Reference no: EM132885031
TOOLS AND TECHNIQUES USED IN DESCRIPTIVE ANALYTICS
Summarization and statistical tools are used to perform descriptive analytics addressing basic questions of "What happened?" or "What is happening?"
One way to explain what has occurred is through descriptive statistics (a tool of descriptive analytics). We define descriptive statistics as brief summaries (or factoids) of a data set that provide a representation of that data as a whole. Descriptive statistics generally are classified as measures of central tendency or measures of variability
Measures of central tendency include:
Mean, median and mode: Summary measures of the central tendency of the data. Medians are usually most useful when there are extreme, or skewed, observations (as often shown by extreme minimums or maximums).
Example: What is the average employee salary? What is the average stock market return over the past 5 years?
By looking at HR data for a period of time, the results can be organized to calculate the average employee salary. However, the data can be skewed by including outliers such as CEO salary, which is generally many times more than the average employee earns.
Example: By sorting sales data from smallest to largest, you can easily see the "minimum" and "maximum" refunds made last month. This is important to understanding how refunds change over the year.
Example: Were there any journal entries that had negative numbers (that might be found by looking at minimums), that might be erroneous?
Example: What was the highest stock price in the past 52 weeks? What was the lowest stock price in the past three months?
Standard deviations: Summary measure that shows the extent of the variability for the sample or population.
Example: What is the standard deviation of the company's stock price over the last quarter?
Quartiles: Division of data observations into four defined intervals based on data values as way of comparing to the overall data set.
Example: In what quartile does Ford fall based on its leverage compared to the automobile industry as a whole?
Deciles: Division of data observations into 10 defined intervals based on data values as way of comparing to the overall data set.
Example: In what decile does Walmart fall based on its return on assets compared to the retail industry as a whole?
Other statistics, tools, and techniques employed in descriptive analyses to explain what happened, may include:
Counts: The number of occurrences of a certain data item or event.