Business analytics techniques are used to facilitate decision making by transforming large amounts of raw data into meaningful information. Many businesses rely on analysis of relevant historical data to make key strategic and operational decisions. Therefore, understanding how to use techniques such as graphical representation and descriptive statistics to translate raw data into useful information can be a valuable skill in an organization.
In this assessment and the next, you will have the opportunity to sharpen your analytics skills by locating and interpreting real-life stock data.
You have been learning about how to explore data. In this assessment, you will apply those skills by downloading a practical dataset and creating graphical representations of that data. The work you do in this assessment will lay the foundation for future assessments in which you analyze and interpret those graphical representations. Since the purpose of business analytics is to make sense of large quantities of raw data, this assessment helps you develop skills in applying analytics to business contexts by practicing the exploration and display of data.
In addition to graphical and tabular summary methods, numeric or quantitative variables and data can be summarized numerically using various techniques of description and display.
Descriptive methods, which describe existing data, are also methods for using a subset of the available data to estimate or test a theory about a measurement on a larger group. This larger group is called the population, and the measurement being studied is the parameter. The smaller group, or subset, of the population that is taken in order to make an inference (to make an estimate or test a theory) is referred to as the sample. The measurement taken on that sample is then referred to as the statistic, which is usually the best single-number estimate for the population parameter of interest. Most often, however, the estimate should not be restricted to a single number that would be exactly correct or incorrect. Instead, it is preferable to calculate some range of possible values between which there can be a certain percent confidence that the true population parameter falls. These are referred to as confidence intervals.
You are an analyst in a publicly traded company. Your supervisor has asked you to create graphical representations from raw stock data for a company-wide meeting at the end of the quarter.