Analysis and Analytics

No this is not hair splitting but a legitimate inquiry. In my view, these two are often used interchangeably by many, if not most.

Most of us may recall ‘Analysis of sentences’ from our grammar lessons in school. The primary meaning of ‘analysis’ is to break down something into its units. You might also recall from your grammar lessons that a simple sentence cannot be analysed.

It is useful to look at some of the definitions:

Analysis

a detailed examination of anything complex in order to understand its nature or to determine its essential features : a thorough study; separation of a whole into its component parts;

(https://www.merriam-webster.com/dictionary/analysis)

the process of studying or examining something in an organized way to learn more about it, or a particular study of something:

the study of something in detail: carry out/perform/conduct an analysis We carried out an analysis of visitors to the website by age, sex, and region.

scientific/chemical analysis Chemical analysis revealed a high content of copper. detailed/comprehensive/in-depth analysis The data can be fed to a computer for detailed analysis. statistical/structural/numerical analysis

(https://dictionary.cambridge.org/dictionary/english/analysis)

Resolution into simpler elements by analysing (opp. synthesis); statement of result of this; … 2. (Math.) Use of algebra and calculus in problem-solving. {§1.1}

(Concise Oxford Dictionary, 1976, as quoted in https://plato.stanford.edu/entries/analysis/s1.html)

Analysis has always been at the heart of philosophical method, but it has been understood and practised in many different ways. Perhaps, in its broadest sense, it might be defined as a process of isolating or working back to what is more fundamental by means of which something, initially taken as given, can be explained or reconstructed. The explanation or reconstruction is often then exhibited in a corresponding process of synthesis. This allows great variation in specific method, however. The aim may be to get back to basics, but there may be all sorts of ways of doing this, each of which might be called ‘analysis’.

(https://plato.stanford.edu/entries/analysis/)

Analytics

Noun – The systematic computational analysis of data or statistics; information resulting from the systematic analysis of data or analytics

(https://languages.oup.com/google-dictionary-en/)

Data analytics is the science of analyzing raw data in order to make conclusions about that information. Many of the techniques and processes of data analytics have been automated into mechanical processes and algorithms that work over raw data for human consumption. (https://www.investopedia.com/terms/d/data-analytics.asp)

Analytics uses data and math to answer business questions, discover relationships, predict unknown outcomes and automate decisions. This diverse field of computer science is used to find meaningful patterns in data and uncover new knowledge based on applied mathematics, statistics, predictive modeling and machine learning techniques.

(https://www.sas.com/en_us/insights/analytics/what-is-analytics.html)

Exploring the two

A careful examination of these definitions indicates that analysis is quite a nuanced expression as it conveys many things. While there is the basic idea of breaking down something into its constitutive components or parts, there is the other aspect of being in-depth. In fact, as the Stanford Encyclopedia explains its meaning as used in philosophy, analysis can be “defined as a process of isolating or working back to what is more fundamental by means of which something, initially taken as given, can be explained or reconstructed. The explanation or reconstruction is often then exhibited in a corresponding process of synthesis. This allows great variation in specific method, however. The aim may be to get back to basics, but there may be all sorts of ways of doing this, each of which might be called ‘analysis’”. There are some critical aspects here – isolating, reconstructing – which are the crux of analysis. There is also the reference to synthesis which allows for great variation in specific method. We might think of specific method today as tools and techniques which help in analysis. However, the whole world of tools & techniques are of no use unless you had a basic idea of what you are looking for. Yes, there have been cases where (unexpected) data came up in a laboratory or through the use of some tools which didn’t make sense, which led to fruitful inquiries. Students of physics will know this to be true in experiments in Quantum physics. In sum, the dominant dimension seems mental here in the sense of a thinking through something using certain tools and techniques to work back to find the kernel of explanation.

I am going to stick my neck out and say this: analytics is not mandatory for analysis. If it were, we would have to accept that there has hitherto been no analysis until the advent of analytics, which clearly is not defensible. The development of science itself bears testimony to this observation. Even literary studies involves analysis without any use of analytics. The rich tradition of literary studies dates earlier than even software, let alone analytics. Using Word in analysis of texts, you can make use of the global ‘Find’ in word to see how frequently certain words populate a text, and together with context, what they mean. Just as you can use Excel to ‘discover’ many things by analyzing quantitative data. The list can go on. The point I wish to make is simple but, in my view, profound.

To emphasize, in what we call analysis, thinking is integral to it. Analysis is simply a way of thinking. On the contrary, what is central to analytics is data and computing power. In fact, there is so much fascination with the sheer computing power available and the technology that there is an implicit belief that this by itself will produce intelligence. Or that you cannot find intelligence otherwise. I always refer people to Einstein’s 1905 year when he wrote five papers that changed Physics forever. There was no computing power that he had access to!

I am not a Luddite and, if I am seen as laboring the point, I am and for a reason. During the last five years and more, I have interviewed over 2000 students and professionals for higher and further studies. And I report with a sense of fear that this fascination is not encouraging because I haven’t seen much evidence of thinking. Computing power can actually be a problem if what is fed into it is flawed or faulty – a simple matter of input-output relationship. And what goes into it depends on what you have considered important, influential factors represented as data. If you input incorrect data, all that will happen is that you will get some absurd result very fast.

What you need to learn first is techniques of analysis. Simple statistics is a good starting point. Even a basic topic like classification and tabulation of data will teach you a great deal. I am a great believer in statistics as a subject which is useful whatever else you study.

More in later posts.

Takeaways

Analysis and analytics are not synonymous with each other

Grammatical understanding of analysis holds clue to a better understanding

Obsession with analytics is clouding people’s minds

Synthesis is a key factor in analysis