Hi, I used simple linear regression with the R software and EXCEL on the same data. Although , I find the same R2=0.84, I find different estimated values (intercept and slope). For the R software (slope =0.0009, Intercept = -0.1478), for EXCEL (slope =927.7, Intercept = 154,41). When I use the estimated values from the R software, the results seem bad, however the results of Exel seem correct. Do you know why I have different estimated values between the R software and EXCEL? I give below a sample of data: Thank you in advance var1 var2 0,11 264,6 0,01 226,7 0,05 168,1 -0,03 144,9 -0,07 108,1 0 118,22 -0,09 85,6 -0,07 103 -0,05 89,6 -0,06 92,8 -0,11 64,9 -0,11 33 -0,08 32,5 -0,12 42,3 -0,14 36,7 -- View this message in context: http://r.789695.n4.nabble.com/Different-Estimated-values-between-R-and-Excel-tp3762508p3762508.html Sent from the R help mailing list archive at Nabble.com.
Different Estimated values between R and Excel
4 messages · Komine, Bart Joosen, David Winsemius
I you had posted your code which gave the results, we would have seen that you switched your variables. Bart -- View this message in context: http://r.789695.n4.nabble.com/Different-Estimated-values-between-R-and-Excel-tp3762508p3762738.html Sent from the R help mailing list archive at Nabble.com.
Thanks, I see the problem. R did the opposite of Excel. I invert the position of variables in my code and the result is now correct. -- View this message in context: http://r.789695.n4.nabble.com/Different-Estimated-values-between-R-and-Excel-tp3762508p3762870.html Sent from the R help mailing list archive at Nabble.com.
On Aug 23, 2011, at 7:48 AM, Komine wrote:
Hi, I used simple linear regression with the R software and EXCEL on the same data. Although , I find the same R2=0.84, I find different estimated values (intercept and slope). For the R software (slope =0.0009, Intercept = -0.1478), for EXCEL (slope =927.7, Intercept = 154,41). When I use the estimated values from the R software, the results seem bad, however the results of Exel seem correct. Do you know why I have different estimated values between the R software and EXCEL?
Well, I don't "know" since you didn't include your code, but on the basis of the slopes being roughly the inverse of each other, I am guessing you reversed the roles of the variables and in Excel were making var2 the dependent variable and in R making var1 dependent.
I give below a sample of data: Thank you in advance var1 var2 0,11 264,6 0,01 226,7 0,05 168,1 -0,03 144,9 -0,07 108,1 0 118,22 -0,09 85,6 -0,07 103 -0,05 89,6 -0,06 92,8 -0,11 64,9 -0,11 33 -0,08 32,5 -0,12 42,3 -0,14 36,7 -- View this message in context: http://r.789695.n4.nabble.com/Different-Estimated-values-between-R-and-Excel-tp3762508p3762508.html Sent from the R help mailing list archive at Nabble.com.
______________________________________________ R-help at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
David Winsemius, MD West Hartford, CT