Two-Stage Least Squares :: SAS(R) Studio 3.5: Task Reference Guide

Example: Two-Stage Least Squares

To create this example:

In the Tasks section, expand the Econometrics folder, and then double-click Causal Models. The user interface for the Causal Models task opens.
On the Data tab, select the SASHELP.PRICEDATA data set.

Tip
If the data set is not available from the drop-down list, click . In the Choose a Table window, expand the library that contains the data set that you want to use. Select the data set for the example and click OK. The selected data set should now appear in the drop-down list.

Assign columns to these roles:

Role	Column Name
Dependent variable	sale
Exogenous explanatory variables	price
Endogenous explanatory variables	cost
Excluded instrumental variables	price1 price2

To run the task, click .

Here is a subset of the results:

Assigning Data to Roles

To perform a two-stage least squares analysis, you must assign an input data set. To filter the input data source, click Filter Icon

.

You also must assign variables to the Dependent variable, Exogenous explanatory variables, Endogenous explanatory variables, and Excluded instrumental variables roles. The number of variables that you assign to the Excluded instrumental variables role must be greater than or equal to the number of endogenous explanatory variables.

Role	Description
Roles
Dependent variable	specifies the dependent variable for the equation. The equation is in this format:. In this equation: y₁ is the dependent variable. y₂ and y₃ are endogenous explanatory variables. x₁ and x₂ are exogenous explanatory variables.
Exogenous explanatory variables	specifies a factor in the model whose values are not determined by the states of other variables in the system.
Endogenous explanatory variables	specifies a factor in the model whose values are determined by the states of other variables in the system.
Excluded instrumental variables	specifies the variables not to include in the equation.
Additional Roles
Group analysis by	enables you to obtain separate analyses of observations for each unique group.

Setting Options

Option	Description
Methods
Optimization method	specifies the optimization method to use. You can use the default method, or you can choose from these methods: Gauss-Newton Marquardt-Levenberg
Maximum number of iterations	specifies the maximum number of iterations for the selected method. You can use the default value or specify a custom value.
Statistics
You can specify whether the results include the statistics that the task creates by default, the default statistics and any additional statistics that you select, or no statistics. Here are the additional statistics that you can include in the results: correlations of the parameter estimates covariances of the parameter estimates iteration history of the objective function and parameter estimates
Plots
By default, a plot of the predicted and actual values is included in the results. You can choose to display all of the plots, selected additional plots, or no plots. You can include these additional plots in the results: autocorrelation plot inverse autocorrelation of residuals partial autocorrelation of residuals QQ plot of residuals residuals studentized residuals histogram of residuals

Creating the Output Data Sets

You can create a data set that contains the parameter estimates from the analysis.