3003PSY Mini Lecture: Cross-Lagged Designs & Longitudinal Assumptions PDF

3003PSY Survey Design and Analysis in Psychology CROSS-LAGGED DESIGNS AND ASSUMPTIONS  CROSS-LAGGED MODELS In cross-lagged models, the two measures serve as both the independent and dependent variable. In this analysis, there is more than one DV.  Cross-lagged models combine...

3003PSY Survey Design and Analysis in Psychology CROSS-LAGGED DESIGNS AND ASSUMPTIONS  CROSS-LAGGED MODELS In cross-lagged models, the two measures serve as both the independent and dependent variable. In this analysis, there is more than one DV.  Cross-lagged models combine two residualised longitudinal regressions into the same analysis. Thus, the stability of the construct is statistically removed, allowing each variable to CROSS-LAGGED predict the change in the other variable. MODELS This technique allows an investigation of bi- directional effects. There are 6 parameters to a two-wave cross- lagged model.  CROSS-LAGGED MODELS 1. Correlation between variables at time 1. 2. Correlation between variables at time 2. CROSS-LAGGED MODELS 3. Stability of Variable 1 4. Stability of Variable 2  CROSS-LAGGED MODELS 5. ‘Cross-lag path’ 1 : Variable 2 at T1 predicting change in Variable 1 6. ‘Cross-lag path’ 2: Variable 1 at T1 predicting change in Variable 2  CROSS-LAGGED MODEL: EXAMPLE 1,006 adolescents were followed over two years. The analysis investigated the longitudinal relationship between binge drinking and sharing alcohol content on SNS (Share Alc). Geusens & Beullens. (2017). The reciprocal associations between sharing alcohol references on social networking sites and binge drinking: A longitudinal study among late adolescents. Computers in Human Behavior, 73, 499-506. DOI: 10.1016/j.chb.2017.03.062 CROSS-LAGGED MODEL: EXAMPLE In this example, there is a bi-directional relationship: B =.37** B =.0 8* * 12*. = B B =.42** OVERVIEW OF LONGITUDINAL REGRESSION Accounts for Explores uni- Explores bi- Estimates Estimates Predicts cross- directional directional stability change change sectional relationships relationships relationship Simplex Model X X Longitudinal X Correlation Residualised X X X X X Regression Cross-lagged X X X X X X model  Inter-individual stability These techniques examine stability and change in the ASSUMPTIONS sample over time. OF Thus, it is assumed that there are LONGITUDINAL no systematic differences in the ANALYSIS stability and change between the participants. This assumption is violated when one group of participants changes faster or slower relative to the other participants.  Consistent Measurement It is assumed that the measurement is the same when using repeated ASSUMPTIONS measures (i.e. the same measure OF over two or more time periods). LONGITUDINAL In practical terms, this means that the items administered to ANALYSIS participants need to be exactly the same across time periods. In conceptual terms, participants need to read and interpret the questions in exactly the same way across time periods.  Synchronicity It is assumed that the administration of questionnaire ASSUMPTIONS occurs with the same interval OF between time periods for all LONGITUDINAL participants. ANALYSIS  Timeframe CONSIDERATIONS In order to find a longitudinal effect, the length of time between OF LONGITUDINAL measurements need to be considered. ANALYSIS The timeframe may be too short for a variable to impact another, and so you won’t find an effect. The timeframe may be too long and the impact of one variable on the other may have dissipated.  Other variables (third CONSIDERATIONS variable effect) It is important to ensure that OF LONGITUDINAL important variables are not omitted. ANALYSIS This idea is related to a causal process or pathway. For this reason, it is easier to say that a variable at time 1 influences or impacts something, rather than causing it. OR  SUMMARY uThe cross-lagged design is the gold standard of panel designs uIt overcomes the limitations of the previous designs by testing for uni-directional and bi-directional relationships uThe 2-wave cross-lagged design has 6 parameters: uCross-sectional associations between the variables at T1 & T2 uThe association over the time for each variable (stability/change) uThe cross-lag paths for each variable at T1 predicting the other at T2 uThe longitudinal design have several assumptions including: inter-individual stability; consistent measurement; synchronicity uOther considerations include the length of the timeframe and potential other variables