Assignment 5: Probabilistic Grammar

Load the Libraries + Functions

Load all the libraries or functions that you will use to for the rest of the assignment. It is helpful to define your libraries and functions at the top of a report, so that others can know what they need for the report to compile correctly.

The data for this project has already been loaded. Here you will be distinguishing between the uses for let, allow, and permit. You should pick two of these verbs to examine and subset the dataset for only those columns. You can use the droplevels() function to help drop the empty level after you subset.

Choosing ‘let’ and ‘permit’

library(Rling)

data(let)

head(let)

##   Year  Reg   Verb Neg Permitter Imper
## 1 2003  MAG  allow  No    Inanim    No
## 2 2005 SPOK  allow  No    Inanim    No
## 3 1990 SPOK    let  No      Anim    No
## 4 2007 SPOK  allow  No    Inanim    No
## 5 1997  MAG permit  No      Anim   Yes
## 6 1996  MAG  allow  No      Anim    No

#install.packages("rms")
#install.packages("visreg")
#install.packages("car")
library(rms)

## Warning: package 'rms' was built under R version 3.5.3

## Loading required package: Hmisc

## Warning: package 'Hmisc' was built under R version 3.5.3

## Loading required package: lattice

## Loading required package: survival

## Loading required package: Formula

## Warning: package 'Formula' was built under R version 3.5.2

## Loading required package: ggplot2

## Warning: package 'ggplot2' was built under R version 3.5.3

## 
## Attaching package: 'Hmisc'

## The following objects are masked from 'package:base':
## 
##     format.pval, units

## Loading required package: SparseM

## Warning: package 'SparseM' was built under R version 3.5.2

## 
## Attaching package: 'SparseM'

## The following object is masked from 'package:base':
## 
##     backsolve

library(car)

## Warning: package 'car' was built under R version 3.5.3

## Loading required package: carData

## Warning: package 'carData' was built under R version 3.5.2

## 
## Attaching package: 'car'

## The following objects are masked from 'package:rms':
## 
##     Predict, vif

library(visreg)

## Warning: package 'visreg' was built under R version 3.5.3

data(let)
letSub <- subset(let, Verb != "allow")

Description of the Data

The data is from the COCA: Corpus of Contemporary American English investigating the verb choice of let, allow, and permit. These are permissive constructions that are often paired with the word to. Predict the verb choice in the Verb column with the following independent variables:

Reg: Spok for spoken conversations, Mag for magazine articles.
Permitter: semantic class of the clause subject, Anim for animate, Inanim for inanimate and Undef for undefined.
Imper: yes for the imperative, no for not.
Note: Year is in the dataset, which would be awesome but gave me trouble. You can try adding it if you want.

Sample Size Requirements

Is the sample size large enough for four predictors?

Yes, the sample size is 187+164 = 351 (large sample size)

Is the split between your choosen verbs even enough to think you could predict them?

There is an almost even split between the verbs. ( ratio is 53:47 )

table(droplevels(letSub)$Verb)

## 
##    let permit 
##    187    164

Running a Binary Logistic Regression

Run the logistic regression using the rms package.
- Use the \(\chi^2\) test - is the overall model predictive of verb choice? Is it significant?
Overall model shows predictive verb choice. \(\chi^2\) is 204.92 which portrays that it is significant.
- What is Nagelkerke’s pseudo-\(R^2\)? What does it tell you about goodness of fit?
60% of the variables can be described by model since \(R^2\) is 59.1%
- What is the C statistic? How well are we predicting? C statistic is 88.2% which is a fairly accurate odel for prediction.

modLR = lrm(Verb ~ Reg + Permitter+ Imper,
            data = letSub)
modLR

## Logistic Regression Model
##  
##  lrm(formula = Verb ~ Reg + Permitter + Imper, data = letSub)
##  
##                        Model Likelihood     Discrimination    Rank Discrim.    
##                           Ratio Test           Indexes           Indexes       
##  Obs           351    LR chi2     204.92    R2       0.591    C       0.882    
##   let          187    d.f.             4    g        2.557    Dxy     0.765    
##   permit       164    Pr(> chi2) <0.0001    gr      12.892    gamma   0.840    
##  max |deriv| 4e-08                          gp       0.385    tau-a   0.382    
##                                             Brier    0.130                     
##  
##                   Coef    S.E.   Wald Z Pr(>|Z|)
##  Intercept        -0.3366 0.2317 -1.45  0.1462  
##  Reg=SPOK          0.3153 0.3096  1.02  0.3085  
##  Permitter=Inanim  2.6323 0.4176  6.30  <0.0001 
##  Permitter=Undef   1.6039 0.5886  2.72  0.0064  
##  Imper=Yes        -3.4614 0.6208 -5.58  <0.0001 
##

Coefficients

Explain each coefficient - are they significant? What do they imply if they are significant (i.e., which verb does it predict)?
- Reg:SPOK compares the spoken conversations with the articles in the magazine and shows that it is not significant.
- Permitter: If the peritter is ‘animate’, the model will predict ‘let’ the most. On the other hand if the permitter is undefined or inanimate, the model will predict ‘permit’ the most and will be significant.
- Imper: If Imper is yes, it will predict ‘let’ the most and will predict ‘permit’ in other situation.

table(droplevels(letSub)$Verb, letSub$Permitter)

##         
##          Anim Inanim Undef
##   let     175      8     4
##   permit   62     86    16

table(droplevels(letSub)$Verb, letSub$Reg)

##         
##          MAG SPOK
##   let     72  115
##   permit 100   64

table(droplevels(letSub)$Verb, letSub$Imper)

##         
##           No Yes
##   let     83 104
##   permit 161   3

Interactions

Add the interaction between Imper and Reg by doing Imper*Reg, but remember you will need to do a glm model.
Use the anova function to answer if the addition of the interaction was significant.
- Is the interaction useful?

The anova p-value displays significant interaction. Interaction term is un-important.

Use the visreg library and funtion to visualize the interaction.
- How would you explain that interaction?

The visualization leans more towards Spoken vs magazine.

modLR1 = glm(Verb ~ Reg + Permitter + Imper,
             family = binomial,
             data = letSub)
modLR2 = glm(Verb ~ Permitter + Imper*Reg,
             family = binomial,
             data = letSub)
anova(modLR1, modLR2, test = "Chisq")

## Analysis of Deviance Table
## 
## Model 1: Verb ~ Reg + Permitter + Imper
## Model 2: Verb ~ Permitter + Imper * Reg
##   Resid. Df Resid. Dev Df Deviance Pr(>Chi)  
## 1       346     280.16                       
## 2       345     276.29  1   3.8693  0.04918 *
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

summary(modLR2)

## 
## Call:
## glm(formula = Verb ~ Permitter + Imper * Reg, family = binomial, 
##     data = letSub)
## 
## Deviance Residuals: 
##     Min       1Q   Median       3Q      Max  
## -2.1737  -0.4172  -0.1557   0.4448   2.9728  
## 
## Coefficients:
##                  Estimate Std. Error z value Pr(>|z|)    
## (Intercept)       -0.4087     0.2357  -1.734  0.08294 .  
## PermitterInanim    2.6723     0.4202   6.360 2.01e-10 ***
## PermitterUndef     1.6249     0.5906   2.752  0.00593 ** 
## ImperYes          -1.9892     0.7753  -2.566  0.01029 *  
## RegSPOK            0.4637     0.3188   1.455  0.14576    
## ImperYes:RegSPOK  -2.4725     1.2881  -1.919  0.05492 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 485.08  on 350  degrees of freedom
## Residual deviance: 276.29  on 345  degrees of freedom
## AIC: 288.29
## 
## Number of Fisher Scoring iterations: 7

visreg(modLR2, "Imper", by = "Reg")

table(droplevels(letSub)$Verb, letSub$Reg, letSub$Imper)

## , ,  = No
## 
##         
##          MAG SPOK
##   let     50   33
##   permit  98   63
## 
## , ,  = Yes
## 
##         
##          MAG SPOK
##   let     22   82
##   permit   2    1

Outliers

Use the car library and the influencePlot() to create a picture of the outliers.
- Are there major outliers for this data?
Noticed that some values lie in the range of 2 and below -2 with respect to Standardized Residuals vs Hat-Values chart

influencePlot(modLR2)

##      StudRes        Hat       CookD
## 36  3.136508 0.01204819 0.168699187
## 59  2.334111 0.04166667 0.083175803
## 88  0.732927 0.05752692 0.003198719
## 106 0.732927 0.05752692 0.003198719

Assumptions

Explore the vif values of the original model (not the interaction model) and determine if you meet the assumption of additivity (meaning no multicollinearity).

No multicolinearity as values are lower. (>5). Assumptions of additivity are met.

rms::vif(modLR)

##         Reg=SPOK Permitter=Inanim  Permitter=Undef        Imper=Yes 
##         1.080051         1.069528         1.027143         1.051163