tssmooth_shwinters.hlp

是一个经济学管理应用软件 很难找的 但是经济学学生又必须用到

{smcl}
{* 09mar2005}{...}
{cmd:help tssmooth shwinters}{right:dialog:  {bf:{dialog tssmooth_shwinters:tssmooth shwinters}}}
{hline}

{title:Title}

{p2colset 5 32 34 2}{...}
{p2col :{hi:[TS] tssmooth shwinters} {hline 2}}Holt-Winters seasonal smoothing{p_end}
{p2colreset}{...}


{title:Syntax}

{p 8 30 2}
{cmd:tssmooth} {opt s:hwinters} {dtype} {newvar} {cmd:=} 
  {it:{help exp}} {ifin} [{cmd:,} {it:options}]

{synoptset tabbed}{...}
{synopthdr}
{synoptline}
{syntab:Main}
{synopt :{cmd:replace}}replace {newvar} if it already exists{p_end}
{synopt :{opt p:arms(#a #b #g)}}use {it:#a}, {it:#b}, and {it:#g} as smoothing parameters{p_end}
{synopt :{opt sa:mp0(#)}}use {it:#} observations to obtain initial values for
  recursions{p_end}
{synopt :{cmd:s0(}{it:#}cons {it:#}1t{cmd:)}}use {it:#}cons and {it:#}lt as initial values for
  recursions{p_end}
{synopt :{opt f:orecast(#)}}use {it:#} periods for the out-of-sample
  forecast{p_end}
{synopt :{opt per:iod(#)}}use {it:#} period of the seasonality{p_end}
{synopt :{opt add:itive}}use additive seasonal Holt-Winters method{p_end}

{syntab:Options}
{synopt :{opth sn0_0(varname)}}use initial seasonal values in {it:varname}{p_end}
{synopt :{opth sn0_v(newvar)}}store estimated initial values for seasonal
  terms in {it:newvar}{p_end}
{synopt :{opth snt_v(newvar)}}store final year's estimated seasonal terms in
  {it:newvar}{p_end}
{synopt :{opt n:ormalize}}normalize seasonal values{p_end}
{synopt :{opt alt:starts}}use alternative method for computing the starting
values{p_end}

{syntab:Max options}
{synopt :{it:{help tssmooth shwinters##maximize_options:maximize_options}}}control the maximization process; seldom used{p_end}
{synopt :{opt fr:om(#a #b #g)}}use {it:#a}, {it:#b}, and {it:#g} as starting values for the parameters{p_end}
{synoptline}
{p2colreset}{...}
{p 4 6 2}You must {helpb tsset} your data before using 
{cmd:tssmooth shwinters}.{p_end}
{p 4 6 2}{it:{help exp}} may contain time-series operators; see 
{help tsvarlist}.{p_end}


{title:Description}

{pstd}
{cmd:tssmooth shwinters} performs the seasonal Holt-Winters method on a
user-specified expression, which is usually just a variable name, and
generates a new variable containing the forecasted series.


{title:Options}

{dlgtab:Main}

{phang}
{opt replace} replaces {newvar} if it already exists.

{phang}
{opt parms(#a #b #g)}, 
{bind:0 {ul:<} {it:#a} {ul:<} 1, 0 {ul:<} {it:#b} {ul:<} 1}, and 
{bind:0 {ul:<} {it:#g} {ul:<} 1}, specifies the parameters.  If
{opt parms()} is not specified, the values are chosen by an iterative process
to minimize the in-sample sum-of-squared prediction errors.

{pmore}
If you experience difficulty converging (many iterations and "not concave"
messages), try using {opt from()} to provide better starting values.

{phang}
{opt samp0(#)} and {cmd:s0(}{it:#}cons {it:#}lt{cmd:)} have to do with how the
initial values {it:#}cons and {it:#}lt for the recursion are obtained.

{pmore}
{cmd:s0(}{it:#}cons {it:#}lt{cmd:)} specifies the initial values to be used.

{pmore}
{opt samp0(#)} specifies that the initial values be obtained using the first
{it:#} observations of the sample.  This calculation is described under
Methods and Formulas of {hi:[TS] tssmooth shwinters} and depends on
whether options {cmd:altstart} and {cmd:additive} are also specified

{pmore}
If neither option is specified, the first half of the sample is used to obtain
initial values.

{phang}
{opt forecast(#)} specifies the number of periods for the out-of-sample
prediction.  {bind:0 {ul:<} {it:#} {ul:<} 500}.  The default is 0, which is
equivalent to not performing an out-of-sample forecast.

{phang}
{opt period(#)} specifies the period of the seasonality.  If {opt period()} is
not specified, the seasonality is obtained from the {helpb tsset} options 
{opt daily}, {opt weekly}, ..., {opt yearly}.  If you did not specify one of
those options when you {cmd:tsset} the data, you must specify the 
{opt period()} option.  For instance, if your data is quarterly and you did
not specify {cmd:tsset}'s {opt quarterly} option, you must now specify 
{cmd:period(4)}.

{pmore}
By default, seasonal values are calculated, but you may specify the initial
seasonal values to be used via the {opth sn0_0(varname)} option.  The first
{opt period()} observations of {it:varname} are to contain the initial
seasonal values.

{phang}
{opt additive} uses the additive seasonal Holt-Winters method instead of the
default multiplicative seasonal Holt-Winters method.

{dlgtab:Options}

{phang}
{opth sn0_0(varname)} specifies the initial seasonal values to use.
{it:varname} must contain a complete year's worth of seasonal values,
beginning with the first observation in the estimation sample.  For example,
if you have monthly data, the first 12 observations of {it:varname} must
contain nonmissing data.  {opt sn0_0()} cannot be used with {opt sn0_v()}.

{phang}
{opth sn0_v(newvar)} stores in {it:newvar} the initial seasonal values after
they have been estimated.  {opt sn0_v()} cannot be used with {opt sn0_0()}. 

{phang}
{opth snt_v(newvar)} stores in {it:newvar} the seasonal values for the final
year's worth of data.

{phang}
{opt normalize} specifies that the seasonal values be normalized.  In the
multiplicative model, they are normalized to sum to one.  In the additive
model, the seasonal values are normalized to sum to zero.

{phang}
{cmd:altstarts} uses an alternative method to compute the starting values for
the constant, the linear, and the seasonal terms.
The default and the alternative methods
are described in Methods and Formulas of {hi:[TS] tssmooth shwinters}.
{cmd:altstarts} may not be specified with {cmd:s0()}.

{dlgtab:Max options}

{phang}
{marker maximize_options}{...}
{it:maximize_options} controls the process for solving for the optimal alpha,
beta, and gamma when {opt parms()} is not specified.

{pmore}
{it:maximize_options:} {opt nodif:ficult}, {opt tech:nique(algorithm_spec)},
{opt iter:ate(#)}, [{cmd:{ul:no}}]{opt lo:g}, {opt tr:ace},
{opt grad:ient}, {opt showstep}, {opt hess:ian}, {opt shownr:tolerance},
{opt tol:erance(#)}, {opt ltol:erance(#)},
{opt gtol:erance(#)}, {opt nrtol:erance(#)}, {opt nonrtol:erance}, see
{help maximize}.  These options are seldom used.

{pmore}
{opt from(#a #b #g)}, 0 < {it:#a} < 1, 0 < {it:#b} < 1, and 0 < {it:#g} < 1,
specifies starting values from which the optimal values of alpha, beta, and
gamma will be obtained.  If {opt from()} is not specified,
 {cmd:from(.5 .5 .5)} is used.


{title:Examples}

{psee}{cmd:. tssmooth shwinters shw1 = sales, parms(.3 .2)}

{psee}{cmd:. tssmooth shwinters shw2 = sales, forecast(4) period(4)}


{title:Also see}

{psee}
Manual:  {bf:[TS] tssmooth shwinters}

{psee}
Online:  {helpb arima}, {helpb egen}, {helpb generate},
{helpb tsset}, {helpb tssmooth dexponential}, {helpb tssmooth exponential},
{helpb tssmooth hwinters}, {helpb tssmooth ma}, {helpb tssmooth nl}
{p_end}