aStep2

Derives the set of observation numbers for forsearch in Step 2 for linear models

 manip 

Identifies potential data outliers and their impact on estimates and
analyses. Tool for evaluation of study credibility. Uses the forward
search approach of Atkinson and Riani, "Robust Diagnostic Regression
Analysis", 2000,<ISBN: o-387-95017-6> to prepare descriptive statistics
of a dataset that is to be analyzed by functions lm {stats}, glm {stats},
nls {stats}, lme {nlme}, or coxph {survival}, or their equivalent in
another language. Includes graphics functions to display the
descriptive statistics.

William Fairweather

forsearch

Diagnostic Analysis Using Forward Search Procedure for Various
Models

aStep2 function

<dl> <dt>yesfactor</dt>
<dd>True or False for presence of factors</dd> <dt>form.A2</dt>
<dd>Formula for analysis of entire dataset</dd> <dt>finalm</dt>
<dd>See VALUE above. finalm argument is the same but only for Step 1 values</dd> <dt>rimbs</dt>
<dd>List, each element is a matrix of obs numbers and corresponding subset codes</dd> <dt>onlyfactor</dt>
<dd>Logical. TRUE if there are no continuous independent variables 
 in the model</dd> <dt>dfa2</dt>
<dd>Data frame being analyzed by forward search. Presence of Observation column has
 no effect on output</dd> <dt>finalm.ls</dt>
<dd>List showing finalm separated into factor subsets</dd> <dt>ycol</dt>
<dd>Response column number, including 1 for Observation</dd> <dt>mstart</dt>
<dd>Number of first subset to be defined in Step 2</dd> <dt>rnk</dt>
<dd>Rank of X matrix. For factors, this is rank with factors removed.</dd> <dt>b.d</dt>
<dd>Number at which to begin diagnostic listings</dd></dl>

Arguments

Author

Update Observation Set in Step 2 — aStep2

<dl>

 <dt>yesfactor</dt>
<dd>True or False for presence of factors</dd>

 <dt>form.A2</dt>
<dd>Formula for analysis of entire dataset</dd>

 <dt>finalm</dt>
<dd>See VALUE above. finalm argument is the same but only for Step 1 values</dd>

 <dt>rimbs</dt>
<dd>List, each element is a matrix of obs numbers and corresponding subset codes</dd>

 <dt>onlyfactor</dt>
<dd>Logical. TRUE if there are no continuous independent variables 
 in the model</dd>

 <dt>dfa2</dt>
<dd>Data frame being analyzed by forward search. Presence of Observation column has
 no effect on output</dd>

 <dt>finalm.ls</dt>
<dd>List showing finalm separated into factor subsets</dd>

 <dt>ycol</dt>
<dd>Response column number, including 1 for Observation</dd>

 <dt>mstart</dt>
<dd>Number of first subset to be defined in Step 2</dd>

 <dt>rnk</dt>
<dd>Rank of X matrix. For factors, this is rank with factors removed.</dd>

 <dt>b.d</dt>
<dd>Number at which to begin diagnostic listings</dd>

</dl>

aStep2: Update Observation Set in Step 2

Description

Usage

Value

Arguments

Author

Details