Comprehensive Study Notes: Experimental Psychology Methods, Statistics, Ethics, and Sampling

Techniques in Experimental Psychology

• Experimental Method: research technique to investigate cause–effect relationships.

  • The researcher manipulates one variable and measures its effect on another variable.
  • Example fragment from transcript: manipulating the Independent Variable (IV) to observe changes in the Dependent Variable (DV).

• Key variables

  • Independent Variable (IV): the variable that is manipulated (the factor being tested to find a cause).
  • Dependent Variable (DV): the variable observed and measured for changes in the experiment.

• Confounding Variables

  • Variables not accounted for or controlled in the study but still affect results.
  • Can distort the true effect of the IV on the DV, making causality harder to determine.
  • Example: prior knowledge of test topics affecting performance.

• Operational Definitions

  • How a researcher measures and manipulates variables in a study.
  • Outlines exact procedures/operations used to define and quantify abstract concepts, making them measurable.
  • Example: specifying exact ingredient instructions, procedures, or scoring methods.
  • Purpose: allows replication and verification by other researchers; ensures consistency and clarity in research.

• Experimental Group vs Control Group

  • Experimental Group: receives the IV (the treatment or intervention).
  • Control Group (placebo): does not receive the IV; serves as a comparison group; may continue with regular methods.

• Random Assignment

  • Assigning participants to different groups randomly to ensure equal chance of being in any condition.
  • Methods: coin toss, random number generator, drawing from a hat.
  • Purpose: minimizes systematic differences between groups that could bias results.

• Placebo Effect

  • Phenomenon where participants expect a beneficial treatment and experience improvement even if they receive no active treatment.
  • Example: placebo alcohol leading to perceived effects.

• Experimenter Bias

  • Researchers' expectations or beliefs about the outcome can influence the study or interpretation of data.
  • Risk: can inadvertently affect data interpretation, leading to inaccurate conclusions.

• Blinding Procedures

  • Single-Blind Study: participants are unaware of whether they are in the experimental or control group; researchers may know.
  • Double-Blind Study: both participants and researchers are unaware of group assignments until after data collection.
  • Purpose: reduces bias in data collection, treatment administration, and interpretation.

• Placebo Condition and Randomization Notes

  • A placebo condition often used to control for the placebo effect.
  • Random assignment helps ensure that observed effects are due to the IV and not preexisting differences.

Statistical Analysis Techniques in Psychology

• Purpose of statistics

  • Turn data into information, describe characteristics, and make predictions about populations.
  • Distinguish between descriptive statistics (describe sample) and inferential statistics (make inferences about a larger population).

• Descriptive Statistics

  • Measures of Central Tendency: describe the center of a data set.
  • Mean: the average value, ext{Mean} = rac{1}{N}
    \sum{i=1}^N xi
  • Median: the middle value when data are ordered.
  • Mode: the most frequently occurring value.
  • Range: the difference between the highest and lowest values.
  • $ext{Range} = x<em>{ ext{max}} - x</em>{ ext{min}}$
  • Spread (variability): describes how spread out the values are.
  • Normal Curve (Bell Curve): majority of data cluster near the center (mean).
  • Unimodal vs Multimodal: single peak vs multiple peaks.
  • Symmetrical Distribution: data are evenly distributed around the center.
  • Skewness:
  • Positive Skew: tail extends to the right; majority of data on the left; outliers or unusually high values.
  • Negative Skew: tail extends to the left; majority of data on the right; outliers or unusually low values.
  • Standard Deviation: measures how spread out the numbers are around the mean.
  • $ext{SD} = \sqrt{\frac{1}{N-1} \sum<em>{i=1}^N (x</em>i - \bar{x})^2}$
  • Percentile Rank: indicates the percentage of scores in a distribution at or below a given value; used to compare an individual's score to a larger group.
  • Bimodal Distribution: two distinct peaks, suggesting two common values or modes; implies uneven distribution or two underlying groups.
  • Regression to the Mean: extreme scores tend to move closer to the average on subsequent measures.
  • Probability and Significance:
  • Probability that an observed result is due to chance is denoted as p.
  • Statistical Significance: typically assessed via a p-value.
  • Threshold commonly used: p < 0.05, indicating results are unlikely to have occurred by chance.

• Inferential Statistics

  • Generalizations: using sample data to infer about a larger population.
  • t-Tests and other inferential tests yield a p-value that informs significance.
  • Effect Size: magnitude of the difference/relationship; important alongside p-values.
  • Large effect size = substantial difference/strong IV impact on DV.
  • Small effect size = minimal difference/weak IV impact on DV.
  • Meta-Analysis: statistical analysis of multiple studies on the same topic to draw broader conclusions; combines data to increase overall sample size and statistical power.

• Key concepts summary

  • Normal distribution and central tendency concepts underpin many statistical tests.
  • Outliers and skewness affect measures like mean and standard deviation.
  • p-values assess whether observed effects are likely due to chance; do not measure practical importance by themselves.
  • Effect sizes and meta-analyses deepen understanding beyond single-study significance.

• Quick formulas to remember

  • Mean: $\bar{x} = \frac{1}{N} \sum<em>{i=1}^N x</em>i$
  • Range: $ext{Range} = x<em>{ ext{max}} - x</em>{ ext{min}}$
  • Standard Deviation (sample): $ext{SD} = \sqrt{\frac{1}{N-1} \sum<em>{i=1}^N (x</em>i - \bar{x})^2}$
  • p-value threshold: p < 0.05
  • Normal distribution (PDF): $f(x) = \frac{1}{\sigma\sqrt{2\pi}} \exp\left(-\frac{(x-\mu)^2}{2\sigma^2}\right)$

Ethical Guidelines in Psychological Research

• Institutional Review Boards (IRBs)

  • Committees responsible for reviewing and approving research proposals to ensure safety, ethics, and compliance.
  • Members typically include researchers, ethicists, and community representatives.

• Steps in the IRB process

  • Proposal Submission: Researchers submit the proposal for IRB review.
  • Initial Review: IRB assesses whether the proposal meets ethical guidelines and regulations.
  • Ethical Assessment: IRB evaluates potential risks and benefits to participants.
  • Feedback and Revision: Researchers revise the proposal based on IRB feedback if needed.
  • Final Approval: IRB grants approval to proceed after revisions.
  • Ongoing Oversight: IRB continues to monitor the research during the study.

• Core Ethical Guidelines

  • Informed Consent: participants voluntarily agree after being given sufficient information about the study.
  • Deception: allowed only when justified and used sparingly; participants should be debriefed after participation if deception occurred.
  • Debriefing: provide a full explanation of the study after data collection.
  • Right to Withdraw: participants can leave the study at any time without consequences.
  • Confidentiality: protect participant data; store data securely and share only as permissible.
  • Informed Assent: similar concept for individuals with limited decision-making capacity (children or cognitive impairments); use age-appropriate information; assess capacity before consent.
  • Deception and Confederates:
  • Some studies use deception to hide true purpose; outcomes may involve confederates—people who are in on the study and act as part of the procedure.

• Practical implications

  • Balancing scientific gain with participant welfare.
  • Ensuring voluntary participation, privacy, and dignity.
  • The ethical justification for any deception must be strong, with thorough debriefing and safeguards.

Sampling, Representation, and Generalizability

• Sample vs. Population

  • Sample: a subset of individuals from a larger population studied to make inferences about the population.
  • Population: the entire group of interest.

• Representativeness and Bias

  • Representative Sample: mirrors the demographics, characteristics, and diversity of the population to improve applicability of results.
  • Sample Bias: when the sample is not representative, leading to inaccurate results.
  • Generalizability: the extent to which findings from the sample can be generalized to the larger population.

• Sampling Methods

  • Stratified Sampling: divide population into subgroups (strata) based on characteristics, then randomly sample from each stratum.
  • Convenience Sampling: select participants based on availability and accessibility; often less representative.
  • Random Sampling: each member of the population has an equal chance of selection; enhances representativeness and generalizability; examples include lottery methods, random software, or drawing from a hat.

• Reducing Bias and Increasing Generalizability

  • Minimize sample bias to improve validity and the likelihood that results generalize beyond the studied cases.

• Key terms

  • Generalizability: confidence researchers have in extending conclusions beyond the sampled cases.
  • Representative Sample: a sample that reflects demographics and diversity of the population.
  • Stratified Sampling: subgroups are proportionally represented in the sample.
  • Convenience Sampling: easy-to-reach participants; may introduce bias.
  • Random Sample: equal opportunity for inclusion; reduces researcher bias.

• Real-world relevance

  • Ethical and practical considerations in selecting samples; trade-offs between representativeness and feasibility.
  • The strength of generalizations relies on how well the sample represents the population of interest.