Input commands are in blue.
Statements generated by PEANUTS are in green.
Define names for the free-format input data. Then define a series
of transformations to be carried out as the data are read. These
transformations illustrate some of the date manipulation capabilities available
in all EPICURE programs. The transformation defined by the CONS command
defines a "named constant", i.e. a scalar variable.In this example the
transformations are defined before the data are read. They will be
carried out as the data are read.
NAMES id bmo bdy byr accmo
accdy accyr trmo trdy tryr
xmo xdy xyr
age surv
surgery allele antigen mismtch reject @
!Define date at program origin
CONS #c1067 = JULIAN(1967,10,1)
;
#c0167=julian(1967,1,1) @
TRAN ! Change years to 4 digits
byr = byr + 1900 ;
accyr = accyr + 1900 ;
tryr = tryr + 1900 ;
xyr = xyr + 1900 ;
! Compute age at acceptance, acceptance data
and survival time
cage = (JULIAN(accyr,accmo,accdy)
- JULIAN(byr,bmo,bdy))/365.25 ;
accdt = JULIAN(accyr,accmo,accdy)
-1 ;
stime = JULIAN(xyr,xmo,xdy)
- accdt ;
IF tryr == 1900 THEN
! Recodes for non-transplant patients
allele = %mv ;
antigen = %mv ; mismtch
= %mv ;
tryr = xyr ;
trmo = xmo ; trdy = xdy ;
trns = 0 ;
ELSE
! Recodes for transplant recipients
trns = 1 ;
ENDIF@
The data are read and a number of additional transformations are carried
out.
INPUT sheart.dat @
Input from sheart.dat
103
records read 103 records used
0 records rejected
Workspace for 300 variables. 33 are
currently defined.
Up to 267 new variables can be created
! Compute exit date, waiting time, and post-transplant
survival time
TRAN
xtdt = JULIAN(tryr,trmo,trdy)
;
wait = xtdt - accdt;
post = stime - wait ;
! Special status code for pre-transplant analyses
IF trns == 1
THEN prestat = 0
ELSE
prestat = surv
ENDIF
! Compute time since 10/1/67 at exit and since
1/1/67 at acceptance
ctime = xtdt -
#c1067 ;
acc = (accdt -
#c0167)/365.25 ;
! Indicator for deselected subjects
ds = (id == 26) or (id
== 27) or (id == 82) ; @
Begin with models for the transplant waiting
time, i.e. time from acceptance to transplant. Cases are those men
who receive transplants. The first model has no covariates and is
used as a null model in a subsequent likelihood ratio test. The second
model uses the time from the start of the transplant program (10/1/1967)
until the patient entered the program. The sign of the effect suggests
that waiting times decreased as the program continued. The likelihood ratio
test indicates that this is statistically significant.
TIME wait @
CASES prestat @
FIT @
Data not sorted on TIME
Data now being sorted.................
Hazard function regression model
Product additive excess RR model {RR = T0*(1
+ T1 + T2 + ...)}
WAIT is used for survival
time.
PRESTAT is used for outcomes
Deviance =
221.001
Free parameters
= 0
Number of risk sets
= 23
TRAN acc = (julian(accyr,accmo,accdy)
- #c0167)/365.25@
NULLFIT acc @
LRT
Iter Step Deviance
0 0 221.0006
1 0 214.3925
2 0 214.3904
3 0 214.3904
Hazard function regression model
Product additive excess RR model {RR = T0*(1
+ T1 + T2 + ...)}
WAIT is used for survival
time.
PRESTAT is used for outcomes
Parameter Summary Table
# Name
Estimate Std.Err. Score
Status
-- ------------------------- -----------
----------- ---------- -------
Log-linear term 0
1 ACC .....................
-0.2600 0.1040 -0.471E-09
Free
Deviance =
214.390
Free parameters
= 1
Number of risk sets
= 23
LR statistic
= 6.610
df = 1
These analyses consider survival time for the
65 men who actually received a transplant. This subset of cases is
selected interactively. The case indicator is changed to survival
status and the time scale to post-transplant survival time.The model fit
includes age at acceptance in to the program, an indicator of a history
of heart surgery, and a mismatch score.
SELECT trns == 1 and antigen >= 0 @
65 records to be used
CASES surv @ TIME post @ FIT age
surgery mismtch @
Data not sorted on TIME
Data now being sorted.................
Iter Step Deviance
0 0 290.8655
1 0 277.1042
2 0 276.9394
3 0 276.9392
4 0 276.9392
Hazard function regression model
Product additive excess RR model {RR = T0*(1
+ T1 + T2 + ...)}
Using TRNS == 1 AND ANTIGEN >= 0
POST is used for survival
time.
SURV is used for outcomes
Parameter Summary Table
# Name
Estimate Std.Err. Score
Status
-- ------------------------- -----------
----------- ---------- -------
Log-linear term 0
1 AGE .....................
0.05155 0.02201 0.281E-10
Free
2 SURGERY .................
-0.8225 0.4846 -0.318E-09
Free
3 MISMTCH .................
0.4913 0.2911 0.215E-10
Free Deviance =
276.939 Free parameters
= 3
Number of risk sets =
39
We now consider models for both pre- and post-transplant
survival. The models will make use of a time-dependent indicator
variable for transplant status.The time indicator is changed to survival
time (from acceptance into the program). The first model has no covariates
and is used as a null model for subsequent tests.The TTRAN command is used
to define time-dependent covariates. The variable %time is a special
variable that contains the current time for the risk set.The first model
includes only the transplant indicator.
NOMODEL @
SELECT @
Model has been reset
103 records
to be used
CASES surv @
TIME stime @
FIT @ NULL @
Data not sorted on TIME
Data now being sorted.................
Hazard function regression model
Product additive excess RR model {RR = T0*(1
+ T1 + T2 + ...)}
STIME is used for survival
time.
SURV is used for
outcomes
Deviance
= 594.386
Free parameters
= 0 Number
of risk sets =
62
TRAN
ht = 0 ; preht = 1 @
TTRAN ht = (%time > wait ) @
FIT ht @ LRT
Iter
Step Deviance
0 0 594.3860
1 0 594.3775
2 0 594.3775
Hazard function regression model with time-dependent
covariates
Product additive excess RR model {RR = T0*(1
+ T1 + T2 + ...)}
STIME is used for survival
time.
SURV is used for
outcomes
Parameter Summary Table
# Name
Estimate Std.Err. Score
Status
-- ------------------------- -----------
----------- ---------- -------
Log-linear term 0
1 HT ......................
-0.02796 0.3020 0.181E-08
Free
Deviance
= 594.377 Free parameters
= 1
Number of risk sets = 62
Non-informative risk sets = 1
LR statistic
= 0.8545E-02 df =
1 P
= 0.9263
The age at transplant is computed and added to the previous model in
a interaction with heart transplant status.
TRAN trage = (julian(tryr,trmo,trdy) - julian(byr,bmo,bdy))/365.25
@
FIT + ht*trage @
Iter Step Deviance
0 0 594.3775
1 0 587.3064
2 0 587.0111
3 0 587.0104
4 0 587.0104
Hazard function regression model with time-dependent
covariates
Product additive excess RR model {RR =
T0*(1 + T1 + T2 + ...)}
STIME is used for survival
time.
SURV is used for
outcomes
Parameter Summary Table
# Name
Estimate Std.Err. Score
Status
-- ------------------------
----------- ----------- ---------- -------
Log-linear term 0
1 HT ......................
-2.746 1.146
-0.400E-09 Free
2 HT * TRAGE ............. 0.05698
0.02243 -0.690E-10 Free
Deviance = 587.010
Free parameters
= 2
Number of risk sets =
62
Non-informative risk sets = 1
LRT
LR statistic = 7.376
df = 2
P = 0.0250
A final model involving various factors that are
believed to affect pre- and post-transplant survival is fit. To fit
this model, a pre-transplant time dependent covariate is defined.
This TTRAN command adds the new transformations to those specified previously.
(The NOTTRAN command is used to remove time-dependent transformations).
TTRAN preht = 1 - ht @
FIT preht*acc preht*surgery preht*age ht ht*acc
ht*surgery ht*age @
Iter Step Deviance
0 0 594.3860
1 0 575.6942
2 0 575.5826
3 0 575.5825
Hazard function regression model with time-dependent
covariates
Product additive excess RR model {RR =
T0*(1 + T1 + T2 + ...)}
STIME is used for survival
time.
SURV is used for
outcomes
Parameter Summary Table
# Name
Estimate Std.Err. Score
Status
-- -----------------------
----------- ----------- ----------
-------
Log-linear term 0
1 PREHT * ACC ............ -0.2478
0.1056 0.148E-05 Free
2 PREHT * SURGERY .. -0.3314
0.6271 0.323E-06 Free
3 PREHT * AGE ............
0.01266 0.01655 0.272E-05 Free
4 HT ......................
-2.726 1.412
-0.578E-05 Free
5 HT * ACC ................
-0.02178 0.09594 -0.333E-05 Free
6 HT * SURGERY .......... -0.7913
0.4534 -0.941E-05 Free
7 HT * AGE ................
0.05122 0.02148 -0.299E-05 Free
Deviance = 575.583
Free parameters
= 7
Return to HiroSoft's Home
Page
Back to the directory
of examples
Back to the PEANUTS overview