Research on Teaching Reform of College Statistics Course in the Age of Big Data

Di Wu
2018 Proceedings of the 2018 3rd International Conference on Education, Sports, Arts and Management Engineering (ICESAME 2018)   unpublished
With the rise of the Internet, people's way of life has changed dramatically. We can read news or interesting things thousands of miles away on our mobile phones without leaving home, and we can browse the information we want on our computers by moving our fingers. For enterprises, the use of data to understand customer demand and consumption habits, and can easily enough to achieve market positioning and market segmentation, so as to achieve the purpose of data management enterprise structure,
more » ... enterprise production. For government organizations, big data can directly reflect the needs of the people, thus improving the governance of government departments, service concepts and policy changes, which is conducive to the unified management of the country. In March 2015, relevant leaders at the two sessions also particularly stressed the importance of big data, so that the common people understand big data and feel the change in life made by big data. To sum up, big data has been widely used in the life of the masses, in the management of enterprises, and in the governance of the country. In such an age background, the talent required by the big data technology has become the object of competition in various industries. However, how to train statistics talents in the new era has naturally become the focus of teaching, and the traditional statistical teaching model is also facing great reform. Disadvantages of Traditional Statistics The Teaching Content does not Apply to Big Data's Time. Statistics, as a discipline to understand the total quantitative characteristics of objective phenomena and the relationship between quantity and quantity, has a relatively long history of development, and the statistical methods have mostly been perfected and summarized by many predecessors, so the contents of statistics are relatively unified. Teaching methods are also relatively fixed[1].In the past two decades, statistics courses for major economic management majors in major universities and colleges have generally been "applied statistics", "principles of statistics", "market investigation and prediction" and so on. However, many of the contents in these courses can no longer adapt to big data's time. Even out of touch with it. For example, its traditional statistical methods of collecting data are mainly sample surveys, then data collation, data classification. After that, not only do related descriptive statistical analysis, but also do extrapolation statistical analysis, there are many steps. The calculation is complicated. For big data, he abandoned the sampling survey of statistics and used the general method of sample data survey to infer the correlation rather than causality of things. From this point of view, the traditional statistical thinking and big data's computational thinking are quite different. But many teachers also ignore this point, resulting in students can not understand and accept new thinking and new ideas, can not understand the characteristics of the two, only one-sided study of the methods of statistics, hindered the expansion of ideas [2] . Teaching Methods are Limited. For the current statistical courses, teachers usually use case analysis and classroom teaching methods. For theoretical knowledge, teachers generally use the combination of teaching and statistical cases to explain. For the practical application chapters, such as investigation and statistics, data collation, data analysis and so on, the teaching methods such as social sampling survey and computer analysis are often used to express the relationship between the data. In addition, teachers often use basic data processing software to teach students to use computer tools to analyze data. However, although the above measures also seem reasonable, in 379
doi:10.2991/icesame-18.2018.78 fatcat:zcnapvikovabfk6l55xhfpeieu