Untitled Flashcards Set

Q: What is the null hypothesis (H₀)?
A: The IV will not have an effect on the DV.

Q: What is the alternative hypothesis (H₁)?
A: The IV will have an effect on the DV.

Q: What is a p-value?
A: The probability that the observed difference between means is due to error variance.

Q: When is a result considered statistically significant?
A: When the p-value is less than the alpha level (commonly 0.05).

Q: Why do journals encourage reporting effect sizes?
A: To quantify how much the IV impacts the DV.

Q: What is the file-drawer problem?
A: The tendency for nonsignificant findings to go unpublished, leading to biased understanding of research.

Q: What is Type I error?
A: Rejecting the null hypothesis when it is true (false positive).

Q: What is Type II error?
A: Failing to reject the null hypothesis when it is false (false negative).

Q: What is statistical power?
A: The probability of correctly rejecting a false null hypothesis.

Q: What is p-hacking?
A: Over-analyzing data to make nonsignificant results significant.

Q: What is Cohen's d?
A: A measure of effect size indicating the difference between two group means relative to standard deviation.

Quasi-Experimental and Single-Case Designs (Lecture 11)

Q: How does a quasi-experiment differ from a true experiment?
A: Quasi-experiments lack random assignment and have less control over IV manipulation.

Q: What is regression to the mean?
A: The tendency for extreme scores to move closer to the mean with repeated testing.

Q: What is a nonequivalent control group design?
A: A design that uses a similar but non-randomly assigned control group.

Q: What is a one-group pretest-posttest design?
A: A study measuring participants before and after an intervention, but without a control group.

Q: What is an ABA design?
A: A single-case experimental design with baseline (A), intervention (B), and return to baseline (A).

Q: What is an ABAB design?
A: A variation of the ABA design, adding a second intervention to confirm effects.

Q: When is a single-case design unethical?
A: When withdrawing a beneficial intervention could harm participants (e.g., removing effective medication).

Q: What is a local history effect?
A: An external event that affects only one group during a study.

Q: What is the difference between nomothetic and idiographic approaches?
A: Nomothetic focuses on group means and generalizations, while idiographic analyzes individual behavior in detail.

Q: What are two limitations of case studies?
A: Observer bias and failure to control extraneous variables.

Key Statistical Tools and Measures

Q: What does NHST stand for?
A: Null Hypothesis Significance Testing.

Q: What is the purpose of NHST?
A: To determine if observed differences exceed what is expected by error variance.

Q: What is the alpha level?
A: The threshold probability (commonly 0.05) for rejecting the null hypothesis.

Q: What is an ANOVA used for?
A: To analyze differences between group means when the IV has more than two levels.

Q1: In the above example on sunlight and happiness, I set my alpha-level to p = .05. However, when I conduct the appropriate analysis, I obtain a p-value of .12. Which is the correct interpretation of p = .12?

• A: There is a 12% chance that our obtained mean difference could be attributed to error variance alone—thus, we fail to reject the null hypothesis.

Q2: Dr. Abbott is investigating whether listening to different genres of music (i.e., pop, R&B, country) enhances memory. Which of the following would be the null hypothesis in this experiment?

• A: Genre of music will not have an effect on memory.

Q3: Which of the following is NOT a concern with null hypothesis significance testing?

• A: It encourages people to use artificial intelligence (AI) rather than traditional statistical software.

Q4: Dr. Hillgrove conducted an experiment on whether studying independently or in a group enhances learning. Which of the following is an example of a one-tailed alternative hypothesis for this experiment?

• A: Students who study in a group will demonstrate better learning than students who study independently.

Q5: As stated in lecture, we cannot simply compare group means in an experiment to see if our IV had an effect; rather, we have to use statistical analyses. Which of the following is NOT a reason why we cannot directly compare group means?

• A: Group means are on a nominal scale, rather than interval/ratio.

Q6: Create a fictional research question that you would analyze with a correlation.

• A: Does the number of hours college students sleep per night relate to their levels of reported stress?
  Explanation: Correlation is used because it examines the relationship between two continuous variables without manipulation.

Q7: Create a fictional research question that you would analyze with a t-test.

• A: Do students who attend a preparatory workshop score higher on a certification exam than those who do not attend?
  Explanation: A t-test is used to compare the means of two independent groups.

Q8: I am conducting an experiment on whether sunlight affects people’s happiness level. To claim that sunlight does have an effect on happiness would be to:

• A: Reject the null.

Q9: Create a fictional research question that you would analyze with an ANOVA.

• A: Do different teaching methods—lecture-based, interactive discussion, and online modules—impact student comprehension levels differently?
  Explanation: ANOVA is used to compare means across three or more groups.

Q10: You conduct a study on whether people are more or less likely to donate to a charity if the person requesting the donation is an adult or a child. In reality, people are more likely to donate if a child is seeking the donation. You fail to reject the null hypothesis. Which of the following best describes this situation?

• A: Type II error.