Most discretization algorithms are univariate and consider only one attribute at a time. Stephen D. Bay presented a multivariate discretization(MVD) method that considers the affects of all the attributes in the procedure of data mining. But as the author mentioned, any test of differences has a limited amount of power. We present OMVD by improving MVD on the power of testing differences with a genetic algorithm.OMVD is more powerful than MVD because the former does not suffer from setting the difference threshold and from seriously depending on the basic intervals. In addition, the former simultaneously searches partitions for multiple attributes. Our experiments with some synthetic and real datasets suggest that OMVD could obtain more interesting discretizations than could MVD.

My dissertation is a collection of three essays that consider various aspects of income inequality and the demand for skill. The first chapter uses the advent of the US Interstate Highway System to examine the effect of reducing trade barriers on the relative demand for skilled labor. The Interstate Highway System was designed to connect major cities, to serve national defense, and to connect the US to Canada and Mexico. As an unintended consequence, many rural counties were connected to the highway system. I find that these counties experienced an increase in trade-related activities, such as trucking and retail sales. By increasing trade, the highways raised the relative demand for skilled manufacturing workers in skill-abundant counties and reduced it elsewhere, consistent with the predictions of the Heckscher-Ohlin model. The second chapter examines the effect of the division of labor on the demand for information processing. I find that manufacturing industries with a more complex division of labor employ relatively more clerks, who process information that is used to coordinate production. An early information technology (IT) revolution that took place around 1900 raised the relative demand for clerks in manufacturing, and significantly more so in industries with a complex division of labor.The increased demand for clerks likely contributed to the subsequent onset of the High School Movement. Interestingly, recent changes in IT have enabled firms to substitute computers for clerks, and I find evidence that this substitution occurred at a faster rate in more complex industries. The third chapter, coauthored with Liz Ananat, examines the effect of marital breakup on the economic outcomes of women with children. We find that having a female firstborn child increases the probability that a woman's first marriage ends in divorce. Using this exogenous variation we find that divorce has little effect on a woman's average household income, but it does increase the probability that her household ends up in the lowest income quartile. While women partially offset the loss of spousal earnings by receiving more child support and welfare, combining households, and increasing their labor supply, divorce still increases the odds of household poverty.

From 1940 to 1990, a 10% increase in a metropolitan area's concentration of college-educated residents was associated with a 0.8% increase in subsequent employment growth. Instrumental variables estimates support a causal relationship between college graduates and employment growth, but show no evidence of an effect of high school graduates. Using data on growth in wages, rents, and house values, I calibrate a neoclassical city growth model and find that roughly 60% of the employment growth effect of college graduates is due to enhanced productivity growth, the rest being caused by growth in the quality of life. This finding contrasts with the common argument that human capital generates employment growth in urban areas solely through changes in productivity.

The unprecedented integration of women into U.S. labor markets was one of the most significant economic and social changes of the Twentieth Century. Indeed, the transformation of legal and economic opportunities for women led The Economist to label the past one hundred years as the "female century" (9 September 1999). My dissertation stresses the larger story of women's recent economic advancement by emphasizing the significance of legal changes, federal policy and technological innovation in forestalling and spurring their progress in three different episodes during the Twentieth Century. Chapter II (with William J. Collins) focuses on the wage gains among African-American women during the 1940s. Using a semi-parametric decomposition, we find that demand shifts during the 1940s were critical to explaining African American women's move from domestic service into more lucrative employment in sectors covered by regulations and unions. Chapter III considers women's rapid economic advancement following the FDA's approval of the first oral contraceptive in 1960. Although a large body of theory and empirical evidence relates the end of the Baby Boom to changes in women's work, this work uses an historical experiment to quantify the importance of "the pill" in affecting broad labor market changes. My findings suggest that from 1970 to 1990, fertility-related shifts in women’s labor supply explain roughly 15 percent of the changes in market employment among younger women. Chapter IV examines the impact of changes in women’s labor supply on the aggregate wage structure from 1960 to 2000. Using legal variation in access to oral contraception as an instrumental variable, I find that increases women's labor supply during the 1980s raised wages among the most skilled men and depressed wage growth among women at the mean. This suggests that sharp declines in the gender gap during this decade would have been even more dramatic in the absence of large shifts in the supply of women’s labor.

Effective pruning is essential for efficient iceberg cube com-putation. Previous studies have focused on exclusive pruning: regionsof a search space that do not satisfy some condition are excluded fromcomputation. In this paper we propose inclusive and anti-pruning. Withinclusive pruning, necessary conditions that solutions must satisfy areidentified and regions that can not be reached by such conditions arepruned from computation. With anti-pruning, regions of solutions areidentified and pruning is not applied. We propose the multiway pruningstrategy combining exclusive, inclusive and anti-pruning with boundingaggregate functions in iceberg cube computation. Preliminary experi-ments demonstrate that the multiway-pruning strategy improves the ef-ficiency of iceberg cubing algorithms with only exclusive pruning.

This paper examines the effects of technology on information processing over more than a century, using industry-level variation in the demand for clerical office workers. Clerks are skilled workers who generate, store, and communicate information that is used by manufacturing firms to coordinate production. I find that production technology affects the demand for clerks. In particular, industries with a more complex division of labor employ relatively more clerks. I document this result using an early information technology (IT) revolution that took place around 1900, when telephones, typewriters, and improved filing techniques were introduced to the office. This IT revolution raised the demand for clerks in all manufacturing industries, but significantly more so in industries with a more complex division of labor. The increased demand for clerks raised the aggregate demand for skill, likely contributing to the onset of the High School Movement and to womens increased labor force participation. Interestingly, recent changes in IT have enabled firms to substitute computers for clerks, providing a concrete case in which technology and a specific set of skills are substitutes rather than complements.

This paper tests the intuition that households whose incomes covary relatively strongly with housing prices should own relatively little housing. Among US households, a one standard deviation in covariance between income and home prices is associated with a decrease of approximately $7500 in the value of owner occupied housing. This result arises in the presence of controls for the level and distribution of home prices. The generally positive correlations between income and home pricessuggests that households enter financial markets with a greater exposure to risk than is typically modeled.

In this paper we document a strong positive association between immigration and averagewages and price of houses of native individuals across U.S. states and metropolitan areas overthe period 1970-2005. Most of the existing literature, focussed on relative wage effects of immigration,missed these strong correlations. By constructing an instrumental variable that proxiesthe supply-driven component of immigration at the state level we show that the positive wageand housing price effects seem genuinely caused by immigration and not by unobserved demandshocks. Then, using parameters estimated on the aggregate U.S. economy and a simple model,we are able to simulate quantitatively most of the estimated effects of immigration on wagesand housing prices, for the average native. We also calculate the distributional effects on highly,medium and less educated natives and we find that all these groups in the average U.S. stateexperienced increases in their total real income (wage plus housing income) as a consequence ofthe 1990-2005 immigration. This is due to the combination of two facts: foreign-born workersdo not perfectly substitute natives in production and immigrants have lower house ownershiprates than natives, so that house price increases act as a transfer from immigrants to natives.

Of course, as even Perlmann concedes, today's twenty-first century economy requires education far beyond what was necessary for those 1940s Italians and Poles, and two low-wage incomes are better than one, so it is unlikely that second-generation Mexican men are opting out of education in favor of plentiful good-paying blue-collar jobs whilst Mexican women are opting out of the labor market all together.

Under the urging of late nineteenth-century humanitarian reformers, U.S. policy toward American Indians shifted from removal and relocation efforts to state-sponsored attempts to "civilize" Indians through allotment of tribal lands, citizenship, and forced education. There is little consensus, however, whether and to what extent federal assimilation efforts played a role in the stabilization and recovery of the American Indian population in the twentieth century. In this paper, we rely on a new IPUMS sample of the 1900 census of American Indians and census-based estimation methods to investigate the impact of federal assimilation policies on childhood mortality. We use children ever born and children surviving data included in the censuses to estimate childhood mortality and [responses to] several questions unique to the Indian enumeration [including tribal affiliation, degree of "white blood", type of dwelling, ability to speak English, and whether a citizen by allotment] to construct multivariate models of child mortality. The results suggest that mortality among American Indians in the late nineteenth century was very high - approximately 62% [standardize as % or percent throughout] higher than that for the white population. The impact of assimilation policies was mixed. Increased ability to speak English was associated with lower child mortality, while allotment of land in severalty was associated with higher mortality. The combined effect was a very modest four percent [as above] decline in mortality. As of 1900, the government campaign to assimilate Indians had yet to result in a significant decline in Indian mortality while incurring substantial economic and cultural costs.

In our research focusing on the 1980s and early 1990s (Hunt and Mueller, 2004), we found that US states have wider returns to skill than Canadian provinces. This favoured the migration of higher-skilled Canadians to the US. In this study, we extend our analysis to include average tax incidence for each income decile in each of the potential areas to which migration occurs as well as per capita expenditures on various public services. We use an expanded observational base of microdata from the US and Canadian censuses of 2000/2001. By being able to identify highly skilled individuals, through the use of our model, we perform simulations regarding the types of economic and non-economic variables that motivate individuals to migrate both within their home country and between countries, as well as the magnitude of these migrations. We find that individuals with lower skills, Canadian nativity (especially French speakers), and age are all negatively related to the propensity to migrate. Amongst those who do migrate, an area with higher mean returns to skill, higher employment growth rates, moderate climates, and geographical proximity to the migrant’s area of origin increase the probability of migration to these areas. The simulations suggest that increasing after-tax returns to skill and fiscal equalization (reducing both average taxes to their average US level as well as expenditures to maintain a balanced budget) would be the most effective policies in reducing southward migration, especially amongst the highly skilled.

This paper uses the 1918 influenza pandemic as a natural experiment for testing the fetal origins hypothesis. The pandemic arrived unexpectedly in the fall of 1918 and had largely subsided by January 1919, generating sharp predictions for long-term effects. Data from the 196080 decennial U.S. Census indicate that cohorts in utero during the pandemic displayed reduced educational attainment, increased rates of physical disability, lower income, lower socioeconomic status, and higher transfer payments compared with other birth cohorts. These results indicate that investments in fetal health can increase human capital.

This study investigates the intersection of suburban political economy and recent immigrant and ethnic minority suburbanization in the United States. It uses both quantitative and qualitative methods to address: what factors lead various minority groups to move to multi-ethnic areas called suburban melting pot metros (SMPMs); how these spatial location decisions vary by class or race-based preferences; and how suburban institutions respond to the issues raised by immigrant and ethnic minority groups. Using the 1990 and 2000 Census Public Use Micro-data Series (PUMS), I test some key theories of residential migration, including spatial assimilation, place stratification, and economic sorting. In a multivariate logit regression analysis, between non-Hispanic whites, blacks, Asians, and Latinos, residing in 29 US suburban areas, I find that SMPMs attract groups with lower levels of educational attainment. Moreover, rising income increases the likelihood that blacks and Latinos seek multi-ethnic suburban residence. While racial change had little impact on SMPM settlement, post-1980s immigration and linguistic isolation were significant predictors of SMPM settlement. Rises in housing values are likely to increase SMPM settlement for whites and Asians, but property tax increases are not a significant predictor of SMPM settlement for any of the groups. These Census results are supplemented by a case study of suburban Washington, DC. Data from five focus group discussions between black, Chinese, Iranian, Korean and Latino groups reveal that quality schools, safe neighborhoods, employment and housing opportunities, and pre-established family ties commonly attracted these individuals to certain suburban DC jurisdictions. Spatial location decisions, particularly for blacks, are limited by income. Perceptions of a countys ability to deliver local goods and services or the race/ethnicity of current county residents also influenced location decisions. Finally, using qualitative data from a collection of 114 in-depth interviews with elite officials in suburban Washington, DC, I develop a concept called Suburban Institutional Interdependency (SII) to examine how local institutions respond to the issues raised by immigrant groups. The central tenets of this approach suggest that through repeated interactions, generalized reciprocity, and an exchange of selective incentives, suburban institutions may collaborate to meet the needs and demands of suburban newcomers.

Since the mid-twentieth-century America has experienced two great social movements: the civil rights movement and the women's movement. Although neither reached all its goals, each achieved major successes. Yet, in the years of their greatest accomplishments, Americans became massively more unequal. How and why did this happen? One Nation Divisible clarifies why America remains one nation divisible, what those divisions are, and the powerful role of government in both mitigating and exacerbating them.Through four themes - the paradoxical history of inequality, the multiple forms of diversity, the powerful influence of government, and the need to reformulate the ideas that guide thinking about great public issues - One Nation Divisible traces the impact of economic globalization at both ends of the century. It shows that today the nation is undergoing economic and social transformations as profound as the ones driven by the industrial revolution of past centuries. This book is the story of their consequences.

Relative to the for-profit sector, women and minorities have been fairly successful in achieving executive and managerial positions in government. Although historically overlooked in employment analyses, the nonprofit sector also tends to employ larger numbers of women and minorities in high-ranking capacities. In fact, the majority of all managers in the nonprofit sector are female. What are the implications of these employment trends for the earning prospects of women and minorities? We use 2000 census data to compare differences in the incomes of female and minority managers by sector in six different occupational categories. We find that women managers are statistically significantly more likely to earn higher incomes in the nonprofit sector than in local government for each of the six occupations we examined. However, minority managers are likely to fare better in terms of income when they are employed by local government organizations. Although this analysis carries some limitations, it represents an important first step toward understanding the economic opportunity structure available to women and minorities within the two public-serving sectors.

We use heterogeneity in the timing of television's introduction to different local markets to identify the effect of preschool television exposure on standardized test scores later in life. Our preferred point estimate indicates that an additional year of preschool television exposure raises average test scores by about .02 standard deviations. We are able to reject negative effects larger than about .03 standard deviations per year of television exposure. For reading and general knowledge scores, the positive effects we find are marginally statistically significant, and these effects are largest for children from households where English is not the primary language, for children whose mothers have less than a high school education, and for non-white children. To capture more general effects on human capital, we also study the effect of childhood television exposure on school completion and subsequent labor market earnings, and again find no evidence of a negative effect.

This chapter provides a brief overview of the way in which social networks are conceptualized, highlighting how that literature tends to frame networks in static and a contextual terms. We then describe the social networks of persons who were born in Mexico and migrated to the United States. We discuss the dynamic context of social networks that Latino elder migrations are embedded in to highlight the lifecourse aspects of the elders' networks. We also examine the structural influences on their networks to show how contextual factors beyond culture may influence the ways in which networks develop over time, even in a population where family norms and values are often viewed as the primary determinants of social networks. The chapter concludes with a discussion of the implications for the public policy and practice.

In few other realms of historical scholarship have the last three decades witnessed such all-encompassing transformations as in African-American history. The Civil Rights Movement changed the way scholars have written about slavery, but the broad wake created by that revolution in the history of the "peculiar institution" has struck every other facet of African-American history as well. During the 1970s, even as scholars penned now-classic works on the plantation South in the antebellum era, the margins of the institution fell open to detailed investigation. In no instance was this more the case than with the free African Americans who lived in the states outside of the slave South. Since the late 1960s and early 1970s, dozens upon dozens of books and hundreds of journal articles have appeared that seek to understand the significance of those who lived, as Leon Litwack put it, "North of slavery."