Unit 0

1. Experimental Research

Goal: Determine cause-and-effect relationships.

Key Terms:

  • Independent Variable (IV): Manipulated by experimenter (e.g., TV program type).

  • Dependent Variable (DV): Measured outcome (e.g., aggression toward doll).

  • Control Variables: Kept constant (e.g., presence of doll).

  • Experimental Group: Receives the IV.

  • Control Group: Does not receive IV; used for comparison.

Sampling & Assignment:

  • Population: Entire group of interest.

  • Sample: Subset drawn from population.

  • Random Sampling: Ensures representativeness of population.

  • Random Assignment: Ensures minimal differences between groups.

Blinding:

  • Single-Blind: Subjects unaware of group.

  • Double-Blind: Both researcher and subjects unaware (avoids bias).

  • Placebo: Fake treatment to mimic experimental condition for control group.

Validity:

  • Internal Validity: Results due to IV, not confounds.

  • External Validity: Results can be generalized to real-world settings.

  • Reliability: Consistent results over repeated trials.

  • Inter-Rater Reliability: Agreement among observers.

2. Correlational Research

Goal: Assess the relationship between variables (no manipulation).

Important Concepts:

  • Correlation ≠ Causation.

  • AConfounding Variable: A third variable affecting both others.

  • Survey Methods: Questionnaires/interviews gather data.

  • Social Desirability Bias: Participants may answer untruthfully to seem favorable.

Types of Studios

  • Longitudinal: Same subjects over long time.

  • Cross-Sectional: Various subjects at one point in time.

3. Clinical Research

Goal: Study individuals in-depth to understand psychological conditions.

Method:

  • Case Studies: Intensive analysis of one person or a few individuals.

    • Strength: Deep detail.

    • Weakness: Not generalizable, can’t determine causation.

  • Used by Freud, Rogers, etc.

Sampling Biases

  1. Selection from Specific Area Bias: E.g., surveying only students in one spot on campus.

  2. Self-Selection Bias: Only motivated individuals volunteer.

  3. Pre-screening/Advertising Bias: Recruitment skews sample (e.g., “want to quit smoking” ad).

  4. Healthy User Bias: Healthier people more likely to participate.

🌍

Other Research Types

  • Naturalistic Observation: Real-world setting; authentic but hard to control.

  • Qualitative Research: Focuses on rich descriptions, not numerical data.

    • Includes case studies, ethnographies, narratives, grounded theory, etc.

📊

Statistics in Psychology

Descriptive Statistics:

  • Mean: Average.

  • Median: Middle value.

  • Mode: Most frequent value.

  • Range: Max – Min.

  • Standard Deviation: Measures variability (spread around the mean).

Inferential Statistics:

  • Allows hypotheses testing and drawing conclusions beyond data set.

📊

Normal Distribution (Bell Curve)

  • A normal distribution depends on:

    • Mean: the center of the curve

    • Standard deviation: the width and height of the curve

      • Large SD: short and wide curve

      • Small SD: tall and narrow curve

  • In a perfect normal distribution, mean = median = mode.

  • Percent of data within standard deviations:

    • 68% within ±1 SD

    • 95% within ±2 SD

    • 99.7% within ±3 SD

📏

Standard Deviation

  • Measures how spread out scores are from the mean.

  • Example: If mean = 1.3 sec and SD = 0.2 sec:

    • Most scores (68%) fall between 1.1 and 1.5 seconds.

📈

Skewed Distributions

  • Positive Skew (tail to the right): Most values are low; a few high outliers.

  • Negative Skew (tail to the left): Most values are high; a few low outliers.

  • Use the median for skewed distributions (it’s less affected by outliers than the mean).

Percentile

  • Shows your position relative to others.

    • Example: 85th percentile = you scored better than 85% of people.

🔄

Correlation

  • Measures relationship between two variables.

  • Correlation coefficient (r):

    • Ranges from -1.0 to +1.0

    • +1 = perfect positive correlation

    • -1 = perfect negative correlation

    • 0 = no correlation

  • Pearson correlation coefficient is commonly used.

    • Direction: + or - tells you if both increase/decrease together (+) or one increases while the other decreases (-).

    • Strength: closer to 1 or -1 means stronger relationship.

📉📈 Examples

  • Positive correlation: More years of education → higher income.

  • Negative correlation: More absences from math class → lower math scores.

  • Study example: Child agreeableness vs behavioral problems = r = -0.6

Correlation ≠ Causation

  • Just because two things are related does not mean one causes the other.

  • Example: Ice cream sales and murder rates both rise in summer. But ice cream doesn’t cause murders — a third variable (temperature) is the real cause.

📊 Inferential Statistics

🔹 Purpose

  • Inferential statistics help determine if research results reflect a real effect or happened by chance.

  • They allow generalization from a sample to a population.

🔹 Key Terms

Sample: small group tested in an experiment

Population: larger group the results aim to represent

Representative sample: A sample reflecting the population’s characteristics

Sample Size: (n or N)

Statistical Power: Likelihood that results reflect a real effect, not chance

💕Hypothesis Testing

Null Hypothesis : treatment had no effect

Alternative Hypothesis: treatment had an effect

🔹 Statistical Significance

  • A result is statistically significant if it’s unlikely to have occurred by chance.

  • Alpha (α): Acceptable level of error (usually set at 0.05 → 5%)

    • Means we’re okay with a 5% chance of being wrong.

🔹 Types of Errors

Error Type

Description

Example

Nickname

Type I Error

False positive: Conclude effect exists, but it doesn’t

Saying a drug works when it doesn’t

False positive

Type II Error

False negative: Conclude no effect, but it does exist

Saying a drug doesn’t work when it does

False negative

  • p-value: Probability that results are due to chance (want p < 0.05)

⚖ Ethics in Psychological Research

🔹 Deception

  • Allowed only when necessary and justified

  • Must be explained during debriefing

  • Example: Milgram’s obedience study (1970s) used deception about electric shocks

🔹 Informed Consent

  • Participants must:

    • Be told what the study involves

    • Voluntarily agree

    • Be allowed to withdraw at any time

🔹 Debriefing

  • After the study ends, participants are:

    • Informed of the true purpose

    • Told about any deception

🔹 Confidentiality

  • Data is usually collected anonymously

  • If not, researchers must keep data confidential

🔹 Institutional Review Boards (IRBs)

  • Review experiments before they begin

  • Ensure ethical standards are followed

🐭 Animal Research

  • Controversial but widely used in psychology

  • Ethical guidelines require:

    • Minimizing pain and stress

    • Using animals only when necessary

    • Proper care and humane treatment

  • Justified by psychologists because:

    • Allows drug testing and experimental control not possible with humans