Percentage of contribution of multiple factors to a single dependent variable using PCA in Matlab

4 visualizaciones (últimos 30 días)
I've got a set of data (underway observation along cruise track) which incorporates one dependent variable A and three independent variables B, C, and D. Now it's known that A is related with each of the three factors, respectively, so I'm thinking maybe I can find out a numerical relationship that allows me to express A by means of B, C, and D somehow, with the benefit of being able to evaluate the relative contribution of each independent variable to the target variable A. I'm aware PCA is the tool to use in this situation, and I've tried it on excel, only to get a biplot where all four variables are treated equally as the same type of dependent variables and variable A is used to explain those principal components, while what I really want is to see how A behaves under the joint influence of B, C, and D, and I don't care how B, C, and D themselves relate to each other. I know the way I stated the question is kinda awkward, but I thought what I'm looking for should have been easier and I'm desperate to find the solutions to the question (preferably the code in Matlab). Thanks Guys.
Lin

Respuestas (1)

Sagar
Sagar el 9 de Ag. de 2015
Unfortunately, PCA may not be the tool for what you are looking for. PCA is more suitable when the number of variables is large and you want to reduce the no. of dimensions. In your case, since you have only three variables, a simple multiple regression model may be more suitable for your analysis.

Categorías

Más información sobre Dimensionality Reduction and Feature Extraction en Help Center y File Exchange.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by