You are here

mxBootstrapEvalByName() bug?

2 posts / 0 new
Last post
dtofighi's picture
Offline
Joined: 10/12/2009 - 14:55
mxBootstrapEvalByName() bug?

Hello,

It appears that the argument bq in mxBootstrapEvalByName() function does not accept new probabilities and only computes the default probabilities. To show, I am pasting below a self-contained example and its output:

library(OpenMx)
data(multiData1)
manifests <- c("x1", "x2", "y")
biRegModelRaw <- mxModel(
  "Regression of y on x1 and x2",
  type="RAM",
  manifestVars=manifests,
  mxPath(from=c("x1","x2"), to="y", 
         arrows=1, 
         free=TRUE, values=.2, labels=c("b1", "b2")),
  mxPath(from=manifests, 
         arrows=2, 
         free=TRUE, values=.8, 
         labels=c("VarX1", "VarX2", "VarE")),
  mxPath(from="x1", to="x2",
         arrows=2, 
         free=TRUE, values=.2, 
         labels=c("CovX1X2")),
  mxPath(from="one", to=manifests, 
         arrows=1, free=TRUE, values=.1, 
         labels=c("MeanX1", "MeanX2", "MeanY")),
  mxAlgebra(b1-b2, name = "diff"),
  mxData(observed=multiData1, type="raw"))
 
biRegModelRawOut <- mxRun(biRegModelRaw)
 
boot <- mxBootstrap(biRegModelRawOut) 
summary(boot, boot.quantile=c(.025,.975))
 
mxBootstrapEval(b1-b2, boot , bq= c(.025,.975) )
 
### The argument bq does not have an effect
mxBootstrapEvalByName("diff", boot , bq= c(.025,.975) )

Here is the output:

Show in New WindowClear OutputExpand/Collapse Output
Running Regression of y on x1 and x2 with 9 parameters
Running Regression of y on x1 and x2 with 9 parameters
Summary of Regression of y on x1 and x2 
 
free parameters:
     name matrix row col  Estimate  Std.Error      2.5%     97.5%
1      b1      A   y  x1 0.4479124 0.04182010 0.3680974 0.5320819
2      b2      A   y  x2 0.4327148 0.03555289 0.3678668 0.5031941
3   VarX1      S  x1  x1 1.1364299 0.05221950 1.0330193 1.2347567
4 CovX1X2      S  x1  x2 0.5811058 0.04784627 0.4802935 0.6586185
5   VarX2      S  x2  x2 1.5556045 0.07247085 1.3744765 1.6734908
6    VarE      S   y   y 1.4119922 0.06697778 1.2766602 1.5362670
7  MeanX1      M   1  x1 0.9848940 0.03743404 0.9010513 1.0645530
8  MeanX2      M   1  x2 1.9741801 0.04444123 1.8710743 2.0624128
9   MeanY      M   1   y 2.5530358 0.07517496 2.3998888 2.6843375
 
Model Statistics: 
               |  Parameters  |  Degrees of Freedom  |  Fit (-2lnL units)
       Model:              9                   1491               3010.73
   Saturated:              9                   1491                    NA
Independence:              6                   1494                    NA
Number of observations/statistics: 500/1500
 
Information Criteria: 
      |  df Penalty  |  Parameters Penalty  |  Sample-Size Adjusted
AIC:       28.73015               3028.730                 3029.097
BIC:    -6255.25053               3066.662                 3038.095
CFI: NA 
TLI: 1   (also known as NNFI) 
RMSEA:  0  [95% CI (NA, NA)]
Prob(RMSEA <= 0.05): NA
To get additional fit indices, see help(mxRefModels)
timestamp: 2018-04-07 12:35:46 
Wall clock time: 0.602927 secs 
OpenMx version number: 2.9.6 
Need help?  See help(mxSummary) 
 
             SE       2.5%    97.5%
[1,] 0.06605965 -0.1085388 0.149956
             SE       25.0%      75.0%
[1,] 0.06605965 -0.01632241 0.05732906
jpritikin's picture
Offline
Joined: 05/24/2012 - 00:35
nice bug report

Should be fixed in v2.9.6-44-ga92273546