Chapter 2: Summarizing and Graphing Data

Visual Display of Data

After organizing data into a frequency distribution, statisticians use various graphs to visually convey information. Graphs help viewers quickly understand patterns, trends, and distributions within the data.

• Dot Plot: A dot plot places a dot for each data item along a number line. This simple graph shows the distribution and ordering of raw data.

• Histogram: A histogram displays the frequency distribution of data. The x-axis shows intervals (bins), and the y-axis shows frequency. Bars touch each other, indicating continuous data.

• Cumulative Line Graph (Ogive): An ogive plots cumulative frequencies or cumulative relative frequencies. The curve starts at 0 and ends at 1.00 (for relative frequency).

• Stem-and-Leaf Plot: This low-tech alternative to a histogram splits each data value into a "stem" (leading digits) and a "leaf" (last digit), showing the shape and distribution of the data.

Example: For the data set {23, 54, 29, 34, 45, 36, 39, 40}, a dot plot would place dots at each value along a number line. A histogram would group these values into intervals (e.g., 20<x≤30, 30<x≤40, etc.) and show frequencies as bar heights.

Pie Chart

Pie charts represent categorical data as slices of a circle, with each slice proportional to the frequency or percentage of each category.

• Calculation: Percentage for each category = (Frequency / Total) × 100%

Example: Car sales data for July can be visualized as a pie chart, showing the proportion of each car type sold.

Scatter Plot

Scatter plots are used to examine relationships between two quantitative variables. Each point represents a pair of values (x, y) for an individual or item.

• Direct Relationship (Positive Correlation): As x increases, y increases (e.g., height vs. weight).

• Inverse Relationship (Negative Correlation): As x increases, y decreases (e.g., temperature vs. gas usage).

• No Relationship (Uncorrelated): Points are scattered randomly, showing no pattern (e.g., height vs. social security number).

Example: Plotting height and weight for adults shows a positive correlation; plotting temperature and gas usage shows a negative correlation.

Skewness and Distribution Shapes

Skewness describes the asymmetry of a distribution. Histograms help visualize skewness and modality.

• Symmetric Distribution: Data is balanced around the center (e.g., defects per lot).

• Skewed Left: Most values are high, with a tail stretching to the left (e.g., test scores with few low values).

• Skewed Right: Most values are low, with a tail stretching to the right (e.g., income distribution with few high earners).

• Bimodal Distribution: Two distinct peaks or modes (e.g., family incomes in a diverse community).

Example: A histogram of quiz grades skewed left indicates most students scored high; a histogram of family incomes skewed right shows most families earn less, with a few earning much more.

Key Concepts for Exam I

• Constructing Relative Frequency Distributions and Cumulative Frequency Distributions

• Determining if sample data is from a normal distribution using histograms or normal quantile plots

• Constructing various graphs: scatterplot, frequency polygon, dotplot, stemplot, bar graph, multiple bar graph, pie chart

• Critically analyzing graphs for objectivity and potential misleading features

Chapter 3: Describing, Exploring, and Comparing Data

Measures of Central Tendency

Measures of central tendency describe the center or typical value of a data set. The three main measures are the mean, median, and mode.

• Mean (Arithmetic Mean): The sum of all data values divided by the number of values. For a sample, the mean is denoted by ; for a population, by .

Sample Mean Formula:

Population Mean Formula:

• Median: The middle value in a ranked (ordered) data set. If the number of values is even, the median is the average of the two middle values. Denoted by or "Mdn" in APA style.

Median Location Formula:

• Mode: The most frequently occurring value in the data set. If no value repeats, there is no mode. If two values tie for highest frequency, the data is bimodal.

Example: For the data set {5, -7, 2, 0, -9, 12, 10, 7}:

• Mean:

• Median:

• Mode: No mode (all values occur once)

Application: In salary data, the mean can be misleading if there are outliers (e.g., one person earns much more than others). The median or mode may better represent the typical value.

Outliers

Outliers are extreme values that differ significantly from other data points. They can distort measures like the mean and affect statistical analysis.

• Example: In a company with five employees earning $10,000 and a president earning $50,000, the president's salary is an outlier.

• Outliers can make the mean unrepresentative of the typical value.

Comparing Measures of Central Tendency

Each measure of central tendency has strengths and weaknesses. The mean is sensitive to outliers, the median is robust to extreme values, and the mode is useful for categorical or discrete data.

Example: In a bus with nine riders earning $50,000 and Bill Gates earning millions, the mean income is misleading, but the median remains $50,000, accurately representing the typical rider.

SPSS Application

Statistical software like SPSS can compute descriptive statistics:

• Click Analyze → Descriptive Statistics → Explore

• Move variable names into the Dependent List

• Click OK to generate summary statistics

Additional info:

• Measures of variation (e.g., range, variance, standard deviation) and measures of relative standing (e.g., percentiles, quartiles, box plots) are also important in Chapter 3 but not detailed in the provided notes.