My academic interests are multidisciplinary but fall at the intersection of information and statistical science. I use quantitative methods to explore human-centered questions with an emphasis on data concerns. I am interested in not only statistical science, that is, drawing quantitative inferences from real-world data, but also in information science, through my emphasis on all aspects of obtaining, preparing, storing, and sharing data.
My work is arranged around three tranches:
- Multilevel regression with post-stratification (MRP).
- Natural language processing (NLP).
- Statistical workflow.
Papers
- Annie Collins and Rohan Alexander, 2021, ‘Reproducibility of COVID-19 pre-prints’, arXiv, 22 July, https://arxiv.org/abs/2107.10724.
- Rohan Alexander, Samantha-Jo Caetano, Haoluan Chen, Michael Chong, Annie Collins, Shirley Deng, Isaac Ehrlich, Paul Hodgetts, Yena Joo, Marija Pejcinovska, Mariam Walaa, and Matthew Wankiewicz, 2021, ‘An Introduction to DoSStoolkit’, arXiv, 19 May, https://arxiv.org/abs/2105.09347.
- Ke-Li Chiu and Rohan Alexander, 2021, ‘Detecting Hate Speech with GPT-3’, arXiv, 23 March, https://arxiv.org/abs/2103.12407.
- Ke-Li Chiu and Rohan Alexander, 2021, ‘On consistency scores in text data with an implementation in R’, arXiv, 13 January, https://arxiv.org/abs/2101.05225.
- Paul A. Hodgetts and Rohan Alexander, 2020, ‘cesR: An R package for the Canadian Election Study’, SocArXiv, 3 September, https://osf.io/preprints/socarxiv/a29h8/.
- Rohan Alexander and Zach Ward, 2018, ‘Age at Arrival and Assimilation During the Age of Mass Migration’, The Journal of Economic History, 78(3), 904-937. Working paper version.
Software
- Rohan Alexander and A Mahfouz, 2021,
heapsofpapers, https://rohanalexander.github.io/heapsofpapers/.
Datasets
AustralianPoliticiansis an R package that consists of a collection of datasets related to Australian politicians. The datasets are up-to-date as of 30 November 2019. You can install the package from GitHub.AustralianElectionsis an R package that consists of a collection of datasets related to Australian elections. The datasets are up-to-date as of 10 September 2019. You can install the package from GitHub.
Presentations
- Turning Our World Into Data
7 July 2021, Harvard Biostatistics Data Science in Action Summer Camp.
- Forecasting Parliamentary Elections
10 December 2019, Monash University, Department of Econometrics & Business Statistics, Melbourne.
9 December 2019, Australian Society for Quantitative Political Science Conference, Melbourne.
2 December 2019, Australian National University, Cake for Comments, Canberra.
20 November 2019, POP Politics Workshop, Canberra.
17 October 2018, University of Toronto, Political Behaviour Group, Toronto.
- A Word-Count Based Classifier of Politicians in the Australian Federal Parliament (1901–2018)
4 September 2019, European Consortium for Political Research, General Conference, Wroclaw.
22 June 2019, European Political Science Association, Annual Conference, Belfast.
18 June 2019, Quantitative Text Analysis Workshop, Dublin. - The Effect of Elections and Prime Ministers on Discussion in the Australian Federal Parliament (1901—2018)
11 January 2019, Political Methodology Specialist Group, Annual Conference, Warwick.
11 December 2018, Max Planck Institute for Demographic Research, Rostock.
22 November 2018, University of Toronto, Political Behaviour Group, Toronto.
25 October 2018, Australian National University, Research School of Economics, Canberra.
25 October 2018, Parliamentary Library, Parliament of Australia, Canberra.
24 October 2018, Australian National University, School of Politics and International Relations, Canberra. - Exploring Australia’s Hansard (1901–2017)
(Poster) 7-9 September, 2018 Economic History Association Meeting, Montreal. - A Surnames-Based Analysis of Tasmanian Social Mobility (1803–2015)
20 May 2016, UC Berkeley, Economic History Lunch, Berkeley.
2 May 2016, Australian National University, Research School of Economics, Canberra.