Require assistance with possible multiple regression analysis

Click For Summary
SUMMARY

Dants is conducting a study to estimate body fat percentage using multiple regression analysis based on measurements from 252 participants. He measures the circumference of 10 body segments and uses underwater weighing for accuracy. The discussion clarifies that in a machine learning context, the terms "multiple regression" and "simple linear regression" can be used interchangeably, as the underlying model remains linear regardless of the curve's shape. The focus is on generating a predictive equation for body fat estimation.

PREREQUISITES
  • Understanding of multiple regression analysis
  • Familiarity with linear regression concepts
  • Knowledge of body composition measurement techniques
  • Experience with statistical software for data analysis
NEXT STEPS
  • Research how to implement multiple regression in Python using libraries like scikit-learn
  • Explore techniques for feature selection in regression models
  • Learn about validation methods for regression models, such as cross-validation
  • Investigate the impact of multicollinearity on regression analysis
USEFUL FOR

Researchers, data analysts, and health professionals interested in body composition analysis and predictive modeling techniques.

Dants
Messages
4
Reaction score
0
I am interested in determining more efficient ways of determining individuals' body fat percentage. To do this, I measure the circumference of a number of segments (10 of them) of the body and determine the person's percentage body fat through underwater weighing. I have done this for 252 total participants, and I have recorded the age for the participants.

My goal is to facilitate the simple estimation of percentage body fat. I wish to generate a predictive equation the best estimate of percentage body fat. Am I correct to assume that I should be using multiple regression or simple linear regression?

Thanks,

Dants
 
Physics news on Phys.org
In a machine learning environment, the terms are essentially interchangeable, and it doesn't matter. The underlying model is the same either way. In fact, any kind of regression in which the coefficients show up linearly is still linear regression, even if the shape of the line or curve being fit is not straight. It's how the coefficients show up that determine if the model is a linear regression model, not the shape of the line or curve.
 

Similar threads

Undergrad What Are the Key Differences Between OLS and GLM Models in Statistical Analysis?
  • · Replies 3 ·
Replies
3
Views
3K
Undergrad What is Nonlinear Least Squares in Regression Analysis?
  • · Replies 4 ·
Replies
4
Views
2K
MHB Forecasting metric using regression. Is this a sound approach?
  • · Replies 3 ·
Replies
3
Views
2K
MHB Can Categorical Variables be Used in Multiple Regression Models?
  • · Replies 1 ·
Replies
1
Views
2K
Undergrad Regression Analysis: Does it Make Sense?
  • · Replies 11 ·
Replies
11
Views
3K
MHB Require assistance with possible ANOVA use
  • · Replies 3 ·
Replies
3
Views
2K
Undergrad How to Handle Non-Normal Residuals in Multiple Regression Analysis
  • · Replies 8 ·
Replies
8
Views
3K
Undergrad Multivariate regression for project cost estimates
  • · Replies 6 ·
Replies
6
Views
3K
Graduate Sports Illustrated Jinx : Regression to the Mean
  • · Replies 6 ·
Replies
6
Views
6K
Intermediate Physics Lab Analysis, Uncertainty and Linear Regression
  • · Replies 1 ·
Replies
1
Views
3K