The plots show that fracture rate rises with increasing exposure; while the data fit a linear model and we use this linear term to describe the effect per cumulative year of exposure subsequently, the graphs also suggest a lag before fracture risk starts to increase, and a flattening of the curve after 4 years of exposure.
The code uses an iterative procedure in which the phase change rate is linearized as truncated Taylor series and then the old iteration values are used to compute the linear term.
A linear model was formed as a function of mix tiles fraction and the analysis of ANOVA suggest that the linear term used for this model is significant.
Tests of linearity used likelihood ratio tests to compare the linear term with the linear term plus cubic splines (27).
On the other hand, if we use d u / d t and the linear term u when determining the Lagrange multiplier, we can derive a Lagrange multiplier explicitly δ U n + 1 ( s ) = δ U n ( s ) + δ λ [ s U n ( s ) − u ( 0 ) − U n ( s ) ] = δ U n ( s ) + λ ( s ) ( s − 1 ) δ U n ( s ) (16). and λ ( s ) = − 1 s − 1. (17).
To test for non-linearity, we compared the model fit including only the linear term with the model fit including the linear and cubic spline terms using the likelihood ratio test.
An alternative, which also avoids the convergence problems inherent to FEP calculations [28], is to evaluate this correction term using the linear response approximation (LRA) [50].
Because a straight line fit inside the 95% confidence bands, we concluded that it was appropriate to use a linear term to describe the relationship.
In the first model we included data on all drugs and modeled the trend associated with at least one of the four possible programs using a linear term for the year of drug approval.
Using a linear term for the effect of CD4-based strategies, estimated survival 240 weeks after baseline was 96%95%5% CI: 94, 97), 95%95%5% CI: 94, 96), and 92% (95% CI: 91, 94) for switching at CD4 <100, CD4 <50, and no CD4 threshold, respectively (each with a non- Candida WHO 4 event as above) (Table 3).
