Category Archives: Uncategorized

Types of Speaking in ESL

In the context of ESL teaching, ~there are at least five types of speaking that take place in the classroom. This post will define and provide examples of each. The five types are as follows…

  • Imitative
  • Intensive
  • Responsive
  • Interactive
  • Extensive

The list above is ordered from simplest to most complex in terms of the requirements of oral production for the student.


At the imitative level, it is probably already clear what the student is trying to do. At this level, the student is simply trying to repeat what was said to them in a way that is understandable and with some adherence to pronunciation as defined by the teacher.

It doesn’t matter if the student comprehends what they are saying or carrying on a conversation. The goal is only to reproduce what was said to them. One common example of this is a “repeat after me” experience in the classroom.


Intensive speaking involves producing a limit amount of language in a highly control context. An example of this would be to read aloud a passage or give a direct response to a simple question.

Competency at this level is shown through achieving certain grammatical or lexical mastery. This depends on the teacher’s expectations.


Responsive is slightly more complex than intensive but the difference is blurry, to say the least. At this level, the dialog includes a simple question with a follow-up question or two. Conversations take place by this point but are simple in content.


The unique feature of intensive speaking is that it is usually more interpersonal than transactional. By interpersonal it is meant speaking for maintaining relationships. Transactional speaking is for sharing information as is common at the responsive level.

The challenge of interpersonal speaking is the context or pragmatics The speaker has to keep in mind the use of slang, humor, ellipsis, etc. when attempting to communicate. This is much more complex than saying yes or no or giving directions to the bathroom in a second language.


Extensive communication is normal some sort of monolog. Examples include speech, story-telling, etc. This involves a great deal of preparation and is not typically improvisational communication.

It is one thing to survive having a conversation with someone in a second language. You can rely on each other’s body language to make up for communication challenges. However, with extensive communication either the student can speak in a comprehensible way without relying on feedback or they cannot. In my personal experience, the typical ESL student cannot do this in a convincing manner.


Intensive Listening and ESL

Intensive listening is listening for the elements (phonemes, intonation, etc.) in words and sentences. This form of listening is often assessed in an ESL setting as a way to measure an individual’s phonological,  morphological, and ability to paraphrase. In this post, we will look at these three forms of assessment with examples.

Phonological Elements

Phonological elements include phonemic consonant and phonemic vowel pairs. Phonemic consonant pair has to do with identifying consonants. Below is an example of what an ESL student would hear followed by potential choices they may have on a multiple-choice test.

Recording: He’s from Thailand

(a) He’s from Thailand
(b) She’s from Thailand

The answer is clearly (a). The confusion is with the adding of ‘s’ for choice (b). If someone is not listening carefully they could make a mistake. Below is an example of phonemic pairs involving vowels

Recording: The girl is leaving?

(a)The girl is leaving?
(b)The girl is living?

Again, if someone is not listening carefully they will miss the small change in the vowel.

Morphological Elements

Morphological elements follow the same approach as phonological elements. You can manipulate endings, stress patterns, or play with words.  Below is an example of ending manipulation.

Recording: I smiled a lot.

(a) I smiled a lot.
(b) I smile a lot.

I sharp listener needs to hear the ‘d’ sound at the end of the word ‘smile’ which can be challenging for ESL student. Below is an example of stress pattern

Recording: My friend doesn’t smoke.

(a) My friend doesn’t smoke.
(b) My friend does smoke.

The contraction in the example is the stress pattern the listener needs to hear. Below is an example of a play with words.

Recording: wine

(a) wine
(b) vine

This is especially tricky for languages that do not have both a ‘v’ and ‘w’ sound, such as the Thai language.

Paraphrase recognition

Paraphrase recognition involves listening to an example of being able to reword it in an appropriate manner. This involves not only listening but also vocabulary selection and summarizing skills. Below is one example of sentence paraphrasing

Recording: My name is James. I come from California

(a) James is Californian
(b) James loves Calfornia

This is trickier because both can be true. However, the goal is to try and rephrase what was heard.  Another form of paraphrasing is dialogue paraphrasing as shown below


Man: My name is Thomas. What is your name?
Woman: My name is Janet. Nice to meet you. Are you from Africa
Man: No, I am an American

(a) Thomas is from America
(b)Thomas is African

You can see the slight rephrase that is wrong with choice (b). This requires the student to listen to slightly longer audio while still have to rephrase it appropriately.


Intensive listening involves the use of listening for the little details of an audio. This is a skill that provides a foundation for much more complex levels of listening.

Recommendation Engines in R

In this post, we will look at how to make a recommendation engine. We will use data that makes recommendations about movies. We will use the “recommenderlab” package to build several different engines. The data comes from

At this link, you need to download the “”. From there, we will use the “ratings” and “movies” files in this post. Ratings provide the ratings of the movies while movies provide the names of the movies. Before going further it is important to know that the “recommenderlab” has five different techniques for developing recommendation engines (IBCF, UBCF, POPULAR, RANDOM, & SVD). We will use all of them for comparative purposes Below is the code for getting started.

ratings <- read.csv("~/Downloads/ml-latest-small/ratings.csv")
movies <- read.csv("~/Downloads/ml-latest-small/movies.csv")

We now need to merge the two datasets so that they become one. This way the titles and ratings are in one place. We will then coerce our “movieRatings” dataframe into a “realRatingMatrix” in order to continue our analysis. Below is the code

movieRatings<-merge(ratings, movies, by='movieId') #merge two files
movieRatings<-as(movieRatings,"realRatingMatrix") #coerce to realRatingMatrix

We will now create two histograms of the ratings. The first is raw data and the second will be normalized data. The function “getRatings” is used in combination with the “hist” function to make the histogram. The normalized data includes the “normalize” function. Below is the code.

hist(getRatings(movieRatings),breaks =10)


hist(getRatings(normalize(movieRatings)),breaks =10)


We are now ready to create the evaluation scheme for our analysis. In this object we need to set the data name (movieRatings), the method we want to use (cross-validation), the amount of data we want to use for the training set (80%), how many ratings the algorithm is given during the test set (1) with the rest being used to compute the error. We also need to tell R what a good rating is (4 or higher) and the number of folds for the cross-validation (10). Below is the code for all of this.


Below is the code for developing our models. To do this we need to use the “Recommender” function and the “getData” function to get the dataset. Remember we are using all six modeling techniques


The models have been created. We can now make our predictions using the “predict” function in addition to the “getData” function. We also need to set the argument “type” to “ratings”. Below is the code.


We can now look at the accuracy of the models. We will do this in two steps. First, we will look at the error rates. After completing this, we will do a more detailed analysis of the stronger models. Below is the code for the first step

ubcf_error<-calcPredictionAccuracy(ubcf_pred,getData(eSetup,"unknown")) #calculate error
error<-rbind(ubcf_error,ibcf_error,svd_error,pop_error,rand_error) #combine objects into one data frame
rownames(error)<-c("UBCF","IBCF","SVD","POP","RAND") #give names to rows
##          RMSE      MSE       MAE
## UBCF 1.278074 1.633473 0.9680428
## IBCF 1.484129 2.202640 1.1049733
## SVD  1.277550 1.632135 0.9679505
## POP  1.224838 1.500228 0.9255929
## RAND 1.455207 2.117628 1.1354987

The results indicate that the “RAND” and “IBCF” models are clearly worst than the remaining three. We will now move to the second step and take a closer look at the “UBCF”, “SVD”, and “POP” models. We will do this by making a list and using the “evaluate” function to get other model evaluation metrics. We will make a list called “algorithms” and store the three strongest models. Then we will make a objective called “evlist” in this object we will use the “evaluate” function as well as called the evaluation scheme “esetup”, the list (“algorithms”) as well as the number of movies to assess (5,10,15,20)

##           TP        FP       FN       TN  precision     recall        TPR
## 5  0.3010965  3.033333 4.917105 661.7485 0.09028443 0.07670381 0.07670381
## 10 0.4539474  6.214912 4.764254 658.5669 0.06806016 0.11289681 0.11289681
## 15 0.5953947  9.407895 4.622807 655.3739 0.05950450 0.14080354 0.14080354
## 20 0.6839912 12.653728 4.534211 652.1281 0.05127635 0.16024740 0.16024740
##            FPR
## 5  0.004566269
## 10 0.009363021
## 15 0.014177091
## 20 0.019075070
## $SVD
##           TP        FP       FN       TN  precision     recall        TPR
## 5  0.1025219  3.231908 5.115680 661.5499 0.03077788 0.00968336 0.00968336
## 10 0.1808114  6.488048 5.037390 658.2938 0.02713505 0.01625454 0.01625454
## 15 0.2619518  9.741338 4.956250 655.0405 0.02620515 0.02716656 0.02716656
## 20 0.3313596 13.006360 4.886842 651.7754 0.02486232 0.03698768 0.03698768
##            FPR
## 5  0.004871678
## 10 0.009782266
## 15 0.014689510
## 20 0.019615377
## $UBCF
##           TP        FP       FN       TN  precision     recall        TPR
## 5  0.1210526  2.968860 5.097149 661.8129 0.03916652 0.01481106 0.01481106
## 10 0.2075658  5.972259 5.010636 658.8095 0.03357173 0.02352752 0.02352752
## 15 0.3028509  8.966886 4.915351 655.8149 0.03266321 0.03720717 0.03720717
## 20 0.3813596 11.978289 4.836842 652.8035 0.03085246 0.04784538 0.04784538
##            FPR
## 5  0.004475151
## 10 0.009004466
## 15 0.013520481
## 20 0.018063361

Well, the numbers indicate that all the models are terrible. All metrics are scored rather poorly. True positives, false positives, false negatives, true negatives, precision, recall, true positive rate, and false positive rate are low for all models. Remember that these values are averages of the cross-validation. As such, for the “POPULAR” model when looking at the top five movies on average, the number of true positives was .3.

Even though the numbers are terrible the “POPULAR” model always performed the best. We can even view the ROC curve with the code below



We can now determine individual recommendations. We first need to build a model using the POPULAR algorithm. Below is the code.

## Recommender of type 'POPULAR' for 'realRatingMatrix' 
## learned using 9066 users.

We will now pull the top five recommendations for the first two raters and make a list. The numbers are the movie ids and not the actual titles

## $`1`
## [1] "78"  "95"  "544" "102" "4"  
## $`2`
## [1] "242" "232" "294" "577" "95" 
## $`3`
## [1] "654" "242" "30"  "232" "287"
## $`4`
## [1] "564" "654" "242" "30"  "232"
## $`5`
## [1] "242" "30"  "232" "287" "577"

Below we can see the specific score for a specific movie. The names of the movies come from the original “ratings” dataset.

## 5 x 671 rating matrix of class 'realRatingMatrix' with 2873 ratings.
colnames(movieresult)<-c("Toy Story","Jumanji","Grumpier Old Men")
##   Toy Story  Jumanji Grumpier Old Men
## 1  2.859941 3.822666         3.724566
## 2  2.389340 3.352066         3.253965
## 3  2.148488 3.111213         3.013113
## 4  1.372087 2.334812         2.236711
## 5  2.255328 3.218054         3.119953

This is what the model thinks the person would rate the movie. It is the difference between this number and the actual one that the error is calculated. In addition, if someone did not rate a movie you would see an NA in that spot


This was a lot of work. However, with additional work, you can have your own recommendation system based on data that was collected.

Clustering Mixed Data in R

One of the major problems with hierarchical and k-means clustering is that they cannot handle nominal data. The reality is that most data is mixed or a combination of both interval/ratio data and nominal/ordinal data.

One of many ways to deal with this problem is by using the Gower coefficient. This coefficient compares the pairwise cases in the data set and calculates a dissimilarity between. By dissimilar we mean the weighted mean of the variables in that row.

Once the dissimilarity calculations are completed using the gower coefficient (there are naturally other choices), you can then use regular kmeans clustering (there are also other choices) to find the traits of the various clusters. In this post, we will use the “MedExp” dataset from the “Ecdat” package. Our goal will be to cluster the mixed data into four clusters. Below is some initial code.

## 'data.frame':    5574 obs. of  15 variables:
##  $ med     : num  62.1 0 27.8 290.6 0 ...
##  $ lc      : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ idp     : Factor w/ 2 levels "no","yes": 2 2 2 2 2 2 2 2 1 1 ...
##  $ lpi     : num  6.91 6.91 6.91 6.91 6.11 ...
##  $ fmde    : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ physlim : Factor w/ 2 levels "no","yes": 1 1 1 1 1 2 1 1 1 1 ...
##  $ ndisease: num  13.7 13.7 13.7 13.7 13.7 ...
##  $ health  : Factor w/ 4 levels "excellent","good",..: 2 1 1 2 2 2 2 1 2 2 ...
##  $ linc    : num  9.53 9.53 9.53 9.53 8.54 ...
##  $ lfam    : num  1.39 1.39 1.39 1.39 1.1 ...
##  $ educdec : num  12 12 12 12 12 12 12 12 9 9 ...
##  $ age     : num  43.9 17.6 15.5 44.1 14.5 ...
##  $ sex     : Factor w/ 2 levels "male","female": 1 1 2 2 2 2 2 1 2 2 ...
##  $ child   : Factor w/ 2 levels "no","yes": 1 2 2 1 2 2 1 1 2 1 ...
##  $ black   : Factor w/ 2 levels "yes","no": 2 2 2 2 2 2 2 2 2 2 ...

You can clearly see that our data is mixed with both numerical and factor variables. Therefore, the first thing we must do is calculate the gower coefficient for the dataset. This is done with the “daisy” function from the “cluster” package.

disMat<-daisy(MedExp,metric = "gower")

Now we can use the “kmeans” to make are clusters. This is possible because all the factor variables have been converted to a numerical value. We will set the number of clusters to 4. Below is the code.

mixedClusters<-kmeans(disMat, centers=4)

We can now look at a table of the clusters

##    1    2    3    4 
## 1960 1342 1356  916

The groups seem reasonably balanced. We now need to add the results of the kmeans to the original dataset. Below is the code


We now can built a descriptive table that will give us the proportions of each variable in each cluster. To do this we need to use the “compareGroups” function. We will then take the output of the “compareGroups” function and use it in the “createTable” function to get are actual descriptive stats.

## --------Summary descriptives table by 'cluster'---------
## __________________________________________________________________________ 
##                    1            2            3            4      p.overall 
##                  N=1960       N=1342       N=1356       N=916              
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ 
## med            211 (1119)   68.2 (333)   269 (820)   83.8 (210)   <0.001   
## lc            4.07 (0.60)  4.05 (0.60)  0.04 (0.39)  0.03 (0.34)   0.000   
## idp:                                                              <0.001   
##     no        1289 (65.8%) 922 (68.7%)  1123 (82.8%) 781 (85.3%)           
##     yes       671 (34.2%)  420 (31.3%)  233 (17.2%)  135 (14.7%)           
## lpi           5.72 (1.94)  5.90 (1.73)  3.27 (2.91)  3.05 (2.96)  <0.001   
## fmde          6.82 (0.99)  6.93 (0.90)  0.00 (0.12)  0.00 (0.00)   0.000   
## physlim:                                                          <0.001   
##     no        1609 (82.1%) 1163 (86.7%) 1096 (80.8%) 789 (86.1%)           
##     yes       351 (17.9%)  179 (13.3%)  260 (19.2%)  127 (13.9%)           
## ndisease      11.5 (8.26)  10.2 (2.97)  12.2 (8.50)  10.6 (3.35)  <0.001   
## health:                                                           <0.001   
##     excellent 910 (46.4%)  880 (65.6%)  615 (45.4%)  612 (66.8%)           
##     good      828 (42.2%)  382 (28.5%)  563 (41.5%)  261 (28.5%)           
##     fair      183 (9.34%)   74 (5.51%)  137 (10.1%)  42 (4.59%)            
##     poor       39 (1.99%)   6 (0.45%)    41 (3.02%)   1 (0.11%)            
## linc          8.68 (1.22)  8.61 (1.37)  8.75 (1.17)  8.78 (1.06)   0.005   
## lfam          1.05 (0.57)  1.49 (0.34)  1.08 (0.58)  1.52 (0.35)  <0.001   
## educdec       12.1 (2.87)  11.8 (2.58)  12.0 (3.08)  11.8 (2.73)   0.005   
## age           36.5 (12.0)  9.26 (5.01)  37.0 (12.5)  9.29 (5.11)   0.000   
## sex:                                                              <0.001   
##     male      893 (45.6%)  686 (51.1%)  623 (45.9%)  482 (52.6%)           
##     female    1067 (54.4%) 656 (48.9%)  733 (54.1%)  434 (47.4%)           
## child:                                                             0.000   
##     no        1960 (100%)   0 (0.00%)   1356 (100%)   0 (0.00%)            
##     yes        0 (0.00%)   1342 (100%)   0 (0.00%)   916 (100%)            
## black:                                                            <0.001   
##     yes       1623 (82.8%) 986 (73.5%)  1148 (84.7%) 730 (79.7%)           
##     no        337 (17.2%)  356 (26.5%)  208 (15.3%)  186 (20.3%)           
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯

The table speaks for itself. Results that utilize factor variables have proportions to them. For example, in cluster 1, 1289 people or 65.8% responded “no” that the have an individual deductible plan (idp). Numerical variables have the mean with the standard deviation in parentheses. For example, in cluster 1 the average family size was 1 with a standard deviation of 1.05 (lfam).


Mixed data can be partition into clusters with the help of the gower or another coefficient. In addition, kmeans is not the only way to cluster the data. There are other choices such as the partitioning around medoids. The example provided here simply serves as a basic introduction to this.

Hierarchical Clustering in R

Hierarchical clustering is a form of unsupervised learning. What this means is that the data points lack any form of label and the purpose of the analysis is to generate labels for our data points. IN other words, we have no Y values in our data.

Hierarchical clustering is an agglomerative technique. This means that each data point starts as their own individual clusters and are merged over iterations. This is great for small datasets but is difficult to scale. In addition, you need to set the linkage which is used to place observations in different clusters. There are several choices (ward, complete, single, etc.) and the best choice depends on context.

In this post, we will make a hierarchical clustering analysis of the “MedExp” data from the “Ecdat” package. We are trying to identify distinct subgroups in the sample. The actual hierarchical cluster creates what is a called a dendrogram. Below is some initial code.

## 'data.frame':    5574 obs. of  15 variables:
##  $ med     : num  62.1 0 27.8 290.6 0 ...
##  $ lc      : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ idp     : Factor w/ 2 levels "no","yes": 2 2 2 2 2 2 2 2 1 1 ...
##  $ lpi     : num  6.91 6.91 6.91 6.91 6.11 ...
##  $ fmde    : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ physlim : Factor w/ 2 levels "no","yes": 1 1 1 1 1 2 1 1 1 1 ...
##  $ ndisease: num  13.7 13.7 13.7 13.7 13.7 ...
##  $ health  : Factor w/ 4 levels "excellent","good",..: 2 1 1 2 2 2 2 1 2 2 ...
##  $ linc    : num  9.53 9.53 9.53 9.53 8.54 ...
##  $ lfam    : num  1.39 1.39 1.39 1.39 1.1 ...
##  $ educdec : num  12 12 12 12 12 12 12 12 9 9 ...
##  $ age     : num  43.9 17.6 15.5 44.1 14.5 ...
##  $ sex     : Factor w/ 2 levels "male","female": 1 1 2 2 2 2 2 1 2 2 ...
##  $ child   : Factor w/ 2 levels "no","yes": 1 2 2 1 2 2 1 1 2 1 ...
##  $ black   : Factor w/ 2 levels "yes","no": 2 2 2 2 2 2 2 2 2 2 ...

Currently, for the purposes of this post. The dataset is too big. IF we try to do the analysis with over 5500 observations it will take a long time. Therefore, we will only use the first 1000 observations. In addition, We need to remove factor variables as hierarchical clustering cannot analyze factor variables. Below is the code.


We now need to scale are data. This is important because different scales will cause different variables to have more or less influence on the results. Below is the code


We now need to determine how many clusters to create. There is no rule on this but we can use statistical analysis to help us. The “NbClust” package will conduct several different analysis to provide a suggested number of clusters to create. You have to set the distance, min/max number of clusters, the method, and the index. The graphs can be understood by looking for the bend or elbow in them. At this point is the best number of clusters.

numComplete<-NbClust(MedExp_small_df,distance = 'euclidean', = 2, = 8,method = 'ward.D2',index = c('all'))


## *** : The Hubert index is a graphical method of determining the number of clusters.
##                 In the plot of Hubert index, we seek a significant knee that corresponds to a 
##                 significant increase of the value of the measure i.e the significant peak in Hubert
##                 index second differences plot. 


## *** : The D index is a graphical method of determining the number of clusters. 
##                 In the plot of D index, we seek a significant knee (the significant peak in Dindex
##                 second differences plot) that corresponds to a significant increase of the value of
##                 the measure. 
## ******************************************************************* 
## * Among all indices:                                                
## * 7 proposed 2 as the best number of clusters 
## * 9 proposed 3 as the best number of clusters 
## * 6 proposed 6 as the best number of clusters 
## * 1 proposed 8 as the best number of clusters 
##                    ***** Conclusion *****                            
## * According to the majority rule, the best number of clusters is  3 
## *******************************************************************
##                     KL       CH Hartigan     CCC    Scott      Marriot
## Number_clusters 2.0000   2.0000   6.0000  8.0000    3.000 3.000000e+00
## Value_Index     2.9814 292.0974  56.9262 28.4817 1800.873 4.127267e+24
##                   TrCovW   TraceW Friedman   Rubin Cindex     DB
## Number_clusters      6.0   6.0000   3.0000  6.0000  2.000 3.0000
## Value_Index     166569.3 265.6967   5.3929 -0.0913  0.112 1.0987
##                 Silhouette   Duda PseudoT2  Beale Ratkowsky     Ball
## Number_clusters     2.0000 2.0000   2.0000 2.0000    6.0000    3.000
## Value_Index         0.2809 0.9567  16.1209 0.2712    0.2707 1435.833
##                 PtBiserial Frey McClain   Dunn Hubert SDindex Dindex
## Number_clusters     6.0000    1   3.000 3.0000      0  3.0000      0
## Value_Index         0.4102   NA   0.622 0.1779      0  1.9507      0
##                   SDbw
## Number_clusters 3.0000
## Value_Index     0.5195

Simple majority indicates that three clusters is most appropriate. However, four clusters are probably just as good. Every time you do the analysis you will get slightly different results unless you set the seed.

To make our actual clusters we need to calculate the distances between clusters using the “dist” function while also specifying the way to calculate it. We will calculate distance using the “Euclidean” method. Then we will take the distance’s information and make the actual clustering using the ‘hclust’ function. Below is the code.

distance<-dist(MedExp_small_df,method = 'euclidean')
hiclust<-hclust(distance,method = 'ward.D2')

We can now plot the results. We will plot “hiclust” and set hang to -1 so this will place the observations at the bottom of the plot. Next, we use the “cutree” function to identify 4 clusters and store this in the “comp” variable. Lastly, we use the “ColorDendrogram” function to highlight are actual clusters.

plot(hiclust,hang=-1, labels=F)
comp<-cutree(hiclust,4) ColorDendrogram(hiclust,y=comp,branchlength = 100)


We can also create some descriptive stats such as the number of observations per cluster.

## comp
##   1   2   3   4 
## 439 203 357   1

We can also make a table that looks at the descriptive stats by cluster by using the “aggregate” function.

##   Group.1         med         lc        lpi       fmde     ndisease
## 1       1  0.01355537 -0.7644175  0.2721403 -0.7498859  0.048977122
## 2       2 -0.06470294 -0.5358340 -1.7100649 -0.6703288 -0.105004408
## 3       3 -0.06018129  1.2405612  0.6362697  1.3001820 -0.002099968
## 4       4 28.66860936  1.4732183  0.5252898  1.1117244  0.564626907
##          linc        lfam    educdec         age
## 1  0.12531718 -0.08861109  0.1149516  0.12754008
## 2 -0.44435225  0.22404456 -0.3767211 -0.22681535
## 3  0.09804031 -0.01182114  0.0700381 -0.02765987
## 4  0.18887531 -2.36063161  1.0070155 -0.07200553

Cluster 1 is the most educated (‘educdec’). Cluster 2 stands out as having higher medical cost (‘med’), chronic disease (‘ndisease’) and age. Cluster 3 had the lowest annual incentive payment (‘lpi’). Cluster 4 had the highest coinsurance rate (‘lc’). You can make boxplots of each of the stats above. Below is just an example of age by cluster.




Hierarchical clustering is one way in which to provide labels for data that does not have labels. The main challenge is determining how many clusters to create. However, this can be dealt with through using recommendations that come from various functions in R.

Validating a Logistic Model in R

In this post, we are going to continue are analysis of the logistic regression model from the the post on logistic regression  in R. We need to rerun all of the code from the last post to be ready to continue. As such the code form the last post is all below

pm<-melt(survey, id.var="Sex")
ggplot(pm,aes(Sex,value))+geom_boxplot()+facet_wrap(~variable,ncol = 3)


set.seed(123) ind<-sample(2,nrow(survey),replace=T,prob = c(0.7,0.3)) train<-survey[ind==1,] test<-survey[ind==2,] fit<-glm(Sex~.,binomial,train) exp(coef(fit))

train$probs<-predict(fit, type = 'response')
test$prob<-predict(fit,newdata = test, type = 'response')

Model Validation

We will now do a K-fold cross validation in order to further see how our model is doing. We cannot use the factor variable “Sex” with the K-fold code so we need to create a dummy variable. First, we create a variable called “y” that has 123 spaces, which is the same size as the “train” dataset. Second, we fill “y” with 1 in every example that is coded “male” in the “Sex” variable.

In addition, we also need to create a new dataset and remove some variables from our prior analysis otherwise we will confuse the functions that we are going to use. We will remove “predict”, “Sex”, and “probs”


We now can do our K-fold analysis. The code is complicated so you can trust it and double check on your own.

bestglm(,IC="CV",CVArgs = list(Method="HTF",K=10,REP=1),family = binomial)
## Morgan-Tatar search since family is non-gaussian.
## CV(K = 10, REP = 1)
## BICq equivalent for q in (6.66133814775094e-16, 0.0328567092272112)
## Best Model:
##                Estimate Std. Error   z value     Pr(>|z|)
## (Intercept) -45.2329733 7.80146036 -5.798014 6.710501e-09
## Height        0.2615027 0.04534919  5.766425 8.097067e-09

The results confirm what we alreaedy knew that only the “Height” variable is valuable in predicting Sex. We will now create our new model using only the recommendation of the kfold validation analysis. Then we check the new model against the train dataset and with the test dataset. The code below is a repeat of prior code but based on the cross-validation<-glm(Sex~Height, family=binomial,train)
##          Female Male
##   Female     61   11
##   Male        7   44
## [1] 0.8536585
test$cv.probs<-predict(,test,type = 'response')
##          Female Male
##   Female     16    7
##   Male        1   22
## [1] 0.826087

The results are consistent for both the train and test dataset. We are now going to create the ROC curve. This will provide a visual and the AUC number to further help us to assess our model. However, a model is only good when it is compared to another model. Therefore, we will create a really bad model in order to compare it to the original model, and the cross validated model. We will first make a bad model and store the probabilities in the “test” dataset. The bad model will use “age” to predict “Sex” which doesn’t make any sense at all. Below is the code followed by the ROC curve of the bad model.<-glm(Sex~Age,family = binomial,test)


The more of a diagonal the line is the worst it is. As, we can see the bad model is really bad.

What we just did with the bad model we will now repeat for the full model and the cross-validated model.  As before, we need to store the prediction in a way that the ROCR package can use them. We will create a variable called “pred.full” to begin the process of graphing the the original full model from the last blog post. Then we will use the “prediction” function. Next, we will create the “perf.full” variable to store the performance of the model. Notice, the arguments ‘tpr’ and ‘fpr’ for true positive rate and false positive rate. Lastly, we plot the results

plot(perf.full, col=2)


We repeat this process for the cross-validated model<-prediction(test$cv.probs,test$Sex)<-performance(,'tpr','fpr')


Now let’s put all the different models on one plot

plot(perf.full, col=2, add=T)
legend(.7,.4,c("BAD","FULL","CV"), 1:3)


Finally, we can calculate the AUC for each model

## [[1]]
## [1] 0.4766734
## [[1]]
## [1] 0.959432<-performance(,'auc')
## [[1]]
## [1] 0.9107505

The higher the AUC the better. As such, the full model with all variables is superior to the cross-validated or bad model. This is despite the fact that there are many high correlations in the full model as well. Another point to consider is that the cross-validated model is simpler so this may be a reason to pick it over the full model. As such, the statistics provide support for choosing a model but the do not trump the ability of the research to pick based on factors beyond just numbers.

Logistic Regression in R

In this post, we will conduct a logistic regression analysis. Logistic regression is used when you want to predict a categorical dependent variable using continuous or categorical dependent variables. In our example, we want to predict Sex (male or female) when using several continuous variables from the “survey” dataset in the “MASS” package.

?MASS::survey #explains the variables in the study

The first thing we need to do is remove the independent factor variables from our dataset. The reason for this is that the function that we will use for the cross-validation does not accept factors. We will first use the “str” function to identify factor variables and then remove them from the dataset. We also need to remove in examples that are missing data so we use the “na.omit” function for this. Below is the code


We now need to check for collinearity using the “corrplot.mixed” function form the “corrplot” package.



We have extreme correlation between “We.Hnd” and “NW.Hnd” this makes sense because people’s hands are normally the same size. Since this blog post  is a demonstration of logistic regression we will not worry about this too much.

We now need to divide our dataset into a train and a test set. We set the seed for. First we need to make a variable that we call “ind” that is randomly assigns 70% of the number of rows of survey 1 and 30% 2. We then subset the “train” dataset by taking all rows that are 1’s based on the “ind” variable and we create the “test” dataset for all the rows that line up with 2 in the “ind” variable. This means our data split is 70% train and 30% test. Below is the code

ind<-sample(2,nrow(survey),replace=T,prob = c(0.7,0.3))

We now make our model. We use the “glm” function for logistic regression. We set the family argument to “binomial”. Next, we look at the results as well as the odds ratios.

## Call:
## glm(formula = Sex ~ ., family = binomial, data = train)
## Deviance Residuals: 
##     Min       1Q   Median       3Q      Max  
## -1.9875  -0.5466  -0.1395   0.3834   3.4443  
## Coefficients:
##              Estimate Std. Error z value Pr(>|z|)    
## (Intercept) -46.42175    8.74961  -5.306 1.12e-07 ***
## Wr.Hnd       -0.43499    0.66357  -0.656    0.512    
## NW.Hnd        1.05633    0.70034   1.508    0.131    
## Pulse        -0.02406    0.02356  -1.021    0.307    
## Height        0.21062    0.05208   4.044 5.26e-05 ***
## Age           0.00894    0.05368   0.167    0.868    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## (Dispersion parameter for binomial family taken to be 1)
##     Null deviance: 169.14  on 122  degrees of freedom
## Residual deviance:  81.15  on 117  degrees of freedom
## AIC: 93.15
## Number of Fisher Scoring iterations: 6
##  (Intercept)       Wr.Hnd       NW.Hnd        Pulse       Height 
## 6.907034e-21 6.472741e-01 2.875803e+00 9.762315e-01 1.234447e+00 
##          Age 
## 1.008980e+00

The results indicate that only height is useful in predicting if someone is a male or female. The second piece of code shares the odds ratios. The odds ratio tell how a one unit increase in the independent variable leads to an increase in the odds of being male in our model. For example, for every one unit increase in height there is a 1.23 increase in the odds of a particular example being male.

We now need to see how well our model does on the train and test dataset. We first capture the probabilities and save them to the train dataset as “probs”. Next we create a “predict” variable and place the string “Female” in the same number of rows as are in the “train” dataset. Then we rewrite the “predict” variable by changing any example that has a probability above 0.5 as “Male”. Then we make a table of our results to see the number correct, false positives/negatives. Lastly, we calculate the accuracy rate. Below is the code.

train$probs<-predict(fit, type = 'response')
##          Female Male
##   Female     61    7
##   Male        7   48
## [1] 0.8861789

Despite the weaknesses of the model with so many insignificant variables it is surprisingly accurate at 88.6%. Let’s see how well we do on the “test” dataset.

test$prob<-predict(fit,newdata = test, type = 'response')
##          Female Male
##   Female     17    3
##   Male        0   26
## [1] 0.9347826

As you can see, we do even better on the test set with an accuracy of 93.4%. Our model is looking pretty good and height is an excellent predictor of sex which makes complete sense. However, in the next post we will use cross-validation and the ROC plot to further assess the quality of it.

Generalized Additive Models in R

In this post, we will learn how to create a generalized additive model (GAM). GAMs are non-parametric generalized linear models. This means that linear predictor of the model uses smooth functions on the predictor variables. As such, you do not need to specific the functional relationship between the response and continuous variables. This allows you to explore the data for potential relationships that can be more rigorously tested with other statistical models

In our example, we will use the “Auto” dataset from the “ISLR” package and use the variables “mpg”,“displacement”,“horsepower”,and “weight” to predict “acceleration”. We will also use the “mgcv” package. Below is some initial code to begin the analysis


We will now make the model we want to understand the response of “accleration” to the explanatory variables of “mpg”,“displacement”,“horsepower”,and “weight”. After setting the model we will examine the summary. Below is the code

## Family: gaussian 
## Link function: identity 
## Formula:
## acceleration ~ s(mpg) + s(displacement) + s(horsepower) + s(weight)
## Parametric coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 15.54133    0.07205   215.7   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## Approximate significance of smooth terms:
##                   edf Ref.df      F  p-value    
## s(mpg)          6.382  7.515  3.479  0.00101 ** 
## s(displacement) 1.000  1.000 36.055 4.35e-09 ***
## s(horsepower)   4.883  6.006 70.187  < 2e-16 ***
## s(weight)       3.785  4.800 41.135  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## R-sq.(adj) =  0.733   Deviance explained = 74.4%
## GCV = 2.1276  Scale est. = 2.0351    n = 392

All of the explanatory variables are significant and the adjust r-squared is .73 which is excellent. edf stands for “effective degrees of freedom”. This modified version of the degree of freedoms is due to the smoothing process in the model. GCV stands for generalized cross validation and this number is useful when comparing models. The model with the lowest number is the better model.

We can also examine the model visually by using the “plot” function. This will allow us to examine if the curvature fitted by the smoothing process was useful or not for each variable. Below is the code.



We can also look at a 3d graph that includes the linear predictor as well as the two strongest predictors. This is done with the “vis.gam” function. Below is the code



If multiple models are developed. You can compare the GCV values to determine which model is the best. In addition, another way to compare models is with the “AIC” function. In the code below, we will create an additional model that includes “year” compare the GCV scores and calculate the AIC. Below is the code.

## Family: gaussian 
## Link function: identity 
## Formula:
## acceleration ~ s(mpg) + s(displacement) + s(horsepower) + s(weight) + 
##     s(year)
## Parametric coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 15.54133    0.07203   215.8   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## Approximate significance of smooth terms:
##                   edf Ref.df      F p-value    
## s(mpg)          5.578  6.726  2.749  0.0106 *  
## s(displacement) 2.251  2.870 13.757 3.5e-08 ***
## s(horsepower)   4.936  6.054 66.476 < 2e-16 ***
## s(weight)       3.444  4.397 34.441 < 2e-16 ***
## s(year)         1.682  2.096  0.543  0.6064    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## R-sq.(adj) =  0.733   Deviance explained = 74.5%
## GCV = 2.1368  Scale est. = 2.0338    n = 392
#model1 GCV
##   GCV.Cp 
## 2.127589
#model2 GCV
##   GCV.Cp 
## 2.136797

As you can see, the second model has a higher GCV score when compared to the first model. This indicates that the first model is a better choice. This makes sense because in the second model the variable “year” is not significant. To confirm this we will calculate the AIC scores using the AIC function.

##              df      AIC
## model1 18.04952 1409.640
## model2 19.89068 1411.156

Again, you can see that model1 s better due to its fewer degrees of freedom and slightly lower AIC score.


Using GAMs is most common for exploring potential relationships in your data. This is stated because they are difficult to interpret and to try and summarize. Therefore, it is normally better to develop a generalized linear model over a GAM due to the difficulty in understanding what the data is trying to tell you when using GAMs.

Wire Framing with Moodle

Before teaching a Moodle course it is critical that a teacher design what they want to do. For many teachers, they believe that they begin the design process by going to Moodle and adding activity and other resources to their class. For someone who is thoroughly familiar with Moodle and have developed courses before this might work. However, for the majority online teachers they need to wire frame what they want their moodle course to look like online.

Why Wire frame a Moodle Course

In the world of  web developers a wire frame is a prototype of what a potential website will look like. The actual wire frame can be made in many different platforms from Word, powerpoint, and even just paper and pencil. Since Moodle is online a Moodle course in many ways is a website so wire framing applies to this context.

It doesn’t matter how a you wire frames their Moodle course. What matters is that you actually do this. Designing what you want to see in your course helps you to make decisions much faster when you are actually adding activities and resources to your Moodle course. It also helps your Moodle support to help you if they have a picture of what the you wants rather than wild hand gestures and frustration.

Wire farming a course also reduces the cognitive load on the teacher. Instead of designing and building the course a the same time. Wire framing splits this task into two steps, which are designing, and then building. This prevents extreme frustration as it is common for a teacher just to stare at the computer screen when trying to design and develop a Moodle course simultaneously.

You never see and architect making his plans while building the building. This would seem careless and even dangerous because the architect doesn’t even know what he wants while he is throwing around concrete and steel. The same analogy applies with designing Moodle courses. A teacher must know what they want, write it down, and then implement it by creating the course.

Another benefit of planning in Word is that it is easier to change things in Word when compared to Moodle. Moodle is amazing but it is not easy to use for those who are not tech-savvy. However, it’s easiest for most of us to copy, paste, and edit in Word.

One Way to Wire Frame a Moodle Course

When supporting teachers to wire frame a Moodle course, I always encourage them to start by developing the course in Microsoft Word. The reason being that the teacher is already familiar with Word and they do not have to struggle to make decisions when using it. This helps them to focus on content and not on how to use Microsoft Word.

One of the easiest ways to wire frame a Moodle course is to take the default topics of a course such as General Information, Week 1, Week 2, etc. and copy these headings into Word, as shown below.

Screenshot from 2017-01-20 09-15-19.png

Now, all that is needed is to type in using bullets exactly what activities and resources you want in each section. It is also possible to add pictures and other content to the Word document that can be added to Moodle later.  Below is a preview of a generic Moodle sample course with the general info and week 1 of the course completed.

Screenshot from 2017-01-20 09-26-00.png

You can see for yourself how this class is developed. The General Info section has an image to serve as a welcome and includes the name of the course. Under this the course outline and rubrics for the course. The information in the parentheses indicate what type of module it is.

For Week 1, there are several activities. There is a forum for introducing yourself. A page that shares the objectives of that week. Following this are the readings for the week, then a discussion forum, and lastly an assignment. This process completes for however many weeks are topics you have in the course.

Depending on the your need to plan, you can even planned other pages on the site beside the main page. For example, I can wire frame what I want my “Objectives” page to look like or even the discussion topics for my “Discussion” forum.

Of course, the ideas for all these activities comes from the course outline or syllabus that was developed first. In other words, before we even wire frame we have some sort of curriculum document with what the course needs to cover.


The example above is an extremely simple way of utilizing the power of wire framing. With this template, you can confidently go to Moodle and find the different modules to make your class come to life. Trying to conceptualize this in your head is possible but much more difficult. As such, thorough planning is a hallmark of learning.


Teaching Advanced ESL Students

Advanced ESL students have their own unique set of traits and challenges that an ESL teacher must deal. This post will explain some of these unique traits as well as how to support advanced ESL students.

Supporting Advanced ESL Students

By this point, the majority of the language processing is automatic. This means that the teacher no longer needs to change the speed at which they talk in most situations.

In addition, the students have become highly independent. This necessitates that the teacher focus on supporting the learning experience  of the students rather than trying to play a more directive role.

The learning activities used in the classroom can now cover a full range of possibilities. Almost all causal reading material is appropriate. Study skills can be addressed at a much deeper level. Such skills as skimming, scanning, determining purpose, etc. can be taught and addressed in the learning. Students can also enjoy debates and author opinion generating experiences.

The Challenges of Advanced ESL Students

One of the challenges of advanced students is they often have a habit of asking the most detailed questions about the most obscure aspects of the target language. To deal this requires a PhD in linguistics or the ability to know what the students really need to know and steer away from mundane grammatical details. It is very tempting to try and answer these types of questions but the average native-speaker does not know all the details of imperfect past tense but rather are much more adept at using it.

Another frustrating problem with advanced students is the ability to continue to make progress in their language development. With any skill, as one gets closer to mastery, the room for improvement becomes smaller and smaller. To move from an advanced student to a superior student takes make several small rather than sweeping adjustments.

This is one reason advanced students often like to ask those minute grammar questions. These small question is where they know they are weak when it comes to communicating. This can be especially stressful if the student is a few points away from reaching some sort of passing score on an English proficiency exam (IELTS, TOEFL, etc.). Minor adjustments need to reach the minimum score are difficult to determine and train.


After beginners, teaching advanced esl students is perhaps the next most challenging teaching experience. Advanced ESL students have a strong sense of what they know and do not know. What makes this challenging is the information they need to understand can be considered some what specializes and not easy to articulate for many teachers.

Using Groups and Groupings in Activities in Moodle

Making groups and groupings are two features in Moodle that can be used for collaboration and or for organizational purposes in a class. This post will provide examples of how to use groups in an activity in Moodle

Using Groups/Groupings in a Forum

Groups and Groupings can be used in a Forum in order to allow groups to interact during a discussion topic. It is assumed that you already know how to make a forum in Moodle.  Therefore, the instruction in this post will start from the settings window for forums in Moodle.

  1.  The option that we need to adjust to use groups in forums is the “Common Module Settings”. If you click on this, you will see the following.

Screenshot from 2016-12-05 09-43-54.png

2. Depending on your goals there are several different ways that groups can be used.

  • Group mode can be set to visible or separate groups. If groups are visible different groups can see each others discussion but they can only post in their own groups discussion.
  • If separate group is selected. Groups will only be able to see their own group’s discussion and no other.
  • If the grouping feature is used. Only the groups that are a part of that grouping are added to the forum. The group mode determines if the groups can see each other or not.

In this example we will select group mode set to “visible groups” and groupings to “none once you click “save and display” you will see the following.

Screenshot from 2016-12-05 11-24-56.png

3. To see what each group said in their discussion click “all participants” and a drop down menu will be displayed that shows each group.

Using Grouping for Assignments

To use groups in assignments you repeat the steps above. In this example, we will use the grouping feature.

  1. The features are viewable in the picture below. I selected “separate groups” and I selected the grouping I wanted. This means only groups in the grouping will have this assignment available to them


2. Another set a features you want to set for an assignment is the “group submission settings”. The options are self-explanatory but here is what I selected.

Screenshot from 2016-12-05 11-31-12.png

3. Click save a display and you will see the following

Screenshot from 2016-12-05 11-32-33.png

The red messages just states that some people are in more than one group or not in any group. For this example, this is not a problem as I did not assign all students to a group.


The concepts presented here for forums and assignments apply to most activities involving groups in Moodle. Group is very useful for large classes in which students need a space in which they can having meaningful communication with a handful of peers.

Making Groups in Moodle

One of the many features available for teachers to use is the group mode for activities within a course in Moodle. This post will look at how to setup groups in a Moodle course.

What to Use the Group Mode For?

As with other features in Moodle, the challenge with the group mode is that you can use it for almost anything. The unlimited variety in terms of the application of the group mode makes it challenge for novices to understand and appreciate it. This is because as humans we often want a single clear way  to use something. Below are several different ways in which the group mode can be used in a Moodle course.

  • If the same Moodle course is used for two or more different sections the group mode can be used to put students in the same moodle course into different groups by section. For example, if a teacher is teaching two sections of English 101, section 1 would be one group and section 2 would be the other group.
  • Groups can also be used so that only certain groups see certain things in a Moodle course. In Moodle, you can limit who sees what be restricting to a certain group.
  • A more traditional use is to have students placed in groups to complete group assignments. Placing them in groups allows the group to submit one assignment that Moodle gives all members of the group credit for when it is marked.

If this is not confusing enough, you can also have students in several different groups simultaneously if you wanted. Therefore, whenever you are trying to use Moodle you need to consider what your goal is rather than whether it is possible to do it in Moodle. As stated before, the problem is the flexibility of Moodle and not its inability to facilitate a learning task.

In this post, we are only going to learn how to make groups. In a future post, we will look at using groups in terms of teaching and assignments.

Creating Groups in Moodle

  1. After logging into Moodle and selecting a course, you need to go to course administration->users->groups. If you do this correctly you should see the following

Screenshot from 2016-11-30 08-19-06.png

2. There are several things to mention before continuing

First, there are two different ways to create groups. You can create them manually by clicking on “create groups” or you can have Moodle make the groups using the “Auto-create groups” button. The auto-group option will be explained in a later post as welling as the grouping feature.

Second, there is a tab called “grouping” this is a feature that allows you to create a group of groups. In other words, several groups can be assigned to a grouping.  This allows you to assign several groups to an activity simultaneously rather than having to add each on manually. This is a great feature for a course that has two sections and each section has group activities. For now we will learn how to make groups manually.

Lastly, the column on the left, called “groups” will display the name of any groups that are created while the column on the left, called “members of” will contain the names of people who are a part of the group. Right now both are empty because there are no groups yet.

3. Click on the “create group” group button and you will see the following.

Screenshot from 2016-11-30 08-26-46.png

4. You now need to give the group a name. You also have the privilege to add other information if you want such as description or even a picture to represent the group. After providing the needed information you need to click “save changes” in order to see the following.

Screenshot from 2016-11-30 08-30-37.png

5. To add members to our practice group we need to click on the “add/remove” button. After doing this, you will see the following.

Screenshot from 2016-11-30 08-33-46.png

6. There are two columns, “potential members” and “group members.” To add people to the “group members” section just highlight whoever you want in the “potential members” side and click “add”. Below is an example of this

Screenshot from 2016-11-30 08-53-02.png

Just a note, at the bottom of both the “group member” and “potential member” list is a search function that can be used to find specific people in either section.

7. After placing people in the group, you can click on the “back to group” button. You will see the following.

Screenshot from 2016-11-30 09-01-57.png

The group name is displayed on the left and the members of the group are displayed on the right.


In this post we learned how to create groups. However, we have not learned yet how to use groups in a moodle course yet. This will be explained in a future post.

Inquiry Learning

From the archives

educational research techniques

Inquiry learning is form of indirect instruction. Indirect instruction is teaching in which the students are actively involved in their learning by seeking solutions to problems or questions. In inquiry learning, students develop and investigate questions that they may have. The focus in inquiry learning is on what the students want to learn with some support from the teacher about a topic. Below are the steps of inquiry learning.

  1. Ask
  2. Investigate
  3. Create
  4. Discuss
  5. Reflect

Step 1: Ask

The teacher begins this process by taking the topic of the lesson and turning it into a question for the students to consider. For example, if the topic of a lesson is about flowers, a question to ask would be “How are flowers different from each other?” This is called the teacher-initiated stage of asking.

The student then develop their own questions that should help to answer the main question posed by the…

View original post 344 more words

Teaching Beginning ESL Students

Beginning ESL students have unique pedagogical needs that make them the most difficult to teach. It’s similar to the challenge of teaching kindergarten. The difficulty is not the content  but rather stripping what is already a basic content into something that is understandable for the most undeveloped of students. Some of the best teachers cannot do this.

This post will provide some suggestions on how to deal with beginning ESL students.

Take Your Time

Beginning students need a great deal of repetition. If you have ever tried to learn a language you probably needed to hear phrases many times to understand them. Repetition helps students to remember and imitate what they heard.

This means that the teacher needs to limit the amount of words, phrases, and sentences they teach. This is not easy, especially for new teachers who are often put in charge of teaching beginners and race through the curriculum to the frustration of the beginning students.

Repetition and a slow pace helps students to develop the automatic processing they need in order to achieve fluency. This can also be enhanced by focusing on purpose in communication rather than the grammatical structure of language.

The techniques use din class should short and simple with a high degree variety to offset the boredom of repetition. In other words, find many ways to teach one idea or concept.

Who’s the Center

Beginning students are highly teacher-dependent because of their lack of skills. Therefore, at least initially, the classroom should probably be teacher-centered until the students develop some basic skills.  In general, whenever you are dealing with a new subject the students are totally unfamiliar with it is better to have a higher degree of control of the learning experience.

Being the center of the learning experiences requires the teacher to provide most of the examples of well-spoken, written English. Your feedback is critical for the students to develop their own language skills. The focus should be more towards fluency rather than accuracy.

However, with time cooperative and student-centered activities can become more prominent. In the beginning, too much freedom can be frustrating for language learners who lack any sort of experience to draw upon to complete activities. Within a controlled environment, student creativity can blossom.


Being a beginning level ESL teacher is a tough job. It requires a skill set of patience, perseverance, and a gift at simplicity.  Taking your time and determining who the center of learning is are ways in which to enhances success for those teaching beginners


Learner-Centered Instruction

Learner-centered instruction is a term that has been used in education for several decades now. One of the challenges of extremely popular terms in a field such as learner-centered instruction is that the term losses its meaning as people throw it into a discussion with  knowing  exactly what the term means.

The purpose of this post is to try and explain some of the  characteristics of learner-centered instruction without being exhaustive.  In addition, we will look at the challenges to this philosophy as well as ways to make it happen in the classroom.

Focus on the Students

Learner-centered instruction is focused on  the students. What this means is that the teacher takes into account the learning goals and objectives of the students in establishing what to teach. This requires the teacher to conduct at least an informal needs assessment to figure out what the students want to learn.

Consultation with the students allows for the students to have some control over their learning which is empowering as viewed by those who ascribe to critical theory. Consultation also allows students to be creative and innovative. This sounds like a perfect learning situation but to be  this centered  on the learner can be difficult

Challenge of Learner-Centered Instruction

Since the learning experience is determined by the students, the teacher does not have any presupposed plan in place prior to consulting with the students. As such, not having a plan in  place before hand is extremely challenging for new teachers and difficult even for experienced ones. The teacher doesn’t know what to expect in terms of the needs of the students.

In theory, almost no class follows such a stringent approach to learner-centered instruction. Most schools have to meet government requirements, prepare students for the work place, and or show improvements in testing. This limits the freedom of the teacher to be learner-centered in many ways. External factors cannot be  ignored to adhere to the philosophy of learner-centered instruction.

Finding a Compromise

One way to be learner-centered while still having some sort of a plan prior to teaching is to rethink the level at which the students have voice in the  curriculum. For example, if it is not possible to change the objectives of a course, the teacher  can have the students develop the assignments they want to do to achieve an objective.

The teacher could also allow the students to pick from several different assignments that all help to achieve the same objective(s). This gives the students some control over their learning while allowing the teacher to adhere to external requirements. It also allows the teacher to be prepared in some way prior to the teaching.


The average educator does not have the autonomy to give to students to allow for the full implementation of learner-centered instruction. However, there are several ways to adjust one’s approach to teaching that will allow students to have a sense of control over their learning.

Axis and Labels in ggplot2

In this post, we will look at how to manipulate the labels and positioning of the data when using ggplot2. We will use the “Wage” data from the “ISLR” package. Below is initial code needed to begin.


Manipulating Labels

Our first example involves adding labels for the x, y axis as well as a title. To do this we will create a histgram of the wage variable and save it as a variable in R. By saving the histogram as a variable it saves time as we do not have to recreate all of the code but only add the additional information. After creating the histogram and saving it to a variable we will add the code for creating the labels. Below is the code

myHistogram<-ggplot(Wage, aes(wage, fill=..count..))+geom_histogram()
myHistogram+labs(title="This is My Histogram", x="Salary as a Wage", y="Number")
download (17).png

By using the “labs” function you can add a title and information for the x and y axis. If your title is really long you can use the code “” to break the information into separate lines as shown below.

myHistogram+labs(title="This is the Longest Title for a Histogram \n that I have ever Seen in My Entire Life", x="Salary as a Wage", y="Number")
download (18).png

Discrete Axis Scale

We will now turn our attention to working with discrete scales. Discrete scales deal with categorical data such as boxplots and bar charts. First, we will store a boxplot of the wages subsetted by level of education in a variable and we will display it.

myBoxplot<-ggplot(Wage, aes(education, wage,fill=education))+geom_boxplot()


Now, by using the “scale_x_discrete” function along with the “limits” argument we are able to change the order of the gorups as shown below

myBoxplot+scale_x_discrete(limits=c("5. Advanced Degree","2. HS Grad","1. < HS Grad","4. College Grad","3. Some College"))

download (20).png

Continuous Scale

The most common modification to a continuous scale is to modify the range. In the code below, we change the default range of “myBoxplot” to something that is larger.


download (21).png


This post provided some basic insights into modifiying plots using ggplot2.

Pie Charts and More Using ggplot2

This post will explain several types of visuals that can be developed in using ggplot2. In particular, we are going to make three specific types of charts and they are…

  • Pie chart
  • Bullseye chart
  • Coxcomb diagram

To complete this ask, we will use the “Wage” dataset from the “ISLR” package. We will nbe using the “education” variable which has five factors in it. Below is the initial code to get started.


Pie Chart

In order to make a pie chart, we first need to make a bar chart and add several pieces of code to change it into a pie chart. Below is the code for making a regular bar plot.

ggplot(Wage, aes(education, fill=education))+geom_bar()

download (11).png

We will now modify two parts of the code. First, we do not want separate bars. Instead we want one bar. The reason being is that we only want one pie chart so before that we need one bar. Therefore, for the x value in the “aes” function we will use the argument “factor(1)” which tells R to force the data as one factor on the chart thus making one bar. We also need to add the “width=1” inside the “geom_bar” function. This helps with spacing. Below is the code for this

ggplot(Wage, aes(factor(1), fill=education))+geom_bar(width=1)


To make the pie chart, we need to add the “coord_polar” function to the code which adjusts the mapping. We will include the argument “theta=y” which tells R that the size of the pie a factor gets depends on the number of people in that factor. Below is the code for the pie chart.

ggplot(Wage, aes(factor(1), fill=education))+

download (13).png

By changing the “width” argument you can place a circle in the middle of the chart as shown below.

ggplot(Wage, aes(factor(1), fill=education))+

download (14).png

Bullseye Chart

A bullseye chart is a pie chart that share the information in a concentric way. The coding is mostly the same except that you remove the “theta” argument from the “coord_polar” function. The thicker the circle the more respondents within it. Below is the code

ggplot(Wage, aes(factor(1), fill=education))+

download (15).png

Coxcomb Diagram

The Coxcomb Diagram is similiar to the pie chart but the data is not normalized to fit the entire area of the circle. To make this plot we have to modify the code to make the by removing the “factor(1)” argument and replacing it with the name of the variable and be readding the “coord_polor” function. Below is the code

ggplot(Wage, aes(education, fill=education))+

download (16).png


These are just some of the many forms of visualizations available using ggplot2. Which to use depends on many factors from personal preference to the needs of the audience.

Providing Quiz Feedback in Moodle

Like all of it’s other features in Moodle, the quiz module has so many options as to make it difficult to use. In this post, we are going to look at providing feedback to students for their participation in a quiz.

In the example used in this post, we are going to use a quiz that was already developed in a prior post as the example for this blogpost.

The first step is to click on “edit settings” to display all of the various options available for the quiz. Once there, you want to scroll down to “review options”. After doing this you will see the following

Screenshot from 2016-09-02 08:09:36.png

As you can see, there are four columns and under each column there are 7 choices. The columns are about the timing of the feedback. Feedback can happen immediately after an attempt, it can happen after the student finishes the quix but is still available for others to take, or it can happen after everyone has taken the quiz and the quiz is no longer available.

Which type of timing you pick depends on your goals. If the quiz is for learning and not for assessment perhaps “immediately after the attempt” is best. However, if this is a formal summative assessment it might be better to provide feedback after the quiz is closed.

The options under each column are the same. By clicking on the question mark you can get a better explanation of what it is.

Overall Feedback

One important feedback feature is “Overall Feedback”. This tells the student a general idea of their understanding. You can set it up so that different overall feedback is given based on their score. Below is a screen shot of overall feedback

Screenshot from 2016-09-02 08:44:25.png

In the example, the first boundary is for scores of 100 and above and the second boundary is for scores 1-99. Students who get 100 know they are OK while students with less than 100 will get a different feedback. You have to add boundaries manually. Also, remember to add the percent sign after the number

General Feedback and Specific Feedbackfor a Question

General feedback for a question is the feedback a person gets regardless of their answer. To find this option you need to either create a question or edit a questions.

Specific feedback depends on the answer they pick. Below is a visual of both general and specific feedback.

Screenshot from 2016-09-02 08:31:17.png

Below is an example of the feedback a student would get taking the example quiz in this post. In the picture below, the student got the question wrong and received the feedback for an incorrect response.

Screenshot from 2016-09-02 08:46:48.png


The quiz module is a great way to achieve many different forms of assessment online. Whether the assessment is formative or summative the quiz module is one option. However, due to the complex nature of Moodle it is important that a teacher knows exactly what they want before attempting to use the quiz module.

Making Quiz Questions in Moodle

One of Moodle’s many features is the quiz activity, which allows a teacher to assess a student’s knowledge in a variety of ways. However, before developing a quiz, a teacher needs to have questions developed and ready to be incorporated into the quiz.

The purpose of this post is to explain how to develop questions that are available to be used in a quiz.

Make a Category

When making questions it is important to be organized and this involves making categories in which to put your questions. To do this you need to click on course administrator|questions bank|Categories. After doing this you will see something similar to the image below.

Screenshot from 2016-08-24 09:40:53.png

You want to click add category and type a name for your category. In the picture below we named the category “example”. When you are finished click “add category and you will see the following.

Screenshot from 2016-08-24 09:43:36.png

Finding the Question Bank

Now that we have a question category we need to go to the question bank. To do so click on  course administrator|question bank. You should see something similar to the following.

Screenshot from 2016-08-24 09:36:40.png

Select the “example” category you made and then “click create new question.” You should see the following.

Screenshot from 2016-08-24 09:50:39.png

As you can see, there are many different forms of questions available. The type of questions you should ask depends on many factors. For now, we will make a true or false example question. Once you select the option for T/F question you will see the following.

Screenshot from 2016-08-24 09:54:15.png

The question name is for identifying the question in the bank and not on the quiz. Therefore, avoid calling your questions “question 1, 2,3 etc.” because if you have multiply quizzes you will not know which question one to take from your bank. You need to develop some sort of cataloging system for your questions such as the following

1 Q1 TF 2016

This means the following

  • 1 means this is number 1
  • Q1 means this is quiz 1
  • TF means the question is true false
  • 2016 is the year the question was developed

How you do this is your own decision and this is just an example.

The other boxes on this page are self-explanatory. General feedback is what the student receives whether they are right or wrong. The other feedback is given depending on the response. After making a question selecting if it is true or false you will see the following.

Screenshot from 2016-08-24 10:10:01.png

In a future post, we will learn how to take questions from the question bank and incorporate them into an actually quiz.

2014 in review

The stats helper monkeys prepared a 2014 annual report for this blog.

Here’s an excerpt:

The concert hall at the Sydney Opera House holds 2,700 people. This blog was viewed about 12,000 times in 2014. If it were a concert at Sydney Opera House, it would take about 4 sold-out performances for that many people to see it.

Click here to see the complete report.