2015
DOI: 10.1037/met0000041
|View full text |Cite
|
Sign up to set email alerts
|

Optimal time lags in panel studies.

Abstract: Cross-lagged regression coefficients are frequently used to test hypotheses in panel designs. However, these coefficients have particular properties making them difficult to interpret. In particular, cross-lagged regression coefficients may vary, depending on the respective time lags between different sets of measurement occasions. This article introduces the concept of an optimal time lag. Further, it is demonstrated that optimal time lags in panel studies are related to the stabilities of the variables inves… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

13
429
0
5

Year Published

2016
2016
2024
2024

Publication Types

Select...
10

Relationship

0
10

Authors

Journals

citations
Cited by 552 publications
(447 citation statements)
references
References 56 publications
(103 reference statements)
13
429
0
5
Order By: Relevance
“…We however note that our choice was guided by previous recommendations (Van Dierendonck, Haynes, Borrill & Stride, 2004), and recent findings that show the methodological superiority of shorter over longer time lags further supports our decision (Dormann & Griffin, 2015). Furthermore, recent evidence shows that burnout varies from day to day (Halbesleben & Wheeler, 2011), implying that changes should be observable over short time frames.…”
Section: Limitations and Strengthsmentioning
confidence: 61%
“…We however note that our choice was guided by previous recommendations (Van Dierendonck, Haynes, Borrill & Stride, 2004), and recent findings that show the methodological superiority of shorter over longer time lags further supports our decision (Dormann & Griffin, 2015). Furthermore, recent evidence shows that burnout varies from day to day (Halbesleben & Wheeler, 2011), implying that changes should be observable over short time frames.…”
Section: Limitations and Strengthsmentioning
confidence: 61%
“…Thus, it cannot be exactly stated that the occurring effects appear within a 6-month time frame. Moreover, due to relatively high stabilities of most investigated variables, longer time lags might show even stronger effects (Dormann and Griffin, 2015). Additionally, though we were able to assess cross-lagged effects with two measurement times, multiple assessments across time are necessary to assess developments and possible non-linear effects (Roe, 2014).…”
Section: Discussionmentioning
confidence: 99%
“…Addressing this gap, we (a) reveal implicit assumptions about time in leadership research, (b) discuss different temporal configurations of leadership, (c) elaborate on unfolding time (i.e., how long it takes for effects to materialize) and persistence of leadership effects, and (d) caution against using non-theory-based time lags. In doing so, we complement recent methodological efforts to find optimal time lags (Dormann & Griffin, 2015) with conceptual considerations to examine leadership processes.…”
Section: It Is Time To Put Time Into Theorizing and Testingmentioning
confidence: 99%