TD_LINEAR_REGR Function | Teradata Vantage - TD_LINEAR_REGR - Teradata Vantage

Database Unbounded Array Framework Time Series Functions

Deployment
VantageCloud
VantageCore
Edition
Enterprise
IntelliFlex
VMware
Product
Teradata Vantage
Release Number
17.20
Published
June 2022
Language
English (United States)
Last Update
2024-10-04
dita:mapPath
ncd1634149624743.ditamap
dita:ditavalPath
ruu1634160136230.ditaval
dita:id
ncd1634149624743

TD_LINEAR_REGR is a simple linear regression function. It fits data to a curve using a formula that defines the relationship between the explanatory variable and the response variable.

Simple linear regression has many applications such as the following:

  • Marketing: Predict sales based on the amount of money spent on advertising. The company can determine the most effective advertising strategy to increase sales.
  • Economics: Analyze the relationship between variables such as inflation and interest rates, or unemployment rates and GDP. Economists can make predictions about the future of the economy.
  • Medicine: Analyze the relationship between a patient's age and a particular disease. Doctors can better predict the likelihood of a patient developing a certain disease and recommend preventative measures.
  • Education: Analyze the relationship between a student's study time and their grades. Teachers can identify which students need additional support and resources to improve their academic performance.
  • Sports: Analyze the relationship between an athlete's performance and their physical attributes such as height or weight. Coaches can optimize their team's performance by selecting players with the optimal physical attributes.
  • Finance: Analyze the relationship between a company's stock price and various financial metrics such as revenue or earnings. Investors can make informed decisions about whether to buy, hold, or sell a particular stock.
The following procedure is an example of how to use TD_LINEAR_REGR to develop a simple regression model. The goal is to create a regression model showing the relationship between, HousePrice (response variable) and Salary (explanatory variable).
  1. Use TD_LINEAR_REGR to curve-fit sample data (HousePrice, Salary) to the FORMULA Y = B1*X1 + Constant, where Y is HousePrice and X1 is Salary.
  2. Use TD_EXTRACT_RESULTS generate an ART table containing the ARTFITMETADATA layer and ARTFITRESIDUAL layer to retrieve goodness-of-fit measures and the residual data after model-fitting, respectively.
  3. Use TD_GENSERIES4FORMULA with new Salary data points to predict the price of the house that the applicant can purchase.