1986
DOI: 10.2307/270922
|View full text |Cite
|
Sign up to set email alerts
|

Some New Results on Indirect Effects and Their Standard Errors in Covariance Structure Models

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

8
609
0
22

Year Published

1989
1989
2020
2020

Publication Types

Select...
6
3

Relationship

0
9

Authors

Journals

citations
Cited by 821 publications
(639 citation statements)
references
References 13 publications
8
609
0
22
Order By: Relevance
“…The "other" religious affiliation included Christianity, Judaism, Jainism, Zoroastrianism, and Buddhism. We conducted mediation analysis using the Sobel-Goodman (Sobel, 1986; UCLA: Statistical Consulting Group) and Karlson/Holm/Breen (Karlson and Holm, 2011) tests to determine if smoking status, health status, or educational attainment mediated the relationship between religiosity and BMI.…”
Section: Discussionmentioning
confidence: 99%
“…The "other" religious affiliation included Christianity, Judaism, Jainism, Zoroastrianism, and Buddhism. We conducted mediation analysis using the Sobel-Goodman (Sobel, 1986; UCLA: Statistical Consulting Group) and Karlson/Holm/Breen (Karlson and Holm, 2011) tests to determine if smoking status, health status, or educational attainment mediated the relationship between religiosity and BMI.…”
Section: Discussionmentioning
confidence: 99%
“…Note that because the bootstrap approach did not assume a particular sampling distribution for the indirect effect, there was no conventional distribution-based test statistic (e.g., t, z) to report. We used this bootstrap approach because it provides a more accurate and statistically powerful test of the significance of a mediated effect than the usual Sobel test (Sobel, 1982(Sobel, , 1986. Details on the bootstrap approach together with worked examples can be found in Shrout and Bolger (2002).…”
Section: Contrast 6: Pure Content (Invisible B Vs No Support): In Comentioning
confidence: 99%
“…Bootstrapping has been recommended when multivariate normality cannot be assumed, which is typically true with small sample sizes. Multivariate normality is especially important when multiple mediators are being included in determining indirect effects in path analysis models using the delta method (Preacher & Hayes, 2008;Sobel, 1982Sobel, , 1986. In this case, we had two mediators:…”
Section: Data Analytic Strategymentioning
confidence: 99%