#delimit; /*Variable definitions: *************************************************************** DEPENDENT VARIABLES aff6: Education Quotas: Do you favor/oppose education quotas strongly or not strongly? Coded: 1=Oppose Strongly; 2=Oppose Not Strongly; 3=Favor Not Strongly; 4=Favor Strongly aff2: Preferential Hiring: Do you favor/oppose preference in hiring and promotion strongly or not strongly? Coded: 1=Oppose Strongly; 2=Oppose Not Strongly; 3=Favor Not Strongly; 4=Favor Strongly welfare1: Welfare Should federal spending on welfare programs be increased, decrease, or kept about the same? Coded: -1=Decreased; 0=Kept about the Same; 1=Increased aidblak: Government assistance for blacks. Some people feel that the government in Washington should make every effort to improve the social and economic position of blacks. Others feel that the government should not make any special effort to help blacks because they should help themselves. Where would you place yourself on this scale? (7 point scale with anchors) Coded: 1=``Blacks should help themselves''; 7=``Government should help blacks.'' biling: Bilingual Education Which one of the following three statements best describes how you feel? 1="All classes should be conducted only in English so that children have to learn English right from the start." 2="Children who don't know English should have classes in their native language just for a year or two until they learn English." 3="There should be one set of classes in English and another set in Spanish or other languages all the way through high school so that children can keep their native languages and culture if they choose." ******************************************************************** INDEPENDENT VARIABLES ageyear: Age of repondent, in years. ageyear2: Age of respondent, squared (for quadratic terms in some models below) sex: 1=Female; 0=Male. lt15K: 1 if Income of respondent reported as being less than 15K; 0 else. gt75K: 1 if Income of respondent reported as being greater than 75K; 0 else. Ihigh: 1=Respondent's level of education is less than high school diploma; 0 else. Icoll: 1=Repondent's level of education is college degree or greater; 0 else. liberal: 1=Moderately or strongly liberal on NES ideology question. 0 else; conserve: 1=Moderately or strongly conservative on NES ideology question. 0 else; prejud: NES racial resentment scale: The scale is comprised of four survey items. The responses for each question are: agree strongly, agree somewhat, neither agree nor disagree, disagree somewhat, disagree strongly. The responses for each question were summed to create the racial resentment scale. Below are the four items. 1. Over the past few years, blacks have gotten less than they deserve. 2. Irish, Italian, Jewish, and many other minorities overcame prejudice and worked their way up. Blacks should do the same without any special favors. 3. It's really a matter of some people not trying hard enough; if blacks would only try harder they could be just as well off as whites. 4. Generations of slavery and discrimination have created conditions that make it difficult for blacks to work their way out of the lower class. egal: NES egalitarianism scale: The scale is comprised of the six survey items. The responses for each question are: agree strongly, agree somewhat, neither agree nor disagree, disagree somewhat, to disagree strongly. The responses for each question were summed to create the egalitarianism scale. 1. Our society should do whatever is necessary to make sure that everyone has an equal opportunity to succeed. 2. We have gone too far in pushing equal rights in this country. 3. This country would be better off if we worried less about how equal people are. 4. It is not really that big a problem if some people have more of a chance in life than others. 5. If people were treated more equally in this country we would have many fewer problems.\\ 6. One of the big problems in this country is that we don't give everyone an equal chance. south: 1=respondent is from Southern state; 0=else. In this data set, these are: Alabama, Florida, Georgia, Louisiana, Mississippi, North Carolina, South Carolina, Tennessee, Texas, Virginia. ccoll: From 1990 Census. Percent of individuals aged 25 and older having college degree. cofrac: Fractionalization index based on census data for percent White, Black, Hispanic, and Indian. Coded as: cofrac=C-((whitea/100)^2+(blacka/100)^2 + (asiana/100)^2 + (indiana/100)^2 + (hispa/100)^2) where C=(whitea/100)+(blacka/100) + (asiana/100) + (indiana/100) + (hispa/100) collfrac=ccoll x cofrac curb: From 1990 Census. Proportion of county that resides in census demarcated urban area: N in urban/total pop N pancros=survey weight (post-stratification) white2=1 if respondent is white, non-Hispanic (self-report); 0 else. */ *Use with dataset: AJPS2005repdata.dta * When we originally estimated these models (c. 2000/2001), the only available * option (short of programming it ourselves) was Kang Fu's (1998) "gologit" module. To * exactly replicate these models, download Kang Fu's ado module. There are better nonPH * options available now. Back then, there were not. /*This code fragment will reproduce the model for "Education Quotas" from Table 1, p. 364, of Branton and Jones, 2005. Note that the ado "gologit" is used to derived the estimates.*/ gologit aff6 ageyear sex lt15K gt75K Ihigh Icoll liberal conserve prejud egal south ccoll cofrac collfrac curb if white2==1 [pweight=pancros]; /*This code fragment will reproduce the model for "Preferential Hiring" from Table 1, p. 364, of Branton and Jones, 2005. Note that the ado "gologit" is used to derived the estimates.*/ gologit aff2 ageyear sex lt15K gt75K Ihigh Icoll liberal conserve prejud egal south ccoll cofrac collfrac curb if white2==1 [pweight=pancros]; /*This code fragment will reproduce the model for "Welfare" from Table 1, p. 364, of Branton and Jones, 2005. Note that the ado "gologit" is used to derived the estimates.*/ gologit welfare1 ageyear sex lt15K gt75K Ihigh Icoll liberal conserve prejud egal south ccoll cofrac collfrac curb if white2==1 [pweight=pancros]; /*This code fragment will reproduce the model for "Govt. Aid to Blacks" from Table 1, p. 365, of Branton and Jones, 2005. Note that the ado "gologit" is used to derived the estimates.*/ gologit aidblak ageyear ageyear2 sex lt15K gt75K Ihigh Icoll liberal conserve prejud egal south ccoll cofrac collfrac curb if white2==1 [pweight=pancros]; /*This code fragment will closely reproduce the model for "Bilingual Education" from Table 1, p. 365, of Branton and Jones, 2005. The estimates from this fragment slightly deviate from those reported in the AJPS paper. In no instance do the differences lead to different conclusions. I will determine source of difference. */ svymlogit biling ageyear sex lt15K gt75K Ihigh Icoll liberal conserve prejud egal south ccoll cofrac collfrac curb if white2==1, base(1);