Samples, Populations, & Sampling

QUIZ-READY STUDY GUIDE: Samples, Populations, & Sampling

1. Core Ideas (Must Know)

  • Purpose of Samples: We use samples to learn about populations.

  • Sampling Error: Every sample contains sampling error.

  • Variability of Results: Different samples yield different results; this is a normal occurrence.

  • Reliability Affected by Variability: Variability in the data affects how reliable a sample is.

  • Distribution of Sample Means: We utilize the distribution of sample means to make inferences about populations.

2. Key Definitions (Memorize These)

  • Population: The entire group of interest (e.g., all college students).

  • Sample: A subset of the population that is measured.

  • Data: An individual score or measurement obtained from the sample.

  • Sampling Error: The difference between a sample result and the true population value due to chance.

  • Variability: The extent to which the data points are spread out in a dataset.

3. Why Sampling Error Happens

  • Imperfect Representation: No sample perfectly represents the population.

  • Effect of Variability: More variability within a population leads to more sampling error in the sample.

  • Sample Size: Larger, more representative samples generally incur less sampling error.

  • Universal Occurrence: All studies, regardless of design, experience some level of sampling error.

4. Sampling Methods (Very Testable)

Probability Sampling

  • Definition: Each individual in the population has a known chance of being selected for the sample.

    • Simple Random Sample: Every individual has an equal chance of being chosen.

    • Stratified Sample: The population is divided into groups (strata), and the samples represent the proportions of these groups within the population.

    • Cluster Sample: Groups (clusters) are randomly selected, and individuals are then sampled within those groups.

    • Best Use: Cluster sampling is advantageous for reducing bias and is effective for large or dispersed populations.

Convenience Sampling

  • Definition: Individuals are selected because they are easily accessible; the probability of selection is unknown.

  • Common Examples: Often involves volunteers or college undergraduates.

  • Drawbacks: Increases sampling error and limits the generalizability of results.

5. Stratified vs. Cluster (Know the Difference)

Stratified Sampling

  • Purpose: Ensures that key characteristics of the population are represented adequately in the sample.

  • Control: Allows for specific percentage control of various subgroups within the population, thus reducing bias.

Cluster Sampling

  • Purpose: Involves random selection of entire groups (e.g., schools, cities).

  • Use Case: More suitable for very large or geographically spread-out populations.

6. Distribution of Sample Means

  • Definition: The distribution of all possible sample means that can be obtained from repeated samples of the same size.

  • Key Facts:

    • Most sample means cluster around the population mean.

    • Extreme sample means are infrequent.

    • This distribution is crucial for determining whether observed results are likely due to chance or suggest a real population effect.

7. Inferential Statistics (Conceptual)

  • Core Question: Is this result likely due to sampling error?

    • If the result is deemed unlikely due to sampling error, it suggests the presence of a real effect in the population.

  • Cautionary Note: A single study does not definitively prove a conclusion; further research and validation are necessary.

8. Comparing Groups (How to Think on the Quiz)

  • Key Questions:

    1. Are the sample means different?

    2. How much variability is present among the samples?

    3. Could the observed differences be explained by sampling error?