Foundations of Descriptive Statistics: Variables, Data, and Distributions

Descriptive Statistics: Key Concepts and Measures

Variables and Data Structures

Statistics involves collecting, analyzing, and interpreting data. Understanding the types of data and their organization is fundamental to statistical analysis.

• Variable: An entity that can assume different values or descriptions. Variables can change from one observation to another.

• Population: The complete group of individuals or items under study. Example: All students at UT.

• Sample: A subset of the population selected for analysis. Example: 20 randomly chosen UT students.

• Sample Space: The set of all possible values a statistical variable can take.

• Observation: A single measurement or record from one element of the population.

• Parameter: A numerical value summarizing a characteristic of a population (e.g., population mean).

• Statistic: A numerical value summarizing a characteristic of a sample (e.g., sample mean).

Types of Variables

• Quantitative Variable: Measures a quantity or amount. Can be discrete or continuous.

• Discrete Variable: Takes on distinct, separate values (often integers). Example: Number of doors on a car.

• Continuous Variable: Can take any value within a range, including fractions and decimals. Example: Miles per gallon.

• Qualitative (Categorical) Variable: Describes a quality or characteristic, not a number. Example: Color of a car.

Basic Statistical Terms

• Proportion: The relative size of one part compared to the whole, often expressed as a ratio.

• Frequency: The number of times a particular observation occurs in a data set.

• Summation Notation (Σ): The Greek letter sigma (Σ) denotes the sum of a set of values.

Descriptive Statistics: Calculating Measures

Descriptive statistics summarize and describe the main features of a data set.

• Sample Mean (\( \overline{X} \)): The average of all sample values.

Formula:

$\overline{X} = \frac{\sum x}{n}$

• Sample Variance (S2): Measures the average squared deviation from the mean.

Formula:

$S^2 = \frac{\sum (x - \overline{X})^2}{n-1}$

• Sample Standard Deviation (S): The square root of the variance; measures spread in the same units as the data.

Formula:

$S = \sqrt{\frac{\sum (x - \overline{X})^2}{n-1}}$

• Units: The mean and standard deviation have the same units as the data; variance has squared units.

Example: For the data set {6, 5, 7, 9, 15, 30}:

• Mean: 6

• Variance: 62

• Standard deviation: $\sqrt{62}$

Interpretation: The mean gives the central value, variance and standard deviation describe the spread of the data.

Percentiles and Quartiles

Percentiles and quartiles are measures that describe the relative standing of a value within a data set.

• Percentile: The value below which a given percentage of observations fall. For example, the 35th percentile (P35) is the value below which 35% of the data lie.

• Quartiles: Special percentiles that divide the data into four equal parts:

  • Q1 (1st Quartile) = 25th percentile

  • Q2 (2nd Quartile) = 50th percentile = Median

  • Q3 (3rd Quartile) = 75th percentile

Example: If 35% of values are less than or equal to 1592 and 65% are greater than or equal to 1592, then 1592 is the 35th percentile (P35).

Example: If 83% of values are less than or equal to 287 and 17% are greater than or equal to 287, then 287 is the 83rd percentile (P83).

Example: If 25% of values are less than or equal to 96 and 75% are greater than or equal to 96, then 96 is the 1st quartile (Q1 = P25).

Types of Distributions

Distributions describe how data values are spread or clustered. Understanding the shape of a distribution is essential for interpreting data.

• Symmetric Distribution: The left and right sides of the distribution are mirror images. Mean = Median = Mode.

• Bimodal Distribution: The distribution has two distinct peaks or modes.

• Uniform Distribution: All values occur with approximately equal frequency. Mean = Median.

• Skewed Right Distribution: The tail on the right side is longer; mean > median > mode.

• Skewed Left Distribution: The tail on the left side is longer; mean < median < mode.

Example Table: Summary of Distribution Types

Distribution Type	Shape	Relationship of Mean, Median, Mode
Symmetric	Bell-shaped or uniform	Mean = Median = Mode
Bimodal	Two peaks	Modes at two different values
Uniform	Flat, all values equally likely	Mean = Median
Skewed Right	Tail to the right	Mean > Median > Mode
Skewed Left	Tail to the left	Mean < Median < Mode

Application Example: Car Data Collection

Suppose data are collected from 100 randomly chosen parked cars on campus. The following variables might be recorded for each car:

• Horsepower (quantitative, continuous)

• Number of doors (quantitative, discrete)

• Miles per gallon (quantitative, continuous)

• Odometer mileage reading (quantitative, continuous)

• Color of the vehicle (qualitative, categorical)

These variables can be analyzed to understand the distribution and variability among cars on campus.

Additional info: In practice, understanding the type of variable helps determine the appropriate statistical methods for analysis. For example, means and standard deviations are meaningful for quantitative variables, while proportions and frequency tables are used for categorical variables.