Вивчаючи статистику

The Pareto Diagram. A special type of bar chart in which the counts, amounts, or percentages of each category are presented in descending order left to right, along with a superimposed plotted line that represents a running cumulative percentage.
When there are many categories, Pareto diagrams enable you to focus on the most important categories by visually separating the “vital few” from the “trivial many” categories. For the keyboard defects data, the Pareto diagram highlights that two categories, warpage and damage, account for nearly one-half of all defects, and that those two combined with the pin mark category account for more than 60% of all defects.
Two-Way Cross-Classification Tables. A multicolumn table that presents the count or percentage of responses to two categorical variables. In two-way tables, the categories of one of the variables form the rows of the table, while the categories of the second variable form the columns. Cross-classification tables are also known as cross-tabulation tables.
The simplest two-way table has but two rows and two columns in its inner part (that is, excluding the total).
Column Variable

		1	2	Total
Row Variable	1	Count or percentage for row 1, column 1	Count or percentage for row 1, column 2	Total for row 1
	2	Count or percentage for row 2, column 1	Count or percentage for row 2, column 2	Total for row 2
Total		Total for column 1	Total for column 2	Overall total

Each cell in the inner part of the table represents the count or percentage of a pairing, or cross-classifying, of categories from each variable. Sometimes additional rows and columns present the percentages of the overall total, the percentages of the row total, and the percentages of the column total for each row and column combination.

Two-way tables can reveal what combination of values is most prevalent in data. In the example, the tables reveal that bad wafers are much more likely to have particles than the good wafers. Because the number of good and bad wafers was unequal in this example, you can best see this pattern in the Row Percentage table. That table shows that nearly three-quarters of the wafers that had particles were bad, but only 20% of wafers that did not have particles were bad.