Dear Statalist,

I am struggling with this problem which is very difficult to explain. I am trying my best to describe it here and really appreciate if anyone can help me.

My dataset based on a survey of the employment status of parents. It has 3 variables: id, year_of_survey, employment_status ( the variable "employment_status" is a dummy with two categories: 1= employed and 0= unemployed).
I want to create another dummy variable called: "unemployment_experience" to define which mother/father has been through unemployment at the time she/he was interviewed (a mother/father once was unemployed will be considered to have experience in unemployment from then on even if he is employed after that). It should take value 1 if from the time interviewing backward, employment_status=0 at least once) and 0 otherwise. (1 = have experience in unemployment , 0 = no experience in unemployment)

For example, I want to generate this following dataset:
id year_of_survey employment_status unemployment_experience
1 2000 1 0
1 2001 1 0
1 2002 0 1
1 2003 1 1
2 2000 1 0
2 2001 1 0
2 2002 1 0
2 2003 0 1
3 2000 0 1
3 2001 1 1
3 2002 1 1
3 2003 1 1
3 2004 1 1
3 2005 1 1
Thank you so much for your time.

Best regards,
Cameron.