1991
DOI: 10.1086/208568
|View full text |Cite
|
Sign up to set email alerts
|

Multitrait-Multimethod Matrices in Consumer Research

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

3
350
1
13

Year Published

1997
1997
2017
2017

Publication Types

Select...
6
3

Relationship

0
9

Authors

Journals

citations
Cited by 582 publications
(367 citation statements)
references
References 5 publications
3
350
1
13
Order By: Relevance
“…Also, as we have noted above, that all t values are significant (greater than 1.96), then these results show direct evidence of convergent validity of the ELR measure [36]. Discriminant validity is defined as a degree to which measures of distinct concepts differ [37]. The discriminant validity of the five dimensional scales was tested in two ways.…”
Section: Assessment Of Reliability Convergent and Discriminant Validitysupporting
confidence: 53%
See 1 more Smart Citation
“…Also, as we have noted above, that all t values are significant (greater than 1.96), then these results show direct evidence of convergent validity of the ELR measure [36]. Discriminant validity is defined as a degree to which measures of distinct concepts differ [37]. The discriminant validity of the five dimensional scales was tested in two ways.…”
Section: Assessment Of Reliability Convergent and Discriminant Validitysupporting
confidence: 53%
“…Thus, discriminant validity is supported for all constructs. Second, the discriminant validity could be tested using the method of [37] which consists in comparing the chi-square free model (where the correlations between the latent variables are free) with the constrained model (where the correlations between the latent variables are set to 1). As emphasized [28], the difference between two chi-square distributions follows is itself a chi-square distribution with degrees of freedom equal to the difference of the degrees of freedom of the two models tested, and can therefore be tested statistically.…”
Section: Assessment Of Reliability Convergent and Discriminant Validitymentioning
confidence: 99%
“…Equally, if the study objective is to investigate employees' efforts in an activity related to their job, the use of self-rating is justified. However, it is important not to minimize the fact that the use of a self-rating source may generate response biases, the causes of which have been identified in the literature (Bagozzi and Yi 1991;Podsakoff et al 2003). This explains why common method variance bias was assessed.…”
Section: Source Of Measurement and Common Variancementioning
confidence: 99%
“…However, it seems quite likely that in many studies, certainly the ones testing theory, that two or more of the constructs in the hierarchy will be included in the study. This introduces a methodological problem because critics have long noted that when constructs are operationalized the same way in a study it may inflate the apparent relationship due to their shared method variance (Bagozzi and Yi 1991). To reduce that possibility, researchers have been urged to conduct research using multiple-method, multiple measure approaches (Campbell and Fiske 1959).…”
Section: The Hierarchy Of Effects and Need For Alba Scalementioning
confidence: 99%