Book Image

Data Analysis Using SQL and Excel - Second Edition

By : Gordon S. S. Linoff
Book Image

Data Analysis Using SQL and Excel - Second Edition

By: Gordon S. S. Linoff

Overview of this book

Data Analysis Using SQL and Excel, 2nd Edition shows you how to leverage the two most popular tools for data query and analysis—SQL and Excel—to perform sophisticated data analysis without the need for complex and expensive data mining tools. Written by a leading expert on business data mining, this book shows you how to extract useful business information from relational databases. You'll learn the fundamental techniques before moving into the "where" and "why" of each analysis, and then learn how to design and perform these analyses using SQL and Excel. Examples include SQL and Excel code, and the appendix shows how non-standard constructs are implemented in other major databases, including Oracle and IBM DB2/UDB. The companion website includes datasets and Excel spreadsheets, and the book provides hints, warnings, and technical asides to help you every step of the way. Data Analysis Using SQL and Excel, 2nd Edition shows you how to perform a wide range of sophisticated analyses using these simple tools, sparing you the significant expense of proprietary data mining tools like SAS.
Table of Contents (18 chapters)
Free Chapter
1
Foreword
17
EULA

Left Truncation

This section moves to another topic, which is the accurate calculation of hazard probabilities. As noted in the previous chapter, the customers in the Subscribers table data have an unexpected property: Customers who stopped before some date (that depends on the market) are excluded from the table. This phenomenon, where customers are excluded based on their stop date, is called left truncation, and naïve hazard calculations on left-truncated data produce incorrect results. In the previous chapter, the problem of left truncation was handled by introducing LeftTruncationDate into all the queries. This section presents a more flexible method, based on an idea called time windows.

Left truncation is a problem because hazard estimates on left truncated data are simply incorrect. The solution to left truncation is to calculate the hazards using only a “time window” of activity—the calculation only uses information from customers active during the time...