Interpretation of coefficient of determination (R^2)
0
0
Entering edit mode
3.2 years ago

I calculatet R^2 via the lm function in R. I examined how differences in my quantitative trait can be explained by differences in the diplotype effect (calculated via ASReml). It resulted in 0.58 for R^2. Or in case of the multiple linear regression (Diplotype effect, age, sex, body weight and height) 0.77. I would like to ask how to interpret these values in my discussion. How good are these values and how much i can trust them. Please advice me some good literature. Thanks in advance

coefficient of determination • 1.1k views
ADD COMMENT
0
Entering edit mode

R-Squared (coefficient of determination) explains the variation in the y variable (response) that is explained by independent variables in the fitted regression. If your R-Squared is 0.58 for simple regression, it explains 58% of the variance in the response variable (quantitative trait) can be explained by the independent variable alone (diplotype effect).

In multiple regression, adjusted R-Squared (corrected for sample size and regression coefficients) is more appropriate than R-Squared as an increasing number of independent variables also increases R-Squared. Read more here about regression and interpretation

ADD REPLY
0
Entering edit mode

Thanks for your answer, i would like to hear your oppinion about the the values 0.58 and 0.77. Do you think they are good or high in that context?

ADD REPLY

Login before adding your answer.

Traffic: 1555 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6