Expanded covariance computations

New covariance computations in GAUSS 19.

New covariance computations provide estimates for broader applications.

  • Clustered and heteroscedastic-robust covariance computations.
  • For stand alone use or use with olsmt.
  • Compute outer product of gradients (OPG) covariance after optimization using sqpSolvemt.
// Set up olsmtControl structure
struct olsmtControl oCtl;
ctl = olsmtControlCreate();

// Set up robust SE
ctl.cov = "robust";

// Estimate model
call olsmt("detroit.sas7bdat", "homicide ~ unemployment + hourly_earn", ctl);

        ↓

Valid cases:                   13          Dependent variable:           homicide
Missing cases:                  0          Deletion method:                  None
Total SS:                3221.790          Degrees of freedom:                 10
R-squared:                   0.834         Rbar-squared:                    0.801
Residual SS:              533.814          Std error of est:                7.306
F(2,10):                   25.177          Probability of F:                0.000
Durbin-Watson:              1.407

Standard                                          Prob    Standardized   Cor with
Variable        Estimate    Error     t-value     >|t|      Estimate     Dep Var
----------------------------------------------------------------------------------
CONSTANT       -35.9829   12.2748    -2.9315     0.015        ---          ---
unemployment    -0.0050    0.6034    -0.0083     0.994    -0.000720     0.210142
hourly_earn     15.4872    1.9391     7.9870     0.000     0.913572     0.913406

Note: Robust standard errors reported

Have a Specific Question?

Get a real answer from a real person

Need Support?

Get help from our friendly experts.