Scribd
Upload
95 views8 pages

ANOVA and Regression Analysis Concepts

The document contains questions related to analysis of variance (ANOVA) and regression analysis. Some key points: 1) Questions 1-10 cover topics related to ANOVA procedures, assumptions, and interpreting F-ratios and degrees of freedom. 2) Questions 11-20 shift to discussing regression analysis, interpreting regression equations, the relationship between r-squared and the correlation coefficient, and properties of the error term. 3) The questions assess understanding of fundamental statistical concepts and calculations for ANOVA and regression models.

Uploaded by

21P410 - VARUN M
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
95 views8 pages

ANOVA and Regression Analysis Concepts

The document contains questions related to analysis of variance (ANOVA) and regression analysis. Some key points: 1) Questions 1-10 cover topics related to ANOVA procedures, assumptions, and interpreting F-ratios and degrees of freedom. 2) Questions 11-20 shift to discussing regression analysis, interpreting regression equations, the relationship between r-squared and the correlation coefficient, and properties of the error term. 3) The questions assess understanding of fundamental statistical concepts and calculations for ANOVA and regression models.

Uploaded by

21P410 - VARUN M
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

WEEK-5

1)The ‘F’ ratio in a completely randomized ANOVA is the ratio of

A. MST/MSE
B. MSTR/MSE
C. MSE/MSTR
D. MSE/MST

2) A term that means the same as the term "variable" in an ANOVA procedure is

A. factor
B. treatment
C. replication
D. variance within

3) An ANOVA procedure is used for four samples, each comprised of 30 observations, were taken from the
four populations. The numerator and denominator (respectively) degrees of freedom for the critical value of
F are

A. 3 and 30
B. 4 and 30
C. 3 and 119
D. 3 and 116

4)Which of the following is not a required assumption for the analysis of variance?

A. The random variable of interest for each population has a normal probability distribution
B. The variance associated with the random variable must be the same for each population
C. At least 2 populations are under consideration
D. Populations have equal means

5)If, sum of square between treatments (SSTR) = 6,750 H0: m1=m2=m3=m4 Sum of square of error (SSE)
= 8,000 Ha: at least one mean is different Total number of elements (nT )= 20 The mean square between
treatments (MSTR) equals

A. 400
B. 500
C. 1,687.5
D. 2,250

6) If, sum of square between treatments (SSTR) = 6,750 H0: m1=m2=m3=m4 Sum of square of error
(SSE) = 8,000 Ha: at least one mean is different Total number of elements (nT )= 20. The mean square
within treatments (MSE) equals

A. 400
B. 500
C. 1687.5
D. 2250

7)If, sum of square between treatments (SSTR) = 6,750 H0: m1=m2=m3=m4 Sum of square of error (SSE)
= 8,000 Ha: at least one mean is different Total number of elements (nT )= [Link] test statistic to test the
null hypothesis is equals

A. 0.22
B. 0.84
C. 4.22
D. 4.5
8)An ANOVA procedure is applied to data obtained from 6 samples where each sample contains 20
observations. The degrees of freedom for the critical value of F are

A. 6 numerator and 20 denominator degrees of freedom


B. 5 numerator and 20 denominator degrees of freedom
C. 5 numerator and 114 denominator degrees of freedom
D. 6 numerator and 114 denominator degrees of freedom

9)The critical F value with 6 numerator and 60 denominator degrees of freedom at alpha = .05 is

A. 3.74
B. 2.25
C. 2.37
D. 1.96

10)The ANOVA procedure is a statistical approach for determining whether or not

A. the means of two samples are equal


B. the means of two or more samples are equal
C. the means of more than two samples are equal
D. the means of two or more populations are equal

WEEK-6

A. 0.887
B. 0.956
C. 0.945
D. 0.932

2)With reference to the data given in question no. 1, test the null hypothesis: "There is no
significant relationship between the variables". we will:
A. Accept the null hypothesis
B. Reject the null hypothesis
C. Can’t state any conclusion
D. None of the above
3)State TRUE or FALSE, in context to regression analysis –

Statement: "The variance of error, is same for all values of the independent variable"

True
False

4)A regression analysis between sales (Y in $1000) and advertising (X in dollars) resulted in the following
equation

Y = 30,000 + 5 X

The above equation implies that an:

A. increase of $5 in advertising is associated with an increase of $5,000 in sales


B. increase of $1 in advertising is associated with an increase of $5 in sales
C. increase of $1 in advertising is associated with an increase of $35,000 in sales
D. increase of $1 in advertising is associated with an increase of $5,000 in sales

5)In a regression and correlation analysis if r2 = 1, then Sum of square of Error (SSE)
A. SSE must also be equal to one
B. SSE must be equal to zero
C. SSE can be any positive value
D. SSE must be negative

6)In a regression analysis if Sum of square of Error (SSE) = 200 and Sum of square of
Regression (SSR) = 300, then the coefficient of determination is

A. 0.6667
B. 0.4000
C. 0.6000
D. 1.5000

7)Regression analysis was applied between demand for a product (Y) and the price of the product (X), and
the following estimated regression equation was obtained.

Y = 120 - 10 X

Based on the above estimated regression equation, if price is increased by 2 units, then demand is
expected to

A. increase by 120 units


B. increase by 100 units
C. increase by 20 units
D. decrease by 20 units
8)Regression analysis was applied between sales (Y in $1,000) and advertising (X in $100), and the
following estimated regression equation was obtained.

Y = 80 + 6.2 X

Based on the above estimated regression line, if advertising is $10,000, then the point estimate for sales (in
dollars) is

A. $62,080
B. $142,000
C. $700
D. $700,000

9)In regression analysis if the dependent variable is measured in dollars, the independent
variable

A. must also be in dollars


B. must be in some units of currency
C. can be any units
D. cannot be in dollars

10)If the coefficient of correlation is 0.90, then the coefficient of determination

A. is also 0.9
B. is either 0.81 or -0.81
C. can be either negative or positive
D. must be 0.81

WEEK-7

1)In a regression analysis, the error term is a random variable with a mean or expected value
of
A. zero
B. one
C. any positive value
D. any value

2)If the coefficient of determination is a positive value, then the coefficient of correlation

A. must also be positive


B. must be zero
C. can be either negative or positive
D. must be larger than 1

3)Larger values of r2 imply that the observations are more closely grouped about the

A. average value of the independent variables


B. average value of the dependent variable
C. least squares line
D. Origin
4)he interval estimate of the mean value of y for a given value of x is

A. prediction interval estimate


B. confidence interval estimate
C. average regression
D. x versus y correlation interval

5)In a regression analysis, the coefficient of determination is 0.4225. The coefficient of


correlation in this situation is

A. ±0.65
B. ±0.1785
C. any positive value
D. any value

6)In a regression and correlation analysis if r2 = 1, then

A. SSE must also be equal to one


B. SSE must be equal to zero
C. SSE can be any positive value
D. SSE must be negative

7) If the coefficient of correlation is 0.8, the percentage of variation in the dependent variable
explained by the variation in the independent variable is

A. 0.80%
B. 80%
C. 0.64%
D. 64%

8)If the coefficient of determination is equal to 1, then the coefficient of correlation

A. must also be equal to 1


B. can be either -1 or +1
C. can be any value between -1 to +1
D. must be -1

9) If all the points of a scatter diagram lie on the least squares regression line, then the
coefficient of determination for these variables based on these data is

A. 0
B. 1
C. either 1 or -1, depending upon whether the relationship is positive or negative
D. could be any value between -1 and 1
10)A simple linear regression equation (y = mx + c ) will always pass through the point
_____

A. (0,0)
B. (1,1)
C. ( Ymean , Xmean )
D. (Xmean , Ymean)

WEEK-8

1)Which of the following methods do we use to best fit the data in Logistic Regression?

A. Least Square Error


B. Maximum Likelihood
C. Jaccard distance
D. All of these

2)Which of the following evaluation metrics can not be applied in case of logistic regression
output to compare with target?

A. AUC-ROC
B. Accuracy
C. Logloss
D. Mean-Squared-Error

3)Let f(x) denote the logistic function. The range of f(x) for any real value of x is

A. (0,1)
B. (-1 , 1)
C. All positive integers
D. All negative integers

4)Which of the following option is true?

A. Linear Regression errors values has to be normally distributed but in case of Logistic
Regression it is not the case
B. Logistic Regression errors values has to be normally distributed but in case of Linear
Regression it is not the case
C. Both Linear Regression and Logistic Regression error values have to be normally distributed
D. Both Linear Regression and Logistic Regression error values have not to be normally
distributed
5)For the figure given below, which decision boundary is overfitting the training data?

A. A
B. B
C. C
D. None of these

6)Select the correct alternatives from the following based on the figure

1. The training error in first plot is maximum as compared to second and third
plot.

2. The best model for this regression problem is the last (third) plot because it
has minimum training error (zero).

3. The second model is more robust than first and third because it will perform
best on unseen data.

4. The third model is overfitting more as compared to first and second.

5. All will perform same because we have not seen the testing data.

A. 1 and 3
B. 1 and 4
C. 1,3 and 4
D. 5

7)For categorical data with ‘n’ categories, the number of dummy variables will be________
A. n
B. n-1
C. n+1
D. 2n

8)In binary logistic regression,

A. The dependent variable is continuous


B. The dependent variable is divided into two equal subcategories
C. The dependent variable consists of two categories
D. There is no dependent variable

9) If the number of False negatives is 5 and number of True Positives is 20, the value of
recall will be equal to _______

A. 0.2
B. 0.6
C. 0.8
D. 0.3

10)If the precision is 0.6 and the recall value is 0.4, the value of f-measure will be

A. 0.48
B. 1
C. 0.24
D. None of these

Common questions

Powered by AI

A regression model with an R² value of 1 indicates that the Sum of Square of Error (SSE) is zero, meaning there is no unexplained variance . This implies that the model explains 100% of the variation in the dependent variable, and all data points lie perfectly on the regression line, indicating a perfect fit.

The F ratio in a completely randomized ANOVA is calculated as MSTR/MSE, where MSTR is the mean square due to treatment, and MSE is the mean square error . This ratio is important as it helps in determining whether the group means are significantly different by comparing the variance due to the treatment against the variance observed within the treatments.

A key assumption in factorial ANOVA is that the variance associated with the random variable must be the same across all populations . Homogeneity of variance ensures that the test results are reliable and any observed differences in group means are not due to variance differences in the populations.

Precision and recall are crucial metrics in classification models like logistic regression because they provide insights into the model’s accuracy in predicting positive classes. Precision, calculated as true positives divided by the sum of true positives and false positives, measures the accuracy of positive predictions. Recall, the ratio of true positives to the sum of true positives and false negatives, assesses the ability of the model to detect all positive instances . Both metrics, especially when combined into the F-measure, give a balanced picture of a model's predictive performance in imbalanced datasets.

Maximum Likelihood Estimation is preferred over Least Square Error in Logistic Regression because logistic regression involves binary outcomes, and Maximum Likelihood Estimation provides a method to estimate the probability of these outcomes accurately by maximizing the probability of observing the given set of data . It is more suited for the distribution of logistic regression outcomes as opposed to the assumptions made by Least Squares Error.

According to the regression equation Y = 120 - 10X, if the price increases by 2 units, the demand is expected to decrease by 20 units . This relationship demonstrates that demand decreases as price increases, which is a common economic principle.

The regression equation Y = 30,000 + 5X implies that for every additional dollar spent on advertising, sales increase by $5. The constant term 30,000 represents the baseline sales amount when no advertising is done . This demonstrates the expected relationship and effect of advertising expenditure on sales, as predicted by the regression model.

When the coefficient of determination is positive, the coefficient of correlation can be either positive or negative, depending on the direction of the relationship between the variables . The coefficient of determination, R², only explains the strength and proportion of variance explained by the model, not the direction.

In an ANOVA procedure, the numerator and denominator degrees of freedom for the critical value of F depend on the number of groups and the total number of observations across these groups. For instance, if four samples of 30 observations each are considered, the numerator and denominator degrees of freedom respectively are 3 and 116 . These degrees of freedom are crucial in the F distribution table to determine the critical value, signifying the number of independent pieces of data that are available for estimating statistical parameters.

An r² of 0.8 indicates that 80% of the variation in the dependent variable is explained by the independent variable . This high proportion suggests a strong relationship, implying the independent variable is a good predictor of the dependent variable.

You might also like