Logical thinking plays a crucial role in any analytical study. It has been seen that the students, research scholars and professionals in this area do not devote enough time on assessing a situation or a problem critically so as to come to a logical conclusion. In absence of a proper logical analysis there is a high probability that the output derived out of particular analysis may be either un-implementable or may draw criticism as it does not necessarily have a proper logical relevance. For instance, “Sun rises in the east” – is a universal truth and hence there is no need to collect data, analyze and infer that “Sun rises in the east” is true. Another instance, “National Sample Survey Organization’s data on household consumption expenditure in India, Say, someone is using the data to verify how household income affects the consumption expenditure? Without the loss of generality, if we logically assess the situation how things are happening around us, then, we could make out that the income impacts the expenditure with some proportion (in aggregate) and hence an appropriate assumption can be framed and tested under a given circumstance. Unless, there are outliers the hypotheses should come true and accepted. So, logically someone (the analyst) should be able to predict the outcome. The same result could also be preserved with support from statistical tests. It’s better to preserve an assumption framed logically than to reject an assumption framed unscientifically or without any logic.
A business analyst generally confronts with data that can be used to draw insightful inferences which help in making a decision that can be implemented to achieve some good results. There are basically three ways to deal with a business problem, namely – building theories from various concepts on a particular topic, mathematical modelling and empirical or evidence based findings. The first calls for a high level of understanding of a particular concept (can be expected from highly experienced researchers or academicians and industrialists with high degree of knowledge and wisdom and with an appetite for learning). The second one needs for a high level of mathematical acumen with an expertise to build and test the validity of the model by a proper empirical technique. The third one is relatively easier and requires for a high level understanding of empirically driven research. However, in all three cases someone should have high level of understanding of domain/sector, research methods, quantitative and software skills, and above all a sound logical mind set.
This is all about understanding a particular business problem and then finding a correct solution for it. It has been observed that people commit mistakes in recognising the real problem (not the symptom), which otherwise indicate absence of proper logical assessment of the situation, and hence commit mistakes in the analysis knowingly or unknowingly. An incorrect assessment of the problem statement leads to an incorrect or incompatible result, which is of no use. Hence, it is said that, “a problem well defined is a problem half solved.”
End of the day, it is the logic that matters – may it be common life or complex business processes. Nobody can really refute an inference that has come through a sound logical process. But, certainly people question if the study or research have not come through a sound logical process, no matter how acceptable the results are. If someone wants his/her work to help someone else and if he/she wants to communicate something through his/her work, then it’s the logic that can really drive the results, which otherwise the analytics alone can’t do.
Authored by Dr. Pramod Kumar Mishra (Faculty), GITAM School of International Business.
For any queries, connect with us here.