Exploring Data Science Fundamentals

What is the primary purpose of a histogram in data visualization?

• To show the relationship between two categorical variables

• To display the distribution of a single numerical variable

• To compare values across different categories using bars

• To illustrate trends over a period of time

Answer explanation

The primary purpose of a histogram is to display the distribution of a single numerical variable, showing how data points are spread across different ranges or intervals.

Which of the following best defines the term "mean" in statistical analysis?

• The middle value when data is arranged in ascending order

• The most frequently occurring value in a dataset

• The sum of all values divided by the number of values

• The difference between the maximum and minimum values

Answer explanation

The term 'mean' in statistical analysis refers to the average, which is calculated by summing all values and dividing by the number of values. This distinguishes it from the median and mode, which are different measures of central tendency.

In data cleaning, what does the term "missing values" refer to?

• Values that are duplicated in the dataset

• Values that are incorrectly formatted

• Entries where no data is recorded for a variable

• Values that fall outside the expected range

Answer explanation

In data cleaning, "missing values" specifically refer to entries where no data is recorded for a variable. This is crucial for accurate analysis, as missing data can lead to biased results.

Which type of chart is most appropriate for displaying the proportion of categories as parts of a whole?

• Line chart

• Scatter plot

• Pie chart

• Box plot

Answer explanation

A pie chart is ideal for displaying proportions of categories as parts of a whole, as it visually represents each category's contribution to the total. Other chart types like line or scatter plots are not suited for this purpose.

• The average of all data points

• The spread or dispersion of data points around the mean

• The total number of observations in the dataset

• The median value of the dataset

Answer explanation

The standard deviation \(\sigma\) measures the spread or dispersion of data points around the mean, indicating how much the data varies from the average value.

A data scientist is analyzing a dataset and notices that a scatter plot of two variables shows points closely following a straight line with a positive slope. Which of the following conclusions is most appropriate?

• The two variables have a strong negative correlation

• The two variables are completely independent of each other

• The two variables have a strong positive linear relationship

• The data contains significant outliers that distort the trend

Answer explanation

The scatter plot shows points closely following a straight line with a positive slope, indicating a strong positive linear relationship between the two variables.

• Median

• Mode

• Mean

• Range-based midpoint

Answer explanation

The mean is most affected by outliers because it takes all values into account. Adding an outlier like 200 will significantly increase the mean, while the median and mode remain unchanged.

• Delete all rows containing missing values

• Replace missing values with the column's mean

• Replace missing values with the string "N/A"

• Duplicate existing rows to fill the gaps

Answer explanation

Replacing missing values with the column's mean is appropriate for normally distributed data, as it maintains the overall data distribution. Other options either lose data or introduce non-numeric values, which are not suitable.

Answer explanation

The IQR is calculated as Q3 - Q1 = 50 - 20 = 30. To find outliers, we use the rule: lower bound = Q1 - 1.5*IQR = 20 - 45 = -25, upper bound = Q3 + 1.5*IQR = 50 + 45 = 95. Thus, 95 is an outlier.

A data analyst wants to compare the monthly sales performance of five different product categories over a 12-month period. Which visualization technique would best allow the analyst to observe both individual category trends and compare them simultaneously?

• A single pie chart showing total annual sales per category

• A multi-line chart with each line representing a product category over the 12 months

• A histogram showing the frequency distribution of sales values

• A single bar chart showing only the total sales for each category

Answer explanation

A multi-line chart effectively displays trends for each product category over 12 months, allowing for easy comparison and observation of individual category performance, unlike pie charts or bar charts that show only totals.