Skip to main content
. Author manuscript; available in PMC: 2013 Sep 3.
Published in final edited form as: J Abnorm Psychol. 2013 May;122(2):542–557. doi: 10.1037/a0031963

Table 4.

Studies 1 and 2: Full Autoregressive Latent Trajectory Model Fit Statistics and Standardized Cross-Lagged Parameter Estimates (Q2: What Is the Direction of Effect Between Language Ability and Behavior Problems?)

Model fit
Lang → BP
BP → Lang
BP Rater Study RMSEA CFI χ2 df SE p β SE p
I-H Teacher 1 .025 0.992 94.77 70 −0.06 0.02 <.001 −0.04 0.02 .030
I-H Mother 1 .021 0.996 87.13 70 −0.07 0.01 <.001 −0.01 0.02 .671
I-H Mother 2 .013 0.995 71.71 26 −0.03 0.01 <.001 0.00 0.01 .771
EXT Teacher 1 .017 0.996 80.60 70 −0.04 0.01 .005 −0.01 0.02 .456
EXT Mother 1 .008 0.999 72.52 70 −0.07 0.02 <.001 −0.03 0.02 .138
EXT Mother 2 .013 0.996 67.85 26 −0.03 0.01 <.001 0.00 0.01 .966

Note. Parameters where p < .05 in bold. BP = behavior problems; CFI = comparative fit index; EXT = externalizing problems; I-H = inattentivehyperactive problems; Lang = language ability; RMSEA = root mean square error of approximation.