Search

The interdisciplinary field of knowledge discovery and data mining emerged from a necessity of big data requiring new analytical methods beyond the traditional statistical approaches to discover new knowledge from the data mine. This emergent approach is a dialectic research process that is both deductive and inductive. The data mining approach automatically or semi-automatically considers a larger number of joint, interactive, and independent predictors to address causal heterogeneity and improve prediction. Instead of challenging the conventional model-building approach, it plays an important complementary role in improving model goodness of fit, revealing valid and significant hidden patterns in data, identifying nonlinear and non-additive effects, providing insights into data developments, methods, and theory, and enriching scientific discovery. Machine learning builds models and algorithms by learning and improving from data when the explicit model structure is unclear and algorithms with good performance are difficult to attain. The most recent development is to incorporate this new paradigm of predictive modeling with the classical approach of parameter estimation regressions to produce improved models that combine explanation and prediction.

This paper analyzes the intersection of individual lives and historical context by examining how cohort membership, historical conditions, and individual maturation influence subjective well-being in urban China. We use cross-classified multilevel models and repeated measures of happiness from seven waves of the Chinese General Social Survey (CGSS 2003–2013, N = 43,308). The results indicate that individuals born between 1956 and 1961 experienced setbacks at various pivotal moments throughout their life, including education, employment, economic stability, and social connections, and this cohort reports a lower overall sense of happiness when compared to other cohorts. The effect of aging on happiness comprises a U-shaped pattern; the middle-aged are the least happy. We observe an upward trend in happiness from 2003 to 2013. These results are confirmed by using subjective socioeconomic status (SES) as an alternative measure of well-being from CGSS 2003 and CGSS 2005 (N = 11,992). This paper contributes to studies of market transition by identifying the birth cohort as an important mechanism of inequality. It also augments the life-course paradigm by highlighting the significance of timing when individual lives intersect with historical context.

Studies have shown that happiness level varies significantly across birth cohorts and baby boomers are the unhappiest of all birth cohorts. Yet, we don’t know if this is due to their large cohort size negatively affecting happiness. We question whether people born in high fertility times are unhappy because they suffer more from economic setbacks and/or social strains. Using 9 waves of data from the European Social Survey United Kingdom Subset 2002–2018 (N = 19,364) and hierarchical age-period-cohort cross-classified models, we analyze the effects of cohort size, socioeconomic status, marital status, and sociality on happiness. Cohort size, marital status, and sociality are the top three factors of cohort difference in happiness, but socioeconomic status is not. Cohort size is negatively associated with happiness. Income, education, or employment are not the source of unhappiness among the Boomers. Besides being members of a large cohort, the Boomers have two known factors against their odds: they are the most likely to separate and divorce and the least likely to socialize with friends despite having a large number of peers. Social disintegration and deprivation, not economic impoverishment, appears to be the culprit of unhappiness of the UK Baby Boomers.

Scholars have posed different hypotheses on the impact of global telecommunications on value orientations. We analyze and characterize the global telecommunication network and test a series of hypotheses on the relationship between gender values and three types of telephone connections: ties with the global society, ties with Western nations, and ties within groups of nations sharing similar cultural, religious, political, or geographical traits. We use multilevel models and data on two levels, between-country telecommunications network data from TeleGeography, and individual-level data (N = 70,225) on people living in 47 countries from the World Value Survey, waves III and IV. Countries with high degrees of communication insulation, measured as a high percentage of within-group ties of all global telephone links, hold less egalitarian attitudes toward gender equality. This negative effect of group insulation depresses the egalitarian effects of younger birth cohort, college education, and higher income. Embeddedness in a localized information diffusion network and isolated from global communication is associated with less egalitarian attitude toward gender equality. But neither global ties nor ties with Western countries are linked with gender attitudes.

These figures display gender-and education-related gaps in U.S. gender attitudes from 1977 to 2018. The authors use data from the General Social Survey (N = 57,224) to estimate the historical trajectory of U.S. attitudes about women in politics, familial roles, and working motherhood. Of all attitudes analyzed, Americans hold the most liberal attitudes toward women in politics, with no gender gap and little educational difference on this issue. Attitudes toward familial roles have the largest educational gap but a small gender difference. The gender gap in attitudes toward working motherhood has persisted over time, with women holding more egalitarian attitudes than men. The educational disparity on this issue disappeared during the mid-1990s “stalled gender revolution” but has widened since. Although the “stall” occurred among all gender and educational groups on all four gender attitude measures, the decline was starkest among the college educated regarding working motherhood.

We examine the pathways by which parents influence adolescents’ close friendships, focusing on three types of behavioral styles: hostile, warm, and problem solving. Structural equation models are estimated using data at two time points from the Iowa Youth and Families Project (N = 227 friendship pairs). Results suggest that the lives of adolescents and both their mother and father are inexorably linked. Observed interactions with a close friend at Time 2 reveal teens recreate their parents’ original hostile, supportive, and problem-solving styles from Time 1. This outcome depends on (a) type of behavior and (b) gender. Mothers’ supportive behavior, fathers’ problem solving, and both parents’ hostile behavior significantly influence adolescents’ comparable interaction styles. Adolescents’ subsequent behavior toward their friend significantly affects friendship quality. Lower levels of hostile behavior in female youth, increased problem solving by males, and supportive actions toward a friend for both relate positively to rewarding friendships.

It remains unclear to what extent shifts in gender attitudes are products of changes in micro-level characteristics, macro-level social transformations, or net cohort and period transitions. We test these questions on 20 waves of data from the General Social Survey, 1977-2016 (N = 45,125). Compositional change in individual characteristics accounts for almost 78 percent of the cohort variation in gender attitudes, but only 32 percent of the historical transformations. Macro dynamics are responsible for an additional 60 percent of the historical change in gender attitudes. Two structural forces are associated with historical transitions in American gender attitudes: gender equality in the labor force and the rise of men's overwork. Each of these factors accounts for a significant proportion of the period variation in gender attitudes in our analysis, and the rise of men's overwork appears to account for the puzzle of the "stalled revolution" in the 1990s and its "restart" in the mid-2000s. The conservative swing in 1994-2004 correlates with the rise of overwork, as the proportion of men who overwork soared during this period when traditional gender roles were reinforced.