Effect of comprehensive cardiac rehabilitation after heart valve surgery (CopenHeartVR): study protocol for a randomised clinical trial

Table 3 The use of imputed values in CopenHeart _VR

Observed pattern in group B at 1, 4 and 6 months	Imputed value in group B at 1 month	Imputed value in group B at 4 month	Imputed value in group B at 6 months
mis^a, mis, mis	X1-bar^b	X4-bar^c	X6-bar^d
mis, mis, Y3^e	Y3 - (delta^f + delta2^g)^h	Y3 - delta2
mis, Y2, mis	Y2 – delta1		Y2 + delta2
Y1, mis, mis		Y1 + delta1	Y1 + delta1 + delta2
Y1, Y2, mis			Y2 + delta2
Y1, mis, Y3		(Y1 + delta1 + Y3 -delta2)/2
mis, Y2, Y3	Y2 - delta1

Table to explain the use of imputing quantities derived from observed values in a group (group A) to impute missing values in a group (group B).
^aThe value at 4 months is missing in group B.
^bMean of values observed in group A at 1 month.
^cMean of values observed in group A at 4 months.
^dMean of values observed in group A at 6 months.
^eObserved value in group B at 6 months.
^fThe mean of difference between values observed at 4 months and value observed at 1 month in group A.
^gThe mean of difference between value observed at time 6 months and value observed at time 4 months in group A.
^hIf an imputed value is 0 it is set equal to 0.
Mis, Missing value; X1, Value at month 1; X4, Value at month 4; X6, Value at month 6.

ISSN: 1745-6215