checkresiduals

If <code>plot=TRUE</code>, produces a time plot of the residuals, the
corresponding ACF, and a histogram. If <code>test</code> is not <code>FALSE</code>,
the output from either a Ljung-Box test or Breusch-Godfrey test is printed.

Methods and tools for displaying and analysing
univariate time series forecasts including exponential smoothing
via state space models and automatic ARIMA modelling.

Rob Hyndman

forecast

Forecasting Functions for Time Series and Linear Models

George Athanasopoulos

Christoph Bergmeir

Gabriel Caceres

Leanne Chhay

Kirill Kuroptev

Mitchell O'Hara-Wild

Fotios Petropoulos

Slava Razbash

Earo Wang

Farah Yasmeen

Federico Garza

Daniele Girolimetto

Ross Ihaka

R Core Team 

Daniel Reid

David Shaub

Yuan Tang

Xiaoqian Wang

Zhenyu Zhou

checkresiduals function

<dl><dt>object</dt>
<dd>Either a time series model, a forecast object, or a time
series (assumed to be residuals).</dd>
<dt>lag</dt>
<dd>Number of lags to use in the Ljung-Box or Breusch-Godfrey test.
If missing, it is set to <code>min(10,n/5)</code> for non-seasonal data, and
<code>min(2m, n/5)</code> for seasonal data, where <code>n</code> is the length of the series,
and <code>m</code> is the seasonal period of the data. It is further constrained to be
at least <code>df+3</code> where <code>df</code> is the degrees of freedom of the model. This
ensures there are at least 3 degrees of freedom used in the chi-squared test.</dd>
<dt>test</dt>
<dd>Test to use for serial correlation. By default, if <code>object</code>
is of class <code>lm</code>, then <code>test="BG"</code>. Otherwise, <code>test="LB"</code>.
Setting <code>test=FALSE</code> will prevent the test results being printed.</dd>
<dt>plot</dt>
<dd>Logical. If <code>TRUE</code>, will produce the plot.</dd>
<dt>...</dt>
<dd>Other arguments are passed to <code>ggtsdisplay</code>.</dd></dl>

Arguments

Author

Check that residuals from a time series model look like white noise — checkresiduals

<dl>

<dt>object</dt>
<dd>Either a time series model, a forecast object, or a time
series (assumed to be residuals).</dd>


<dt>lag</dt>
<dd>Number of lags to use in the Ljung-Box or Breusch-Godfrey test.
If missing, it is set to <code>min(10,n/5)</code> for non-seasonal data, and
<code>min(2m, n/5)</code> for seasonal data, where <code>n</code> is the length of the series,
and <code>m</code> is the seasonal period of the data. It is further constrained to be
at least <code>df+3</code> where <code>df</code> is the degrees of freedom of the model. This
ensures there are at least 3 degrees of freedom used in the chi-squared test.</dd>


<dt>test</dt>
<dd>Test to use for serial correlation. By default, if <code>object</code>
is of class <code>lm</code>, then <code>test="BG"</code>. Otherwise, <code>test="LB"</code>.
Setting <code>test=FALSE</code> will prevent the test results being printed.</dd>


<dt>plot</dt>
<dd>Logical. If <code>TRUE</code>, will produce the plot.</dd>


<dt>...</dt>
<dd>Other arguments are passed to <code>ggtsdisplay</code>.</dd>

</dl>

Check that residuals from a time series model look like white noise

checkresiduals: Check that residuals from a time series model look like white noise

Description

Usage

Value

Arguments

Author

See Also

Examples