Proc mixed in SAS vs. R (Additional questions)

General
1

Hi.
I am trying to reproduce output from the PROC MIXED procedure using R.

But SAS result and R result are so different.

There are variables, SAS code and R code below.

[Variable]

Y : Numeric

Year: Numeric (2017, 2018) but want to analyze as a categorical variable

Level: Numeric (1, 2) but want to analyze as a categorical variable

[SAS code]

data m (keep=country y year level) ; set m2;

y=_8_4q ; year=2017; output m;

y=_0_2q; year=2018; output m; run;

proc mixed data=m;
class level y country;
model y = level|year;
repeated / type=ar(1) sub=country;
run;

[R code]
library(nlme)
gls(y ~ level*year, correlation = corAR1(form = ~ 1 | Country), weights = varIdent(form = ~ 1 | year), data=data, method = "REML")

Please give me advice on how to change the R code to similar values to SAS results.
And how do I change the level and year as the categorical variable in R?

Thank you in advance.

2

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.