Scribd
Upload
30 views

Assignment 7

The document contains the answers and scoring for an assignment on logistic regression. It includes multiple choice questions about logistic regression concepts like the sigmoid function and odds ratios. It also discusses building logistic regression models on sample datasets and interpreting the results.

Uploaded by

anil
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
30 views

Assignment 7

The document contains the answers and scoring for an assignment on logistic regression. It includes multiple choice questions about logistic regression concepts like the sigmoid function and odds ratios. It also discusses building logistic regression models on sample datasets and interpreting the results.

Uploaded by

anil
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

Assignment 7

The due date for submitting this assignment has passed.


Due on 2019-09-18, 23:59 IST.

Assignment submitted on 2019-09-16, 23:17 IST


1 point
In Logistic Regression a linear relationship is assumed between the independent variables and the

Sigmoid of the dependent variable


Log of the dependent variable
Sine of the dependent variable
None of the above
No, the answer is incorrect.
Score: 0
Accepted Answers:
Sigmoid of the dependent variable
1 point
The value of the sigmoid function is bounded between:-

[−∞,∞][−∞,∞]

[−1,+∞][−1,+∞]

[0,1][0,1]

[−∞,0][−∞,0]
Yes, the answer is correct.
Score: 1
Accepted Answers:
[0,1][0,1]
1 point
Which one of the following is called as the odds ratio?

The ratio of the probability of an event occurring to the probability of the event not occurring
The ratio of the probability of an event not occurring to the probability of the event occurring
The probability of an event occurring
The probability of an event not occurring
Yes, the answer is correct.
Score: 1
Accepted Answers:
The ratio of the probability of an event occurring to the probability of the event not occurring
1 point
The confusion matrix for a binary classifier gives
Only True Positives and True Negatives
Only False Positives and False Negatives
Only True Positives, False Positives and False Negatives
True Positives, False Positives, True Negatives and False Negatives
Yes, the answer is correct.
Score: 1
Accepted Answers:
True Positives, False Positives, True Negatives and False Negatives
1 point
In confusion matrix, the misclassification rate is given by

FalseNegative+FalsepositiveTotalnumberofsamplesFalseNegative+FalsepositiveTotalnumberofsamples

TrueNegative+FalsepositiveTotalnumberofsamplesTrueNegative+FalsepositiveTotalnumberofsamples

FalseNegative+TruepositiveTotalnumberofsamplesFalseNegative+TruepositiveTotalnumberofsamples

TrueNegative+TruepositiveTotalnumberofsamplesTrueNegative+TruepositiveTotalnumberofsamples

Yes, the answer is correct.


Score: 1
Accepted Answers:
FalseNegative+FalsepositiveTotalnumberofsamplesFalseNegative+FalsepositiveTotalnumberofsamples

1 point
Overall effectiveness of a classifier (Accuracy) is given by

Truepositive+FalsepositiveTotalnumberofsamplesTruepositive+FalsepositiveTotalnumberofsamples

Truepositive+TruenegativeTotalnumberofsamplesTruepositive+TruenegativeTotalnumberofsamples

Truenegative+FalsenegativeTotalnumberofsamplesTruenegative+FalsenegativeTotalnumberofsamples

Falsepositive+FalsenegativeTotalnumberofsamplesFalsepositive+FalsenegativeTotalnumberofsamples

Yes, the answer is correct.


Score: 1
Accepted Answers:
Truepositive+TruenegativeTotalnumberofsamplesTruepositive+TruenegativeTotalnumberofsamples

1 point
The value of both sensitivity and specificity lies between

-1 and 1
-1 and 0
-2 and 2
0 and 1
No, the answer is incorrect.
Score: 0
Accepted Answers:
0 and 1
Consider the “income.csv” dataset. The data has values for per capita income and different parameters
for some states. The description of the variables is given below:

Build a linear regression model and answer questions 8-15.

1 point
The coefficient of COL from the full model is: - (rounded off to 3 decimal places)

7.162
-6.410
0.800
-10.302
Yes, the answer is correct.
Score: 1
Accepted Answers:
7.162
1 point
The t value corresponding to the coefficient of URate from the full model is: - (rounded off to 3 decimal
places)

3.506
1.035
0.701
2.163
Yes, the answer is correct.
Score: 1
Accepted Answers:
2.163
1 point
The significant variables after building the full model are: -
URate and Pop
COL, PD and Taxes
RTWL, Taxes and PD
COL
Yes, the answer is correct.
Score: 1
Accepted Answers:
URate and Pop
1 point
The adjusted R2R2 value of the full model is: - (rounded off to 3 decimal places)

0.431
0.660
0.327
0.783
Yes, the answer is correct.
Score: 1
Accepted Answers:
0.327
1 point
The adjusted R2R2

rewards the model for adding independent variables


penalizes the model for adding independent variables that do not influence the dependent variable
cannot be less than 0
is not dependent on the number of variables used for model building
No, the answer is incorrect.
Score: 0
Accepted Answers:
penalizes the model for adding independent variables that do not influence the dependent variable
1 point
The standard error associated in the estimation of the coefficient of COL is:-

-0.003
4.698
0.267
9500.000
Yes, the answer is correct.
Score: 1
Accepted Answers:
4.698
1 point
The numerator and denominator degrees of freedom for the F-statistic computed using the intercept model
and the model built using the variables URate,
Pop, COL and PD are respectively: -

4 and 194
6 and 33
6 and 34
4 and 33
Yes, the answer is correct.
Score: 1
Accepted Answers:
4 and 33
1 point
The overall F statistic (rounded off to 3 decimal places) between the full model built using all six variables
and the reduced model built by dropping Taxes
and RTWL is:

0.366
0.844
0.283
0.946
No, the answer is incorrect.
Score: 0
Accepted Answers:
0.366

Follow the instructions below and answer questions 16 to 21 :


Download the data set “companies.csv”. The data contains three financial ratios (X1, X2 and X3) of
solvent and bankrupt companies. Y indicates whether the company is bankrupt or solvent after 2 years

Load the data set to your R workspace using a suitable variable name.
1 point
To predict the future of a company, i.e. bankruptcy or solvency, what would the dependent and
independent variables be?

Y as the predicted variable and X1,X2 and X3 as the independent variables


X1 as the predicted variable and Y,X2 and X3 as the independent variables
X2 as the predicted variable and Y,X1 and X3 as the independent variables
X3 as the predicted variable and Y,X1 and X2 as the independent variables
Yes, the answer is correct.
Score: 1
Accepted Answers:
Y as the predicted variable and X1,X2 and X3 as the independent variables
1 point
Number of variables in dataset companies are

2
4
5
3
Yes, the answer is correct.
Score: 1
Accepted Answers:
4
1 point
Which command would be used to build a logistic regression model between the independent variables
and the dependent variable?

lm ( )
abline ( )
glm ( )
None of the above
Yes, the answer is correct.
Score: 1
Accepted Answers:
glm ( )
1 point
The estimate of intercept (rounded off to 3 decimal places) of the model is

0.087
5.707
-6.681
0.322
No, the answer is incorrect.
Score: 0
Accepted Answers:
0.322
1 point
The standard error of the variable X3 (rounded off to 3 decimal places) of the model developed is

0.045
9.743
0.060
1.877
No, the answer is incorrect.
Score: 0
Accepted Answers:
0.045
1 point
The p- value for the variable X2 (rounded off to 3 decimal places) is
0.303
0.060
0.004
-1.030
No, the answer is incorrect.
Score: 0
Accepted Answers:
0.004

You might also like