class: center, middle, inverse, title-slide # POL90: Statistics ## Introduction & Overview ### Prof. Wasow, PoliticsPomona College ### 2022-01-19 --- ## Why study applied stats? .large[ * What do we mean by statistical thinking? + Central tendencies *and* uncertainty + From datum to data to data generating process ] -- .large[ * Why "model thinking"? + Evidence shows that people who think with models consistently outperform those who don't. And, moreover people who think with lots of models outperform people who use only one.</br> — Scott E Page, University of Michigan ] -- .large[ * Why data as rhetoric? ] --- ## Example: US smartphone adoption <img src="images/asymco_us_smartphone_adoption.png" width="70%" style="display: block; margin: auto;" /> .small[ Source: http://www.asymco.com/2013/11/06/the-diffusion-of-iphones-as-a-learning-process/ ] --- ## Example: US smartphone adoption <img src="images/statistic_id201183_smartphone-penetration-in-the-us-as-share-of-population-2010-2021.png" width="80%" style="display: block; margin: auto;" /> .small[Source: https://www.statista.com/statistics/201183/forecast-of-smartphone-penetration-in-the-us/] --- ## All tech adoption as a social process? <img src="images/asymco_smartphone_trends_text_like_other_tech.png" width="100%" style="display: block; margin: auto;" /> .small[ Source: http://www.asymco.com/2014/01/07/when-will-smartphones-saturate/ ] --- <iframe src="https://ourworldindata.org/grapher/technology-adoption-by-households-in-the-united-states?tab=chart&stackMode=absolute®ion=World" allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen style="width: 100%; height: 600px; border: 0px none;"></iframe> --- ## US smartphone adoption as a social process <img src="images/technology-adoption-curve-Rogers.png" width="80%" style="display: block; margin: auto;" /> .small[ Rogers (1962), https://en.wikipedia.org/wiki/Diffusion_of_innovations ] --- ## US smartphone adoption as a social process <img src="images/800px-Diffusion_of_ideas_svg.png" width="80%" style="display: block; margin: auto;" /> .small[ Source: https://en.wikipedia.org/wiki/Diffusion_of_innovations ] --- ## Benefits of applied stats? .large[ * Statistical literacy makes us smarter - Statistics provides us with tools to make sense of many complicated real world phenomena and to overcome some of the limitations and biases of normal human thought. You're adding tools to your mental problem solving toolkit. ] -- .large[ * Statistical models can be applied widely + Medical imaging, viral media, privacy, weddings. In this course, our primary interest is in stats for social science but we'll draw upon examples from across many disciplines. ] --- ## Benefits of applied stats? .large[ * Stats is like a language - It's hard to teach to yourself. Some classes, you could read the books on your own. Stats you learn, in significant part, by doing and it really helps to have a structured course to guide you. ] -- .large[ * Junior Papers, Senior Theses, future careers - If you work hard in this class, your future work, both academic and professional, will be of much better quality. ] --- ## Benefits of applied stats? .large[ * Stats is philosophy + Challenges some pretty deeply held ideas about the world. ] -- .large[ * Applied stats is fun + Stats can be very abstract and it makes a lot more sense when applied. ] --- # Careers and life <img src="images/buzzfeed_dao_secret_weapon.png" width="85%" style="display: block; margin: auto;" /> --- <img src="images/buzzfeed_dao_secret_weapon3.png" width="95%" style="display: block; margin: auto;" /> <br><br> .small[ Source: https://www.inc.com/christine-lagorio/buzzfeed-secret-growth-weapon.html ] --- <br/><br/> <img src="images/ijeamaka_anyene_homepage.jpg" width="100%" style="display: block; margin: auto;" /> .small[ Source: https://ijeamaka-anyene.netlify.app ] --- <iframe src="https://ijeamaka-anyene.netlify.app/posts/2021-01-04-radial-patterns-in-ggplot2/" allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen style="width: 100%; height: 600px; border: 0px none;"></iframe> --- ## Why R? LinkedIn Jobs Survery 2020 <img src="images/linkedin_jobs_2020.png" width="45%" style="display: block; margin: auto;" /> .small[ Source: https://business.linkedin.com/content/dam/me/business/en-us/talent-solutions/emerging-jobs-report/Emerging_Jobs_Report_U.S._FINAL.pdf ] --- <img src="images/linkedin_jobs_2018.png" width="85%" style="display: block; margin: auto;" /> .small[ Source: LinkedIn Job Survey 2018, https://news.linkedin.com/2018/1/in-demand-skills-2018 ] --- class: inblack <img src="images/oreilly_salary_survey_hist_salary_2017.png" width="95%" style="display: block; margin: auto;" /> .small[ Souce: O'Reilly data scientist survey, 2017, https://www.oreilly.com/library/view/2017-data-science/9781491997079/ ] --- class: inblack <img src="images/oreilly_salary_survey_median_salary_2017.png" width="95%" style="display: block; margin: auto;" /> .small[ Souce: O'Reilly data scientist survey, 2017, https://www.oreilly.com/library/view/2017-data-science/9781491997079/ ] --- class: inblack <img src="images/oreilly_salary_survey_languages_2017.png" width="95%" style="display: block; margin: auto;" /> .small[ Souce: O'Reilly data scientist survey, 2017, https://www.oreilly.com/library/view/2017-data-science/9781491997079/ ] --- <img src="images/oreilly_salary_survey_ggplot_2017.png" width="95%" style="display: block; margin: auto;" /> .small[ Souce: O'Reilly data scientist survey, 2017, https://www.oreilly.com/library/view/2017-data-science/9781491997079/ ] --- ## R and Scholarship: Citations <img src="images/Fig_2a_ScholarlyImpact2018-1.png" width="60%" style="display: block; margin: auto;" /> .small[ Source: http://r4stats.com/articles/popularity/ ] --- ## R and Scholarship: Trends Over Time <img src="images/Fig_2d_ScholarlyImpact2016.png" width="65%" style="display: block; margin: auto;" /> .small[ Source: http://r4stats.com/articles/popularity/ ] --- ## R and Scholarship: Trends Zoomed <img src="images/Fig_2e_ScholarlyImpactSubset2016.png" width="65%" style="display: block; margin: auto;" /> .small[ Source: http://r4stats.com/articles/popularity/ ] --- ## R Popularity: PYPL <img src="images/pypl_list_2021.png" width="90%" style="display: block; margin: auto;" /> .small[ Source: https://pypl.github.io/PYPL.html ] --- ## R Popularity: TIOBE <img src="images/tiobe_popularity_2021.png" width="100%" style="display: block; margin: auto;" /> <br/> .small[ Source: https://www.tiobe.com/tiobe-index/ ] --- # Who am I? .large[ * Worked in social media for about a dozen years * Went back to grad school to study the rise of mass incarceration ] --- # Who am I? <img src="images/incarceration1910.png" width="90%" style="display: block; margin: auto;" /> --- # Themes of POL90 * Intuition + What is the story behind the stats? - You're going to forget a lot of what you learn in this class (as in any other) and, so, each week we'll try to identify stories that can help you think intuitively about the concepts at hand. * Application + How do you learn? - We're going to learn by doing. That means working together in class, working through problem sets on your own and doing original research sometimes on a team, sometimes on your own. --- # Themes of POL90 - Interpretation - Why do we have child-prodigy musicians and mathematicians but not child prodigy novelists or statisticians? - Breakout discussion -- - One answer: - With math and music, you can be exceptional by following rules. With novels and stats, you need experience to make sense of the world. Learning to interpret statistical findings, identify their strengths and weaknesses, and to weigh the trade-offs in trying to improve results will be central to the course. -- - Communication - We want both to move closer to the truth *and* to persuade others of these truths -- - A lot of stats classes emphasize the math but this class is a little different. There will be math, but another central element will be communicating your findings in meaningful language. In other words, we will emphasize using statistics to communicate findings through words, plots, and other tools. Data as rhetoric. --- # Grade components .large[ * Class precept participation - 4% + Precept, lecture, Ed Discussion * Problem sets - 24% + Nine problem sets, you will need to complete *eight* * Reports - 24% + Four reports + First, 6%, Second, 8%, Third, 10% + Completed with teams (solo option) * Quizzes - 12% * Take home final - 36% ] --- ## Summary <img src="images/pol346_venn_diagram_large_type.png" width="65%" style="display: block; margin: auto;" /> --- ## Questions?