13.(a)create numerical and graphical summaries of the Weekly Do there appear to be any patterns?

attach(Weekly)
summary(Weekly)
##       Year           Lag1               Lag2               Lag3         
##  Min.   :1990   Min.   :-18.1950   Min.   :-18.1950   Min.   :-18.1950  
##  1st Qu.:1995   1st Qu.: -1.1540   1st Qu.: -1.1540   1st Qu.: -1.1580  
##  Median :2000   Median :  0.2410   Median :  0.2410   Median :  0.2410  
##  Mean   :2000   Mean   :  0.1506   Mean   :  0.1511   Mean   :  0.1472  
##  3rd Qu.:2005   3rd Qu.:  1.4050   3rd Qu.:  1.4090   3rd Qu.:  1.4090  
##  Max.   :2010   Max.   : 12.0260   Max.   : 12.0260   Max.   : 12.0260  
##       Lag4               Lag5              Volume            Today         
##  Min.   :-18.1950   Min.   :-18.1950   Min.   :0.08747   Min.   :-18.1950  
##  1st Qu.: -1.1580   1st Qu.: -1.1660   1st Qu.:0.33202   1st Qu.: -1.1540  
##  Median :  0.2380   Median :  0.2340   Median :1.00268   Median :  0.2410  
##  Mean   :  0.1458   Mean   :  0.1399   Mean   :1.57462   Mean   :  0.1499  
##  3rd Qu.:  1.4090   3rd Qu.:  1.4050   3rd Qu.:2.05373   3rd Qu.:  1.4050  
##  Max.   : 12.0260   Max.   : 12.0260   Max.   :9.32821   Max.   : 12.0260  
##  Direction 
##  Down:484  
##  Up  :605  
##            
##            
##            
## 
corrplot(cor(Weekly[, -9]), type = "lower", diag = FALSE, method = "ellipse")

cor(Weekly[, -9])
##               Year         Lag1        Lag2        Lag3         Lag4
## Year    1.00000000 -0.032289274 -0.03339001 -0.03000649 -0.031127923
## Lag1   -0.03228927  1.000000000 -0.07485305  0.05863568 -0.071273876
## Lag2   -0.03339001 -0.074853051  1.00000000 -0.07572091  0.058381535
## Lag3   -0.03000649  0.058635682 -0.07572091  1.00000000 -0.075395865
## Lag4   -0.03112792 -0.071273876  0.05838153 -0.07539587  1.000000000
## Lag5   -0.03051910 -0.008183096 -0.07249948  0.06065717 -0.075675027
## Volume  0.84194162 -0.064951313 -0.08551314 -0.06928771 -0.061074617
## Today  -0.03245989 -0.075031842  0.05916672 -0.07124364 -0.007825873
##                Lag5      Volume        Today
## Year   -0.030519101  0.84194162 -0.032459894
## Lag1   -0.008183096 -0.06495131 -0.075031842
## Lag2   -0.072499482 -0.08551314  0.059166717
## Lag3    0.060657175 -0.06928771 -0.071243639
## Lag4   -0.075675027 -0.06107462 -0.007825873
## Lag5    1.000000000 -0.05851741  0.011012698
## Volume -0.058517414  1.00000000 -0.033077783
## Today   0.011012698 -0.03307778  1.000000000

Volume is strongly positively correlated with Year.

Time Series Plot

Weekly$Week <- 1:nrow(Weekly)
year_breaks <- Weekly %>%
  group_by(Year) %>%
  summarize(Week = min(Week))

ggplot(Weekly, aes(x = Week, y = Volume)) + 
  geom_line() +
  geom_smooth() + 
  scale_x_continuous(breaks = year_breaks$Week, minor_breaks = NULL, labels = year_breaks$Year) + 
  labs(title = "Average Daily Shares Traded vs. Time", 
       x = "Time") + 
  theme_light()
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'

We notice a trend of increasing volume over time between 1990-2008.

prop.table(table(Weekly$Direction))
## 
##      Down        Up 
## 0.4444444 0.5555556

We can see the accuracy for the stocks to be up weekly is 55.56%, while the accuracy of them being down is 44.44%.

(b) Use the full data set to perform a logistic regression with Direction as the response and the five lag variables plus Volume as predictors. Use the summary function to print the results. Do any of the predictors appear to be statistically significant? If so, which ones?

fit <- glm(Direction ~ Lag1+Lag2+Lag3+Lag4+Lag5+Volume,data = Weekly,family = binomial)
summary(fit)
## 
## Call:
## glm(formula = Direction ~ Lag1 + Lag2 + Lag3 + Lag4 + Lag5 + 
##     Volume, family = binomial, data = Weekly)
## 
## Coefficients:
##             Estimate Std. Error z value Pr(>|z|)   
## (Intercept)  0.26686    0.08593   3.106   0.0019 **
## Lag1        -0.04127    0.02641  -1.563   0.1181   
## Lag2         0.05844    0.02686   2.175   0.0296 * 
## Lag3        -0.01606    0.02666  -0.602   0.5469   
## Lag4        -0.02779    0.02646  -1.050   0.2937   
## Lag5        -0.01447    0.02638  -0.549   0.5833   
## Volume      -0.02274    0.03690  -0.616   0.5377   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 1496.2  on 1088  degrees of freedom
## Residual deviance: 1486.4  on 1082  degrees of freedom
## AIC: 1500.4
## 
## Number of Fisher Scoring iterations: 4

predictor Lag2 is significant.

(c) Compute the confusion matrix and overall fraction of correct predictions.Explain what the confusion matrix is telling you about the types of mistakes made by logistic regression.

contrasts(Weekly$Direction)
##      Up
## Down  0
## Up    1
pred <- predict(fit, type = "response") > 0.5
(t <- table(ifelse(pred, "Up (pred)", "Down (pred)"), Weekly$Direction))
##              
##               Down  Up
##   Down (pred)   54  48
##   Up (pred)    430 557
sum(diag(t)) / sum(t)
## [1] 0.5610652

Although logistic regression correctly predicts upwards movements well, it incorrectly predicts most downwards movements as up. The accuracy is 56%.

(d) Now fit the logistic regression model using a training data period from 1990 to 2008, with Lag2 as the only predictor. Compute the confusion matrix and the overall fraction of correct predictions for the held out data (that is, the data from 2009 and 2010).

Weekly.train <- Weekly$Year < 2009
glm.train <- glm(Direction ~Lag2,data = Weekly[Weekly.train,],family =  binomial)
summary(glm.train)
## 
## Call:
## glm(formula = Direction ~ Lag2, family = binomial, data = Weekly[Weekly.train, 
##     ])
## 
## Coefficients:
##             Estimate Std. Error z value Pr(>|z|)   
## (Intercept)  0.20326    0.06428   3.162  0.00157 **
## Lag2         0.05810    0.02870   2.024  0.04298 * 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 1354.7  on 984  degrees of freedom
## Residual deviance: 1350.5  on 983  degrees of freedom
## AIC: 1354.5
## 
## Number of Fisher Scoring iterations: 4
pred <- predict(glm.train,Weekly[!Weekly.train,], type = "response") > 0.5
(t <- table(ifelse(pred, "Up (pred)", "Down (pred)"), Weekly[!Weekly.train,]$Direction))
##              
##               Down Up
##   Down (pred)    9  5
##   Up (pred)     34 56
sum(diag(t)) / sum(t)
## [1] 0.625

(e) Repeat (d) using LDA.

Weekly.train <- Weekly$Year < 2009
lda.train <- lda(Direction ~Lag2,data = Weekly[Weekly.train,],family =  binomial)
pred <- predict(lda.train,Weekly[!Weekly.train,], type = "response")$class
(t <- table(pred,  Weekly[!Weekly.train,]$Direction))
##       
## pred   Down Up
##   Down    9  5
##   Up     34 56
sum(diag(t)) / sum(t)
## [1] 0.625

(f) Repeat (d) using QDA.

qda.train <- qda(Direction ~Lag2,data = Weekly[Weekly.train,],family =  binomial)
pred <- predict(qda.train,Weekly[!Weekly.train,], type = "response")$class
(t <- table(pred,  Weekly[!Weekly.train,]$Direction))
##       
## pred   Down Up
##   Down    0  0
##   Up     43 61
sum(diag(t)) / sum(t)
## [1] 0.5865385

(g) Repeat (d) using KNN with \(K = 1\).

fit <- knn(
  Weekly[Weekly.train, "Lag2", drop = FALSE],
  Weekly[!Weekly.train, "Lag2", drop = FALSE],
  Weekly$Direction[Weekly.train]
)
(t <- table(fit, Weekly[!Weekly.train, ]$Direction))
##       
## fit    Down Up
##   Down   21 30
##   Up     22 31
sum(diag(t)) / sum(t)
## [1] 0.5

h. Repeat (d) using naive Bayes.

fit <- naiveBayes(Direction ~ Lag2, data = Smarket, subset = Weekly.train)
pred <- predict(fit, Weekly[!Weekly.train, ], type = "class")
(t <- table(pred, Weekly[!Weekly.train, ]$Direction))
##       
## pred   Down Up
##   Down   27 29
##   Up     16 32
sum(diag(t)) / sum(t)
## [1] 0.5673077

i. Which of these methods appears to provide the best results on this data?

Logistic regression and LDA are the best performing.

j. Experiment with different combinations of predictors, including possible transformations and interactions, for each of the methods. Report the variables, method, and associated confusion matrix that appears to provide the best results on the held out data. Note that you should also experiment with values for \(K\) in the KNN classifier.

fit <- glm(Direction ~ Lag1, data = Weekly[Weekly.train, ], family = binomial)# logistic regresion
pred <- predict(fit, Weekly[!Weekly.train, ], type = "response") > 0.5
mean(ifelse(pred, "Up", "Down") == Weekly[!Weekly.train, ]$Direction)
## [1] 0.5673077
fit <- glm(Direction ~ Lag3, data = Weekly[Weekly.train, ], family = binomial)#change predictor
pred <- predict(fit, Weekly[!Weekly.train, ], type = "response") > 0.5
mean(ifelse(pred, "Up", "Down") == Weekly[!Weekly.train, ]$Direction)
## [1] 0.5865385
fit <- glm(Direction ~Lag4, data = Weekly[Weekly.train, ], family = binomial)
pred <- predict(fit, Weekly[!Weekly.train, ], type = "response") > 0.5
mean(ifelse(pred, "Up", "Down") == Weekly[!Weekly.train, ]$Direction)
## [1] 0.5865385
fit <- glm(Direction ~ Lag1 + Lag2 + Lag3 + Lag4, data = Weekly[Weekly.train, ], family = binomial)
pred <- predict(fit, Weekly[!Weekly.train, ], type = "response") > 0.5
mean(ifelse(pred, "Up", "Down") == Weekly[!Weekly.train, ]$Direction)
## [1] 0.5865385
fit <- glm(Direction ~ Lag1 * Lag2 * Lag3 * Lag4, data = Weekly[Weekly.train, ], family = binomial)
pred <- predict(fit, Weekly[!Weekly.train, ], type = "response") > 0.5
mean(ifelse(pred, "Up", "Down") == Weekly[!Weekly.train, ]$Direction)#check interaction
## [1] 0.5961538
fit <- lda(Direction ~ Lag1 + Lag2 + Lag3 + Lag4,data = Weekly[Weekly.train, ])
pred <- predict(fit, Weekly[!Weekly.train, ], type = "response")$class
mean(pred == Weekly[!Weekly.train, ]$Direction)
## [1] 0.5769231
fit <- qda(Direction ~ Lag1 + Lag2 + Lag3 + Lag4, data = Weekly[Weekly.train, ])
pred <- predict(fit, Weekly[!Weekly.train, ], type = "response")$class
mean(pred == Weekly[!Weekly.train, ]$Direction)
## [1] 0.5192308
fit <- naiveBayes(Direction ~ Lag1 + Lag2 + Lag3 + Lag4, data = Weekly[Weekly.train, ])
pred <- predict(fit, Weekly[!Weekly.train, ], type = "class")
mean(pred == Weekly[!Weekly.train, ]$Direction)
## [1] 0.5096154
set.seed(1)
res <- sapply(1:30, function(k) {
  fit <- knn(
    Weekly[Weekly.train, 2:4, drop = FALSE],
    Weekly[!Weekly.train, 2:4, drop = FALSE],
    Weekly$Direction[Weekly.train],
    k = k
  )
  mean(fit == Weekly[!Weekly.train, ]$Direction)
})#try k from 1 to 30
plot(1:30, res, type = "o", xlab = "k", ylab = "Fraction correct")

(k <- which.max(res))
## [1] 26
fit <- knn(
  Weekly[Weekly.train, 2:4, drop = FALSE],
  Weekly[!Weekly.train, 2:4, drop = FALSE],
  Weekly$Direction[Weekly.train],
  k = k
)
table(fit, Weekly[!Weekly.train, ]$Direction)
##       
## fit    Down Up
##   Down   23 18
##   Up     20 43
mean(fit == Weekly[!Weekly.train, ]$Direction)
## [1] 0.6346154

By using KNN, \(k = 26\) provides the best prediction(.63). Using the interaction, including lag1, lag2, lag3,lag4 , to fit logisticn regression get second(.6).

14 In this problem, you will develop a model to predict whether a given car gets high or low gas mileage based on the Auto data set.

a. Create a binary variable, mpg01, that contains a 1 if mpg contains a value above its median, and a 0 if mpg contains a value below itsmedian. You can compute the median using the median() function. Note you may find it helpful to use the data.frame() function to create a single data set containing both mpg01 and the other Auto variables.

attach(Auto)
## The following object is masked from package:lubridate:
## 
##     origin
## The following object is masked from package:ggplot2:
## 
##     mpg
med <- median(mpg)
mpg01<- ifelse (mpg>med, 1,0)

x <- cbind(Auto[, -1], data.frame(mpg01))

b. Explore the data graphically in order to investigate the association between mpg01 and the other features. Which of the other features seem most likely to be useful in predicting mpg01? Scatterplots and boxplots may be useful tools to answer this question. Describe your findings.

par(mfrow = c(2, 4))
for (i in 1:7) hist(x[, i], breaks = 20, main = colnames(x)[i])

par(mfrow = c(2, 4))

for (i in 1:7) boxplot(x[, i] ~ x$mpg01, main = colnames(x)[i])

pairs(x[, 1:7])

mpg01 can differnciate most of variables.cylinders, weight, displacement, and horsepower is higly linear.

c. Split the data into a training set and a test set.

set.seed(1)
train <- sample(seq_len(nrow(x)), nrow(x) * 2/3)
summary(x[train,])
##    cylinders      displacement     horsepower        weight      acceleration  
##  Min.   :3.000   Min.   : 68.0   Min.   : 46.0   Min.   :1649   Min.   : 8.00  
##  1st Qu.:4.000   1st Qu.:105.0   1st Qu.: 78.0   1st Qu.:2226   1st Qu.:14.00  
##  Median :4.000   Median :151.0   Median : 92.0   Median :2790   Median :15.50  
##  Mean   :5.452   Mean   :192.2   Mean   :103.4   Mean   :2958   Mean   :15.71  
##  3rd Qu.:8.000   3rd Qu.:260.0   3rd Qu.:120.0   3rd Qu.:3605   3rd Qu.:17.30  
##  Max.   :8.000   Max.   :455.0   Max.   :230.0   Max.   :5140   Max.   :24.80  
##                                                                                
##       year           origin                      name         mpg01       
##  Min.   :70.00   Min.   :1.000   amc gremlin       :  4   Min.   :0.0000  
##  1st Qu.:73.00   1st Qu.:1.000   amc hornet        :  4   1st Qu.:0.0000  
##  Median :76.00   Median :1.000   amc matador       :  3   Median :1.0000  
##  Mean   :76.11   Mean   :1.529   chevrolet chevette:  3   Mean   :0.5057  
##  3rd Qu.:79.00   3rd Qu.:2.000   chevrolet impala  :  3   3rd Qu.:1.0000  
##  Max.   :82.00   Max.   :3.000   dodge colt        :  3   Max.   :1.0000  
##                                  (Other)           :241

d. Perform LDA on the training data in order to predict mpg01 using the variables that seemed most associated with mpg01 in (b). What is the test error of the model obtained?

fit <- lda(mpg01 ~cylinders+weight+displacement,data = x[train,])
head(fit)
## $prior
##         0         1 
## 0.4942529 0.5057471 
## 
## $counts
##   0   1 
## 129 132 
## 
## $means
##   cylinders   weight displacement
## 0  6.736434 3583.419     268.4419
## 1  4.196970 2347.720     117.6136
## 
## $scaling
##                        LD1
## cylinders    -0.3720649450
## weight       -0.0007789977
## displacement -0.0035033284
## 
## $lev
## [1] "0" "1"
## 
## $svd
## [1] 19.67491
pred <- predict(fit, x[-train, ], type = "response")$class
mean(pred != x[-train, ]$mpg01)
## [1] 0.1068702

e. Perform QDA on the training data in order to predict mpg01 using the variables that seemed most associated with mpg01 in (b). What is the test error of the model obtained?

fit <- qda(mpg01 ~ cylinders + weight + displacement, data = x[train, ])
pred <- predict(fit, x[-train, ], type = "response")$class
mean(pred != x[-train, ]$mpg01)
## [1] 0.09923664

f. Perform logistic regression on the training data in order to predict mpg01 using the variables that seemed most associated with mpg01 in (b). What is the test error of the model obtained?

fit <- glm(mpg01 ~ cylinders+weight+displacement, data = x[train, ], family = binomial)
pred <- predict(fit, x[-train, ], type = "response") > 0.5
mean(pred != x[-train, ]$mpg01)
## [1] 0.1145038

g. Perform naive Bayes on the training data in order to predict mpg01 using the variables that seemed most associated with mpg01 in (b). What is the test error of the model obtained?

fit <- naiveBayes(mpg01 ~ cylinders + weight + displacement, data = x[train, ])
pred <- predict(fit, x[-train, ], type = "class")
mean(pred != x[-train, ]$mpg01)
## [1] 0.09923664

h. Perform KNN on the training data, with several values of \(K\), in order to predict mpg01. Use only the variables that seemed most associated with mpg01 in (b). What test errors do you obtain? Which value of \(K\) seems to perform the best on this data set?

res <- sapply(1:50, function(k) {
  fit <- knn(x[train, c(1, 4, 2)], x[-train, c(1, 4, 2)], x$mpg01[train], k = k)
  mean(fit != x[-train, ]$mpg01)
})
names(res) <- 1:50
plot(res, type = "o")

res[which.min(res)]
##         3 
## 0.1068702

\(k= 4\) has the best error rate.

Using the Boston data set, fit classification models in order to predict whether a given census tract has a crime rate above or below the median. Explore logistic regression, LDA, naive Bayes and KNN models using various sub-sets of the predictors. Describe your findings.

Hint: You will have to create the response variable yourself, using the variables that are contained in the Boston data set.

x <- cbind(
  ISLR2::Boston[, -1], 
  data.frame("highcrim" = Boston$crim > median(Boston$crim))
)
set.seed(1)
train <- sample(seq_len(nrow(x)), nrow(x) * 2/3)

Performing wilcox tests find the most associated variables

ord <- order(sapply(1:12, function(i) {
  p <- wilcox.test(as.numeric(x[train, i]) ~ x[train, ]$highcrim)$p.value
  setNames(log10(p), colnames(x)[i])
}))
ord <- names(x)[ord]
ord
##  [1] "nox"     "dis"     "indus"   "tax"     "age"     "rad"     "zn"     
##  [8] "lstat"   "medv"    "ptratio" "rm"      "chas"

Variables nox (nitrogen oxides concentration) followed by dis (distance to employment center) appear to be most associated with high crime.

reorder columns by those most associated with highcrim (in the training data)

x <- x[, c(ord, "highcrim")]

univariate associations with highcrim (in the training data)

x[train, ] |>
  pivot_longer(!highcrim) |>
  mutate(name = factor(name, levels = ord)) |>
  ggplot(aes(highcrim, value)) + 
  geom_boxplot() + 
  facet_wrap(~name, scale = "free")

Fit lda, logistic regression, naive Bayes and KNN models (with k = 1..50) for a set of specific predictors and return the error rate. We fit models using increasing numbers of predictors: column 1, then columns 1 and 2 etc.

fit_models <- function(cols, k_vals = 1:50) {
  dat_train <- x[train, cols, drop = FALSE]
  dat_test <- x[-train, cols, drop = FALSE]

  fit <- lda(x$highcrim[train] ~ ., data = dat_train)
  pred <- predict(fit, dat_test, type = "response")$class
  lda_err <- mean(pred != x$highcrim[-train])

  fit <- glm(x$highcrim[train] ~ ., data = dat_train, family = binomial)
  pred <- predict(fit, dat_test, type = "response") > 0.5
  logreg_err <- mean(pred != x$highcrim[-train])

  fit <- naiveBayes(x$highcrim[train] ~ ., data = dat_train)
  pred <- predict(fit, dat_test, type = "class")
  nb_err <- mean(pred != x$highcrim[-train])

  res <- sapply(k_vals, function(k) {
    fit <- knn(dat_train, dat_test, x$highcrim[train], k = k)
    mean(fit != x$highcrim[-train])
  })
  knn_err <- min(res)

  c("LDA" = lda_err, "LR" = logreg_err, "NB" = nb_err, "KNN" = knn_err)
}
res <- sapply(1:12, function(max) fit_models(1:max))
res <- as_tibble(t(res))
res$n_var <- 1:12
pivot_longer(res, cols = !n_var) |>
  ggplot(aes(n_var, value, col = name)) + 
  geom_line() + 
  xlab("Number of predictors") + 
  ylab("Error rate")

KNN appears to perform better (if we tune \(k\)) for all numbers of predictors.

fit <- knn(
  x[train, "nox", drop = FALSE],
  x[-train, "nox", drop = FALSE],
  x$highcrim[train],
  k = 1
)
table(fit, x[-train, ]$highcrim)
##        
## fit     FALSE TRUE
##   FALSE    78    2
##   TRUE      3   86
mean(fit != x[-train, ]$highcrim) * 100
## [1] 2.95858

The best model use the method of KNN, error rate is 2.95% when \(k = 1\). The approach based on the town with the single most similar nitrogen oxide concentration (nox). Possible explaination is nearby towns have similar crime rates, and we can obtain good predictions by predicting crime rate based on a nearby town.

Reconsider the k value, \(k = 20\)

res <- sapply(1:12, function(max) fit_models(1:max, k_vals = 20))
res <- as_tibble(t(res))
res$n_var <- 1:12
pivot_longer(res, cols = !n_var) |>
  ggplot(aes(n_var, value, col = name)) +
  geom_line() +
  xlab("Number of predictors") +
  ylab("Error rate")

KNN still performs best with a single predictor (nox), but logistic regression with 12 predictors also performs well and has an error rate of ~12%.

vars <- names(x)[1:12]
dat_train <- x[train, vars]
dat_test <- x[-train, vars]

fit <- glm(x$highcrim[train] ~ ., data = dat_train, family = binomial)
pred <- predict(fit, dat_test, type = "response") > 0.5
table(pred, x[-train, ]$highcrim)
##        
## pred    FALSE TRUE
##   FALSE    70    9
##   TRUE     11   79
mean(pred != x$highcrim[-train]) * 100
## [1] 11.83432
summary(fit)
## 
## Call:
## glm(formula = x$highcrim[train] ~ ., family = binomial, data = dat_train)
## 
## Coefficients:
##               Estimate Std. Error z value Pr(>|z|)    
## (Intercept) -44.525356   7.935621  -5.611 2.01e-08 ***
## nox          55.062428  10.281556   5.355 8.53e-08 ***
## dis           1.080847   0.304084   3.554 0.000379 ***
## indus        -0.067493   0.058547  -1.153 0.248997    
## tax          -0.005336   0.003138  -1.700 0.089060 .  
## age           0.020965   0.014190   1.477 0.139556    
## rad           0.678196   0.192193   3.529 0.000418 ***
## zn           -0.099558   0.045914  -2.168 0.030134 *  
## lstat         0.134035   0.058623   2.286 0.022231 *  
## medv          0.213114   0.088922   2.397 0.016547 *  
## ptratio       0.294396   0.155285   1.896 0.057981 .  
## rm           -0.518115   0.896423  -0.578 0.563278    
## chas          0.139557   0.798632   0.175 0.861280    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 467.04  on 336  degrees of freedom
## Residual deviance: 135.80  on 324  degrees of freedom
## AIC: 161.8
## 
## Number of Fisher Scoring iterations: 9