W9 Thinking Like a Psychological Scientist
Introduction
Presenter: Hannah Keege
Topic: Thinking like a psychological scientist and applying skills from IRM in everyday life.
Thinking Like a Psychological Scientist
Importance of Critical Thinking
Critical thinking involves not taking information at face value.
Key steps:
Question the validity, authenticity, and truth of reports.
Investigate the sources of knowledge.
Avoid reliance on superstition or intuition.
Emphasis on logical and rational thought supported by empirical data.
Evidence-Based Decision Making
Psychological scientific knowledge is built on critical thinking and empirical evidence.
Example - Reading Articles:
Analyze claims in articles about the correlation between income and psychological disorders.
Article Example: Reports a negative relationship - more psychological diagnoses lead to lower income.
Critical Inquiry:
Is this a correct conclusion?
Correlation does not imply causation; it may be spurious.
Explore alternate explanations for the correlation.
Analyzing Personal Anecdotes and Treatments
Example: Claims of olive oil curing headaches from a friend.
Important considerations:
Subjective reports cannot be generalized.
Discuss alternative explanations:
May be due to massage, placebo effect, or mindfulness rather than the olive oil.
Scientific Approach to Treatments:
Standard of evidence should involve randomized controlled trials (RCTs).
RCTs test the full treatment versus various isolated components.
Scientific Hypothesis and Testing
The Nature of Proof in Science
Definition: Science does not prove anything conclusively.
Goal: To find evidence for or against a hypothesis; must be able to disprove to support.
Falsifiability: A valid hypothesis must be falsifiable.
Logic and Hypothesis Testing
Example: Hypothesis - To drive, one must be 18 or over.
Use cards in a logic game to test the hypothesis:
Cards: 1) Driving a car; 2) 16 years old; 3) Riding a bike; 4) 24 years old.
Testing the Rule:
To validate the hypothesis, you must look for situations that could falsify it.
The correct cards to turn are:
Driving a car: Check if under 18.
16 years old: Check if driving.
The Implications of Falsification
Finding evidence against a hypothesis doesn't make it false.
Always consider confounding factors that may affect results.
Communicating Variability and Uncertainty
Understanding Variability in Data
Importance in communicating findings with the public.
Issues of Misinterpretation:
Illustrates the idea that risk is not destiny (e.g., many smokers do not develop lung cancer).
Communication Strategy:
Must convey that estimates include uncertainty; singular narratives can be misleading.
Importance of Context in Data Presentation
Avoid using terms like "gap," which may imply a lack of variability.
Stressing on effect size alongside statistical significance.
Effects of Dichotomization
Avoiding False Dichotomies
Most subjects exist within the continuum between categories like rich and poor.
Importance of continuous assessment rather than classifying as categorical.
Data Interpretation and Multiple Comparisons
Awareness that conducting multiple tests increases the type I error rate.
Definition: Type I error - incorrectly rejecting a true null hypothesis.
Note on regression to the mean:
Extreme values tend to be closer to the mean upon subsequent observations.
Future of Psychological Science and Data Skills
Importance of Collaboration and Continuous Learning
Encourage building a network of peers for feedback on research ideas.
Essential to read entire research papers, especially methods and results, to understand findings fully.
Additional learning opportunities in data courses available.
Responsibility in Data Communication
Quote from Nate Silver: "Data does not speak for itself."
The individual must synthesize and communicate findings responsibly.
Growing job opportunities in psychology combined with data science.
Conclusion
Need for statistical literacy in understanding and communicating data in everyday life.
Encouragement to pursue further education in statistics and data science.
Call to inform others about the ethical use of statistical knowledge for public good.