Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It only takes a minute to sign up.
Sign up to join this community
I have 4 covariates - $A$, $B$, $C$ and $D$. Three of them ($A$, $B$, $C$) independently show strong correlation with the forth one ($D$). I can create a chart in Excel for each pair ($A$-$D$, $B$-$D$, $C$-$D$), add a trend line, and get an equation for the trend line. In my case all of them show quadratic trends with the fourth covariate $D$.
I would like to create an equation using the three covariates ($A$,$B$,$C$) to predict the forth one ($D$).
As @whuber said, you need a cookie-cutter linear regression (you can add polynomial so without problem). You can use excel to accomplish it, but it is better to use a statistical package (R, STATA, SPSS etc..) each of these packages have easy tools for importing the data from excel as a .xls or .csv in a fairly straightforward format. After which you get a fairly easily interpretable output.
