spellproof

Author: martin-smira

Bayesian_Cognitive_Modeling/ParameterEstimation/DataAnalysis/ChaSaSoon_Stan.R

@@ -4,9 +4,9 @@ rm(list=ls())
 library(rstan)
 
 #### Notes to Stan model #######################################################
-## 1) Approach to this model can be difficult to understand for beginners. 
-##    Therefore I suggest either not trying to understand it and look on WinBUGS
-##    version or go deep into Stan manual.
+## Implementation of this model can be difficult to understand for beginners. 
+## Therefore I suggest either not trying to understand it and look on WinBUGS
+## version or go deep into Stan manual.
 ################################################################################
 model <- "
 # ChaSaSoon Censored Data

Bayesian_Cognitive_Modeling/ParameterEstimation/DataAnalysis/ChangeDetection_Stan.R

@@ -9,7 +9,7 @@ library(rstan)
 ##    you change the values, you'll need to increment iterations significantly  
 ## 2) Code is quite dissimilar to original WinBUGS model - using conditionals 
 ##    instead of step function. This will happen in further models more often.
-##    There are difference in what functions are efficient in BUGS and Stan.
+##    There is a difference in what functions are efficient in BUGS and Stan.
 ################################################################################
 model <- "
 // Change Detection

Bayesian_Cognitive_Modeling/ParameterEstimation/DataAnalysis/Correlation_1_Stan.R

@@ -4,7 +4,7 @@ rm(list=ls())
 library(rstan)
 
 #### Notes to Stan model #######################################################
-## 1) Multivariate normal distribution in Stan uses covariance matrix insted of 
+## 1) Multivariate normal distribution in Stan uses covariance matrix instead of 
 ##    precision matrix.
 ## 2) Multivariate normal distribution can be (and is) also vectorized.
 ## 3) Warnings may occur during sampling, ignore them.

Bayesian_Cognitive_Modeling/ParameterEstimation/DataAnalysis/Correlation_2_Stan.R

@@ -4,7 +4,7 @@ rm(list=ls())
 library(rstan)
 
 #### Notes to Stan model #######################################################
-## 1) All notes from previsou model Correlation_1 also applies to this model.
+## 1) All notes from previous model Correlation_1 also apply to this model.
 ## 2) If you change sigmaerror to c(0.03, 10) as suggested in excercise 5.2.2
 ##    warning statements will be more frequent and posterior less smooth.
 ################################################################################

Bayesian_Cognitive_Modeling/ParameterEstimation/DataAnalysis/Kappa_Stan.R

@@ -4,12 +4,12 @@ rm(list=ls())
 library(rstan)
 
 #### Notes to Stan model #######################################################
-## 1) First time we use simplex data type. Simplex is similar to vector, but 
-##    with a property that sum of all it's elements is equal to 1.
+## 1) This is the first time we use simplex data type. Simplex is similar to 
+##    vector, but with a property that sum of all it's elements is equal to 1.
 ## 2) Sampling statements for parameters alpha, beta and gamma could be removed
 ##    leading to uniform prior on (0, 1) interval which is the same as beta(1, 1)
 ## 3) Variable n was removed here. Stan doesn't need this information as
-##    an argument for multinomial distribution. Always make sure, that you know 
+##    an argument for multinomial distribution. Always make sure that you know 
 ##    what arguments are required for a function / sampling statement. In many 
 ##    cases these are different from BUGS. Very useful for this are last pages 
 ##    of Stan manual

Bayesian_Cognitive_Modeling/ParameterEstimation/DataAnalysis/Planes_Stan.R

@@ -5,7 +5,7 @@ library(rstan)
 
 #### Notes to Stan model #######################################################
 ## Stan has hypergeometric distribution implemented, so in one way the code
-## is more intuitive. On the other side, Stan can't sample discrete parameters
+## is more intuitive. On the other hand, Stan can't sample discrete parameters,
 ## therefore we have to increment log probability manually (as we did in 
 ## Survey example).  
 ################################################################################

Bayesian_Cognitive_Modeling/ParameterEstimation/Gaussian/Gaussian_Stan.R

@@ -5,11 +5,11 @@ library(rstan)
 
 #### Notes to Stan model #######################################################
 ## 1) If parameter's prior distribution is not specified, Stan will assume that
-##    you want it distributed uniformly with boundaries given by variable 
-##    constraints. Here constrains <lower=0,upper=10> gives uniform(0, 100)
-## 2) In Stan most of the sampling statements can be vectorized. In this example
-##    you can see it in a statement for vector x. Instead of using for loop for  
-##    each element of the vector, we can simple write it as above. Saves code, 
+##    you want it to be distributed uniformly with boundaries given by variable 
+##    constraints. Here constrains <lower=0,upper=10> give uniform (0, 100)
+## 2) In Stan, most of the sampling statements can be vectorized. In this example
+##    you can see it in the statement for vector x. Instead of using for loop for  
+##    each element of the vector, we can simple write it as above. This saves code, 
 ##    speeds up computation. For more information read Vectorization chapter in
 ##    the Stan manual (p.231 in version 2.4.0)
 ################################################################################

Bayesian_Cognitive_Modeling/ParameterEstimation/Gaussian/IQ_Stan.R

@@ -5,7 +5,7 @@ library(rstan)
 
 #### Notes to Stan model #######################################################
 ## 1) We used implicit uniform distribution for sigma and vector mu
-## 2) The second loop in this model (1:m) is unnecessary here. You can try to
+## 2) The second loop in this model (1:m) is not necessary here. You can try to
 ##    remove it, but don't forget to remove its index j. Remember vectorization!
 ################################################################################
 model <- "