-02-01 |archive-date=2024-06-20 |archive-url=https://web.archive.org/web/20240620205540/http://www.thefunctionalart.com/2016/08/download-datasaurus-never-trust-summary.html |url-status=dead }}{{Cite web |last=Murtagh |first=Jack |date=2024-02-01 |title=What This Graph of a Dinosaur Can Teach Us about Doing Better Science |url=https://www.scientificamerican.com/article/what-this-graph-of-a-dinosaur-can-teach-us-about-doing-better-science/ |access-date=2024-03-08 |website=Scientific American |language=en}} It was proposed by Maarten Lambrechts that this data set also be called "Anscombosaurus". This data set was then accompanied by twelve other data sets that were created by Justin Matejka and George Fitzmaurice at [Autodesk](/source/Autodesk). Unlike Anscombe's quartet, where it is not known how the data set was generated,{{cite journal |last1=Chatterjee |first1=Sangit |last2=Firat |first2=Aykut |year=2007 |title=Generating Data with Identical Statistics but Dissimilar Graphics: A follow up to the Anscombe dataset |journal=[The American Statistician](/source/The_American_Statistician) |volume=61 |issue=3 |pages=248–254 |doi=10.1198/000313007X220057 |jstor=27643902 |s2cid=121163371}} the authors used [simulated annealing](/source/simulated_annealing) to make these data sets. They made small, random, and biased changes to each point towards the desired shape. Each shape took 200,000 iterations of perturbations to complete. The [pseudocode](/source/pseudocode) for this algorithm is as follows: current_ds ← initial_ds for x iterations, do: test_ds ← perturb(current_ds, temp) if similar_enough(test_ds, initial_ds): current_ds ← test_ds function perturb(ds, temp): loop: test ← move_random_points(ds) if fit(test) > fit(ds) or temp > random(): return test where * initial_ds is the seed data set * current_ds is the latest version of the data set * fit() is a function used to check whether moving the points gets closer to the desired shape * temp is the temperature of the simulated annealing algorithm * similar_enough() is a function that checks whether the statistics for the two given data sets are similar enough * move_random_points() is a function that randomly moves data points == See also == * [Exploratory data analysis](/source/Exploratory_data_analysis) * [Goodness of fit](/source/Goodness_of_fit) * [Regression validation](/source/Regression_validation) * [Simpson's paradox](/source/Simpson's_paradox) * [Statistical model validation](/source/Statistical_model_validation) * [Anscombe's quartet](/source/Anscombe's_quartet) ==References== {{Reflist}} ==External links== * [https://www.autodeskresearch.com/publications/samestats Animated examples from Autodesk] for the Datasaurus Dozen datasets * [https://cran.r-project.org/package=datasauRus datasauRus], datasets from the Datasaurus Dozen in [R](/source/R_(programming_language)) * The Datasaurus Dozen in [CSV](/source/Comma-separated_values) and [tab-delimited files](/source/Tab-separated_values) https://www.openintro.org/data/index.php?data=datasaurus Category:Misuse of statistics Category:Statistical charts and diagrams Category:Statistical data sets Category:Data and information visualization --- Adapted from the Wikipedia article [Datasaurus dozen](https://en.wikipedia.org/wiki/Datasaurus_dozen) by Wikipedia contributors ([contributor history](https://en.wikipedia.org/wiki/Datasaurus_dozen?action=history)). Available under [Creative Commons Attribution-ShareAlike 4.0 International](https://creativecommons.org/licenses/by-sa/4.0/). Changes may have been made.