How to generate a conditional dummy in R?

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]]

fkdf$X

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]]

29 maj 2018 kl. 02:15 skrev Jim Lemon <drjimlemon at gmail.com>:

Hi Faradj,
What a problem! I think I have worked it out, but only because the
result is the one you said you wanted.

# the sample data frame is named fkdf
Y2Xby3<-function(x) {
nrows<-dim(x)[1]
X<-rep(0,nrows)
for(i in 1:(nrows-2)) {
 if(!is.na(x$Y[i])) {
  if(x$Y[i] == 1 && any(is.na(x$Y[(i+1):(i+2)]))) X[i]<-1
  if(i > 1) {
   if(X[i-1] == 1) X[i]<-0
  }
 }
 else {
  if(!is.na(x$Y[i+1])) {
   if(x$Y[i+1] == 1 && is.na(x$Y[i+2]) && X[i] == 0)
    X[i+1]<-1
  }
 }
}
return(X)
}
countries<-as.character(unique(fkdf$country))
X1<-NULL
for(country in countries)
X1<-c(X1,Y2Xby3(fkdf[fkdf$country == country,]))
X1
 [1] 1 0 0 1 0 0 1 0 1 0 1 0 1 0 0 1 0 1 0 1 0 0 1 0 0 0 1 0 1 0 1 0 0 0 1 0 0
[38] 1 0 1 0 1 0 0 1 0 0 0 0 0 1 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0 1 0 1 0 1 0 1 0
[75] 1 0 0 0 1 0 0 1 0 1 0 1 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 1 0 0 1 0 0 1 0 0

fkdf$X

 [1] 1 0 0 1 0 0 1 0 1 0 1 0 1 0 0 1 0 1 0 1 0 0 1 0 0 0 1 0 1 0 1 0 0 0 1 0 0
[38] 1 0 1 0 1 0 0 1 0 0 0 0 0 1 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0 1 0 1 0 1 0 1 0
[75] 1 0 0 0 1 0 0 1 0 1 0 1 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 1 0 0 1 0 0 1 0 0

Jim

On Mon, May 28, 2018 at 8:43 PM, Faradj Koliev <faradj.g at gmail.com> wrote:

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]]

Dear Jim,

wow! It worked! Thanks a lot.

I did as you suggested and it worked well with the real data. Although it
gave me this error: Error in if (!is.na(x$Y[i])) { : argument is of length
zero. For some reason the X1 produced less observations than it is in the
data. But it's not a big deal - I identified those cases and simply deleted
from the data (it was countries that only appeared twice in the data (e.g.
USSR Yugoslavia etc).

Best,
Faradj


29 maj 2018 kl. 02:15 skrev Jim Lemon <drjimlemon at gmail.com>:

Hi Faradj,
What a problem! I think I have worked it out, but only because the
result is the one you said you wanted.

# the sample data frame is named fkdf
Y2Xby3<-function(x) {
nrows<-dim(x)[1]
X<-rep(0,nrows)
for(i in 1:(nrows-2)) {
 if(!is.na(x$Y[i])) {
  if(x$Y[i] == 1 && any(is.na(x$Y[(i+1):(i+2)]))) X[i]<-1
  if(i > 1) {
   if(X[i-1] == 1) X[i]<-0
  }
 }
 else {
  if(!is.na(x$Y[i+1])) {
   if(x$Y[i+1] == 1 && is.na(x$Y[i+2]) && X[i] == 0)
    X[i+1]<-1
  }
 }
}
return(X)
}
countries<-as.character(unique(fkdf$country))
X1<-NULL
for(country in countries)
X1<-c(X1,Y2Xby3(fkdf[fkdf$country == country,]))
X1
 [1] 1 0 0 1 0 0 1 0 1 0 1 0 1 0 0 1 0 1 0 1 0 0 1 0 0 0 1 0 1 0 1 0 0 0 1 0
0
[38] 1 0 1 0 1 0 0 1 0 0 0 0 0 1 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0 1 0 1 0 1 0 1
0
[75] 1 0 0 0 1 0 0 1 0 1 0 1 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 1 0 0 1 0 0 1 0 0

fkdf$X

 [1] 1 0 0 1 0 0 1 0 1 0 1 0 1 0 0 1 0 1 0 1 0 0 1 0 0 0 1 0 1 0 1 0 0 0 1 0
0
[38] 1 0 1 0 1 0 0 1 0 0 0 0 0 1 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0 1 0 1 0 1 0 1
0
[75] 1 0 0 0 1 0 0 1 0 1 0 1 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 1 0 0 1 0 0 1 0 0

Jim

On Mon, May 28, 2018 at 8:43 PM, Faradj Koliev <faradj.g at gmail.com> wrote:

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]]