Skip to main content
Cross Validated

Return to Answer

replaced http://stats.stackexchange.com/ with https://stats.stackexchange.com/
Source Link
Community Bot
Community Bot
  • 1

At this point you haven't described the within-group heteroscedasticity structure in your model yet. Try weights=varPower() as shown in the example in ?gls. That gets rid of the heteroscedasticity in your case.

Compare:

m1 <- gls(salary ~ age*sex)
plot(m1)

enter image description here

m2 <- gls(salary ~ age*sex, weights=varPower())
plot(m2)

enter image description here

Also if you look in Chapter 5.2.1 (page 208) in Mixed Effects Models in S and S-Plus by Pinheiro and Bates 2000, there is a lot of information on the Variance Functions in nlme. This answer may also be helpful: Regression modelling with unequal varianceRegression modelling with unequal variance .

At this point you haven't described the within-group heteroscedasticity structure in your model yet. Try weights=varPower() as shown in the example in ?gls. That gets rid of the heteroscedasticity in your case.

Compare:

m1 <- gls(salary ~ age*sex)
plot(m1)

enter image description here

m2 <- gls(salary ~ age*sex, weights=varPower())
plot(m2)

enter image description here

Also if you look in Chapter 5.2.1 (page 208) in Mixed Effects Models in S and S-Plus by Pinheiro and Bates 2000, there is a lot of information on the Variance Functions in nlme. This answer may also be helpful: Regression modelling with unequal variance .

At this point you haven't described the within-group heteroscedasticity structure in your model yet. Try weights=varPower() as shown in the example in ?gls. That gets rid of the heteroscedasticity in your case.

Compare:

m1 <- gls(salary ~ age*sex)
plot(m1)

enter image description here

m2 <- gls(salary ~ age*sex, weights=varPower())
plot(m2)

enter image description here

Also if you look in Chapter 5.2.1 (page 208) in Mixed Effects Models in S and S-Plus by Pinheiro and Bates 2000, there is a lot of information on the Variance Functions in nlme. This answer may also be helpful: Regression modelling with unequal variance .

Source Link
Stefan
Stefan
  • 6.6k
  • 1
  • 24
  • 45

At this point you haven't described the within-group heteroscedasticity structure in your model yet. Try weights=varPower() as shown in the example in ?gls. That gets rid of the heteroscedasticity in your case.

Compare:

m1 <- gls(salary ~ age*sex)
plot(m1)

enter image description here

m2 <- gls(salary ~ age*sex, weights=varPower())
plot(m2)

enter image description here

Also if you look in Chapter 5.2.1 (page 208) in Mixed Effects Models in S and S-Plus by Pinheiro and Bates 2000, there is a lot of information on the Variance Functions in nlme. This answer may also be helpful: Regression modelling with unequal variance .