Curated Content

Below we provide links to supplementary online material. Hopefully, some of the items will inspire you to view the module material in a broader context and lead to further investigations.

Investigation 1

What is Statistics?

Cambridge Ideas - Professor Risk

https://www.youtube.com/watch?v=a1PtQ67urG4
Prof David Spiegelhalter (Cambridge University) discusses public understanding of risk. You may also be interested in reading (Spiegelhalter 2020).
The Joy of Statistics

https://www.youtube.com/watch?v=jbkSRLYSojo
Prof Hans Rosling (Karolinska Institute and Gapminder Foundation) analyses data from 200 Countries over 200 Years in 4 Minutes - The Joy of Stats - BBC Four.
Teach statistics before calculus!

https://www.ted.com/talks/arthur_benjamin_teach_statistics_before_calculus
Prof Arthur Benjamin (Harvey Mudd College) argues that the pinnacle of math education is probability and statistics — not calculus.
Kaggle

https://www.kaggle.com/
Towards data science.

https://www.youtube.com/watch?v=TNzDMOg_zsw
What’s Kaggle?

Investigation 2

Defence against the dark arts.

Three ways to spot bad statistics

https://www.ted.com/talks/mona_chalabi_3_ways_to_spot_a_bad_statistic
Mona Chalabi (Data Journalist) discusses three ways to spot bad statistics.

Statistics Done Wrong

https://www.statisticsdonewrong.com/
A book by Dr Alex Reinhart (Carnegie Mellon University).
How to defend yourself against misleading statistics in the news

https://www.youtube.com/watch?v=mJ63-bQc9Xg
Sanne Blauw (Journalist) discusses how the presentation of statistics can mislead.

Investigation 3

Data analysis and visualisation.

The Grammar of Graphics

https://www.youtube.com/watch?v=h-62NwWUI5c
What Makes A Good Visualisation? Rhys Jackson from RocketMill, a UK Digital Marketing Agency, gives a perspective on visualising data from a marketing perspective.

https://www.youtube.com/watch?v=kepKM7Z2O54
David Keyes (RStudio) discusses how the grammar of graphics underpins the ggplot2 data visualization package in R.
Same Stats, Different Graphs

https://www.autodeskresearch.com/publications/samestats
Generating Datasets with Varied Appearance and Identical Statistics through Simulated Annealing (ACM SIGCHI Conference on Human Factors in Computing Systems) by Justin Matejka, George Fitzmaurice.
Why do we so often use 0.05 for hypothesis testing?

https://www.openintro.org/book/stat/why05/
In this online exercise, you will gain an improved understanding of what a significance level is, and why a value in the neighbourhood of 0.05 is reasonable as a default.
Data visualisations

https://flowingdata.com/
FlowingData blog by Nathan Yau.

https://fivethirtyeight.com/
FiveThirtyEight blog by Nate Silver.
Storytelling with data

http://www.storytellingwithdata.com/blog
Blog with nice hints and tips for how to present data in tables, graphics, and visualisations.

https://community.storytellingwithdata.com/challenges
Monthly challenge.

Investigation 4

Statistical paradoxes.

How statistics can be misleading (TED-Ed)

https://www.ted.com/talks/mark_liddell_how_statistics_can_be_misleading
Mark Liddell (Educator) discusses Simpson’s Paradox in this TED-Ed animation.
Low birth-weight paradox

https://www.wikiwand.com/en/Low_birth-weight_paradox
Gambler’s Fallacy

https://www.youtube.com/watch?v=4eVluL-idkM
Prof Kelly Shue (Chicago Booth) discusses the gambler’s fallacy.

Investigation 5

The law and interpreting statistics.

How stats fool juries.

https://youtu.be/kLmzxmRcUTo
Prof Peter Donnelly (Oxford University) discusses common mistakes in interpreting statistics.

Measurement Uncertainty Calculator (MUCalc)

https://discovery.dundee.ac.uk/en/publications/measurement-uncertainty-calculator-mucalc
The Leverhulme Research Centre for Forensic Science Measurement Uncertainty Calculator (MUCalc) is an application for calculating measurement uncertainty in accordance with the standards of International Organization for Standardization ISO/IEC 17025.
Prosecutor’s fallacy

https://www.wikiwand.com/en/Prosecutor%27s_fallacy
A fallacy of statistical reasoning, typically used by a prosecutor to exaggerate the likelihood of guilt: because P(\text{hypothesis} \mid \text{evidence}) \neq P(\text{evidence} \mid \text{hypothesis})!

Investigation 6

Data-driven decision making in epidemiology.

Project Tycho

https://www.tycho.pitt.edu/
Digitized archival epidemiological data for the United States and the world.

https://www.youtube.com/watch?v=Kn9OJy1BPDo
An overview of the origins of project Tycho.

Our World in Data

https://ourworldindata.org/
A project of the Oxford Martin School to make public health data, including progress in UN Sustainable Development Goals, available and accessible.
Demographic Party Trick

https://www.youtube.com/watch?v=2nDh8MQuS-Y
Prof Hans Rosling (Karolinska Institute and Gapminder Foundation) and Bill Gates seek to shed light on the true statistics of childhood vaccinations.

Investigation 7

Spurious correlations!

The danger of mixing up causality and correlation

https://www.youtube.com/watch?v=8B271L3NtAw
Prov Ionica Smeets (University of Leiden) discusses causality and correlation.
Spurious correlations

https://tylervigen.com/spurious-correlations
Tyler Vigen’s site dedicated to spurious correlations.
Cause & Effect

https://www.youtube.com/watch?v=lbODqslc4Tg
Correlation vs. causality from the Clip from the 2010 documentary “Freakonomics: The Movie”.

Investigation 8

Data and Society: can data-driven and predictive modelling lead to a better world? What are the ethics of mass data collection?

Science behind the news: Predictive Policing

https://www.youtube.com/watch?v=74_jreara3w
The Los Angeles Police Department is using a new tactic in their fight against crime called “predictive policing.” It’s a computer program originally developed by a team at UCLA, including mathematician Andrea Bertozzi and anthropologist Jeff Brantingham. “Science Behind the News” is produced in partnership with NBC Learn. (Provided by the National Science Foundation & NBC Learn)
You should get paid for your data

https://www.nytimes.com/video/opinion/100000006678020/data-privacy-jaron-lanier-2.html
Jaron Lanier (Computer Scientist and Author) discusses a compensation plan and data dignity.

https://www.ted.com/talks/jennifer_zhu_scott_why_you_should_get_paid_for_your_data
Jennifer Zhu Scott (Computer Scientist) also thinks you should get paid for your data.
How tech companies deceive you into giving up your data and privacy

https://www.ted.com/talks/finn_lutzow_holm_myrstad_how_tech_companies_deceive_you_into_giving_up_your_data_and_privacy
Finn Lützow-Holm Myrstad (Norwegian Consumer Council) discusses consumer protections and data collection.
Your company’s data could help end world hunger

https://www.ted.com/talks/mallory_freeman_your_company_s_data_could_help_end_world_hunger
Mallory Freeman (Data Scientist) discusses how to do the most good with data.

Investigation 9

Machine learning / big data.

What is Machine Learning?

https://www.youtube.com/watch?v=f_uwKZIAeM0
OxfordSparks discusses the topic of supervised learning algorithms and how machine learning is used all around us.
Big Data (TED-Ed)

https://www.youtube.com/watch?v=j-0cUmUyb-Y
Tim Smith (educator) discusses the historical arc of big data in this TED-Ed animation.
The human insights missing from big data

https://www.ted.com/talks/tricia_wang_the_human_insights_missing_from_big_data
Tricia Wang (Ethnographer) discusses the human insights missing from big data.
How we can find ourselves in data

https://www.ted.com/talks/giorgia_lupi_how_we_can_find_ourselves_in_data
Giorgia Lupi (Designer) discusses a humanistic approach to data and data visualization.

{{< include preamble.qmd >}} # Curated Content {-} Below we provide links to supplementary online material. Hopefully, some of the items will inspire you to view the module material in a broader context and lead to further investigations. ## Investigation 1 {-} What is Statistics? - Cambridge Ideas - Professor Risk : [https://www.youtube.com/watch?v=a1PtQ67urG4](https://www.youtube.com/watch?v=a1PtQ67urG4) \newline Prof David Spiegelhalter (Cambridge University) discusses public understanding of risk. You may also be interested in reading [@Spiegelhalter:2020ps]. - The Joy of Statistics : [https://www.youtube.com/watch?v=jbkSRLYSojo](https://www.youtube.com/watch?v=jbkSRLYSojo) \newline Prof Hans Rosling (Karolinska Institute and Gapminder Foundation) analyses data from 200 Countries over 200 Years in 4 Minutes - The Joy of Stats - BBC Four. - Teach statistics before calculus! : [https://www.ted.com/talks/arthur_benjamin_teach_statistics_before_calculus](https://www.ted.com/talks/arthur_benjamin_teach_statistics_before_calculus) \newline Prof Arthur Benjamin (Harvey Mudd College) argues that the pinnacle of math education is probability and statistics --- not calculus. - Kaggle : [https://www.kaggle.com/](https://www.kaggle.com/) \newline Towards data science. : [https://www.youtube.com/watch?v=TNzDMOg_zsw](https://www.youtube.com/watch?v=TNzDMOg_zsw) \newline What's Kaggle? ## Investigation 2 {-} Defence against the dark arts. - Three ways to spot bad statistics : [https://www.ted.com/talks/mona_chalabi_3_ways_to_spot_a_bad_statistic](https://www.ted.com/talks/mona_chalabi_3_ways_to_spot_a_bad_statistic) \newline Mona Chalabi (Data Journalist) discusses three ways to spot bad statistics.   - Statistics Done Wrong : [https://www.statisticsdonewrong.com/](https://www.statisticsdonewrong.com/) \newline A book by Dr Alex Reinhart (Carnegie Mellon University). - How to defend yourself against misleading statistics in the news : [https://www.youtube.com/watch?v=mJ63-bQc9Xg](https://www.youtube.com/watch?v=mJ63-bQc9Xg) \newline Sanne Blauw (Journalist) discusses how the presentation of statistics can mislead. ## Investigation 3 {-} Data analysis and visualisation. - The Grammar of Graphics : [https://www.youtube.com/watch?v=h-62NwWUI5c](https://www.youtube.com/watch?v=h-62NwWUI5c) \newline What Makes A Good Visualisation? Rhys Jackson from RocketMill, a UK Digital Marketing Agency, gives a perspective on visualising data from a marketing perspective. : [https://www.youtube.com/watch?v=kepKM7Z2O54](https://www.youtube.com/watch?v=kepKM7Z2O54) \newline David Keyes (RStudio) discusses how the grammar of graphics underpins the `ggplot2` data visualization package in `R`. - Same Stats, Different Graphs : [https://www.autodeskresearch.com/publications/samestats](https://www.autodeskresearch.com/publications/samestats) \newline Generating Datasets with Varied Appearance and Identical Statistics through Simulated Annealing (ACM SIGCHI Conference on Human Factors in Computing Systems) by Justin Matejka, George Fitzmaurice. - Why do we so often use 0.05 for hypothesis testing? : [https://www.openintro.org/book/stat/why05/](https://www.openintro.org/book/stat/why05/) \newline In this online exercise, you will gain an improved understanding of what a significance level is, and why a value in the neighbourhood of 0.05 is reasonable as a default. - Data visualisations : [https://flowingdata.com/](https://flowingdata.com/) \newline FlowingData blog by Nathan Yau. : [https://fivethirtyeight.com/](https://fivethirtyeight.com/) \newline FiveThirtyEight blog by Nate Silver. - Storytelling with data : [http://www.storytellingwithdata.com/blog](http://www.storytellingwithdata.com/blog) \newline Blog with nice hints and tips for how to present data in tables, graphics, and visualisations. : [https://community.storytellingwithdata.com/challenges](https://community.storytellingwithdata.com/challenges) \newline Monthly challenge. ## Investigation 4 {-} Statistical paradoxes. - How statistics can be misleading (TED-Ed) : [https://www.ted.com/talks/mark_liddell_how_statistics_can_be_misleading](https://www.ted.com/talks/mark_liddell_how_statistics_can_be_misleading) \newline Mark Liddell (Educator) discusses Simpson's Paradox in this TED-Ed animation. - Low birth-weight paradox : [https://www.wikiwand.com/en/Low_birth-weight_paradox](https://www.wikiwand.com/en/Low_birth-weight_paradox) - Gambler's Fallacy : [https://www.youtube.com/watch?v=4eVluL-idkM](https://www.youtube.com/watch?v=4eVluL-idkM) \newline Prof Kelly Shue (Chicago Booth) discusses the gambler's fallacy. ## Investigation 5 {-} The law and interpreting statistics. - How stats fool juries. : [https://youtu.be/kLmzxmRcUTo](https://youtu.be/kLmzxmRcUTo) \newline Prof Peter Donnelly (Oxford University) discusses common mistakes in interpreting statistics.   - Measurement Uncertainty Calculator (MUCalc) : [https://discovery.dundee.ac.uk/en/publications/measurement-uncertainty-calculator-mucalc](https://discovery.dundee.ac.uk/en/publications/measurement-uncertainty-calculator-mucalc) \newline The Leverhulme Research Centre for Forensic Science Measurement Uncertainty Calculator (MUCalc) is an application for calculating measurement uncertainty in accordance with the standards of International Organization for Standardization ISO/IEC 17025. - Prosecutor's fallacy : [https://www.wikiwand.com/en/Prosecutor%27s_fallacy](https://www.wikiwand.com/en/Prosecutor%27s_fallacy) \newline A fallacy of statistical reasoning, typically used by a prosecutor to exaggerate the likelihood of guilt: because $P(\text{hypothesis} \mid \text{evidence}) \neq P(\text{evidence} \mid \text{hypothesis})$! ## Investigation 6 {-} Data-driven decision making in epidemiology. - Project Tycho : [https://www.tycho.pitt.edu/](https://www.tycho.pitt.edu/) \newline Digitized archival epidemiological data for the United States and the world. : [https://www.youtube.com/watch?v=Kn9OJy1BPDo](https://www.youtube.com/watch?v=Kn9OJy1BPDo) \newline An overview of the origins of project Tycho.   - Our World in Data : [https://ourworldindata.org/](https://ourworldindata.org/) \newline A project of the Oxford Martin School to make public health data, including progress in UN Sustainable Development Goals, available and accessible. - Demographic Party Trick : [https://www.youtube.com/watch?v=2nDh8MQuS-Y](https://www.youtube.com/watch?v=2nDh8MQuS-Y) \newline Prof Hans Rosling (Karolinska Institute and Gapminder Foundation) and Bill Gates seek to shed light on the true statistics of childhood vaccinations. ## Investigation 7 {-} Spurious correlations! - The danger of mixing up causality and correlation : [https://www.youtube.com/watch?v=8B271L3NtAw](https://www.youtube.com/watch?v=8B271L3NtAw) \newline Prov Ionica Smeets (University of Leiden) discusses causality and correlation. - Spurious correlations : [https://tylervigen.com/spurious-correlations](https://tylervigen.com/spurious-correlations) \newline Tyler Vigen's site dedicated to spurious correlations. - Cause & Effect : [https://www.youtube.com/watch?v=lbODqslc4Tg](https://www.youtube.com/watch?v=lbODqslc4Tg) \newline Correlation vs. causality from the Clip from the 2010 documentary "Freakonomics: The Movie". ## Investigation 8 {-} Data and Society: can data-driven and predictive modelling lead to a better world? What are the ethics of mass data collection? - Science behind the news: Predictive Policing : [https://www.youtube.com/watch?v=74_jreara3w](https://www.youtube.com/watch?v=74_jreara3w) \newline The Los Angeles Police Department is using a new tactic in their fight against crime called "predictive policing." It's a computer program originally developed by a team at UCLA, including mathematician Andrea Bertozzi and anthropologist Jeff Brantingham. "Science Behind the News" is produced in partnership with NBC Learn. (Provided by the National Science Foundation & NBC Learn) - You should get paid for your data : [https://www.nytimes.com/video/opinion/100000006678020/data-privacy-jaron-lanier-2.html](https://www.nytimes.com/video/opinion/100000006678020/data-privacy-jaron-lanier-2.html) \newline Jaron Lanier (Computer Scientist and Author) discusses a compensation plan and data dignity. : [https://www.ted.com/talks/jennifer_zhu_scott_why_you_should_get_paid_for_your_data](https://www.ted.com/talks/jennifer_zhu_scott_why_you_should_get_paid_for_your_data) \newline Jennifer Zhu Scott (Computer Scientist) also thinks you should get paid for your data. - How tech companies deceive you into giving up your data and privacy : [https://www.ted.com/talks/finn_lutzow_holm_myrstad_how_tech_companies_deceive_you_into_giving_up_your_data_and_privacy](https://www.ted.com/talks/finn_lutzow_holm_myrstad_how_tech_companies_deceive_you_into_giving_up_your_data_and_privacy) \newline Finn Lützow-Holm Myrstad (Norwegian Consumer Council) discusses consumer protections and data collection. - Your company's data could help end world hunger : [https://www.ted.com/talks/mallory_freeman_your_company_s_data_could_help_end_world_hunger](https://www.ted.com/talks/mallory_freeman_your_company_s_data_could_help_end_world_hunger) \newline Mallory Freeman (Data Scientist) discusses how to do the most good with data. ## Investigation 9 {-} Machine learning / big data. - What is Machine Learning? : [https://www.youtube.com/watch?v=f_uwKZIAeM0](https://www.youtube.com/watch?v=f_uwKZIAeM0) \newline OxfordSparks discusses the topic of supervised learning algorithms and how machine learning is used all around us. - Big Data (TED-Ed) : [https://www.youtube.com/watch?v=j-0cUmUyb-Y](https://www.youtube.com/watch?v=j-0cUmUyb-Y) \newline Tim Smith (educator) discusses the historical arc of big data in this TED-Ed animation. - The human insights missing from big data : [https://www.ted.com/talks/tricia_wang_the_human_insights_missing_from_big_data](https://www.ted.com/talks/tricia_wang_the_human_insights_missing_from_big_data) \newline Tricia Wang (Ethnographer) discusses the human insights missing from big data. - How we can find ourselves in data : [https://www.ted.com/talks/giorgia_lupi_how_we_can_find_ourselves_in_data](https://www.ted.com/talks/giorgia_lupi_how_we_can_find_ourselves_in_data) \newline Giorgia Lupi (Designer) discusses a humanistic approach to data and data visualization.