## The Effects of Nonindependent Rater Sets in Multilevel–Multitrait–Multimethod Models

Research output: Journal contributions › Journal articles › Research › peer-review

### Standard

**The Effects of Nonindependent Rater Sets in Multilevel–Multitrait–Multimethod Models.**/ Schultze, Martin; Koch, Tobias; Eid, Michael.

In: Structural Equation Modeling, Vol. 22, No. 3, 03.07.2015, p. 439-448.

Research output: Journal contributions › Journal articles › Research › peer-review

### Harvard

*Structural Equation Modeling*, vol. 22, no. 3, pp. 439-448. https://doi.org/10.1080/10705511.2014.937675

### APA

*Structural Equation Modeling*,

*22*(3), 439-448. https://doi.org/10.1080/10705511.2014.937675

### Vancouver

### Bibtex

}

### RIS

TY - JOUR

T1 - The Effects of Nonindependent Rater Sets in Multilevel–Multitrait–Multimethod Models

AU - Schultze, Martin

AU - Koch, Tobias

AU - Eid, Michael

PY - 2015/7/3

Y1 - 2015/7/3

N2 - Multiple ratings are becoming increasingly popular for the assessment of a wide range of behaviors. Teaching evaluation designs and 360-degree feedback often use multiple raters alongside self-ratings. Eid and colleagues (2008) proposed a multilevel structural equation model for the analysis of data stemming from such designs that assumes that raters stem from independent populations of raters. However, it is quite common for raters to rate multiple targets, thus implying a cross-classified data structure. A simulation study was conducted to assess the effects of this rater nonindependence on parameter and standard error estimates in multilevel structural equation models. Results show parameter estimation biases to be small, whereas standard errors pertaining to the Level 1 covariance matrices as well as the mean structure on Level 2 are underestimated.

AB - Multiple ratings are becoming increasingly popular for the assessment of a wide range of behaviors. Teaching evaluation designs and 360-degree feedback often use multiple raters alongside self-ratings. Eid and colleagues (2008) proposed a multilevel structural equation model for the analysis of data stemming from such designs that assumes that raters stem from independent populations of raters. However, it is quite common for raters to rate multiple targets, thus implying a cross-classified data structure. A simulation study was conducted to assess the effects of this rater nonindependence on parameter and standard error estimates in multilevel structural equation models. Results show parameter estimation biases to be small, whereas standard errors pertaining to the Level 1 covariance matrices as well as the mean structure on Level 2 are underestimated.

KW - cross-classified

KW - MTMM

KW - multilevel

KW - simulation study

KW - structural equation modeling

KW - Economics, empirical/statistics

UR - http://www.scopus.com/inward/record.url?scp=84930572250&partnerID=8YFLogxK

U2 - 10.1080/10705511.2014.937675

DO - 10.1080/10705511.2014.937675

M3 - Journal articles

VL - 22

SP - 439

EP - 448

JO - Structural Equation Modeling

JF - Structural Equation Modeling

SN - 1070-5511

IS - 3

ER -