Example pics below:
Interesting paper by Michael Posner, who was chair of the UK Social Science Research Council (SSRC) when it was under attack by the Conservative Thatcher government in the early 1980s.
Secretary of State Sir Keith Joseph considered dismantling SSRC and asked for an independent review into its utility by an established biologist.
SSRC survived, though one notable change was made…
“Joseph opted for a public, but very light punishment: a change of name. I told him that I could persuade scores of academics to accept a name change if he would promise, on the record, the continuing independence of the SSRC. He agreed, and the SSRC was duly renamed the « Economic and Social Research Council » (ESRC). The significance of this change was the omission of the word « science », which Joseph had insisted upon and which many of us at the council and in academia found it difficult to accept.”
Read more over here.
“The aim of critical realist philosophy is, when the practice is adequate, to provide a better or more adequate theory of the practice; and, when it is not, to transform the practice in the appropriate way. That is to say the aim of critical realist philosophy is enhanced reflexivity or transformed practice (or both). […]
“Since there is only one world, the theories and principles of critical realist philosophy should also apply to our everyday life. If they do not, then something is seriously wrong. This means that our theories and explanations should be tested in everyday life, as well as in specialist research contexts.”
—Bhaskar, Roy (2013) The consequences of the revindication of philosophical ontology for philosophy and social theory. In: Archer, Margaret and Maccarini, Andrea, (eds.) Engaging with the world. (pp. 11-21). Routledge: London.
“Sociologist Sherry Turkle’s 2011 book Alone Together argues that through our increased use of technology we remain connected but increasingly isolated from one another. This turn of phrase is frequently weaponized to undermine the value of the digital and speaks recklessly through a white, straight, cisgender lens. Turkle’s fear-mongering equation Internet = alienation fails to take into consideration the enduring relevance of this material most specifically for queer people, female-identifying people, and people of color. To reify the binary of, on the one hand, the Internet as a dead utopia and, on the other, “real life” (read: IRL) as being devoid of actual and/or social death for QTPOCIA+ bodies is a violent propaganda. The Internet remains a club space for collective congregation of marginalized voices and bodies when all else fails. In fact and in concept “real life” as it travels in an unbroken loop between on- and offline is sexist, racist, classist, homophobic, transphobic, and ableist.”
—Legacy Russell (2020, p. 124). Glitch Feminism: A Manifesto
This year as part of Covid-enforced “digital transformation” I ended up writing longer tutorial notes than usual so that students could work at their own pace. The module I teach assumes that students have already taken an intro stats course using software other than R, covering up to regression, but that they are likely to have forgotten how to do the latter.
The core texts I use are Fox and Weisberg (2019), An R Companion to Applied Regression (Third Edition) and Healy (2019) Data Visualization: A Practical Introduction – both excellent.
These notes add explanations where students were likely to be struggling and exercises with solutions.
I’ll be putting them all online over here.
Evolving scribbles (file under note-to-self)
Many have just noticed that the digital and the “real world” are not as separable as they may have thought. For large sections of society, this is new – and may have led to changed attitudes to those who have already been engaged in digital life.
But we already lived in a world where people interact on social media and find relationships on apps like Bumble and Grindr. Online dating has changed dramatically over even the last decade. LGBTQ+ people rely heavily on online worlds to meet each other and build communities – especially important for trans people given the hostile media environment.
Up until recently, these digital worlds were frowned upon by mainstream cishet society. Research frequently appeared in the media claiming that digital life was harmful (correlational research). That has collapsed. It has become the norm for people to work and socialise only online now. People go on Zoom to work and to play.
Rather than thinking in terms of what (implicitly, detrimental) “impact” relying more on digital ways of living has had, let’s ponder how society has developed. What does social connection really mean? What is sexuality like now and how do people cope without physical contact? How many people have chosen to move in together because of lockdown who might not have done otherwise and what is that like? How many covertly use Uber?
With a standard couple-focused and monogamous model, lovers either live together (sex as usual) or apart (break lockdown rules or engage in what used to be called “cyber”). But there are also couples living together who meet other couples and singles online; see Zoom banned virtual orgies. Here’s how sex parties and orgy-seekers are getting around it. This is another way the digital/”real” boundaries merge.
Glitch Feminism by Legacy Russell is a thought-provoking book on how online and offline worlds are interwoven, written pre-pandemic. The author introduces the term “AFK” – away from keyboard – to work towards “undermining the fetishisation of ‘real life,’ helping us to see that because realities in the digital are echoed offline, and vice versa, our gestures, expressions, actions online can inform and even deepen our offline, or AFK, existence.”
In other words, for some, the heavy reliance on online worlds is new – maybe even surprising in how it works. But there are others for whom this is not at all new – who skipped merrily between IRC and pub. There are already experts out there from whom the dominant digitally-naive majority can learn.
There is another digital divide of sorts, which is most apparent when we enter lockdowns. There are people who must still physically travel to work – supermarket workers, cleaners. There are others who are furloughed, so highly dependent on what the Treasury can offer. There are others who can work as before, their means of income hardly affected, many of whom were already working from home and online.
But how do these different degrees of online/offline ways of life relate to existing understandings of social class and intersections such as race and gender? What is the best way, methodologically, to go about developing new typologies and theories? I’m thinking here of some of the debate that arose from the Great British Class Survey, which used a statistical bottom-up approach, versus more theory-driven approaches which can then be tested through social research.
Finally, another phenomena which has become more apparent in recent months is the variety of closed yet huge online worlds – private Facebook and WhatsApp groups, Telegram channels – where people can support each other, live and even love, but where in some cases conspiracy theories can thrive, such as the bizarre claim that 5G causes Covid. Again these “online” worlds impact life AFK – leading to protests and people refusing to wear masks. But how can we understand these communities? Do any existing theories of AFK society help? What do people get from being in these groups? (See also Escape the echo chamber, by C. Thi Nguyen.)
Last edited 19 Nov 2020
I’ll be updating this, but first thoughts:
Fitting regression models, GLMs, etc.
Fox, J., & Weisberg, S. (2019). An R companion to applied regression (3rd ed.). London: SAGE Publications Ltd.
See also online material, including free appendices and R code.
Data transformation and visualisation
Healy, K. (2019). Data Visualization: A Practical Introduction. Princeton University Press. (Free online version.)
Wickham, H., & Grolemund, G. (2017). R for Data Science: Import, Tidy, Transform, Visualize, and Model Data. Sebastopol, CA: O’Reilly. (Free online version.)
Chang, W. (2020). R Graphics Cookbook (2nd ed.). Sebastopol, CA: O’Reilly. (Free online version.)
Lüdecke D (2018). ggeffects: Tidy Data Frames of Marginal Effects from Regression Models. Journal of Open Source Software, 3(26), 772. doi: 10.21105/joss.00772
This is very handy for getting predictions from models, focusing on the effect of predictors of interest whilst holding covariates at some fixed values like a mean or (for factors) mode.
See also the package website for illustrative examples.
Gelman, A. (2011). Tables as graphs: The Ramanujan principle. Significance, 8, 183.
Missing data imputation
Van Buuren, S. (2018). Flexible Imputation of Missing Data. Second Edition.. Chapman & Hall/CRC. Boca Raton, FL. (Free online version.)
See also the package website.
Greenland, S., Senn, S. J., Rothman, K. J., Carlin, J. B., Poole, C., Goodman, S. N., & Altman, D. G. (2016). Statistical tests, P values, confidence intervals, and power: a guide to misinterpretations. European Journal of Epidemiology, 31, 337–350.
“… correct use and interpretation of these statistics requires an attention to detail which seems to tax the patience of working scientists.”
Colquhoun, D. (2014). An investigation of the false discovery rate and the misinterpretation of p-values. Royal Society Open Science, 1, 140216. doi: 10.1098/rsos.140216
This generated lots of debate – I like how it attempts to use Bayes rule to turn p-values into something useful and the explanation in terms of diagnostic test properties. See also this on PPV and NPV.
Rafi, Z., & Greenland, S. (2020). Semantic and cognitive tools to aid statistical science: replace confidence and significance by compatibility and surprise. BMC Medical Research Methodology, 20(1), 244. doi: 10.1186/s12874-020-01105-9
Interesting proposal to use s-values, calculated from p-values as −log₂(p). It’s a simple transformation: p is probability of getting all heads from −log₂(p) fair coin tosses. For example if p = 0.5 then s = 1; toss a coin once then the probability of head is 0.5. If p = 0.03125 then s = 5; toss a coin 5 times then the probability of all heads is 0.03125. But the s-value is supposedly easier to think about. I’m not sure if it really is, but I like the idea!