Falling in love with statistics

It’s kind of obvious a DBA should be a journey of discovery: of knowledge, growth, and change. Yet a mindset change caught me off guard. I did not predict falling a little in love with statistics!

As popularised by Twain, statistics to me, was a tad boring and pliable [1]; worrisome in the wrong hands. My head and gut comfortably attuned to the view that it’s the rich, in-depth detail that matters, prioritising access to the ‘complexity of human experience or perceptions’ [2]. My focus to date: the how and the why!

However, time getting up, close, and personal to data types, mathematical operators, distributions, and tests, has revealed statistics has hidden depths. My preconceptions shown as based on formative, rather than complex, understanding [3]. My ‘quants’ module has ‘Rosetta Stone- style’ [4], forced deep immersion into quants design and its’ specialist terminology [5].

The early stages of the relationship, played out in an Educational research context has tested my patience: hypotheses development, variable identification, drafting of questions and navigating the ethical approval process. However, statistical language no longer feels alien, and I’ve definitely been pushed to reduce bias, rather than accept it happens [6].

Rollercoaster Relationship

The experience has not been without tension, an inner turmoil based on a strong inclination towards storytelling, which contrasts with the more transparent, objective and unambiguous attributes of statistics [7; 8]. In my heart, I cannot fully commit to numerical aggregates and averages without fear of the numbers being too easily manipulated [9]. I worry more over a Type II than Type I error [7], and I still crave the detail, the why.

Statistical Imprints

This isn’t going to be the Semantics-Statistics love-match of the century, but numbers will now figure more deliberately in the telling of my stories.  I foresee a research future more open to both inductive and deductive approaches; open to the complementarity and integration of reasoning on offer [10]. I embrace a heightened awareness of the sensitivity and representativeness of my questions design.

Imprinted forever on my memory is the time stepped out in the company of Andy Pemberton [11], and the possibilities for a broader audience through new ‘data vis’ techniques; that visual content is more engaging than text alone[12].

With improving statistical literacy, I’m more confident evaluating and critiquing quants research outputs [5], less oblivious to erroneous statistical conclusions. I’ve learned statistics can help convert data into information [13] and can help to replicate rather than deliver one hit single study wonders.

Timely indeed, given the large amounts of complex data more readily available to us!

References

1. Wikipedia (2018) ‘Lies,damned lies and statistics’ [online]. Available at: https://en.wikipedia.org/wiki/Lies,_damned_lies,_and_statistics[Accessed 20/10/2018].
2. University of Lancaster (2016) ‘Qualitative and quantitative research’ (online). Available at: https://www.lancaster.ac.uk/media/lancaster-university/content-assets/documents/learning-skills/quantitativevqualitativeresearchanswers.pdf[Accessed 3/12/2018].
3. Bond, M.E., Perkins, S.N. & Ramirez, C. (2012) ‘Students’ Perceptions Of Statistics: AnExploration Of Attitudes, Conceptualizations, And Content Knowledge OfStatistics’, Statistics EducationResearch Journal, 11(2), pp. 6-25.
4. Rosetta Stone (2018)General Questions (online). Available at: https://www.rosettastone.com/lp/faq/#02.[Accessed 3/12/2018].
5. Lee,P. (2006) ‘Understanding and critiquing quantitative research papers’, Nursing Times, 102(28), pp.28.
6. Pannucci, C. J., & Wilkins, E. G. (2010) ‘Identifying and avoiding bias in research’, Plastic and Reconstructive surgery, 126(2), pp. 619-25.
7. Paulous, J.A. (2010)‘Stories vs. Statistics’ [blog]. Available at: https://opinionator.blogs.nytimes.com/2010/10/24/stories-vs-statistics/[Accessed 4/12/2018].
8. Gelman, A. & Hennig, C. (2015) ‘Beyond subjective and objective in statistics’ (unpublished) (online). Available at: http://stat.columbia.edu/~gelman/research/unpublished/objectivity10.pdf[Accessed 4/12/2018].
9. Davies, W. (2016) ‘How statistics lost their power – and why we should fear what comes next’, The Guardian, 19^th January2017 (online). Available at:  https://www.theguardian.com/politics/2017/jan/19/crisis-of-statistics-big-data-democracy[Accessed 4/12/2018].
10. Sánchez-Algarra, P., & Anguera, M. (2013) ‘Qualitative/quantitative integration in the inductive observational study of interactive behaviour: Impact of recording and coding among predominating perspectives’, Quality & Quantity, 47(2), pp. 1237-125.
11. Pemberton, A. (2017) ‘Furthr’s director, Andy Pemberton, inspires LSST students and staff on data visualisation and a ‘broken’ social media’ (online). Available at: https://www.lsst.ac/news/furthrs-director-andy-pembertoninspires-lsst-students-and-staff-on-data-visualisation-and-a-broken-social-media/ [Accessed 28/11/2018].
12. Sukhraj, R. (2018) ‘Blogging Statistics to boost your strategy’. Available at:  https://www.impactbnd.com/blog/blogging-statistics-to-boost-your-strategy[Accessed 2/12/2018].
13. Fields, W.L. & Siroky, K.A. (1994) ‘Converting data into information’, Journal of Nursing Care Quality, 8(3), pp. 1-11.
14. Murphy, S. (2016) ‘I love statistics and like that it permits so much freedom: An interview with Susan Murphy’ (online). Available at: http://www.statisticsviews.com/details/feature/9078321/I-love-statistics-and-like-that-it-permits-so-much-freedom-An-interview-with-Sus.html [Accessed 3/12/2018]