Why is statistics so important in our lives? Also, why is it considered the invisible demi-god of analytics by statisticians across the world?
The first time humans ever used statistics (unknowingly of course) was in 2,500 BC when the Egyptians used censuses to work out how many people they needed to build their pyramids. They also used this information to understand how to share lands after the annual flooding of the Nile. The Romans too conducted censuses every five years to track the population. Since then civilizations have effectively used the supremacy of number analysis to understand population, demographics and diseases.
Over the years statistics has played an important role in leading us into the 21st century. Therefore, this year, statisticians, academia and organizations have come together to celebrate The International Year of Statistics. Considered as a rather interesting field, The American Statistics Association’s newsletter terms a statistician’s job as the third best in the US. After reading the ‘Freakonomics’, an excellent book by Steven Levitt and Stephen Dubner, one would believe so. The book makes interesting observations in various areas of life like wrestling, abortion, crime etc. These observations were made by digging enormous statistical data and through various data mining techniques. However, closer to our work life, the technology industry has embraced statistics from the beginning. Deep understanding of statistics by technology companies has helped them go up the quality ladder and enjoy increased efficiency and profitability. They have made use of both internal and external data sources (ranging from customer transaction and survey data to official statistics). Statistics has also supported growth of data mining, a relatively new discipline that has developed mainly from studies carried out in disciplines such as in the field of computing and marketing.
Many of these methodologies used in data mining are derived from two branches of research, one developed in the machine learning community and the other developed in the statistical community, particularly in multivariate and computational statistics. In many applications the aim is to gain value from customer data and investigate business complexity. Techniques including decision trees, logistic regression, cluster analysis and self-organizing maps are used to measure customer value, segment customer data, predict customer attrition and understand the acceptance of new technologies such as online buying. Much research is underway in web mining as well, particularly looking at association models for web usage mining and comparison of different models to understand the best model that can be used to describe web visit patterns.
Therefore, it is not surprising that statisticians are in great demand in modern day analytics organizations. Troubleshooting, process improvement, quality control and planning – all require a statistical approach and form the basis of why organizations are so keen to adopt statistics. They are increasingly recognizing the importance of statisticians and are basing their growth on two fundamental disciplines of applied statistics: ‘data analyses and ‘probability calculus’.
Today, statistics and statisticians form an important part of the analytics organization and provide crucial guidance in determining what information is reliable and which predictions can be trusted. While many tools have only made life of statisticians simpler, organizations must remember that it’s all about statistical thinking rather than a focus on statistical tools. I personally believe that endorsement from management, in any organization, is necessary and will go a long way in understanding and efficient implementation of statistics.
Statistics has an important role to play in overcoming business challenges; it will remain omnipotent and ever pervasive in organizations. Like Florence Nightingale once said, “To understand God’s thoughts we must study statistics, for these are the measure of His purpose.”
Try deep learning using MATLAB