Hierarchical Multiple Regression in Counseling Research: Common Problems and Possible Remedies

Petrocelli, John V.

doi:10.1080/07481756.2003.12069076

Cited by 286 publications

(208 citation statements)

References 27 publications

Supporting

Mentioning

206

Contrasting

Unclassified

Order By: Relevance

“…This allowed the researcher to determine the independent effect of the environmental variables on retention rates. Hierarchical regression allows for the researcher to gauge the additional importance of subsequent blocks of variables as they are entered into the analysis, after controlling for the set of variables entered in the previous blocks (Pallant, 2007;Petrocelli, 2003).…”

Section: Resultsmentioning

confidence: 99%

“…While the overarching purpose of this study was not to estimate retention rates based on student and institutional characteristics, but to determine the relative impact of institutional characteristics on student retention, the standardized coefficients for each variable have been presented, as they do inform the reader about the direction and relative importance or effect of each variable within each model. Based on the advice of Petrocelli (2003), each variable coefficient was discussed only for the first step in which it was entered. This provided the information necessary to judge the variable's impact after controlling for the variables entered in the previous steps.…”

Section: Resultsmentioning

confidence: 99%

“…This table includes a summary of the information necessary to gauge the impact of each independent variable on student retention rates upon initial entry, as well as the additional effect of each block of variables entered into the analysis. Once again, as Petrocelli (2003) advised, variable coefficients were discussed only upon initial entry into the analysis.…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Institutional Characteristics and Student Retention in Public 4-Year Colleges and Universities

Marsh

2014

Journal of College Student Retention: Research, Theory & Pr

View full text Add to dashboard Cite

The purpose of this study was to determine the relative importance of specific student and institutional factors and characteristics on the retention of students at public, 4-year colleges and universities in the United States based on aggregate student cohort and institutional data. The overriding goal of this research was to identify any institutional characteristics that may improve student retention rates, which would provide administrators with valuable information for planning purposes. Hierarchical multiple regression was utilized to measure the relative effect of each of five blocks of independent variables on institutional student retention rates. Results of the study indicated that while entering student characteristics were most successful in explaining variances in retention rates among institutions, the various institutional characteristic blocks also had significant effects on student retention rates, to varying degrees. Results from this study may be instructive for college and university administrators in the institutional decisionmaking process.While colleges and universities in the United States have experienced increasing enrollments, levels of student attrition remain high at many institutions (Braunstein, Lesser, & Pescatrice, 2006). Student departure from institutions of higher education prior to graduation has been a central topic of discussion and concern for college and university administrators and researchers, particularly

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Institutional Characteristics and Student Retention in Public 4-Year Colleges and Universities

Marsh

2014

Journal of College Student Retention: Research, Theory & Pr

View full text Add to dashboard Cite

show abstract

“…All variables were entered into the regression model in a specified order so that each predictor contributed to the explanatory variance of the dependent variable (i.e., alcohol use severity) after controlling for the variance explained by the previous variables (Petrocelli, 2003). Predictor variables were grouped into three broad domains and entered in the following order: (1) age, gender, academic level, marital status, parents’ education level, perception of parents’ alcohol consumption, and symptoms of depression; (2) behavioral acculturation and enculturation; and (3) cultural congruity.…”

Section: Methodsmentioning

confidence: 99%

Alcohol Use Severity Among Hispanic Emerging Adults in Higher Education: Understanding the Effect of Cultural Congruity

Cano

Vaughan

Dios

et al. 2015

Substance Use & Misuse

View full text Add to dashboard Cite

Background Identifying and understanding determinants of alcohol use behavior among Hispanic college students is an increasingly important public health issue, particularly during emerging adulthood. Studies examining ethnocultural determinants of alcohol use behavior among Hispanic college students have focused on direct associations with cultural orientation (e.g., acculturation and enculturation); yet there is a need for research that accounts for the complex interplay of other culturally relevant sociocultural factors. Objectives This study examined associations of behavioral acculturation, behavioral enculturation, and cultural congruity (perception of cultural fit between the values of the academic environment and the student's personal values) with alcohol use severity (AUS); and tested if gender moderated those associations. Methods A hierarchical linear regression and moderation analysis were conducted on a sample of 167 Hispanic emerging adults (ages 18 to 25) enrolled in college. Results All predictor variables entered in the regression model accounted for 20.9% of the variance in AUS. After controlling for demographic variables and depressive symptoms, behavioral acculturation and enculturation did not have a statistically significant association with AUS. Further, gender did not moderate either of these associations. Conversely, greater cultural congruity was associated with lower reports of AUS. A moderation analysis suggested that cultural congruity predicted lower reports of AUS among men, but not among women. Conclusions This was the first known study to examine the association of cultural congruity with alcohol use. Findings highlight the value of examining contextual factors of culture and moving beyond reductive measures of cultural orientation.

show abstract

“…Based on results of our between-group comparisons, we selected sexual identity and educational level as control variables entered in the first step of the model. Given that CSA logically precedes other risk factors during men’s lifetimes (logic of causal priority; Petrocelli, 2003), we chose to enter CSA severity prior to IH and numbers of male sexual partners. Finally, given prior literature suggesting that problematic alcohol use may be a primary risk factor for ASA and a potential consequence of CSA and IH, we entered history of past alcohol problems as the final step in our regression analysis.…”

Section: Methodsmentioning

confidence: 99%

Sexual Assault Risks Among Gay and Bisexual Men

Hequembourg¹,

Parks²,

Hughes

2014

The Journal of Sex Research

View full text Add to dashboard Cite

The goal of this study was to examine lifetime patterns of sexual assault and associated risks among a purposive sample of gay and bisexual men (N = 183; 18–35 years old, M = 24.3). Cross-sectional data were collected via written, self-administered questionnaires and face-to-face, event-based qualitative interviews. Alcohol severity scores indicated high rates of hazardous drinking (53.0%) and possible dependence (14.2%) among participants. One half of men (50.8%) reported childhood sexual abuse (CSA) and 67.2% reported adult sexual assault (ASA). Average age at most recent ASA was 21 years. Most perpetrators of recent ASA incidents (83.9%) were male; 67.0% of participants reported consuming alcohol and/or drugs prior to the most recent incident. Regression findings indicated more severe CSA experiences and past alcohol-related problems predicted recent severe ASA. Although we found similarities between gay and bisexual men in lifetime sexual assault history, we found some distinct differences in ASA risk factors. Bisexual men reported higher alcohol severity scores, more female ASA perpetrators, higher internalized homophobia scores, and fewer male sexual partners than gay men. Findings suggest the need for interventions that reduce ASA risk among sexual minority men—and the potential benefits of focusing on alcohol consumption in risk reduction efforts.

show abstract

Hierarchical Multiple Regression in Counseling Research: Common Problems and Possible Remedies

Cited by 286 publications

References 27 publications

Institutional Characteristics and Student Retention in Public 4-Year Colleges and Universities

Institutional Characteristics and Student Retention in Public 4-Year Colleges and Universities

Alcohol Use Severity Among Hispanic Emerging Adults in Higher Education: Understanding the Effect of Cultural Congruity

Sexual Assault Risks Among Gay and Bisexual Men

Contact Info

Product

Resources

About