An Introduction to Sample Selection Bias in Sociological Data

Berk, Richard A.

doi:10.2307/2095230

Cited by 1,102 publications

(613 citation statements)

References 14 publications

Supporting

Mentioning

595

Contrasting

Unclassified

Order By: Relevance

“…Most importantly, the sample for this study was initially restricted to youth with grade point averages of 3.0 or below in eighth grade due to the focus of the larger study on youth at risk for school dropout and substance use. Truncating the sample in this way can threaten the internal and external validity of survey data (Berk, 1983). Several factors, however, may mitigate the problems associated with this sampling approach.…”

Section: Discussionmentioning

confidence: 99%

Racial Discrimination and Racial Identity as Risk or Protective Factors for Violent Behaviors in African American Young Adults

Caldwell

Kohn-Wood

Schmeelk-Cone

et al. 2004

American J of Comm Psychol

270

223

View full text Add to dashboard Cite

This study examined the influences of racial discrimination and different racial identity attitudes on engaging in violent behavior among 325 African American young adults. The contributions of racial discrimination and racial identity attitudes in explaining violent behavior during the transition into young adulthood while controlling for the influences of prior risk behaviors at ninth grade were examined separately for males and females. In addition, the buffering effects of racial identity attitudes on the relationship between racial discrimination and violent behavior were tested. Results indicated that experience with racial discrimination was a strong predictor of violent behavior, regardless of gender. The centrality of race for males and the meaning others attribute to being Black for both males and females were moderators of the influence of racial discrimination on violent behavior. KEY WORDS:African American adolescents; racial discrimination; gender differences; protective factors; racial identity; violence.Most studies find that about 30-40% of male and 15-30% of female youths report having committed violent acts by age 17 (USDHHS, 2001). Extensive evidence has accumulated on the effects of specific psychosocial and environmental risk factors for the perpetration of violent behaviors. Youth violence in the United States has been associated consistently with aggressiveness, antisocial behavior, and poverty during childhood, substance use, antisocial peer groups, parent disciplinary practices, parents with favorable attitudes toward violence, family functioning, academic failure, and being male (Blaske, Borduin, Henggeler, & Mann, 1989;Farrington & Loeber, 2000;Florsheim, Tolan, & Gorman-Smith, 1996;Gorman-Smith, Tolan, Zelli, & Huesmann, 1996;Gorman-Smith, Tolan, Loeber, & Henry, 1998;Guerra, Husemann, Tolan, Van Acker, & Eron, 1995; Hawkins et al., 2000;Henggeler, 1989; Henry, Tolan, & Gorman-Smith, 2001;Kosterman et al., 2001;Loeber & Stouthamer-Loeber, 1998; Tolan & Lorion, 1988;USDHHS, 2001). Yet, the majority of youth at risk for committing violent acts do not engage in violent behaviors (Zimmerman, Steinman, & Rowe, 1998).The Surgeon General's (USDHHS, 2001) recent report on youth violence concludes that risk factors do not operate in isolation and that they can be buffered by protective factors. Several individual characteristics (e.g., self-concept, intolerant attitude toward deviance, commitment to school) and environmental conditions (e.g., supportive family and school environments, resource rich neighborhoods) have been proposed to be protective against youth violence (Hawkins et al., 1998;Kosterman et al., 2001; Caldwell, Kohn-Wood, Schmeelk-Cone, Chavous, and Zimmerman Paschall & Hubbard, 1998;Resnick et al., 1997). This suggests the importance of an ecological framework in explaining these behaviors. The ecological model posits that youth violence is a function of individual psychosocial characteristics, social influences, and societal constraints (Guerra et al. 1995;Paschall & Hubb...

show abstract

Section: Discussionmentioning

confidence: 99%

Racial Discrimination and Racial Identity as Risk or Protective Factors for Violent Behaviors in African American Young Adults

Caldwell

Kohn-Wood

Schmeelk-Cone

et al. 2004

American J of Comm Psychol

270

223

View full text Add to dashboard Cite

show abstract

“…This is in contrast to the theory of probability sampling where each individual must have an equal chance of being included in the survey for the sample to generate unbiased results (Kish, 1965;Bethlehem, 2010;Sanchez-Fernandez et al, 2012). Self-selection into a survey implies that the principles of probability sampling are not followed (Berk, 1983;Lee and Marsh, 2000;Bethlehem, 2010). When this situation arises it is referred to as sample selection bias (Rubin, 1976;Berk, 1983).…”

Section: A C C E P T E D Accepted Manuscriptmentioning

confidence: 99%

“…Self-selection into a survey implies that the principles of probability sampling are not followed (Berk, 1983;Lee and Marsh, 2000;Bethlehem, 2010). When this situation arises it is referred to as sample selection bias (Rubin, 1976;Berk, 1983). Selection bias occurs because non-participation is rarely random (e.g., distributed equally across subgroups); instead, bias often is correlated with variables that also are related to the dependent variable of interest (Goodfellow et al, 1988;Winship and Mare, 1992).…”

Section: A C C E P T E D Accepted Manuscriptmentioning

confidence: 99%

“…Selection bias occurs because non-participation is rarely random (e.g., distributed equally across subgroups); instead, bias often is correlated with variables that also are related to the dependent variable of interest (Goodfellow et al, 1988;Winship and Mare, 1992). Sample selection bias is a threat to both the internal and external validity of the model (Berk, 1983;Lee and Marsh, 2000;Cuddleback et al, 2004) whereby independent variables are correlated with a disturbance term (i.e., error) and analyses based on biased samples can lead to inaccurate estimates of the relationships between variables (e.g., regression coefficients).…”

Section: A C C E P T E D Accepted Manuscriptmentioning

confidence: 99%

“…In the decades since, as noted by Cuddleback and colleagues (2004), an extensive literature has evolved in the area of sample selection bias (Berk, 1983;Stolzenberg & Relles, 1997). These methods are known as sample selection models and although developed over forty years ago, they are designed to overcome the same issues associated with Internet based surveys in the New Millennium.…”

Section: A C C E P T E D Accepted Manuscriptmentioning

confidence: 99%

See 2 more Smart Citations