data analysis with r coursera week 6 quiz answers

Final Exam

1. Which of the following is NOT a task facilitated by R?

  • Model evaluation
  • Data cleaning
  • Model development
  • Data generation

2. To combine functions, use the _____________________.

  • slash
  • two commas
  • pipe operator
  • parentheses

3. Which of the following is NOT true?

  • Data formating ensures that data is consistent and easily understandable.
  • Fully coherent data is consistent and can be reliably combined for analysis.
  • In a data set, data is usually collected from a single source and stored in a single format.
  • In statistics, coherence is an indication of the quality of the information in a single data set.

4. Which of the following situations does NOT call for data normalization?

  • When the scale of a feature causes it to have a disproportional impact on results
  • When there are outliers that might skew the results
  • When you want to compare numerical and character values
  • When different data set features are in very different ranges

5. Which of the following is NOT true of a scatter plot?

  • It shows the relationship between two variables.
  • It cannot suggest a liner relationship between two variables.
  • Each observation is represented as a point.
  • The predictor/independent variables are on the x-axis.

6. What does a P-score measure?

  • If it is large, it indicate a strong correlation between variable categories and the target variable.
  • It indicates whether the ANOVA test result is statistically significant.
  • It indicates the validity of data within a data set.
  • It is the ratio of various between group means over the variance within each of the sample group means.

7. A positive correlation is one in which _____________.

  • both variables move in opposite directions
  • both variables move in the same direction
  • only one variable moves
  • a causative relationship is shown

8. Which of the following is NOT true about a model?

  • The amount of data you have should have no effect on the accuracy of the model.
  • A model helps predict a value given one or more other values.
  • Models work by relating one or more independent variables to dependent variables.
  • Different types of models may be more accurate in different situations.

9. Which of the following is NOT a method for evaluating a regression model?

  • Root mean squared error (RMSE)
  • Root absolute error (RAE)
  • Mean squared error (MSE)
  • Mean absolute error (MAE)

10. A training set is ________.

  • a small portion of the data used to evaluate the performance of a model
  • a large portion of a data set that is used to build a sound model
  • multiple data sets that have been run on the model
  • a selected porion of the data set that is known to function well within the model

Leave a Reply