{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T00:40:03Z","timestamp":1751676003781,"version":"3.41.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,4,16]],"date-time":"2022-04-16T00:00:00Z","timestamp":1650067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,4,16]],"date-time":"2022-04-16T00:00:00Z","timestamp":1650067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comput Stat"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s00180-022-01222-7","type":"journal-article","created":{"date-parts":[[2022,4,16]],"date-time":"2022-04-16T09:04:24Z","timestamp":1650099864000},"page":"3127-3151","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Results and student perspectives on a web-scraping assignment from Utah State University\u2019s data technologies course to evaluate the African activity in the statistical computing community"],"prefix":"10.1007","volume":"40","author":[{"given":"Adelyn","family":"Fleming","sequence":"first","affiliation":[]},{"given":"Joanna D.","family":"Coltrin","sequence":"additional","affiliation":[]},{"given":"Jhonatan","family":"Medri","sequence":"additional","affiliation":[]},{"given":"Cody","family":"Hilyard","sequence":"additional","affiliation":[]},{"given":"Rigoberto","family":"Tellez","sequence":"additional","affiliation":[]},{"given":"J\u00fcrgen","family":"Symanzik","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,4,16]]},"reference":[{"key":"1222_CR1","unstructured":"Auguie B (2017) gridExtra: miscellaneous functions for \u201cGrid\u201d graphics. R package version 2.3. https:\/\/CRAN.R-project.org\/package=gridExtra"},{"issue":"1","key":"1222_CR2","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s00180-014-0527-9","volume":"30","author":"N Balakrishnan","year":"2015","unstructured":"Balakrishnan N, Pal S (2015) An EM algorithm for the estimation of parameters of a flexible cure rate model with generalized gamma lifetime and model discrimination using likelihood- and information-based methods. Comput Stat 30(1):151\u2013189. https:\/\/doi.org\/10.1007\/s00180-014-0527-9","journal-title":"Comput Stat"},{"key":"1222_CR3","unstructured":"Dahl DB, Scott D, Roosen C, Magnusson A, Swinton J (2019) xtable: Export tables to LaTeX or HTML. R package version 1.8-4. https:\/\/CRAN.R-project.org\/package=xtable"},{"key":"1222_CR4","unstructured":"Dowle M, Srinivasan A (2019) data.table: Extension of \u2018data.frame\u2019. R package version 1.12.8. https:\/\/CRAN.R-project.org\/package=data.table"},{"key":"1222_CR5","unstructured":"Firke S (2020) Janitor: simple tools for examining and cleaning dirty data. R package version 2.0.1. https:\/\/CRAN.R-project.org\/package=janitor"},{"key":"1222_CR6","unstructured":"Grothendieck G (2017) sqldf: manipulate R data frames using SQL. R package version 0.4-11. https:\/\/CRAN.R-project.org\/package=sqldf"},{"key":"1222_CR7","doi-asserted-by":"publisher","unstructured":"Hardin J, Hoerl R, Horton NJ, Nolan D, Baumer B, Hall-Holt O, Murrell P, Peng R, Roback P, Temple Lang D, Ward MD (2015) Data science in statistics curricula: preparing students to \u201cThink with Data\u201d. Am Stati 69(4):343\u2013353. https:\/\/doi.org\/10.1080\/00031305.2015.1077729","DOI":"10.1080\/00031305.2015.1077729"},{"issue":"3","key":"1222_CR8","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1007\/s00180-015-0559-9","volume":"30","author":"J Kolbe","year":"2015","unstructured":"Kolbe J, Schulz R, Wersing M, Werwatz A (2015) Identifying Berlin\u2019s land value map using adaptive weights smoothing. Comput Stat 30(3):767\u2013790. https:\/\/doi.org\/10.1007\/s00180-015-0559-9","journal-title":"Comput Stat"},{"key":"1222_CR9","unstructured":"Medri J, Coltrin J, Fleming A, Hilyard C, Tellez R, Symanzik J (2021) Is Africa ready for a new regional IASC section? Results and student experiences from a web-scraping assignment. In: Moncayo-Martinez LA, Munoz DF (eds) LACSC2021 Proceedings, V Latin American conference on statistical computing April 19th-21st, 2021. Sello Editorial ITAM, Mexico City, pp 81\u201389"},{"issue":"3","key":"1222_CR10","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1111\/j.1467-8454.2004.00231.x","volume":"43","author":"IA Moosa","year":"2004","unstructured":"Moosa IA, Smith L (2004) Economic development indicators as determinants of medal winning at the Sydney Olympics: an extreme bounds analysis. Aust Econ Pap 43(3):288\u2013301. https:\/\/doi.org\/10.1111\/j.1467-8454.2004.00231.x","journal-title":"Aust Econ Pap"},{"issue":"2","key":"1222_CR11","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1111\/1467-9884.00307","volume":"51","author":"RH Morton","year":"2002","unstructured":"Morton RH (2002) Who won the Sydney 2000 Olympics? An allometric approach. J R Stat Soc Ser D 51(2):147\u2013155. https:\/\/doi.org\/10.1111\/1467-9884.00307","journal-title":"J R Stat Soc Ser D"},{"key":"1222_CR12","unstructured":"M\u00fcller K, Wickham H (2020) tibble: simple data frames. R package version 3.0.1. https:\/\/CRAN.R-project.org\/package=tibble"},{"key":"1222_CR13","doi-asserted-by":"crossref","unstructured":"Munzert S, Rubba C, Mei\u00dfner P, Nyhuis D (2014) Automated data collection with R: a practical guide to web scraping and text mining. Wiley, Chichester, UK","DOI":"10.1002\/9781118834732"},{"key":"1222_CR14","doi-asserted-by":"publisher","DOI":"10.1201\/9781420065183","volume-title":"Introduction to data technologies","author":"P Murrell","year":"2009","unstructured":"Murrell P (2009) Introduction to data technologies. Chapman and Hall, Boca Raton, FL"},{"key":"1222_CR15","unstructured":"Ooms J (2021) pdftools: text extraction, rendering and converting of pdf documents. R package version 3.0.1. https:\/\/CRAN.R-project.org\/package=pdftools"},{"issue":"1","key":"1222_CR16","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s00180-014-0526-x","volume":"30","author":"AG Pereira","year":"2015","unstructured":"Pereira AG, de Andrade BB (2015) On the genetic algorithm with adaptive mutation rate and selected statistical applications. Comput Stat 30(1):131\u2013150. https:\/\/doi.org\/10.1007\/s00180-014-0526-x","journal-title":"Comput Stat"},{"key":"1222_CR17","volume-title":"R: a language and environment for statistical computing","author":"R Core Team","year":"2019","unstructured":"R Core Team (2019) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna"},{"key":"1222_CR18","unstructured":"Rocks B, Lyttle I, Day N (2019) boxr: interface for the \u2018Box.com API\u2019. R package version 0.3.5. https:\/\/CRAN.R-project.org\/package=boxr"},{"issue":"2","key":"1222_CR19","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1080\/09332480.2016.1181966","volume":"29","author":"C Rundel","year":"2016","unstructured":"Rundel C, \u00c7etinkaya-Rundel M (2016) Taking a chance in the classroom: La Quinta is Spanish for \u201cNext to Denny\u2019s\u2019\u2019. Chance 29(2):53\u201357. https:\/\/doi.org\/10.1080\/09332480.2016.1181966","journal-title":"Chance"},{"issue":"4","key":"1222_CR20","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1080\/09332480.1996.11884584","volume":"9","author":"PM Sommers","year":"1996","unstructured":"Sommers PM (1996) Meddling with 1996 Olympic results. Chance 9(4):28\u201330. https:\/\/doi.org\/10.1080\/09332480.1996.11884584","journal-title":"Chance"},{"issue":"2","key":"1222_CR21","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1080\/09332480.1997.10542031","volume":"10","author":"PM Sommers","year":"1997","unstructured":"Sommers PM (1997) Tonga won the Atlanta Olympics! Chance 10(2):63\u201364. https:\/\/doi.org\/10.1080\/09332480.1997.10542031","journal-title":"Chance"},{"key":"1222_CR22","unstructured":"StatisticsTimescom (2020) List of continents by population. https:\/\/statisticstimes.com\/demographics\/continents-by-population.php"},{"key":"1222_CR23","unstructured":"Temple Lang D (2020) XML: tools for parsing and generating XML within R and S-Plus. R package version 3.99-0.3. https:\/\/CRAN.R-project.org\/package=XML"},{"key":"1222_CR24","unstructured":"United Nations, Department of Economic and Social Affairs, Population Division (2019) World Population Prospects 2019, Online Edition. Rev. 1. https:\/\/population.un.org\/wpp\/"},{"key":"1222_CR25","doi-asserted-by":"publisher","unstructured":"Wang B, Chen C, Liu K (2011) The research of Olympic medal ranking methods. In: 2011 2nd international conference on artificial intelligence, management science and electronic commerce (AIMSEC). IEEE, pp 7406\u20137410 (in Chinese). https:\/\/doi.org\/10.1109\/AIMSEC.2011.6011459","DOI":"10.1109\/AIMSEC.2011.6011459"},{"key":"1222_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24277-4","volume-title":"ggplot2: elegant graphics for data analysis","author":"H Wickham","year":"2016","unstructured":"Wickham H (2016) ggplot2: elegant graphics for data analysis, 2nd edn. Springer, New York","edition":"2"},{"key":"1222_CR27","unstructured":"Wickham H (2019) httr: tools for working with URLs and HTTP. R package version 1.4.1. https:\/\/CRAN.R-project.org\/package=httr"},{"key":"1222_CR28","unstructured":"Wickham H, Fran\u00e7ois R, Henry L, M\u00fcller K (2020) dplyr: a grammar of data manipulation. R package version 0.8.5. https:\/\/CRAN.R-project.org\/package=dplyr"},{"key":"1222_CR29","unstructured":"Wilke CO (2019) cowplot: streamlined plot theme and plot annotations for \u2018ggplot2\u2019. R package version 1.0.0. https:\/\/CRAN.R-project.org\/package=cowplot"},{"key":"1222_CR30","doi-asserted-by":"publisher","unstructured":"Zhao B (2017) Web scraping. In: Schintler L, McNeely C (eds) Encyclopedia of big data. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-319-32001-4_483-1","DOI":"10.1007\/978-3-319-32001-4_483-1"},{"key":"1222_CR31","unstructured":"Zhu H (2019) kableExtra: construct complex table with \u2018kable\u2019 and Pipe syntax. R package version 1.1.0. https:\/\/CRAN.R-project.org\/package=kableExtra"}],"container-title":["Computational Statistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00180-022-01222-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00180-022-01222-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00180-022-01222-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T00:03:01Z","timestamp":1751673781000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00180-022-01222-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,16]]},"references-count":31,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["1222"],"URL":"https:\/\/doi.org\/10.1007\/s00180-022-01222-7","relation":{},"ISSN":["0943-4062","1613-9658"],"issn-type":[{"type":"print","value":"0943-4062"},{"type":"electronic","value":"1613-9658"}],"subject":[],"published":{"date-parts":[[2022,4,16]]},"assertion":[{"value":"30 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}