Its large
number of observations (32,800 in 2008 and 55,400 in 2010) provide
sufficient samples
of the non-immigrant sub-population, with 339 non-citizen respondents in 2008 and 489 in 2010.
With regard to the sample size required for valid application
of this modeling approach, we are hesitant to speak
of sufficient sample sizes, since a large
number of observations with little score variation over time (as in our second empirical application) does not necessarily provide richer information than a smaller sample with more fluctuations.