[Depmix-commits] r420 - papers/jss

noreply at r-forge.r-project.org noreply at r-forge.r-project.org
Wed Jun 30 17:06:55 CEST 2010


Author: ingmarvisser
Date: 2010-06-30 17:06:55 +0200 (Wed, 30 Jun 2010)
New Revision: 420

Modified:
   papers/jss/dpx4.sh
   papers/jss/dpx4Rev.Rnw
   papers/jss/dpx4Rev.bib
Log:
Minor updates to the jss paper.

Modified: papers/jss/dpx4.sh
===================================================================
--- papers/jss/dpx4.sh	2010-06-30 13:30:54 UTC (rev 419)
+++ papers/jss/dpx4.sh	2010-06-30 15:06:55 UTC (rev 420)
@@ -4,6 +4,8 @@
 
 R --vanilla < dpx4Sweave.R ;
 
+R --vanilla < dpx4SweaveNoEval.R ;
+
 R --vanilla < dpx4Stangle.R ;
 
 

Modified: papers/jss/dpx4Rev.Rnw
===================================================================
--- papers/jss/dpx4Rev.Rnw	2010-06-30 13:30:54 UTC (rev 419)
+++ papers/jss/dpx4Rev.Rnw	2010-06-30 15:06:55 UTC (rev 420)
@@ -17,12 +17,12 @@
 \author{Ingmar Visser\\University of Amsterdam \And 
         Maarten Speekenbrink\\University College London}
         
-\title{\pkg{depmixS4} : An \proglang{R}-package for hidden Markov models}
+\title{\pkg{depmixS4} : An \proglang{R}-package for Hidden Markov Models}
 
 
 %% for pretty printing and a nice hypersummary also set:
 \Plainauthor{Ingmar Visser, Maarten Speekenbrink} %% comma-separated
-\Plaintitle{depmixS4: An R-package for hidden Markov models} %% without formatting
+\Plaintitle{depmixS4: An R-package for Hidden Markov Models} %% without formatting
 
 \Shorttitle{depmixS4: Hidden Markov Models} %% a short title (if necessary)
 
@@ -31,16 +31,18 @@
 	
 	\pkg{depmixS4} implements a general framework for defining and
 	estimating dependent mixture models in the \proglang{R}
-	programming language \citep{R2009}.  This includes standard Markov
+	programming language \citep{R2010}.  This includes standard Markov
 	models, latent/hidden Markov models, and latent class and finite
 	mixture distribution models.  The models can be fitted on mixed
 	multivariate data with distributions from the \code{glm} family,
-	the (logistic) multinomial, or the multivariate normal distribution.
-	Other distributions can be added easily, and an example is
-	provided with the exgaus distribution.  Parameters are estimated by
-	the EM algorithm or, when (linear) constraints are imposed on the
-	parameters, by direct numerical optimization with the
-	\pkg{Rsolnp} or \pkg{Rdonlp2} routines.}
+	the (logistic) multinomial, or the multivariate normal
+	distribution.  Other distributions can be added easily, and an
+	example is provided with the {\em exgaus} distribution.
+	Parameters are estimated by the EM algorithm or, when (linear)
+	constraints are imposed on the parameters, by direct numerical
+	optimization with the \pkg{Rsolnp} or \pkg{Rdonlp2} routines.
+	
+}
 
 \Keywords{hidden Markov model, dependent mixture model, mixture 
 model, constraints}
@@ -88,22 +90,24 @@
 \SweaveOpts{echo=TRUE}
 \usepackage{a4wide}
 
-%\usepackage{Sweave}
+%% \usepackage{Sweave}
 
 \begin{document}
 
+
 %set width of figures produced by Sweave
 \setkeys{Gin}{width=0.9\textwidth}
 
 \maketitle
 
+<<echo=FALSE>>=	
+.Options$digits<-3
+library(depmixS4)
+@
+
 %% include your article here, just as usual
 %% Note that you should use the \pkg{}, \proglang{} and \code{} commands.
 
-\begin{center}
-\bf{DRAFT: DO NOT QUOTE WITHOUT CONTACTING AUTHOR}
-\end{center}
-
 \section{Introduction}
 %% Note: If there is markup in \(sub)section, then it has to be escape as above.
 
@@ -119,7 +123,9 @@
 latent Markov models are usually referred to as hidden Markov models.
 See for example \citet{Fruhwirth2006} for an overview of hidden Markov
 models with extensions.  Further examples of applications can be found
-in e.g.\ \citet[][chapter~1]{Cappe2005}.
+in e.g.\ \citet[][chapter~1]{Cappe2005}.  A more gentle introduction
+into hidden Markov models with applications is the book by
+\citet{Zucchini2009}.
 
 The \pkg{depmixS4} package was motivated by the fact that while Markov
 models are used commonly in the social sciences, no comprehensive
@@ -181,8 +187,6 @@
 \begin{figure}[htbp]
 \begin{center}
 <<fig=TRUE,echo=FALSE,height=5,width=7,eps=FALSE>>=	
-.Options$digits<-3
-library(depmixS4)
 data(speed)
 plot(as.ts(speed[1:168,]),main="Speed-accuracy trade-off")
 @
@@ -215,12 +219,6 @@
 distributions, the initial mixture probabilities and transition
 probabilities can all depend on covariates $\vc{z}_t$.
 
-%transition probability functions $a_{ij}$ and the initial state
-%probability functions $\greekv{\pi}$ may depend on covariates as well
-%as the response distributions $\vc{b_{j}^{k}}$.  See for example
-%\citet{Fruhwirth2006} for an overview of hidden Markov models with
-%extensions.
-
 In a dependent mixture model, the joint likelihood of observations
 $\vc{O}_{1:T}$ and latent states $\vc{S}_{1:T} = (S_1,\ldots,S_T)$,
 given model parameters $\greekv{\theta}$ and covariates $\vc{z}_{1:T}
@@ -259,6 +257,7 @@
 state probability functions $\greekv{\pi}$ may depend on covariates as
 well as the response distributions $b_{j}^{k}$.
 
+
 \subsection{Likelihood}
 
 To obtain maximum likelihood estimates of the model parameters, we
@@ -357,7 +356,6 @@
 the expected values $\gamma_t(j)$ are used as prior weights of the
 observations $O^k_t$.
 
-
 The EM algorithm however has some drawbacks.  First, it can be slow to
 converge towards the end of optimization.  Second, applying
 constraints to parameters can be problematic; in particular, EM can
@@ -370,15 +368,17 @@
 linear (in)equality constraints (and optionally also non-linear
 constraints).
 
+
 \section[Using depmixS4]{Using \pkg{depmixS4}}
 
 Two steps are involved in using \pkg{depmixS4} which are illustrated
 below with examples:
 \begin{enumerate}
-	\item model specification with function \code{depmix} (or with \code{mix}
-	for latent class and finite mixture models, see example below on adding
-	covariates to prior probabilities)
 	
+	\item model specification with function \code{depmix} (or with
+	\code{mix} for latent class and finite mixture models, see example
+	below on adding covariates to prior probabilities)
+	
 	\item  model fitting with function \code{fit}
 \end{enumerate}
 We have separated the stages of model specification and model fitting
@@ -520,10 +520,10 @@
 distribution for the response).  The resulting model indicates two
 well-separated states, one with slow and the second with fast
 responses.  The transition probabilities indicate rather stable
-states, i.e., the probability of remaining in either of the states is around 0.9.
-The initial state probability estimates indicate that state 1 is the
-starting state for the process, with a negligible probability of starting in
-state 2.
+states, i.e., the probability of remaining in either of the states is
+around 0.9.  The initial state probability estimates indicate that
+state 1 is the starting state for the process, with a negligible
+probability of starting in state 2.
 
 \subsection{Covariates on transition parameters}
 
@@ -543,7 +543,7 @@
 repeated measurement data ($T=2$) using logistic regression on the
 transition parameters; they rely on Bayesian methods of estimation.
 Covariates on the transition probabilities can be specified using a
-one-sided formula as in the following example: 
+one-sided formula as in the following example:
 <<>>=
 set.seed(1)
 mod <- depmix(rt~1, data=speed, nstates=2, family=gaussian(),
@@ -614,9 +614,10 @@
 instead of \code{conpat}, with zeroes for fixed parameters and other
 values (ones e.g.) for non-fixed parameters.  Fitting the models
 subject to these constraints is handled by the optimization routine
-\code{solnp} or, optionally, by \code{donlp2}.  To be able to construct the \code{conpat} and/or
-\code{fixed} vectors one needs the correct ordering of parameters
-which is briefly discussed next before proceeding with an example.
+\code{solnp} or, optionally, by \code{donlp2}.  To be able to
+construct the \code{conpat} and/or \code{fixed} vectors one needs the
+correct ordering of parameters which is briefly discussed next before
+proceeding with an example.
 
 \paragraph{Parameter numbering} When using the \code{conpat} and
 \code{fixed} arguments, complete parameter vectors should be supplied,
@@ -673,19 +674,20 @@
 @
 
 Using \code{summary} on the fitted model shows that the regression
-coefficients are now estimated at the same value of 12.66.  Setting 
-elements 13 and 14 of \code{conpat} to zero resulted in fixing those parameters
-at their starting values of 0.5.  This means that state 1 can now be interpreted
-as a 'guessing' state which is associated with comparatively fast responses.
-Similarly for elements 1 and 2, resulting in fixed initial probabilities. The
-function \code{llratio} computes the likelihood ratio
-$\chi^2$-statistic and the associated $p$-value with appropriate
-degrees of freedom for testing the tenability of constraints
-\citep{Dannemann2007}.  Note that these arguments (i.e. \code{conpat}
-and \code{conrows}) provide the possibility for arbitrary constraints,
-also between, e.g., a multinomial regression coefficient for the
-transition matrix and the mean of a Gaussian response model.  Whether
-such constraints make sense is hence the responsibility of the user.
+coefficients are now estimated at the same value of 12.66.  Setting
+elements 13 and 14 of \code{conpat} to zero resulted in fixing those
+parameters at their starting values of 0.5.  This means that state 1
+can now be interpreted as a 'guessing' state which is associated with
+comparatively fast responses.  Similarly for elements 1 and 2,
+resulting in fixed initial probabilities.  The function \code{llratio}
+computes the likelihood ratio $\chi^2$-statistic and the associated
+$p$-value with appropriate degrees of freedom for testing the
+tenability of constraints \citep{Dannemann2007}.  Note that these
+arguments (i.e. \code{conpat} and \code{conrows}) provide the
+possibility for arbitrary constraints, also between, e.g., a
+multinomial regression coefficient for the transition matrix and the
+mean of a Gaussian response model.  Whether such constraints make
+sense is hence the responsibility of the user.
 
 
 \subsection{Adding covariates on the prior probabilities}
@@ -694,8 +696,8 @@
 included another data set with \pkg{depmixS4}.  The \code{balance}
 data consists of 4 binary items (correct-incorrect) on a balance scale
 task \citep{Siegler1981}.  The data form a subset of the data
-published in \citet{Jansen2002}. Before specifying specifying a model 
-for these data, we briefly describe them. 
+published in \citet{Jansen2002}.  Before specifying specifying a model
+for these data, we briefly describe them.
 
 The balance scale taks is a famous task for testing cognitive
 strategies developed by Jean Piaget \citep[see][]{Siegler1981}.
@@ -1036,27 +1038,28 @@
 
 We are currently working on implementing the gradients for response
 and transition models with two goals in mind.  First, to speed up
-(constrained) parameter optimization using \pkg{Rdonlp2}.  Second,
-analytic gradients are useful in computing the Hessian of the
-estimated parameters so as to arrive at standard errors for those.  We
-are also planning to implement goodness-of-fit statistics
-\citep{Titman2008}. 
+(constrained) parameter optimization using \pkg{Rdonlp2} or
+\pkg{Rsolnp}.  Second, analytic gradients are useful in computing the
+Hessian of the estimated parameters so as to arrive at standard errors
+for those.  We are also planning to implement goodness-of-fit
+statistics \citep{Titman2008}.
 
 
 \section*{Acknowledgements} 
 
 Ingmar Visser was supported by an EC Framework 6 grant, project 516542
-(NEST).  Maarten Speekenbrink was supported by ESRC grant RES-062-23-1511 
-and the ESRC Centre for Economic Learning and Social Evolution (ELSE).  
-Han van der Maas provided the speed-accuracy data \cite{Dutilh2010} and thereby
-neccessitated implementing models with time-dependent covariates.
-Brenda Jansen provided the balance scale data set \citep{Jansen2002}
-which was the perfect opportunity to test the covariates on the prior
-model parameters.  The examples in the help files use both of these
-data sets.
+(NEST).  Maarten Speekenbrink was supported by ESRC grant
+RES-062-23-1511 and the ESRC Centre for Economic Learning and Social
+Evolution (ELSE).  Han van der Maas provided the speed-accuracy data
+\citep{Dutilh2010} and thereby neccessitated implementing models with
+time-dependent covariates.  Brenda Jansen provided the balance scale
+data set \citep{Jansen2002} which was the perfect opportunity to test
+the covariates on the prior model parameters.  The examples in the
+help files use both of these data sets.
 
 \bibliography{dpx4Rev}
 
+
 \end{document}
 
 

Modified: papers/jss/dpx4Rev.bib
===================================================================
--- papers/jss/dpx4Rev.bib	2010-06-30 13:30:54 UTC (rev 419)
+++ papers/jss/dpx4Rev.bib	2010-06-30 15:06:55 UTC (rev 420)
@@ -2,21 +2,54 @@
 %% http://bibdesk.sourceforge.net/
 
 
-%% Created for Ingmar Visser at 2010-03-10 17:01:34 +0100 
+%% Created for Ingmar Visser at 2010-06-30 16:36:57 +0200 
 
 
 %% Saved with string encoding Unicode (UTF-8) 
 
 
 
+ at book{Zucchini2009,
+	Address = {Boca Raton},
+	Author = {Walter Zucchini and Iain MacDonald},
+	Date-Added = {2010-06-30 14:53:53 +0200},
+	Date-Modified = {2010-06-30 14:53:53 +0200},
+	Number = {110},
+	Publisher = {CRC Press},
+	Series = {Monographs on statistics and applied probability},
+	Title = {Hidden Markov Models for Time Series: An Introduction Using R},
+	Year = {2009}}
+
+ at manual{Ghalanos2010,
+	Author = {Alexios Ghalanos and Stefan Theussl},
+	Date-Added = {2010-06-30 14:45:04 +0200},
+	Date-Modified = {2010-06-30 14:45:31 +0200},
+	Note = {R package version 1.0-2},
+	Title = {Rsolnp: General Non-linear Optimization Using Augmented Lagrange Multiplier Method},
+	Url = {https://r-forge.r-project.org/projects/rino/},
+	Year = {2010},
+	Bdsk-Url-1 = {https://r-forge.r-project.org/projects/rino/}}
+
+ at manual{R2010,
+	Address = {Vienna, Austria},
+	Author = {{R Development Core Team}},
+	Date-Added = {2010-06-30 14:42:17 +0200},
+	Date-Modified = {2010-06-30 14:42:17 +0200},
+	Note = {{ISBN} 3-900051-07-0},
+	Organization = {R Foundation for Statistical Computing},
+	Title = {R: A Language and Environment for Statistical Computing},
+	Url = {http://www.R-project.org},
+	Year = {2010},
+	Bdsk-Url-1 = {http://www.R-project.org}}
+
 @book{Salzberg1998,
 	Address = {Amsterdam},
 	Booktitle = {Computational methods in molecular biology},
 	Date-Added = {2010-03-10 16:58:42 +0100},
-	Date-Modified = {2010-03-10 16:58:42 +0100},
+	Date-Modified = {2010-06-30 16:34:58 +0200},
 	Editor = {S. L. Salzberg and D. B. Searls and S. Kasif},
 	Publisher = {Elsevier},
-	Title = {Computational methods in molecular biology},
+	Title = {Computational Methods in Molecular Biology},
 	Year = 1998}
 
 @phdthesis{Ye1987,
@@ -29,9 +62,9 @@
 	Address = {San Francisco},
 	Author = {Thomas D. Wickens},
 	Date-Added = {2010-03-05 15:47:54 +0100},
-	Date-Modified = {2010-03-05 15:47:54 +0100},
+	Date-Modified = {2010-06-30 16:36:50 +0200},
 	Publisher = {W. H. Freeman and Company},
-	Title = {Models for Behavior: Stochastic processes in psychology},
+	Title = {Models for Behavior: Stochastic Processes in Psychology},
 	Year = 1982}
 
 @manual{Vermunt2003,
@@ -70,27 +103,27 @@
 	Address = {Voorburg: The Netherlands},
 	Author = {Frank {Van de Pol} and Rolf Langeheine and W. De Jong},
 	Date-Added = {2010-03-05 15:46:41 +0100},
-	Date-Modified = {2010-03-05 15:46:41 +0100},
+	Date-Modified = {2010-06-30 16:33:16 +0200},
 	Publisher = {Statistics Netherlands},
-	Title = {PANMARK 3. Panel analysis using {M}arkov chains. A latent class analysis program [User manual].},
+	Title = {PANMARK 3. Panel Analysis Using {M}arkov Chains. A Latent Class Analysis Program [User manual].},
 	Year = 1996}
 
 @article{Titman2008,
 	Author = {Andrew C. Titman and Linda D. Sharples},
 	Date-Added = {2010-03-05 15:46:23 +0100},
-	Date-Modified = {2010-03-05 15:46:23 +0100},
+	Date-Modified = {2010-06-30 16:36:30 +0200},
 	Journal = {STATISTICS IN MEDICINE},
 	Pages = {2177--2195},
-	Title = {A general goodness-of-fit test for Markov and hidden Markov models},
+	Title = {A General Goodness-of-fit Test for Markov and Hidden Markov Models},
 	Volume = {27},
 	Year = {2008}}
 
 @manual{Tamura2009,
 	Author = {Ryuichi Tamura},
 	Date-Added = {2010-03-05 15:46:10 +0100},
-	Date-Modified = {2010-03-05 15:46:10 +0100},
+	Date-Modified = {2010-06-30 16:36:07 +0200},
 	Note = {R package version 0.4},
-	Title = {Rdonlp2: an R extension library to use {Peter Spelluci's DONLP2} from {R}.},
+	Title = {Rdonlp2: An R Extension Library to Use {Peter Spelluci's DONLP2} from {R}.},
 	Url = {http://arumat.net/Rdonlp2/},
 	Year = {2009},
 	Bdsk-Url-1 = {http://arumat.net/Rdonlp2/}}
@@ -128,52 +161,40 @@
 @book{Siegler1981,
 	Author = {Robert S. Siegler},
 	Date-Added = {2010-03-05 15:44:59 +0100},
-	Date-Modified = {2010-03-05 15:44:59 +0100},
+	Date-Modified = {2010-06-30 16:35:42 +0200},
 	Number = {46},
 	Publisher = {SRCD},
 	Series = {Monographs of the Society for Research in Child Development},
-	Title = {Developmental sequences within and between concepts},
+	Title = {Developmental Sequences Within and Between Concepts},
 	Year = {1981}}
 
 @article{Ratcliff1978,
 	Author = {Roger Ratcliff},
 	Date-Added = {2010-03-05 15:44:46 +0100},
-	Date-Modified = {2010-03-05 15:44:46 +0100},
+	Date-Modified = {2010-06-30 16:34:44 +0200},
 	Journal = {Psychological Review},
 	Pages = {59-108},
-	Title = {A theory of memory retrieval},
+	Title = {A Theory of Memory Retrieval},
 	Volume = {85},
 	Year = {1978}}
 
 @article{Rainer2000,
 	Author = {Gregor Rainer and Earl K. Miller},
 	Date-Added = {2010-03-05 15:44:29 +0100},
-	Date-Modified = {2010-03-05 15:44:29 +0100},
+	Date-Modified = {2010-06-30 16:34:29 +0200},
 	Journal = {Neurocomputing},
 	Pages = {961--966},
-	Title = {Neural ensemble states in prefrontal cortex identified using a hidden {M}arkov model with a modified EM algorithm},
+	Title = {Neural Ensemble States in Prefrontal Cortex Identified Using a Hidden {M}arkov Model with a Modified EM Algorithm},
 	Volume = {32--33},
 	Year = 2000}
 
- at manual{R2009,
-	Address = {Vienna, Austria},
-	Author = {{R Development Core Team}},
-	Date-Added = {2010-03-05 15:44:13 +0100},
-	Date-Modified = {2010-03-05 15:44:13 +0100},
-	Note = {{ISBN} 3-900051-07-0},
-	Organization = {R Foundation for Statistical Computing},
-	Title = {R: A Language and Environment for Statistical Computing},
-	Url = {http://www.R-project.org},
-	Year = {2009},
-	Bdsk-Url-1 = {http://www.R-project.org}}
-
 @article{Lystig2002,
 	Author = {Theodore C. Lystig and James P. Hughes},
 	Date-Added = {2010-03-05 15:43:58 +0100},
-	Date-Modified = {2010-03-05 15:43:58 +0100},
+	Date-Modified = {2010-06-30 16:32:48 +0200},
 	Journal = {Journal of Computational and Graphical Statistics},
 	Summary = {Authors introduce an interpretation of the forward variables in terms of conditional probabilities and a new scaling regime that allows exact computation of the score function and the observed information matrix.},
-	Title = {Exact computation of the observed information matrix for hidden Markov models},
+	Title = {Exact Computation of the Observed Information Matrix for Hidden Markov Models},
 	Year = {2002}}
 
 @article{Leroux1992,
@@ -205,34 +226,34 @@
 	Booktitle = {Computational methods in molecular biology},
 	Chapter = 4,
 	Date-Added = {2010-03-05 15:43:21 +0100},
-	Date-Modified = {2010-03-10 17:01:34 +0100},
+	Date-Modified = {2010-06-30 16:31:57 +0200},
 	Editor = {S. L. Salzberg and D. B. Searls and S. Kasif},
 	Keywords = {hidden markov model, application},
 	Pages = {45--63},
 	Publisher = {Elsevier},
-	Title = {An introduction to hidden {M}arkov models for biological sequences},
+	Title = {An Introduction to Hidden {M}arkov Models for Biological Sequences},
 	Year = {1998}}
 
 @article{Kim1994,
 	Author = {Chang-Jin Kim},
 	Date-Added = {2010-03-05 15:43:13 +0100},
-	Date-Modified = {2010-03-05 15:43:13 +0100},
+	Date-Modified = {2010-06-30 16:31:31 +0200},
 	Journal = {Journal of Econometrics},
 	Keywords = {markov models},
 	Pages = {1--22},
-	Title = {Dynamic linear models with {M}arkov-switching},
+	Title = {Dynamic Linear Models with {M}arkov-switching},
 	Volume = {60},
 	Year = 1994}
 
 @article{Jansen2002,
 	Author = {Brenda R. J. Jansen and Han L. J. van der Maas},
 	Date-Added = {2010-03-05 15:43:02 +0100},
-	Date-Modified = {2010-03-05 15:43:02 +0100},
+	Date-Modified = {2010-06-30 16:31:21 +0200},
 	Journal = {Journal of Experimental Child Psychology},
 	Keywords = {balance scale},
 	Number = {4},
 	Pages = {383-416},
-	Title = {The development of children's rule use on the balance scale task},
+	Title = {The Development of Children's Rule Use on the Balance Scale Task},
 	Volume = {81},
 	Year = {2002}}
 
@@ -248,12 +269,6 @@
 	Volume = {12},
 	Year = 1994}
 
- at manual{Ghalanos2010,
-	Author = {Alexios Ghalanos and Stefan Theussl},
-	Note = {R package version 1.0-1.},
-	Title = {Rsolnp: General Non-linear Optimization Using Augmented Lagrange Multiplier Method},
-	Year = {2010}}
-
 @book{Fruhwirth2006,
 	Author = {Sylvia Fr\"uhwirth-Schnatter},
 	Date-Added = {2010-03-05 15:42:33 +0100},
@@ -273,7 +288,7 @@
 	Title = {Likelihood Ratio Testing for Hidden Markov Models Under Non-standard Conditions},
 	Volume = {25},
 	Year = {2007},
-	Bdsk-File-1 = {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}}
+	Bdsk-File-1 = {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}}
 
 @article{Chung2007,
 	Author = {Hwan Chung and Theodore Walls and Yousung Park},
@@ -287,7 +302,7 @@
 	Url = {http://ideas.repec.org/a/spr/psycho/v72y2007i3p413-435.html},
 	Volume = {72},
 	Year = 2007,
-	Bdsk-File-1 = {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}}
+	Bdsk-File-1 = {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}}
 
 @book{Cappe2005,
 	Address = {New York},
@@ -302,22 +317,22 @@
 @article{Baum1966,
 	Author = {L. E. Baum and T. Petrie},
 	Date-Added = {2010-03-05 15:41:40 +0100},
-	Date-Modified = {2010-03-05 15:41:40 +0100},
+	Date-Modified = {2010-06-30 16:30:30 +0200},
 	Journal = {Annals of Mathematical Statistics},
 	Keywords = {hidden markov model},
 	Pages = {1554--40},
-	Title = {Statistical inference for probabilistic functions of finite state {M}arkov Chains},
+	Title = {Statistical Inference for Probabilistic Functions of Finite State {M}arkov Chains},
 	Volume = 67,
 	Year = 1966}
 
 @article{Rabiner1989,
 	Author = {Lawrence R. Rabiner},
 	Date-Added = {2010-03-05 15:40:56 +0100},
-	Date-Modified = {2010-03-05 15:40:56 +0100},
+	Date-Modified = {2010-06-30 16:33:50 +0200},
 	Journal = {Proceedings of IEEE},
 	Number = 2,
 	Pages = {267--295},
-	Title = {A tutorial on hidden {M}arkov models and selected applications in speech recognition},
+	Title = {A Tutorial on Hidden {M}arkov Models and Selected Applications in Speech Recognition},
 	Volume = {77},
 	Year = 1989}
 
@@ -335,11 +350,11 @@
 @article{Schmittmann2006,
 	Author = {Verena D. Schmittmann and Ingmar Visser and Maartje E. J. Raijmakers},
 	Date-Added = {2010-03-05 15:39:23 +0100},
-	Date-Modified = {2010-03-05 15:39:23 +0100},
+	Date-Modified = {2010-06-30 16:35:25 +0200},
 	Journal = {Neuropsychologia},
 	Number = 11,
 	Pages = {2079--2091},
-	Title = {Multiple learning modes in the development of rule-based category-learning task performance},
+	Title = {Multiple Learning Modes in the Development of Rule-based Category-learning Task Performance},
 	Volume = 44,
 	Year = 2006,
 	Bdsk-File-1 = {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}}



More information about the depmix-commits mailing list