Chapter 1: Using Graphs to Describe Data

Introduction

This chapter introduces foundational concepts in statistics for business, focusing on how to use graphs and tables to describe and summarize data. It covers the importance of statistical thinking in decision-making, key definitions, types of data, sampling methods, and graphical techniques for both categorical and numerical variables.

Section 1.1: Decision Making in an Uncertain Environment

Role of Statistics in Decision Making

• Statistics provides tools to process, summarize, analyze, and interpret data, especially when decisions must be made with incomplete information.

• Examples include predicting job market trends, stock prices, and the impact of economic policies.

Key Definitions

Population vs. Sample

• Population: The entire set of items or individuals of interest (denoted as N).

• Sample: A subset of the population that is actually observed or analyzed (denoted as n).

• We use samples to make inferences about populations.

Parameter vs. Statistic

• Parameter: A numerical measure describing a characteristic of a population (e.g., population mean μ).

• Statistic: A numerical measure describing a characteristic of a sample (e.g., sample mean ̄x).

• Sample statistics are used to estimate population parameters.

Descriptive vs. Inferential Statistics

• Descriptive Statistics: Methods for summarizing and presenting data (e.g., tables, graphs, averages).

• Inferential Statistics: Methods for making predictions or decisions about a population based on sample data (e.g., estimation, hypothesis testing).

Types of Data and Levels of Measurement

Primary vs. Secondary Data

• Primary Data: Collected directly by the researcher (more control, but time-consuming and costly).

• Secondary Data: Collected by others (less control, but often cheaper and faster).

Levels of Measurement

• Nominal: Categories without order (e.g., gender, yes/no).

• Ordinal: Categories with a meaningful order (e.g., satisfaction level).

• Numerical (Quantitative): Numbers representing counts or measurements.

  • Discrete: Countable values (e.g., number of children).

  • Continuous: Any value within a range (e.g., wage, temperature).

Sampling Methods

Simple Random Sampling

• Each member of the population has an equal chance of being selected.

• Ensures unbiased representation of the population.

Other Sampling Methods

• Multistage samples

• Stratified samples

• Voluntary response samples

• Convenience samples

Sampling and Non-sampling Errors

• Sampling Error: Variability due to the sample being only one of many possible samples.

• Non-sampling Error: Errors not related to the act of sampling (e.g., non-response, response bias, coverage error).

Cases and Variables

• Cases: The objects described by a set of data (e.g., people, companies).

• Variables: Characteristics measured on each case (e.g., age, wage).

Section 1.2: Classification of Variables

Types of Variables

• Qualitative (Categorical): Nominal and ordinal variables (cannot compute an average).

• Quantitative (Numerical): Discrete and continuous variables (can compute an average).

Section 1.3–1.5: Graphical Representation of Data

Tables and Graphs for Categorical Variables

• Frequency Distribution Table: Lists categories and their frequencies.

• Bar Chart: Visualizes frequencies or percentages for each category.

• Pareto Diagram: Bar chart with categories in descending order of frequency, often with a cumulative line.

• Pie Chart: Shows proportions of categories as slices of a circle.

• Cross Table (Contingency Table): Shows frequencies for combinations of two categorical variables.

Tables for Categorical Data

Tables and Graphs for Numerical Variables

• Frequency Distribution: Groups numerical data into intervals (bins) and counts frequencies.

• Histogram: Bar graph for numerical data; bars touch, representing intervals.

• Ogive: Cumulative frequency line graph.

• Stem-and-Leaf Display: Shows distribution while preserving original data values.

Scatterplots and Relationships Between Variables

• Scatterplot: Graphs paired data to reveal relationships between two numerical variables.

• Direction: Positive association (both variables increase together) or negative association (one increases, the other decreases).

• Strength: Strong or weak association, presence of outliers.

Summary Table: Graphical Methods

Key Formulas

• Sample Mean:

• Relative Frequency:

• Percent Frequency:

Conclusion

Understanding the types of data, sampling methods, and graphical techniques is essential for effective statistical analysis in business. Proper use of tables and graphs allows for clear communication of data insights, supporting informed decision-making.