Statistics: Data Collection and Sampling Methods - Study Guide

Study Guide - Smart Notes

Tailored notes based on your materials, expanded with key definitions, examples, and context.

Introduction to Statistics

Parameters vs. Statistics

Statistics is the science of collecting, organizing, analyzing, and interpreting data to make informed decisions. Understanding the distinction between populations and samples, as well as parameters and statistics, is fundamental in statistical analysis.

Data: Information gathered from counting, measuring, or collecting responses.
Population: The entire set containing all data points of interest ("every", "each").
Sample: A subset of the population, selected for study.
Parameter: A numerical value summarizing a characteristic for the whole population.
Statistic: A numerical value summarizing a characteristic for a sample.

Example: The salary of every employee at a marketing firm is a population; the average salary of all employees is a parameter. The salaries of 12 out of 100 employees is a sample; the average salary of those 12 is a statistic.

Practice Questions

Collecting test scores of every other student in a class: Sample
46.5% of all registered voters are registered democrats: Parameter
Amount spent by each customer in a grocery store: Population
Average workout duration from 40 gym members: Statistic

Types of Data

Qualitative vs. Quantitative Data

Data can be categorized as qualitative or quantitative, each with distinct properties and uses in statistical analysis.

Qualitative Data: Describes qualities or categories (e.g., favorite color, eye color).
Quantitative Data: Describes quantities or numerical values (e.g., number of students, dice roll).
Discrete Quantitative Data: Numbers that cannot be broken down further (e.g., number of goals scored).
Continuous Quantitative Data: Numbers that can be broken down infinitely (e.g., time, temperature).

Example: Surveying nationalities is qualitative; measuring distances walked is quantitative and continuous.

Brands of smartphones owned: Qualitative
Number of goals scored: Discrete Quantitative
Time to complete a lap: Continuous Quantitative

Clock representing time as continuous data Thermometer representing temperature as continuous data

Levels of Measurement

Classification of Data by Measurement Level

Levels of measurement describe the nature of data and what mathematical operations are meaningful.

Level	Description	Qualitative/Quantitative	Example
Nominal	Categories, names, or labels; no order; no calculations	Qualitative	Hair color
Ordinal	Ordered data; differences are not meaningful	Qualitative or Quantitative	Letter grades, jersey numbers
Interval	Meaningful differences; no true zero; ratios are meaningless	Quantitative	Temperature
Ratio	True zero exists; ratios are meaningful	Quantitative	Heights, distances

Example: Birth years (interval), satisfaction ratings (ordinal), working hours (ratio), favorite music genre (nominal).

Nominal level example Ordinal level example Interval level example Ratio level example

Practice: Rating symptoms as mild, moderate, or severe is ordinal; birth weights are ratio; favorite menu item is nominal.

Ordinal level example Interval level example Nominal level example Ratio level example

Example: Recording water temperature at multiple points is interval; saying water is "twice as hot" does not make sense because interval data lacks a true zero.

Temperature measurement example Explanation of interval level

Collecting Data

Observational Studies vs. Experiments

Data collection methods are crucial for determining whether causation can be inferred.

Experiment: Apply a treatment and measure its effects; causation can be assumed if properly controlled.
Observational Study: No intervention; only measure characteristics; causation cannot be assumed.

Example: Testing medication with placebo and actual treatment is an experiment; surveying sleep habits is observational.

Experiment example Observational study example

Sampling Methods

Simple Random Sampling

Sampling is the process of selecting a subset of subjects from a population. A representative sample accurately reflects the characteristics of the population.

Simple Random Sampling (SRS): Each subject and each possible group is equally likely to be selected.
Representative Sample: Contains proportions of characteristics similar to the population.

Example: Randomly selecting marbles from a bag or students from a class.

Random selection example

Other Sampling Methods

When SRS is impractical, other methods are used:

Systematic Sampling: Select every nth subject from the population.
Cluster Sampling: Divide population into groups (clusters), then randomly select entire clusters.
Stratified Sampling: Divide population into strata with similar characteristics, then randomly select subjects from each stratum.

Method	Description	Example
SRS	Randomly select sample from whole population	Random number generator for employee survey
Systematic	Select every nth subject	Testing every 12th cookie
Cluster	Divide into clusters, select entire clusters	Randomly select 1 class per grade
Stratified	Divide into strata, select from each stratum	Surveying undergrads and grad students

Systematic sampling example Cluster sampling example Stratified sampling example

Practice: Selecting every tenth unit is systematic; selecting random units from each machine is stratified; selecting random cases is cluster.

Summary Table: Sampling Methods

Sampling Method	How It Works	When to Use
Simple Random	Random selection from entire population	When all subjects are equally accessible
Systematic	Select every nth subject	When a list of subjects is available
Cluster	Divide into clusters, select whole clusters	When population is naturally grouped
Stratified	Divide into strata, select from each	When subgroups are important

Additional info: These notes cover Chapter 1: Data Collection, including definitions, examples, and practice questions relevant to introductory statistics. All images included directly reinforce the concepts explained in the adjacent paragraphs.