__Title__

**[P] _crcar1** -- Programmer's utility for computing AR(1) rho from
residuals

__Syntax__

**_crcar1** *rho_scalar* *method_macro* **:** *resids_varname* [**,** **k(***#***)** __c__**heck** **dw**
**freg** __nag__**ar** __reg__**ress** __th__**eil** __tsc__**orr** ]

**_crcar1** is for use with time-series data. You must **tsset** your data
before using **_crcar1**; see **[TS] tsset**.

__Description__

**_crcar1** is a programmer support command. It computes the first-order
autocorrelation parameter for a variable (presumably containing
residuals) using any of several estimates of the autocorrelation.

**_crcar1** expects the first argument to be the name of a scalar into which
the value of rho is saved and the second argument to be the name of a
local macro which will be set to the fully expanded name of the method
for computing rho.

__Options__

**check** specifies that rho is not computed, but that the command is simply
checked for syntax and an error reported if the syntax is not proper.

**k(***#***)** specifies the number of parameters estimated in the model. This is
only required for the **theil** and **nagar** options which use **k** to adjust
the degrees of freedom.

The remaining options specify how rho is to be computed; **regress** is the
default.

**regress** rho_reg = B from the residual regression e_t = B * e_(t-1).

**freg** rho_freg = B from the residual regression e_t = B * e_(t+1).

**tscorr** rho_tscorr = e'e_(t-1)/e'e, where e is the vector of residuals.

**dw** rho_dw = 1 - DW / 2.

**theil** rho_theil = rho_tscorr * (N - k) / N.

**nagar** rho_nagar = (rho_dw * N^2 + k^2) / (N^2 - k^2).

__Examples__

**. _crcar1 rho fullopt : my_res**

**. _crcar1 rho fullopt : my_res, theil k(3)**