Defining Data

Key Definitions

Understanding the foundational terminology in statistics is essential for analyzing business data. The following definitions are central to the study of statistics:

• Population: The entire collection of objects or individuals of interest in a study.

• Sample: A subset of the population selected for analysis.

• Parameter: A numerical measure that describes a characteristic of a population.

• Statistic: A numerical measure that describes a characteristic of a sample.

Variables and Observations

• Variable: A characteristic, attribute, or measurement recorded for members of a population (e.g., age, height, income).

• Observation: A single member of the population for whom variables are measured.

• Variables are unpredictable prior to measurement, hence the term 'variable'.

Example

• A student in a class is an observation.

• Characteristics such as age, hair color, height, and weight are variables.

• Exact values of these variables cannot be predicted with certainty before measurement.

Branches of Statistics

Descriptive Statistics

Descriptive statistics involve collecting, summarizing, and presenting data. They provide simple summaries about the sample and the measures.

• Example formula for sample mean:

Inferential Statistics

Inferential statistics use sample data to make generalizations about a population. Key activities include:

• Estimation: Estimating population parameters (e.g., mean salary) using sample statistics.

• Hypothesis Testing: Testing claims about population parameters (e.g., is the mean salary $50,000?).

Classifying Variables

Types of Variables

• Numerical Variables: Allow meaningful arithmetic operations. Examples: age, grades, number of children.

• Categorical Variables: Do not allow meaningful arithmetic operations. Examples: gender, race, color.

Numerical Data

• Discrete: Finite or countable values (e.g., number of children).

• Continuous: Infinite or very large number of possible values (e.g., weight, salary).

• Sometimes, crude measurement of continuous variables makes them appear discrete.

Categorical Data

• Ordinal: Natural ordering exists (e.g., grades, shoe size).

• Nominal: No natural ordering (e.g., gender, race, color, state).

Example Classification

• Numerical variables: income, age, bank balance.

• Categorical variables: gender (nominal), education level (ordinal).

Organizing and Visualizing Data

Graphical Presentation of Data

Visualizing data helps in understanding distributions and relationships. Common methods include:

• Categorical Data: Pie charts, bar charts.

• Numerical Data: Frequency distributions, histograms, boxplots, scatter plots, time series plots.

Frequency Distributions

A frequency distribution is a table that displays class groupings (ranges) and the corresponding frequencies of data within each grouping.

• Each class grouping has the same width.

• Class boundaries do not overlap.

Example Frequency Distribution Table

Histograms

A histogram is a graphical representation of a frequency distribution. It uses bars to show the number of observations within each class interval.

• Horizontal axis: class boundaries or midpoints.

• Vertical axis: frequency, relative frequency, or percentage.

• Bars represent the number of observations per class.

Creating Histograms in Excel

1. Open the data file (e.g., temperature.xls).

2. Use the Data Analysis tool to select 'Histogram'.

3. Specify input range and bin range.

4. Check 'Labels' if data includes labels.

5. Select 'Chart Output' for graphical display.

Interpreting Histograms

• Histograms reveal the distribution shape (e.g., bell-shaped, skewed).

• They help compare spread and central tendency between data sets.

Scatter Diagrams

Scatter diagrams are used to examine relationships between two numerical variables.

• One variable on the vertical axis, one on the horizontal axis.

• Each point represents a pair of observations.

• Patterns may indicate direct (positive), inverse (negative), or no relationship.

Example: Scatter Plot in Excel

1. Select data columns (e.g., Income and Bank Balance).

2. Insert a scatter plot from the Chart menu.

3. Label axes and chart title appropriately.

Scatter Plot Interpretation

• Direct/Positive Relationship: As X increases, Y increases.

• Indirect/Negative Relationship: As X increases, Y decreases.

• No Relationship: No discernible pattern.

Summary Table: Types of Variables

Conclusion

This session introduced the foundational concepts of business statistics, including definitions, classification of variables, and methods for organizing and visualizing data. Mastery of these topics is essential for further study in statistical analysis and business decision-making.