Scribd Logo
Upload

Welcome to Scribd!

  • 60 views

    Practice Midterm Questions 1 and 2

    Uploaded by

    Mandapalli Satish
    The document contains a practice midterm exam with 10 multiple choice questions. Question 1 asks about normalizing crime data based on graphs of the original and normalized data. Question 2 asks which statement about the original crime data histogram is most likely. Questions 3 and 4 consider a boxplot of employee work experience and performance categories. Questions 5-10 provide a correlation matrix and regression output to answer questions about estimating relationships between employee compensation and other factors like work experience, age, education and promotions.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    Practice Midterm Questions 1 and 2

    Uploaded by

    Mandapalli Satish
    60 views4 pages
    The document contains a practice midterm exam with 10 multiple choice questions. Question 1 asks about normalizing crime data based on graphs of the original and normalized data. Question 2 asks which statement about the original crime data histogram is most likely. Questions 3 and 4 consider a boxplot of employee work experience and performance categories. Questions 5-10 provide a correlation matrix and regression output to answer questions about estimating relationships between employee compensation and other factors like work experience, age, education and promotions.

    Original Description:

    Just reading

    Original Title

    Practice Midterm

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document contains a practice midterm exam with 10 multiple choice questions. Question 1 asks about normalizing crime data based on graphs of the original and normalized data. Question 2 asks which statement about the original crime data histogram is most likely. Questions 3 and 4 consider a boxplot of employee work experience and performance categories. Questions 5-10 provide a correlation matrix and regression output to answer questions about estimating relationships between employee compensation and other factors like work experience, age, education and promotions.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    60 views4 pages

    Practice Midterm Questions 1 and 2

    Uploaded by

    Mandapalli Satish
    The document contains a practice midterm exam with 10 multiple choice questions. Question 1 asks about normalizing crime data based on graphs of the original and normalized data. Question 2 asks which statement about the original crime data histogram is most likely. Questions 3 and 4 consider a boxplot of employee work experience and performance categories. Questions 5-10 provide a correlation matrix and regression output to answer questions about estimating relationships between employee compensation and other factors like work experience, age, education and promotions.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 4

    Practice Midterm

    Questions 1 and 2

    Consider the histogram and the associated box plot of the dataset called “Crime Data”, below
    and answer questions 1 and 2

    1. The data was normalized (by subtracting the mean and dividing by standard deviation of
    the data). Which of the following graphs best represents the normalized data?

    (A)$ (B)

    (C) (D)

    2. Based on the histogram of the original data, which of the following statements is most
    likely?
    A. If we use this variable as a predictor (independent) variable, it will definitely be an
    influential variable
    B. If we use this variable as a predictor (independent) variable, it will definitely be a
    leverage point
    C. The distribution is left skewed
    D. The distribution is right skewed$
    Questions 3 and 4
    Consider the boxplot below which gives the distribution of work experience (in months) of
    employees in the company. The employees are categorized into two groups based
    performance. The first category is “Low” Performers (with an annual rating of 3.15 or less
    out of 4.00) denoted by “0” and “High” players (with an annual rating of above 3.15 out of
    4.00) denoted by “1”.

    3. Which of the following statements is true?


    A. Employees with shorter work experience perform better$
    B. Employees with longer work experience perform better
    C. The performance category is independent of the work experience
    D. Cannot say unless a combined box plot is drawn

    4. We would like to build a prediction model for predicting the category of employees (Low
    or High performers). Then, ________
    A. Work experience is not a good predictor because there is a large amount of overlap
    B. Work experience is a good predictor even though there is a large amount of overlap$
    C. Work experience cannot be used as a predictor because there is a large difference
    between the two medians
    D. Work experience cannot be used because the two distributions are not similar

    Questions 5 to 10

    Yajvin is trying to estimate the relationship between compensation and other factors. He had
    collected data on 150 employees in the company from HR department. He collected the data
    on the Compensation (Comp) (Rs. lakhs), Months of work experience (WorkEx), Age in
    months (Age), Number of years of post-high school education (EDU) and Number
    Promotions (Promo) in the company. The correlation matrix across all the variables is given
    below:

      Comp (lakhs) WorkEx Age Edu Promo

    Comp (lakhs) 1.0000


    WorkEx 0.6968 1.0000
    Age 0.4852 0.1063 1.0000
    EDU 0.5765 0.8296 0.0504 1.0000
    Promo 0.6605 0.7710 0.1339 0.6572 1.0000

    5. He has estimated a simple linear regression with EDU as the dependent variable and
    Comp as the independent variable. What percentage of the variation of the dependent
    variable is explained by the regression equation (i.e., what is the R2?)?
    A. 57.65% B. 33.24%$ C. 75.93% D. 82.96%

    6. He decided to interchange the dependent and independent variables of the above


    regression, i.e., he decided to estimate a simple linear regression with Comp as the
    dependent variable and EDU as the independent variable. What percentage of the
    variation of the dependent variable is explained by the regression equation?
    A. 57.65% B. 33.24%$ C. 75.93% D. 82.96%
      Coeffici Standard t Stat P-value Lower Upper
    ents Error 95% 95%
    Intercept 55.2050 10.1448 0.0000
    WorkEx 0.0070 0.0000 0.0170 0.0448
    Age 0.8836 0.0000 5.7886 9.2815
    EDU 0.8232 0.3533 0.7244 -3.7823 5.4287
    Promo 14.7222 4.3345 0.0009 6.1553

    7. What is the value of the t statistic with respect to the regression coefficient of the variable
    “WorkEx”?
    A. 0.0070 B. 0.0309 C. 0.0000 D. 4.4143$

    8. If we reject the null hypothesis that the variable Promo has no impact on the
    compensation, what is the probability of Type I error?
    A. 0.09%$ B. 99.91% C. 14.72% D. cannot be calculated

    9. Based on the regression equation estimated above and appropriate hypothesis tests, which
    of the variables need to be dropped from the regression equation?
    A. WorkEx
    B. EDU$
    C. Age
    D. Promo

    10. What is the degrees of freedom with respect to “residuals”?


    A. 150 B. 149 C. 148 D. 145$

    You might also like