Hi everyone,
I am trying to generate a conditional dummy variable ”X" with the following
rules
set X=1 if Y is =1, two years prior to the NA. [0,0,NA].
For example, if the pattern for Y is 0,0,NA then the X variable is =0 for all
the two years prior to the NA. If the pattern for Y is 0,1,NA or 1,0,NA then
the X =1 . To be clear, if 1,1,NA then the X=1 that first specific year, it
should only count once (X=1), not twice.
The code that I have now is not complete and I would appreciate some advice
here. This is the code:
dat2 <- dat1 %>%
group_by(country) %>%
group_by(grp = cumsum(is.na(lag(Y))), add = TRUE) %>%
mutate(first_year_at_1 = match(1, Y) * any(is.na(Y)) * any(tail(Y, 3) == 1L),
X = {x <- integer(length(Y)) ; x[first_year_at_1] <- 1L ; x}) %>%
ungroup()
It doesn’t really generate what I described above. Any help here would be much
appreciated.
Below you can see my sample data with the desired outcome ”X” dummy in it.
Thank you!
> dput(data)
structure(list(year = c(1991L, 1992L, 1993L, 1994L, 1995L, 1996L,
1997L, 1998L, 1999L, 2000L, 2001L, 2002L, 2003L, 2004L, 2005L,
2006L, 2007L, 2008L, 2009L, 2010L, 2011L, 1990L, 1991L, 1992L,
1993L, 1994L, 1995L, 1996L, 1997L, 1998L, 1999L, 2000L, 2001L,
2002L, 2003L, 2004L, 2005L, 2006L, 2007L, 2008L, 2009L, 2010L,
2011L, 1990L, 1991L, 1992L, 1993L, 1994L, 1995L, 1996L, 1997L,
1998L, 1999L, 2000L, 2001L, 2002L, 2003L, 2004L, 2005L, 2006L,
2007L, 2008L, 2009L, 2010L, 2011L, 1990L, 1991L, 1992L, 1993L,
1994L, 1995L, 1996L, 1997L, 1998L, 1999L, 2000L, 2001L, 2002L,
2003L, 2004L, 2005L, 2006L, 2007L, 2008L, 2009L, 2010L, 2011L,
1990L, 1991L, 1992L, 1993L, 1994L, 1995L, 1996L, 1997L, 1998L,
1999L, 1999L, 2000L, 2001L, 2002L, 2003L, 2004L, 2005L, 2006L,
2007L, 2008L, 2009L, 2010L, 2011L), country = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L), .Label = c("Canada",
"Cuba", "Dominican Republic", "Haiti", "Jamaica"), class = "factor"),
Y = c(1L, NA, 1L, 1L, 1L, NA, 1L, NA, 1L, NA, 1L, NA, 1L,
1L, NA, 1L, NA, 1L, NA, 1L, NA, NA, 1L, 1L, NA, NA, 1L, NA,
1L, NA, 1L, NA, 1L, 1L, 1L, 1L, NA, 1L, NA, 1L, NA, 1L, NA,
NA, 1L, NA, 1L, 0L, 0L, 0L, 1L, NA, 0L, 1L, 0L, 0L, 0L, 0L,
0L, 1L, NA, 0L, 1L, 1L, NA, 0L, 1L, NA, 1L, NA, 1L, NA, 1L,
NA, 1L, NA, 1L, 1L, 1L, 1L, NA, 1L, NA, 1L, NA, 1L, NA, 1L,
0L, 0L, 0L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, NA, 0L, 1L, 1L, 1L,
NA, 1L, NA, 0L, 1L, 1L, NA), X = c(1L, 0L, 0L, 1L, 0L, 0L,
1L, 0L, 1L, 0L, 1L, 0L, 1L, 0L, 0L, 1L, 0L, 1L, 0L, 1L, 0L,
0L, 1L, 0L, 0L, 0L, 1L, 0L, 1L, 0L, 1L, 0L, 0L, 0L, 1L, 0L,
0L, 1L, 0L, 1L, 0L, 1L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 1L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 1L, 0L, 0L, 0L,
1L, 0L, 1L, 0L, 1L, 0L, 1L, 0L, 1L, 0L, 0L, 0L, 1L, 0L, 0L,
1L, 0L, 1L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
1L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 1L, 0L, 0L, 1L, 0L, 0L)), .Names =
c("year",
"country", "Y", "X"), class = "data.frame", row.names = c(NA,
-110L))
[[alternative HTML version deleted]]
______________________________________________
[email protected] mailing list -- To UNSUBSCRIBE and more, see
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.
