Business Analytics Final Exam

What is the purpose of data normalization in EDA?

• To remove outliers

• To standardize data to a common scale

• To create new variables

• To perform hypothesis testing

Answer explanation

Data normalization in EDA is used to standardize data to a common scale, which helps in comparing different variables effectively. This ensures that no single variable dominates due to its scale, making analysis more reliable.

Which statistical measure quantifies the strength and direction of a linear relationship between two variables?

• Standard deviation

• Variance

• Correlation coefficient

• P-value

Answer explanation

The correlation coefficient quantifies the strength and direction of a linear relationship between two variables, indicating how closely they move together. Other options like standard deviation and variance measure variability, not correlation.

What does the law of large numbers state?

• Larger samples are always more accurate

• Sample means converge to the population mean as sample size increases

• All large samples are normally distributed

• Larger populations have more variability

Answer explanation

The law of large numbers states that as the sample size increases, the sample means will get closer to the population mean. This makes the choice 'Sample means converge to the population mean as sample size increases' correct.

In R, which package is commonly used for data manipulation and transformation?

• ggplot2

• dplyr

• caret

• stats

Answer explanation

The 'dplyr' package in R is specifically designed for data manipulation and transformation, providing functions for filtering, selecting, and summarizing data. Other options like 'ggplot2' and 'caret' serve different purposes.

Which statistical test would you use to compare means among three or more groups?

• t-test

• Chi-square test

• ANOVA

• z-test

Answer explanation

ANOVA (Analysis of Variance) is the appropriate test for comparing means across three or more groups, as it assesses whether there are statistically significant differences between the group means.

What type of chart is best for displaying the distribution of a continuous variable?

• Pie chart

• Bar chart

• Histogram

• Scatter plot

Answer explanation

A histogram is the best choice for displaying the distribution of a continuous variable as it groups data into bins, allowing for visualization of frequency and distribution patterns. Other charts are less effective for this purpose.

What does 'data wrangling' involve in EDA?

• Collecting raw data

• Transforming and mapping data from one format to another

• Deleting all missing values

• Creating complex visualizations

Answer explanation

Data wrangling in EDA primarily involves transforming and mapping data from one format to another, ensuring it is clean and structured for analysis. This is crucial for effective exploratory data analysis.

Which R function is used to create a data frame?

• create.dataframe()

• make.df()

• data.frame()

• new.dataframe()

Answer explanation

The correct function to create a data frame in R is data.frame(). The other options, create.dataframe(), make.df(), and new.dataframe(), do not exist in R, making data.frame() the only valid choice.

In hypothesis testing, what does the significance level (αα) represent?

• The probability of rejecting a true null hypothesis

• The test statistic value

• The probability of accepting the alternative hypothesis

• The sample size required for the test

Answer explanation

The significance level (α) represents the probability of rejecting a true null hypothesis, also known as a Type I error. It indicates how much risk of error the researcher is willing to accept when making a decision.

Which visualization technique is best for showing the relationship between two continuous variables?

• Bar chart

• Pie chart

• Scatter plot

• Histogram

Answer explanation

A scatter plot is the best visualization technique for showing the relationship between two continuous variables, as it displays individual data points and reveals patterns, trends, and correlations effectively.