Step 2: Data Collection
Step 2: Data Collection
A. Purpose of Data Collection
Collect data from a sample due to difficulty or expense of gathering from the entire population.
Use statistical analysis to generalize findings if proper sampling procedures are followed.
B. Sampling Approaches
Probability Sampling
Every member has a chance of being selected.
Reduces research bias and ensures representativeness.
Suitable for parametric tests.
Non-probability Sampling
Some members are more likely to be selected based on convenience or self-selection.
Easier data collection but can introduce biases.
More appropriate for non-parametric tests, though weaker inferences result.
C. Generalization and Validity
External validity applies findings to those sharing characteristics with the sample.
Results from WEIRD (Western, Educated, Industrialized, Rich and Democratic) populations may not generalize to non-WEIRD populations.
Discuss limitations of generalizing findings when using parametric tests to data fromnon-probability samples.
D. Creating an Appropriate Sampling Procedure
Determine how to recruit participants and whether a diverse representation is feasible.
E. Experimental Example: Sampling
Contact schools to recruit diverse students for an experiment.
F. Correlational Example: Sampling
Use social media to recruit male college students from various universities.
G. Sample Size Calculation
Assess sample size using existing studies, statistics, or calculators.
Minimum of 30 units per subgroup recommended.
Key components to input into calculators:
Significance level (alpha): the risk of rejecting a true null hypothesis that you are willing to take, usually set at 5%.
Statistical power: the probability of your study detecting an effect of a certain size if there is one, usually 80% or higher.
Expected effect size: a standardized indication of how large the expected result of your study will be, usually based on other similar studies.
Population standard deviation: an estimate of the population parameter based on a previous study or a pilot study of your own.
H. Conclusion
Proper sampling strategies are crucial for reliable data and analyses.