Declare an object by entering the keyword model, followed by a name:

declares an empty model named MYMOD. To fill MYMOD, open the model and edit the specification view, or use the append view. Note that models are not used for estimation of unknown parameters.

See also the section on model keywords in “Text View”.

The commands:

create, specify, and solve the model MOD1.

The command:

plots the endogenous series X, Y, and Z, in the active scenario for model MOD1.

where equation_spec identifies the equations for which you wish to assign add factors. You may either provide a list of endogenous variables, or you can use one of the following shorthand keywords:

The options identify the type of add factor to be used, and control the assignment behavior for equations where you have previously assigned add factors. addassign may be called multiple times to add different types of add factors to different equations. addassign may also be called to remove existing add factors.

assigns a variable shift to all equations in the model.

changes the stochastic equation add factors to intercept shifts.

assigns variable shifts to the stochastic equations and the equations for Y1, Y2, and Y3, and assigns intercept shifts to the identities.

See “Using Add Factors”. See also “Models” for a general discussion of models.

See Model::addinit.

where equation_spec identifies the equations for which you wish to initialize the add factors. You may either provide a list of endogenous variables, or you may use one of the following shorthand keywords:

The options control the type of initialization and the scenario for which you want to perform the initialization. addinit may be called multiple times to initialize various types of add factors in the different scenarios.

sets all of the add factors in the active scenario to the values of the baseline.

first sets the active scenario stochastic equation add factors to zero, and then sets the Y1, Y2, and Y3 equation residuals to zero (evaluated at actuals).

sets the baseline scenario add factors to zero.

See “Using Add Factors”. See also “Models” for a general discussion of models.

See also Model::addassign.

Set the active scenario add factor overrides.

overrides the active scenario’s add factors.

See “Models” for a discussion of specifying and solving models in EViews. See also Model::append, Model::merge and Model::solve.

The adjust proc allows you to adjust the values of the series ser in the current scenario. If the series is an exogenous variable, it will be added to the override list. If the series is an endogenous variable it will be added to both the excluded list and the override list.

If an array expression is provided, the overridden series will be modified according to the expression specification. Note that a transform may optionally be provided as part of the variable name using the syntax: transform(varname).

If you use an array expression which applies an operator to existing series values the overriden series must already exist in the workfile, unless the init option is used.

simply sets the variable GDP as an overriden variable in the current scenario. If GDP is endogenous, it is also added to the exclude list.

sets the current scenario as “SIM1”, with an alias of _1, and then overrides the variable GDP, setting the override series, GDP_1, equal to the previous values in GDP_1 plus 10.

performs the same operation, but rather than using the previous values in GDP_1 for the array expression, the values in GDP_2 (corresponding to the scenario SIM2) are used.

See “Models” for a discussion of specifying and solving models in EViews. See also the discussion in “Specifying Scenarios”.

See Model::scenario and Model::compare.

Type the text to be added after the append keyword.

The first line declares a model object. The second and third lines merge existing equations into the model. The fourth and fifth line appends an assign statement and a trace of GDP to the model. The last line solves the model.

For details, see “Models”.

Show the block structure of the model, identifying which blocks are recursive and which blocks are simultaneous.

See “Block Structure View” for details. “Models” provides a general discussion of models.

See also Model::eqs, Model::text and Model::vars for alternative representations of the model.

Show a display of any series that have crossed their set boundaries during a solve.

See “Block Structure View” for details. “Models” provides a general discussion of models.

See also Model::setboundsl.

Removes the model’s history attribute, as shown in the label view of the model.

The first line removes the history from the model M1, and the second line displays the label view of M1, including the now blank history field.

See “Labeling Objects” for a discussion of labels and display names.

See also Model::label.

Removes the model’s remarks attribute, as shown in the label view of the model.

The first line removes the remarks from the model M1, and the second line displays the label view of M1, including the now blank remarks field.

See “Labeling Objects” for a discussion of labels and display names.

See also Model::label.

The compare view allows you to quickly compare the results from different scenarios (or the actual values) following a model solve. By default the output table will show any of the series specified in model_vars whose difference between the current active and comparison scenarios exceeds a specified tolerance. You may optionally use the “patt=” option to specify a separate set of comparison series from those in the current comparison scenario.

The list of model_vars may include the following special keywords:

The first two lines of this example set the current active scenario “Scenario0”, and set the comparison scenario to “Scenario1”, with a name alias of “_1”. The model is then solved for both scenarios. The compare command is used to produce a table detailing the differences between the two scenarios for the three variables GDP, UNEMP and INFL. Any differences between the solved series GDP_0 and GDP_1, UNEMP_0 and UNEMP_1 or INFL_0 and INFL_1 greater than 0.001 will be shown in the table.

produces the same table, but uses a lower tolerance rate (of 0.00001).

produces a table comparing all endogenous variables in the model, not just GDP, UNEMP and INFL.

produces a table that compares GDP_0 with GDP_2, UNEMP_0 with UNEMP_2 and INFL_0 with INFL_2, even though the current comparison scenario is still “Scenario1”.

See “Models” for a discussion of specifying and solving models in EViews. See also, the discussion in “Specifying Scenarios”.

See Model::scenario and Model::adjust.

The controls, targets, and trajectories parameters are all lists of variable/series names, which may comprise any combination of individual series or group object names. The controls should be exogenous variables and the targets endogenous variables, with the trajectories being arbitrary series. An equal number of control, target, and trajectory series must be specified. These three lists do not need to be ordered strictly as above; they may be interleaved or kept together in blocks. For example, any of the following arrangements of the six arguments for a two-variable control would be acceptable: Examples

The solved values overwrite the original control series unless the ‘create’ or ‘csuffix’ option is specified. When the names for target and trajectory series share a common base, the ‘tsuffix’ option may be used to abridge the parameter list.

will alter the values of exogenous variable MYVAR such that the model solution will produce values for endogenous variable TARGETVAR to match series TRAJVAR over the current workfile sample.

will determine the values of exogenous variables ISAV and IRTN such that the model solution will produce values for endogenous variables FTOT and GTOT that match series FTOT_TR and GTOT_TR, respectively. Assuming the current model scenario suffix is _0, the control values will be stored in series named ISAV_0 and IRTN_0.

similar to the previous example, but the trajectory series names are implicitly defined as the target names appended with the _tr suffix, i.e., FTOT_TR and GTOT_TR.

See “Solve Control for Target”. See “Models” for a general discussion of models.

Creates either a named or unnamed copy of the model.

creates an unnamed copy of the model M1.

creates M2, a copy of the model M1.

See also copy.

Display the contents of a table, graph, or spool in the window of the model object.

Display the contents of the table TAB1 in the window of the object MODEL1.

Most often used in constructing an EViews Add-in. See “Custom Object Output”.

Attaches a display name to a model object which may be used in place of the standard model object name.

Display names are case-sensitive, and may contain a variety of characters, such as spaces, that are not allowed in model object names.

The first line attaches a display name “Sept 2006” to the model object MOD1, and the second line displays the label view of MOD1, including its display name.

See “Labeling Objects” for a discussion of labels and display names.

See also Model::label.

Where var_list is a space delimited list of variables whose equations will be dropped from the model. By default if a variable is contained in a multi-equation object, such as a system, VAR or model, the entire object will be dropped, which will also drop the specification for the other variables defined in that object.

will drop the equation/object which has GDP as a dependent variable from the model M1.

will drop the equations which have GDP or UNEMP as dependent variables. Systems, VARs, models, etc… will not be dropped.

Where obj_list is a space delimited list of objects to be dropped from the model.

will drop the equation EQ1 and the model MOD1 from the model M1.

Note that endog and makeendog are no longer supported for model objects. See instead, Model::makegroup.

Lists the equations in the model. This view also allows you to identify which equations are entered by text, or by link, and to access and modify the equation specifications.

See “Equation View” for details. See “Models” for a general discussion of models.

See also Model::block, Model::text, and Model::vars for alternative representations of the model.

Follow the exclude keyword with the argument list containing the endogenous variables you wish to exclude from the solution, along with an optional sample for exclusion. If a sample is not provided, the variable will be excluded for the entire solution sample.

will create an exclude list containing the variables FEDFUNDS and GOVEXP. FEDFUNDS will be excluded for the entire solution sample, while GOVEXP will only be excluded for the specified sample.

If you then issue the command:

EViews will replace the original exclude list with one containing only GOVEXP. To add excludes to an existing list, use the “m” option:

The excluded list now contains both GOVEXP and FEDFUNDS.

instructs EViews to keep all existing excludes (the “m” option) in the current active scenario and in addition to exclude all endogenous variables in periods where actuals exist.

See the discussion in “Specifying Scenarios”.

See also Model::override, Model::reinclude, and Model::solveopt.

visualizes the dependencies among the model's variables as a directed graph.

See “Dependency Graph View” for further details on the model dependency graph.

The variables parameter is a list of endogenous and exogenous variables in any order. Group objects may be included in the list. An equal number of endogenous and exogenous variables must be specified. Each listed endogenous variable will be made exogenous and each listed exogenous variable will be made endogenous by rewriting a number of the model’s equations. The number of equations modified will be at least the number of endogenous/exogenous variables specified, e.g., flipping a set of three endogenous and three exogenous variables will require at least three equations to be modified. All modified equations will have any associated add factor or innovation variance dropped from their specification (see the af2exog option below). The optional @lock clause can be used to prevent the modification of any equation whose endogenous variable is listed in fixed-variables. Inclusion of the optional @lockafs or @lockinnovs tags indicates that all equations with either add factors or innovations variances, respectively, should not be modified.

will flip the endogenous/exogenous role of variables VAR1 and VAR2 in the model by rewriting the model’s equations. For example, if VAR1 is initially endogenous and VAR2 is initially exogenous, the procedure will rewrite the equations of the model so that VAR2 becomes endogenous (the first left-hand side variable of some equation) and VAR1 becomes exogenous (not the first left-hand side variable of any equation). The role of all other variables in the model is unchanged.

See “Solve Control for Target”. See “Models” for a general discussion of models.

See also Model::undoflip.

Follow the innov keyword with a list of model variables and options. If the variable is an endogenous variable (or add factor), it identifies a model equation and will use different options than an exogenous variable.

specifies that the endogenous variable GDP be treated as an identity in stochastic solution.

indicates that the endogenous variable CONS is stochastic with standard error equal to 5600, GDP is an identity, and CPI is stochastic with unknown innovation variance.

specifies that the forecast standard error of the exogenous variable GOVEXP is 12210.

See the discussion in “Stochastic Options”.

See also Model::model, Model::stochastic, and Model::solve.

As a procedure, label changes the fields in the model object label.

The first version of the command displays the label view of the model. The second version may be used to modify the label. Specify one of the following options along with optional text. If there is no text provided, the specified field will be cleared.

The following lines replace the remarks field of M1 with “Data from CPS 1988 March File”:

To append additional remarks to M1, and then to print the label view:

To clear and then set the units field, use:

See “Labeling Objects” for a discussion of labels.

See also Model::displayname.

Note that in endog and makeendog are no longer supported for model objects. See instead, Model::makegroup.

where graph_name is the name of the resulting graph object, and models_vars are the names of the series. The list of model_vars may include the following special keywords:

creates a graph containing the model series Y1, Y2, and Y3 in the active scenario and the actual Y1, Y2, and Y3.

plots the same graph, but with data displayed as 1-year percent changes.

See “Displaying Data” for details. See “Models” for a general discussion of models.

See Model::makegroup.

The makegroup keyword should be followed by options, the name of the destination group, and the list of model variables to be created. The options control the choice of model series, and transformation and grouping features of the resulting dated data table view. The list of model_vars may include the following special keywords:

places all of the actual endogenous series in the group group1.

See “Displaying Data” for details. See “Models” for a general discussion of models.

See also Model::makegraph.

If you supply only the object’s name, EViews first searches the current workfile for the object containing the equation. If the object is not found, EViews looks in the default directory for an equation or pool file (.DBE). If you want to merge the equations from a system file (.DBS), a var file (.DBV), or a model file (.DBL), include the extension in the command and an optional path when merging files. You must merge objects to a model one at a time; merge appends the object to the equations already existing in the model.

Follow the keyword with a name of an object containing estimated equation(s) to merge.

The first line makes a model named MOD1 from EQ1. The second line merges (appends) EQ2 to MOD1 and the third line further merges (appends) the text file TEST from the specified directory.

The keyword model should be followed by a name for the model. To fill the model, you may use Model::append or Model::merge.

declares an empty model named MACRO and adds three lines to MACRO.

See “Models” for a discussion of specifying and solving models in EViews.

See also Model::append, Model::merge and Model::solve.

Show view containing messages generated by the most recent model solution.

See “Models” for a discussion of specifying and solving models in EViews.

See also Model::solve and Model::solveopt.

See “Object Linking and Embedding (OLE)” for a discussion of using OLE with EViews.

Follow the keyword with the argument list containing the exogenous variables or add factors you wish to override.

creates an override list containing the variables FED1 and ADD1.

If you then issue the command:

EViews will replace the original exclude list with one containing only FED1. To add overrides to an existing list, use the “m” option:

The override list now contains both series.

See the discussion in “Specifying Scenarios”. See also “Models” for a general discussion of models.

See Model::exclude. Model::scenario and Model::revert.

Show enhanced display of the model specification.

displays the model with broken links, identities, and @innov statements.

displays numeric values with three significant digits.

See “Print View” for a discussion

See also Model::text.

The specified variables are removed from the current active scenario’s exclude list, and generates an add factor for each variable so that the solution for the current scenario remains unchanged.

removes both X and Z from the exclude list in the current scenario, and creates add factors for each.

See “Models” for a discussion of specifying and solving models in EViews.

See also Model::exclude.

The replace command will only replace the specification for variables that currently have a text specification in the model. Variables defined by a linked object cannot have their specification replace. New_specification should be the new text specification for the variable. Note EViews will automatically detect the endogenous variable in the new specification, even if it is contained in an implicit expression, and will replace the existing specification for that variable.

this trivial example first creates a model, M1, then adds a text specification for the variable X, setting it equal to 3*Y.  It then changes the specification for X to set it equal to 4*Y.

this example replaces the specification for X by setting the log of X equal to 4*Y.

old_obj should be the name of an object currently linked inside the model. That object will be removed from the model and replaced with the new object, new_obj.

replaces the linked equation, EQ1, with a different equation, EQ1_NEW.

See also Model::append, Model::replace and Model::replacevar.

replacevar can only replace variables defined by a text specification inside the model. It will not replace variables contained inside linked objects. Note that replacevar does not do a simple text substitution, and is capable of determining full variable names from other pieces of text.

this example creates a model, M1, and adds a text specification for the variable Y, setting it equal to 3*X. It then replaces all occurrences of X with Z, changing the specification of Y to be equal to 3*Z.

this example generates a specification for Y, setting it equal to 3 times the log of the twice lagged value of X, and a specification for W, setting it equal to 4 times X1.  It then replaces all instances of the variable X with the variable Z, changing the specification of Y to be equal to 3 times the log of twice lagged Z.  Note that the specification of W does not change, since X1 is a different variable from X.

See also Model::append, Model::replacelink and Model::replacevar.

The specified variables will be removed from the override and exclude list of this scenario, and the associated overridden series in the workfile will be deleted.

If an asterisk is provided for the variable name, all overridden series in the active model scenario will be reverted.

removes X and Z from the override list in the current scenario.

See also Model::override, Model::exclude, and Model::scenario.

The scenario procedure is used to set the active and comparison scenarios for a model, to create new scenarios, to initialize one scenario with settings from another scenario, to delete scenarios, and to change the variable aliasing associated with a scenario.

performs scenario options on a scenario given by the specified name (entered in double quotes). By default the scenario procedure also sets the active scenario to the specified name.

The command string,

sets the active scenario to the baseline, while:

sets the comparison scenario to the actuals (warning: this action will overwrite any historical data in the solution period).

A newly created scenario will become the active scenario. Thus:

creates a scenario called “Peace Scenario” and makes it the active scenario. The scenario will automatically be assigned a unique numeric alias. To change the alias, simply use the “a=” option:

changes the alias for “Peace Scenario” to “_PS” and makes this scenario the active scenario.

The command:

creates a scenario called “War Scenario”, initializes it with the Excludes and Overrides contained in “Peace Scenario”, associates it with the alias “_W”, and makes this scenario the comparison scenario.

copies the Excludes and Overrides in “Scenario 1” to “Scenario 2” and makes “Scenario 2” the active scenario.

For backward compatibility with EViews 4, the single character option “a” may be used to set the comparison scenario, but future support for this option is not guaranteed.

In all of the arguments above the quotation marks around scenario name are currently optional. Support for the non-quoted names is provided for backward compatibility, but may be dropped in the future, thus

is currently valid, but may not be in future versions of EViews.

Scenarios are described in detail in “Specifying Scenarios”. “Models” documents EViews models.

See also Model::solve.

displays the list of scenarios view of the object MODEL1.

See “Scenario List” for further details on the scenario list view.

See also Model::scenario.

Sets the attribute attr to attr_value. Note that quoting the arguments may be required. Once added to an object, the attribute may be extracted using the @attr data member.

sets the “revised” attribute in the object A to the string “never”, and extracts the attribute into the string object S.

See “Adding Custom Attributes in the Label View” and “Adding Your Own Label Attributes”.

EViews will warn if any variable’s solved for value is higher than the upper bound or less than the lower bound for any observation during the solve.

specifies a lower bound of 0 and 1,000 for GDP and the series bounds UN_LOWER and UN_HIGHER for UNEMP in model MODEL01.

See “Boundaries” for details.

See also Model::boundscheck.

Specifies the endogenous variables for which you wish to keep intermediate calculations at the next deterministic simulation. The intermediate results of all traced variables will be part of the model solution output. Tracing intermediate values may give you some idea of where to look for problems when a model is generating errors or failing to converge.

If the endogenous_list of variables is omitted, settrace clears out the existing trace specification.

specifies that GDP, CONS, INTEREST, and CPI should be traced at the next simulation.

If you then issue the command:

EViews will clear the trace list.

See the discussion in “Diagnostics”.

See also Model::trace and Model::track.

solve finds the solution to a simultaneous equation model for the set of observations specified in the current workfile sample.

Note: when solve is used in a program (batch mode) models are always solved over the workfile sample. If the model contains a solution sample, it will be ignored in favor of the workfile sample.

You should follow the name of the model after the solve command. The default solution method is dynamic simulation. You may modify the solution method as an option.

solve first looks for the specified model in the current workfile. If it is not present, solve attempts to fetch a model file (.DBL) from the default directory or, if provided, the path specified with the model name.

solve can take any of the options available in Model::solveopt. Stochastic solution options should be set using Model::stochastic.

solves the model MOD1 using the default solution method.

solves the model NONLIN2 with an extended search of up to 500 iterations.

See “Models” for a discussion of models.

See also Model::model, Model::msg, Model::solveopt, and Model::stochastic.

solveopt sets options for model solution but does not solve the model. The same options can be set directly in a solve procedure.

See “Models” for a discussion of models.

See also Model::model, Model::msg, and Model::solve. Stochastic solution options should be set using Model::stochastic.

displays the specification of the object MODEL1.

See also Model::append, Model::merge, Model::printview.

stochastic sets options for stochastic model solution but does not solve the model.

Note that these options have no effect on the current solve if deterministic solution has been selected.

See “Models” for a discussion of models. See Model::innov to set options on individual series in stochastic solution.

See also Model::model, Model::solve and Model::solveopt.

The text command is equivalent to Model::spec.

displays the text representation of the object MODEL1.

See “Models” for further details on models.

See also Model::printview.

See “Diagnostics” for further details on tracing model solutions.

See also Model::msg, Model::solve and Model::solveopt.

Sets the list of endogenous variables that will be tracked at the next simulation. Results of all tracked endogenous variables will be part of the model solution output.

Specify a list of endogenous variables to be tracked. You may use @all to track all endogenous variables.

specifies that GDP, CONS, INTEREST, and CPI should be tracked at the next simulation.

tracks all endogenous variables at the next simulation.

See also Model::model and Model::trace.

If the model was previously altered by an invocation of the fliptype procedure, then the model's specification is reverted to its prior/unaltered state. Other model changes that may have been made in the intervening time, such as changes to its scenarios, are not affected by this procedure. This procedure provides only one level of undo (multiple invocations of fliptype cannot be undone) and the undo capability is only available until the workfile is closed (saving and reopening a workfile will not allow alterations from a previous session to be undone).

The endogenous/exogenous usage of variables VAR1 and VAR2 is flipped and the model then solved for the new set of endogenous variables. The changes made by fliptype are then undone, restoring the original endogenous/exogenous usage of variables VAR1 and VAR2.

See Model::fliptype.

unlink breaks equation links in the model. Follow the name of the model object by a period, the keyword, and a specification for the variables to unlink.

The spec may contain either a list of the endogenous variables to be unlinked, the name of an estimation object, or the keyword “@ALL”, instructing EViews to unlink all equations in the model.

Note: if a link is to another model or a system object, more than one endogenous variable may be associated with the link. If the spec contains any of the endogenous variables in a linked model or system, EViews will break the link for all of the variables found in the link.

The expressions:

unlink all of equations in MOD1, and all of the variables associated with the links for Z1 and Z2 in MOD2.

See “Models” for a discussion of specifying and solving models in EViews. See also Model::append, Model::merge and Model::solve.

Recompiles the model and updates links.

Follow the name of the model object by a period the keyword update, and optionally a list of estimation objects to update. If no argument is provided, every object is updated.

recompiles and updates all of the links in MOD1.

updates the links to equation objectEQ01 and VAR object VAR01.

See “Models” for a discussion of specifying and solving models in EViews. See also Model::append, Model::merge and Model::solve.

Display the model in variable form with identification of endogenous, exogenous, and identity variables, with dependency tracking.

See “Variable View” for details. See “Models” for a general discussion of models.

See also Model::block, Model::text, and Model::eqs for alternative representations of the model.