^ help on INFLOGIT.ADO
Joseph Hilbe, CRC/STB    9/25/91

syntax:

      logiodd2 <response> <varlist> if [exp] in [range], ^i 
      

^inflogit.ado^ provides an ^i^ option to the ^logiodd2.ado^ command.
The option provides m-asymptotic influence statistics following
Hosmer & Lemeshow, Applied Logistic Regression, John Wiley & Sons, 1989. 

A covariate pattern represents the constitution of the respective
independent variable values. For example, the data set

                    y     x1  x2  x3

                    1     1    0   1
                    1     1    1   0
                    0     0    1   1
                    0     1    0   1
                    1     1    1   0


consists of five observations but of only three covariate patterns.
H & L influence statistics are concerned with covariate patterns;
specifically the number of such patterns in the data set, the
number of observations sharing the same covariate pattern, and the
number of positive responses within each pattern.

Hosmer & Lemeshow suggest the following four diagnostic plots:

. gr deltax pred, xlab ylab yline(4)
. gr deltad pred, xlab ylab yline(4)
. gr deltab pred, xlab ylab yline(1)
. gr deltax pred=deltab, xlab ylab yline(4)

Observations or covariate patterns whose values exceed the yline
are considered significantly influential.

^An Example

Hosmer & Lemeshow present a full model example based upon a study 
of low birth weight babies. The following is the command and part 
of the output.


. logiodd2 low age race2 race3 smoke ht ui lwd ptd inter1 inter2, i

         [ ODDS RATIO STATISTICS NOT SHOWN ]


Number of Predictors         =        10
Number of Non-Missing Obs    =       189
Number of Covariate Patterns =       128
Pearson X2 Statistic         =       137.7503
  P>chi2(117)                =         0.0923
Deviance                     =       147.3371
  P>chi2(117)                =         0.0303


Additional diagnostic variables created...
    logindex =  Logit; Index value
    sepred   =  Standard error of index
    pred     =  Probability of success (1)
    mpred    =  Prob of covariate pattern success
    presid   =  Pearson Residual
    stpesid  =  Standardized Pearson Residual
    hat      =  Hat matrix diagonal
    dev      =  Deviance
    cook     =  Cook's distance
    deltad   =  Change in Deviance
    deltax   =  Change in Pearson chi-square
    deltab   =  Difference in coefficient due to
                deletion of observation and others
                sharing same covariate pattern