This course is designed to provide an introduction to understanding, evaluating data, and making rational data-driven decisions.
Using data is a powerful tool for conducting research. However, several points must be considered to draw correct conclusions from the data. For example, data rarely give an accurate picture of the research subject as it is. Even in carefully planned experiments and surveys, it is inevitable that there will be a variety of errors in the measurements. In the case of statistical surveys, where we are trying to obtain knowledge about the whole (population) from a subset of data (sample), the problem is further complicated by adding sampling error. We must deal with data affected by such chance variation and find conclusions in the face of uncertainty.
Statistics is a way to manage risk under uncertainty and to draw reasonable conclusions from data. In this course, you will learn "Estimation" (point estimation and interval estimation) and "Test" (tests of association in contingency tables, analysis of variance, and tests of differences in means of two groups), which are methods for making surrogate inferences about a population from a sample. The goal is to acquire the ability to understand the mechanics of each analysis, perform them appropriately, and write reports.
The course is characterized by its focus on mastering concepts and interpreting data and statistical analysis results rather than on detailed computational techniques and by its practice of statistical learning in the computer age, including computer-based experiments to deepen students' understanding of theoretical distributions.