Attitudes Toward Immigration in Europe 407 Germany,Italy,Luxembourg,Switzerland,Greece,Spain,Portugal,Israel,Czech Republic,Hungary,Poland,and Slovenia.It consists of answers of up to 42,000 respondents to an hour-long questionnaire,with an average country sample of about 2,000 respondents.The broad coverage provides substantial cross-national varia- tion in social,political,and economic contexts.The stratified random sample was designed to be representative of the residential population of each nation,aged sixteen years and above,regardless of their nationality,citizenship,or legal status.33 The questionnaire consists of a "core"module that contains a large range of socioeconomic and demographic questions and several rotating,topic-specific mod- ules,one of which focuses on the issue of immigration.Our primary empirical tests involve individual responses to a set of questions taking the following form: To what extent do you think [respondent's country]should allow people from source]to come and live here? Allow many to come and live here ·Allow some ·Allow a few ·Allow none ·Don't know There are four different versions of this question in which the source of the immigrants is identified alternatively as: The richer countries in Europe The poorer countries in Europe The richer countries outside Europe The poorer countries outside Europe For each of the questions we created a dichotomous variable that equals 1 (pro-immigration)if the answer was“allow many'”or“allow some”and0(anti- immigration)if the answer was "allow a few"or"allow none."34 The dichoto- mous dependent variables just allow a simpler and more intuitive summary of the basic results than alternative treatments using the "raw"categorical variables and estimating ordered probit models (which would require reporting the marginal effects that each independent variable has on the probability of a response falling into each possible category).In the section below on robustness tests,we describe the sensitivity analysis we have performed using ordered probit models and also rerunning all the analysis reported below using all alternative cutoff points for 33.The majority (55 percent)of the questionnaires were administered in face-to-face interviews. For a full discussion of the EES methodology,see Stoop,Jowell,and Mohler 2002. 34.We excluded the few "don't know"and missing answers from the sample.Including these obser- vations as either pro-or anti-immigration answers does not change any of the substantive results we report since only 4 to 5 percent of the answers to each question fall in this category.Germany, Italy, Luxembourg, Switzerland, Greece, Spain, Portugal, Israel, Czech Republic, Hungary, Poland, and Slovenia+ It consists of answers of up to 42,000 respondents to an hour-long questionnaire, with an average country sample of about 2,000 respondents+ The broad coverage provides substantial cross-national varia￾tion in social, political, and economic contexts+ The stratified random sample was designed to be representative of the residential population of each nation, aged sixteen years and above, regardless of their nationality, citizenship, or legal status+ 33 The questionnaire consists of a “core” module that contains a large range of socioeconomic and demographic questions and several rotating, topic-specific mod￾ules, one of which focuses on the issue of immigration+ Our primary empirical tests involve individual responses to a set of questions taking the following form: To what extent do you think @respondent’s country# should allow people from @source# to come and live here? • Allow many to come and live here • Allow some • Allow a few • Allow none • Don’t know There are four different versions of this question in which the source of the immigrants is identified alternatively as: • The richer countries in Europe • The poorer countries in Europe • The richer countries outside Europe • The poorer countries outside Europe For each of the questions we created a dichotomous variable that equals 1 ~pro-immigration! if the answer was “allow many” or “allow some” and 0 ~anti￾immigration! if the answer was “allow a few” or “allow none+” 34 The dichoto￾mous dependent variables just allow a simpler and more intuitive summary of the basic results than alternative treatments using the “raw” categorical variables and estimating ordered probit models ~which would require reporting the marginal effects that each independent variable has on the probability of a response falling into each possible category!+ In the section below on robustness tests, we describe the sensitivity analysis we have performed using ordered probit models and also rerunning all the analysis reported below using all alternative cutoff points for 33+ The majority ~55 percent! of the questionnaires were administered in face-to-face interviews+ For a full discussion of the EES methodology, see Stoop, Jowell, and Mohler 2002+ 34+ We excluded the few “don’t know” and missing answers from the sample+ Including these obser￾vations as either pro- or anti-immigration answers does not change any of the substantive results we report since only 4 to 5 percent of the answers to each question fall in this category+ Attitudes Toward Immigration in Europe 407