33 Reading the Output
1 What This Chapter is About
This chapter describes NONMEM’s output in detail. Each page of a NONMEM-PREDPP output file is shown and discussed.
The input file to NM-TRAN is that of figure 2.12, which is reproduced here as figure 10.1 for convenience.
$PROBLEM PHENOBARB WITH WEIGHT IN MODELS FOR CL AND V
$INPUT ID TIME AMT WT APGR DV
$DATA INDATA
$SUBROUTINE ADVAN1
$PK
TVCL=THETA(1)+THETA(3)*WT
CL=TVCL+ETA(1)
TVVD=THETA(2)+THETA(4)*WT
V=TVVD+ETA(2)
; THE FOLLOWING ARE REQUIRED BY PREDPP
K=CL/V
S1=V
$ERROR
Y=F+ERR(1)
$THETA (0,.0027) (0,.70) .0018 .5
$OMEGA .000007, .3
$SIGMA 8
$ESTIMATION PRINT=10
$COVARIANCE UNCONDITIONAL
$TABLE ID TIME AMT WT APGR DV
$SCATTER PRED VS DV UNIT
$SCATTER RES VS WTFigure 10.1. The NM-TRAN input file (same as figure 2.12).
2 NONMEM Describes its Inputs
The first page of NONMEM’s output is shown in figure 10.2. In this page, NONMEM repeats (“echos”) the instructions it was given in the control file and describes the data file. The first page of the output should be checked carefully. Problems in a NONMEM run can often be traced to errors in the problem specification. For example, always check that the initial parameter estimates were entered correctly.
NONLINEAR MIXED EFFECTS MODEL PROGRAM (NONMEM) VERSION 7.6.0
ORIGINALLY DEVELOPED BY STUART BEAL, LEWIS SHEINER, AND ALISON BOECKMANN
CURRENT DEVELOPERS ARE ROBERT BAUER, ICON DEVELOPMENT SOLUTIONS,
AND ALISON BOECKMANN. IMPLEMENTATION, EFFICIENCY, AND STANDARDIZATION
PERFORMED BY NOUS INFOSYSTEMS.
PROBLEM NO.: 1
PHENOBARB WITH WEIGHT IN MODELS FOR CL AND V
DATA CHECKOUT RUN: NO
DATA SET LOCATED ON UNIT NO.: 2
THIS UNIT TO BE REWOUND: NO
CREATE/ADD TO FDATA.csv: YES
NO. OF DATA RECS IN DATA SET: 744
NO. OF DATA ITEMS IN DATA SET: 8
ID DATA ITEM IS DATA ITEM NO.: 1
DEP VARIABLE IS DATA ITEM NO.: 6
MDV DATA ITEM IS DATA ITEM NO.: 8
INDICES PASSED TO SUBROUTINE PRED:
7 2 3 0 0 0 0 0 0 0 0
LABELS FOR DATA ITEMS:
ID TIME AMT WT APGR DV EVID MDV
FORMAT FOR DATA: (6E6.0,2F2.0)
TOT. NO. OF OBS RECS: 155
TOT. NO. OF INDIVIDUALS: 59
LENGTH OF THETA: 4
DEFAULT THETA BOUNDARY TEST OMITTED: NO
OMEGA HAS SIMPLE DIAGONAL FORM WITH DIMENSION: 2
DEFAULT OMEGA BOUNDARY TEST OMITTED: NO
SIGMA HAS SIMPLE DIAGONAL FORM WITH DIMENSION: 1
DEFAULT SIGMA BOUNDARY TEST OMITTED: NO
INITIAL ESTIMATE OF THETA:
LOWER BOUND INITIAL EST UPPER BOUND
0.0000E+00 0.2700E-02 0.1000E+07
0.0000E+00 0.7000E+00 0.1000E+07
-0.1000E+07 0.1800E-02 0.1000E+07
-0.1000E+07 0.5000E+00 0.1000E+07
INITIAL ESTIMATE OF OMEGA:
0.7000E-05
0.0000E+00 0.3000E+00
INITIAL ESTIMATE OF SIGMA:
0.8000E+01
COVARIANCE STEP OMITTED: NO
(...additional options displayed...)Figure 10.2. The first page of the output report.
Line 8 (problem description) shows the contents of the $PROBLEM record. Lines 10 through 26 describe the input data file. Lines 13 and 14 describe the numbers of rows and columns in the input file. Specifically, line 13 shows how many data records were read according to the FORTRAN format specification given in line 23. (Records that are dropped by the Data Preprocessor using $DATA...IGNORE=... are never read by NONMEM, hence cannot be included in line 13.) With NONMEM 7.5, line 13 also does not include records that were read by NONMEM but dropped by PRED using the PRED_IGNORE_DATA variable. Line 14 describes the number of data items per record, which is the number of data items listed in the $INPUT record, less any that were dropped by the Data Preprocessor, plus any that it added (see Chapter 6).
Lines 15 to 17 describe the locations of those data items of interest to NONMEM itself (i.e. NONMEM data items). Line 21 gives the labels for all the data items. The first six labels are those of the data items specified in the $INPUT record and the next two (EVID, MDV) are those of two data items added to the data set by the Data Preprocessor. (NONMEM itself supplies labels PRED, RES, and WRES for the prediction, residual, and weighted residual data items.)
In the terminology of Chapter 4 (e.g. (4.15a)), ID, TIME, AMT, WT, and APGR are the elements of \(x\); DV is \(y\); PRED is \(f\) (evaluated for the typical individual in the population). Line 23 shows the format used to read each data record. Line 25 gives the number of observation records. Line 26 gives the number of individual records; that is, one less than the number of times that the ID data item changed value.
Lines 27 through 43 describe the contents of the $THETA, $OMEGA and $SIGMA records. First, the number of elements of \(\theta\), \(\Omega\) and \(\Sigma\) are given (lines 27, 29 and 31), then their initial estimates are displayed. Notice the values 0.1000e+07 and -0.1000e+07. These are NONMEM’s way of expressing the values \(+\infty\) and \(-\infty\); i.e., of describing \(\theta\)s which are unbounded on one or both sides. Another FORTRAN system may display these numbers differently (e.g., 1.0000e+06), but the absolute value will always be 1,000,000.
The remaining lines of figure 10.2 describe the tasks that NONMEM will perform. Lines 44 through 62 describe the $COVARIANCE record, giving the default options chosen by NM-TRAN. Lines 63 through 81 describe the $TABLE record. Lines 82 through 89 describe the $SCATTERPLOT records.
Figure 10.2b describes the options of the $ESTIMATION record.
#TBLN: 1
#METH: First Order
ESTIMATION STEP OMITTED: NO
SHRINK INFO WITH EVALUATION (EVALSHRINK) NO
ANALYSIS TYPE: POPULATION
NUMBER OF SADDLE POINT RESET ITERATIONS: 0
GRADIENT METHOD USED: NOSLOW
EPS-ETA INTERACTION: NO
NO. OF FUNCT. EVALS. ALLOWED: 360
NO. OF SIG. FIGURES REQUIRED: 3
INTERMEDIATE PRINTOUT: YES
ESTIMATE OUTPUT TO MSF: NO
...Figure 10.2b. The $ESTIMATION record description.
Line 1 contains the tag #TBLN:, and specifies that following it, on the same line, will be found an integer that refers to the number of this estimation method. As of NONMEM7, each $ESTIMATION record represents a separate estimation method, in which the final parameters of the previous estimation are passed as initial parameters to the next estimation. This is further described in Introduction to NONMEM7. This number is also the table number listed in the title to tables in the various output files (raw output file .ext, .cov, .cor, etc). The table number is incremented for each $EST statement, across all problems in the control stream file. On Line 2, the tag #METH: specifies that following it, on the same line, will be found a text that describes the estimation method.
Lines 4 through 40 show the defaults (set by NM-TRAN) for various options, all of which could have been specified explicitly on the $ESTIMATION record. In line 10 for example, NONMEM displays the maximum number of times it will evaluate the objective function during the Estimation Step (this number can be slightly exceeded). The value 360 was supplied by NM-TRAN. It is a function of the sizes of \(\theta\), \(\Omega\), and \(\Sigma\). Line 11 displays the desired number of significant digits in the final parameter estimate; the value 3 is the default number requested by NM-TRAN.
3 PREDPP Describes Its Inputs
The next two pages are produced by PREDPP and will not appear if $PRED statements (or a user-written PRED subroutine) are used. PREDPP uses these pages to repeat (“echo”) the instructions it was given in the control file, and to identify the ADVAN and TRANS routines chosen by the user.
In its first page of output, PREDPP describes the features of the pharmacokinetic model and its parameterization encoded into the ADVAN and TRANS routines specified on the $SUBROUTINE record. The information displayed here includes the kind of information summarized in Appendices 1 and 2.
DOUBLE PRECISION PREDPP VERSION 7.6.0
ONE COMPARTMENT MODEL (ADVAN1)
MAXIMUM NO. OF BASIC PK PARAMETERS: 2
BASIC PK PARAMETERS (AFTER TRANSLATION):
ELIMINATION RATE (K) IS BASIC PK PARAMETER NO.: 1
COMPARTMENT ATTRIBUTES
COMPT. NO. FUNCTION INITIAL ON/OFF DOSE DEFAULT DEFAULT
STATUS ALLOWED ALLOWED FOR DOSE FOR OBS.
1 CENTRAL ON NO YES YES YES
2 OUTPUT OFF YES NO NO NOFigure 10.3. The first page of PREDPP’s output.
The information concerning basic parameters and compartments is displayed in a format similar to that used in NONMEM Users Guide, Part VI, which is the complete reference for PREDPP.
Lines 4 and 6 describe the basic PK parameters, which in this example is the single microconstant K. If a translator other than TRANS1 had been requested, an additional line would appear describing the translation. E.g., with TRANS2, this line would read:
TRANSLATOR WILL CONVERT PARAMETERS CLEARANCE (CL) AND VOLUME (V) to KLines 8 through 12 describe the compartment attributes. Even though the output compartment is never turned on by the data of this example, its attributes are described here because it is part of the model.
PREDPP’s second page of output describes user choices related to the given ADVAN routine, including choices for the scale parameters (and thus, to the model for computing concentrations).
ADDITIONAL PK PARAMETERS - ASSIGNMENT OF ROWS IN GG
INDICES
COMPT. NO. SCALE BIOAVAIL. ZERO-ORDER ZERO-ORDER ABSORB
FRACTION RATE DURATION LAG
1 3 * * * *
2 * - - - -
- PARAMETER IS NOT ALLOWED FOR THIS MODEL
* PARAMETER IS NOT SUPPLIED BY PK SUBROUTINE;
WILL DEFAULT TO ONE IF APPLICABLE
DATA ITEM INDICES USED BY PRED ARE:
EVENT ID DATA ITEM IS DATA ITEM NO.: 7
TIME DATA ITEM IS DATA ITEM NO.: 2
DOSE AMOUNT DATA ITEM IS DATA ITEM NO.: 3
PK SUBROUTINE CALLED WITH EVERY EVENT RECORD.
PK SUBROUTINE NOT CALLED AT NONEVENT (ADDITIONAL OR LAGGED) DOSE TIMES.
DURING SIMULATION, ERROR SUBROUTINE CALLED WITH EVERY EVENT RECORD.
OTHERWISE, ERROR SUBROUTINE CALLED ONCE IN THIS PROBLEM.Figure 10.4. The second page of PREDPP’s output.
Positions marked with “*” correspond to additional PK parameters that are allowed by the model but that are not assigned a value by $PK statements; an example is F1, the bioavailability fraction for compartment 1. Positions marked with “-” correspond to additional parameters that may not be computed; for instance, dose-related parameters are not allowed for the output compartment.
Lines 10 through 13 describe the locations in the input data record of those data items of interest to PREDPP (PREDPP data items). Note that data item 7, EVID, was appended by the Data Preprocessor. Line 15 reflects the fact that, by default, $PK statements are evaluated with every event record. Line 18 reflects the fact that the $ERROR statements describe the simple error model (3.4). This model uses no data items and no elements of \(\eta\) whatsoever (directly or indirectly). NM-TRAN has instructed PREDPP that the $ERROR statements need be evaluated only once at the beginning of the problem. Line 17 indicates that, should the Simulation Step be implemented, PREDPP will disregard this limitation and evaluate the $ERROR statements with every event record.
Finally, note that the $PK and $ERROR models (figure 10.1, lines 5-14) are not documented in the NONMEM-PREDPP output. It is a good idea to attach a printed copy of the NM-TRAN input records to the corresponding NONMEM output. MS/DOS batch file nmfe7x.bat and Unix C-shell script nmfe7x (supplied with NONMEM) do this automatically.
4 Diagnostic Output from the Estimation Step
The next page of output is produced during the running of the Estimation Step.
4.1 Intermediate Output from the Estimation Step
Lines 1 through 33 are referred to as the intermediate output.
MONITORING OF SEARCH:
ITERATION NO.: 0 OBJECTIVE VALUE: 675.657684094370 NO. OF FUNC. EVALS.: 7
CUMULATIVE NO. OF FUNC. EVALS.: 7
NPARAMETR: 2.7000E-03 7.0000E-01 1.8000E-03 5.0000E-01 7.0000E-06 3.0000E-01 8.0000E+00
PARAMETER: 1.0000E-01 1.0000E-01 1.0000E-01 1.0000E-01 1.0000E-01 1.0000E-01 1.0000E-01
GRADIENT: -3.9976E+01 -8.0006E+01 -4.2941E+02 -1.0001E+03 1.5391E+01 5.2661E+01 9.0187E+00
ITERATION NO.: 10 OBJECTIVE VALUE: 613.258949532521 NO. OF FUNC. EVALS.: 84
CUMULATIVE NO. OF FUNC. EVALS.: 91
NPARAMETR: 7.1965E-04 2.5796E-01 4.3459E-03 8.4505E-01 2.2246E-06 9.9144E-02 8.9710E+00
PARAMETER: -1.2222E+00 -8.9828E-01 2.4144E-01 1.6901E-01 -4.7316E-01 -4.5360E-01 1.5728E-01
GRADIENT: 3.7213E+00 6.3503E+00 5.0514E+01 5.2246E+01 2.6041E+00 4.2624E+00 1.4554E+01
... (iterations continue) ...
ITERATION NO.: 31 OBJECTIVE VALUE: 609.179165845924 NO. OF FUNC. EVALS.: 0
CUMULATIVE NO. OF FUNC. EVALS.: 271
NPARAMETR: 2.7000E-05 1.1935E-01 4.7519E-03 9.1899E-01 1.3698E-06 7.5079E-02 8.7026E+00
PARAMETER: -4.5116E+00 -1.6690E+00 2.6399E-01 1.8380E-01 -7.1561E-01 -5.9262E-01 1.4209E-01
GRADIENT: 0.0000E+00 8.9319E-03 1.4467E-01 5.4480E-01 -1.7084E-03 -3.2719E-03 -7.7586E-03
#TERM:
MINIMIZATION SUCCESSFUL
NO. OF FUNCTION EVALUATIONS USED: 271
NO. OF SIG. DIGITS IN FINAL EST.: 3.7
PARAMETER ESTIMATE IS NEAR ITS BOUNDARY
TOTAL DATA POINTS NORMALLY DISTRIBUTED (N): 155
N*LOG(2PI) CONSTANT TO OBJECTIVE FUNCTION: 284.870945293449
OBJECTIVE FUNCTION VALUE WITHOUT CONSTANT: 609.179165845924
OBJECTIVE FUNCTION VALUE WITH CONSTANT: 894.050111139373
REPORTED OBJECTIVE FUNCTION DOES NOT CONTAIN CONSTANT
TOTAL EFFECTIVE ETAS (NIND*NETA): 118
#TERE:
Elapsed estimation time in seconds: 0.61
S MATRIX ALGORITHMICALLY SINGULAR
S MATRIX IS OUTPUT
INVERSE COVARIANCE MATRIX SET TO RS*RMAT, WHERE S* IS A PSEUDO INVERSE OF S
Elapsed covariance time in seconds: 0.16
Elapsed postprocess time in seconds: 0.10Figure 10.5. The output from the Estimation Step.
Lines 4 through 8 give numbers summarizing the 0-th iteration, which are based on the initial parameter estimates. Line 4 shows the initial value of the objective function. The value following “NO. OF FUNC. EVALS.” is the number of objective function evaluations which were needed during the iteration. Line 5 gives the cumulative number of function evaluations including this and all prior iteration summaries.
With NONMEM 7, the parameter estimates are displayed in their natural (unscaled) space. These lines are identified as NPARAMETR. Line 7 gives the unconstrained parameter (UCP) estimates. The search is carried out in a different parameter space. The parameters are transformed to unconstrained parameters (UCP). In the transformation process a scaling occurs so that the initial estimate of each of the UCP is 0.1. Thus, in line 7, all parameters are .1 at the 0-th iteration. Parameters are printed in the following order: elements of \(\theta\), elements of \(\Omega\), elements of \(\Sigma\). In this example, reading from left to right, the parameters are \(\theta_1\), \(\theta_2\), \(\theta_3\), \(\theta_4\), \(\omega_{11}\), \(\omega_{22}\), and \(\sigma_{11}\).
Two points should be noted. First, fixed parameters do not appear in the list. Therefore, the off-diagonal element \(\omega_{12}\), which is effectively fixed to 0, does not appear. Second, when off-diagonal elements of \(\Omega\) are being estimated, then as many additional UCP’s appear as there are off-diagonal elements of \(\Omega\) being estimated. However, a 1-1 correspondence between each of the elements of \(\Omega\) and an UCP does not exist. The same is true for elements of \(\Sigma\) and the UCP’s for \(\Sigma\) when off-diagonal elements of \(\Sigma\) are estimated.
Line 8 shows the gradient for each parameter, which may be thought of as the partial derivative of the objective function with respect to that parameter.
The Estimation Step proceeds in a series of stages called iterations. In this example, intermediate printout is produced for each of every 5 iterations, as well as for the 0-th and final iterations, for which intermediate printout is always printed by default. This printout consists of the same four lines as for the 0-th iteration, but using the parameters estimates obtained at the end of the iteration.
Observe that the objective function drops quickly at first, and then more slowly. After iteration number 31, there is no change above the fourth significant digit. Each parameter also changes rapidly at first and then more slowly as it converges to its final value. (The first parameter, \(\theta_1\), is an exception. It is clearly approaching a very small value close to its lower bound, 0. In Chapter 12, we shall see that both \(\theta_1\) and \(\theta_3\) are best fixed at 0.) Finally, the gradients also approach 0, another sign that a minimum of the objective function has been located.
The values computed for the gradients are very sensitive to differences in computer arithmetic and precision. If a given NONMEM run is repeated on a different computer, or on the same computer with different machine precision or a different FORTRAN compiler, it is likely that the gradients will be different. This will cause the search to follow a different path to the minimum. However, each final estimate of a parameter should always be the same to the number of requested significant digits.
4.2 Summary Output from the Estimation Step
Lines 34 to 37 are always printed, even when intermediate printout is suppressed. The tag #TERM: defines the beginning of the summary output statements of the estimation results, and ends with the #TERE: tag. This allows a third party software to locate the summary output paragraph between these two tags.
Line 35, “MINIMIZATION SUCCESSFUL”, signifies that the search appears to have located a minimum of the objective function. Before one can be certain that a minimum has been located, or one which corresponds to a reasonable parameter estimate (there can be a number of “local minima”), the final parameter estimates must be examined in their (untransformed) state; see Section 5 below. The Estimation Step is not always successful. Chapter 13 discusses two other messages that sometimes appear instead of line 35.
The number of function evaluations used is a total value and includes all iterations (not just those for which intermediate printout was displayed).
The number of significant digits in the final estimate is given as 3.7. This can be interpreted as meaning that no (transformed) parameter estimate is actually determined to less than 3.7 significant digits. More specifically, when the UCP estimates were compared between the last two iterations, none differed in the first (almost) 4 significant figures including leading zeros after the decimal point. Because NONMEM displays only 3 significant digits in the printed parameter estimates, and for other reasons as well, by default NM-TRAN requests only 3 significant digits. However, more significance can be requested, as was discussed in Chapter 9, Section 4.1.
5 Minimum Value of the Objective Function and Final Parameter Estimates
The next two pages in the NONMEM output are produced whether or not the Estimation Step was implemented and, if it was, whether or not the search terminated successfully. They give the values of the objective function and the parameter estimates, using the final parameter estimates if the Estimation Step was implemented (whether or not the search terminated successfully), and using the initial parameter estimates otherwise. These pages have already been shown in Chapter 2, figure 2.13.
Even when the minimization routine is successful in locating a minimum of the objective function, the final (untransformed) parameter estimates must be carefully checked. Is any parameter’s final estimate physiologically unreasonable? Is any parameter’s final estimate near its upper or lower constraint? If either answer is yes, the model, the constraints on \(\theta\)’s, or the data may be incorrect; see Chapter 11.
Sometimes the final estimates do not match anticipated values, e.g., values obtained by some other system of analysis. Additional refinement of the model may be needed, as discussed in Chapter 11. However, the discrepancy may well be traceable to an error in model specification, such as an error in specifying a compartment’s scale. Along with the Estimation Step, it is important to obtain a scatterplot of PRED vs DV and make sure the unit slope line is visible. See Chapter 13, Section 4.4.
6 Output from the Covariance Step
The output of the Covariance Step (requested via the $COVARIANCE record) includes the standard errors of the parameter estimates, the covariance matrix, correlation matrix, and inverse covariance matrix. Standard errors are discussed extensively in Chapters 5 and 11.
Note the use of the notation ......... in these outputs. Each sequence of dots denotes a value (such as the standard error in the estimate of \(\omega_{12}\)) that is 0 by definition, rather than due to a computation.
STANDARD ERROR OF ESTIMATE (FIRST ORDER)
THETA - VECTOR OF FIXED EFFECTS PARAMETERS
TH 1 TH 2 TH 3 TH 4
0.00E+00 1.48E-01 2.24E-04 1.13E-01
OMEGA - COV MATRIX FOR RANDOM EFFECTS - ETAS
ETA1 ETA2
ETA1 7.30E-07
ETA2 ......... 3.63E-02
SIGMA - COV MATRIX FOR RANDOM EFFECTS - EPSILONS
EPS1
EPS1 1.71E+00Figure 10.6. Standard error of the estimate.
COVARIANCE MATRIX OF ESTIMATE
TH 1 TH 2 TH 3 TH 4 OM11 OM12 OM22 SG11
TH 1 0.00E+00
TH 2 0.00E+00 2.18E-02
TH 3 0.00E+00 -1.46E-05 5.01E-08
TH 4 0.00E+00 -1.60E-02 1.05E-05 1.29E-02
OM11 0.00E+00 2.22E-08 -5.96E-12 -1.58E-08 5.33E-13
OM12 ......... ......... ......... ......... ......... .........
OM22 0.00E+00 4.64E-04 -5.35E-07 5.43E-04 6.53E-10 ......... 1.32E-03
SG11 0.00E+00 -5.85E-02 1.12E-04 4.56E-02 -3.80E-07 ......... -1.04E-02 2.92E+00Figure 10.7. Covariance matrix of the estimate.
The correlation matrix shows the correlation between parameter estimates (Figure 10.8) and the inverse covariance matrix (Figure 10.9) is also output.
7 Additional Output: Tables and Scatterplots
The use of $TABLE and $SCATTERPLOT records to request tables and scatterplots is discussed in Chapter 9.
7.1 Output from the Table Step
A portion of the table produced by the $TABLE record is shown below. This is the data for the first individual.
TABLE NO. 1
LINE NO. ID TIME AMT WT APGR DV PRED RES WRES
1 1.00E+00 0.00E+00 2.50E+01 1.40E+00 7.00E+00 0.00E+00
2.00E+00 0.00E+00 1.40E+00 7.00E+00 1.73E+01
1.25E+01 3.50E+00 1.40E+00 7.00E+00 0.00E+00
2.45E+01 3.50E+00 1.40E+00 7.00E+00 0.00E+00 1.78E+01 0.00E+00 0.00E+00
...Figure 10.10. A portion of a NONMEM table.
Each row in the table corresponds to a record of the input file, and the rows appear in the same order as do the corresponding records of the input data file. Note that the values of RES and WRES are always shown as zero for non-observation records, whereas a (possibly) nonzero value of PRED is printed for every record.
If there are more than 900 data records, separate tables are produced for groups of 900 records. The last table contains the remaining records. If the rows of the table are sorted, each group of records is sorted separately. When the input data file is large, the table will require many pages to print. Therefore, the $TABLE record should be omitted unless needed for diagnostic purposes (such as when initially checking a new data set or model).
Strictly speaking, RES and WRES are always zero for records having MDV=1. With PREDPP, this is the same thing.
7.2 Output from the Scatterplot Step
Many examples of scatterplots are present in Chapters 2 and 11. Whereas all the records in the input data file correspond to rows of a table, this is not true of a scatterplot that includes one or more of the items RES, WRES, and DV. When one of these three is being plotted, then only observation records contribute points to the scatterplot. In figure 2.5, there are exactly 10 points “*“, corresponding to the 10 observation records in figure 2.2; the dose record does not contribute a point.
NONMEM displays only the first 900 records of the appropriate type in a scatterplot. This limit applies before any partitioning. For example, in a plot of DV VS ID, the first 900 observation records are displayed; in a plot of WT vs ID, the first 900 records of the data file are displayed. Additional scatterplots can be requested, showing additional points, using options FROM= and TO= of the $SCATTERPLOT record. See NONMEM Users Guide, Part IV.
Strictly speaking, it is only the records having MDV=0 that contribute points. With PREDPP, this is the same thing.