Skip to main content
Cross Validated

Return to Question

edited body
Source Link
user405152
user405152
  • 21
  • 2

In change analyses (of any variable, from pre to post) we usually controll for the pre-score, as it may affect the rate of change. However, what if I am especially interested in the effect of the pre score on the rate of change, like

Diff(post - pre) = a + b*pre.

What if I am especially interested in b? Is the model above reasonable or are theirthere any problems with that?

In multilevel-analysis of longitudinal data there is a correlation coefficient for the relation between the initial level (intercept) and the rate of change (slope). Thats the information I need, but in an ordinary regression model.

In change analyses (of any variable, from pre to post) we usually controll for the pre-score, as it may affect the rate of change. However, what if I am especially interested in the effect of the pre score on the rate of change, like

Diff(post - pre) = a + b*pre.

What if I am especially interested in b? Is the model above reasonable or are their any problems with that?

In multilevel-analysis of longitudinal data there is a correlation coefficient for the relation between the initial level (intercept) and the rate of change (slope). Thats the information I need, but in an ordinary regression model.

In change analyses (of any variable, from pre to post) we usually controll for the pre-score, as it may affect the rate of change. However, what if I am especially interested in the effect of the pre score on the rate of change, like

Diff(post - pre) = a + b*pre.

What if I am especially interested in b? Is the model above reasonable or are there any problems with that?

In multilevel-analysis of longitudinal data there is a correlation coefficient for the relation between the initial level (intercept) and the rate of change (slope). Thats the information I need, but in an ordinary regression model.

Source Link
user405152
user405152
  • 21
  • 2

Is it reasonable/possible to use pre-scores as predictors of change?

In change analyses (of any variable, from pre to post) we usually controll for the pre-score, as it may affect the rate of change. However, what if I am especially interested in the effect of the pre score on the rate of change, like

Diff(post - pre) = a + b*pre.

What if I am especially interested in b? Is the model above reasonable or are their any problems with that?

In multilevel-analysis of longitudinal data there is a correlation coefficient for the relation between the initial level (intercept) and the rate of change (slope). Thats the information I need, but in an ordinary regression model.