PSY1HPM Lecture Notes - Lecture 9: Confidence Interval, Thomas Kuhn, Normal Science
30 Jun 2018
School
Department
Course
Professor
HPM Lecture 9 – PHILOSOPHICAL FOUNDATIONS OF PSYCHOLOGY (3)
The Importance of Replication in Psychological Research
Which is worse: replication or failure to replicate? A growing number of researchers say replications add substantial value to science
The Open Science Framework has a free, open-source Web application to help researchers organize, archive, document and share
their research materials and data.
Post Popper
As yet no philosopher has provided a definitive account of how science has proceeded or how it should proceed
The three most important philosophers to follow on from Popper were Kuhn, Lakatos and Laudan
All propose that science is best understood in terms of larger units of evaluation than of individual theories
The Problems with Psychology
The vast majority of psychological research violates falsificationism
Sometimes that’s psychology’s fault but sometimes it isn’t
We tend to rely too heavily on null hypothesis testing
This results in our developing “real” hypotheses that aren’t truly risky
How do we move to units of analysis beyond the single study?
Meta-analysis and other forms of analysis
Primary analysis: The analysis of data from a single study to test the hypotheses originally formulated.
Secondary analysis: The re-analysis of data from a single study to test new hypotheses or to apply more
appropriate statistical procedures to test the original hypotheses.
Meta-analysis: The application of statistical procedures to examine tests of a common hypothesis from more than one study.
“The analysis of analyses”
A Basic Definition
Meta-analysis attempts to apply to a collection of studies the same methodological rigor and statistical precision ordinarily found in
primary research.
In a meta-analysis, the collection of studies test the same conceptual hypothesis, but may do so using a wide variety of methods,
measures, sample, and settings.
The challenge that meta-analysis answers is to provide a way to combine the seemingly disparate studies to provide a convincing
overall test of the hypothesis and to explore its moderators.
Smith & Glass
Smith and Glass (1977) examined over 300 therapy outcome studies and concluded that, overall, therapy was quite effective, placing
the average treated person better off than 80% of untreated people.
Collating diverse studies to produce a single measure
Hypothesis: Frustration produces aggression
oStudy 1: Sample = college students
oSetting = psychology laboratory
oIV = easy versus impossible anagrams
oDV = rating of the experimenter’s competence
Hypothesis: Frustration produces aggression
oStudy 2: Sample = college students
oSetting = psychology laboratory
oIV = helpful versus unhelpful confederate
oDV = shock level chosen to punish the
confederate during a learning task
Hypothesis: Frustration produces aggression
oStudy 3: Sample = movie goers
oSetting = natural setting
oIV = number of people ahead in line when a
show sells out
oDV = observed nonverbal and verbal
behavioural indicators of anger
Does frustration cause aggression
Hypothesis: Frustration produces aggression
Several years go by the challenge: How can several studies, testing the same hypothesis, but using different methods, measures,
samples, and settings be combined?
The solution: In a meta-analysis, each study outcome is “standardized” to allow their combination and comparison. The seemingly
troublesome differences (e.g., settings, measures) are coded and become moderators that are incorporated into the analysis which
can each in turn be analysed for their respective effects.
A common metric
In a meta-analysis, the unit of analysis is the individual study, akin to an individual participant in primary research.
Each study provides a statistical test of the conceptual hypothesis. The outcome of that statistical test (e.g., statistical significance,
effect size) provides a standardized outcome, akin to the dependent measure in primary research.
find more resources at oneclass.com
find more resources at oneclass.com
Document Summary
Hpm lecture 9 philosophical foundations of psychology (3) A growing number of researchers say replications add substantial value to science. The open science framework has a free, open-source web application to help researchers organize, archive, document and share their research materials and data. As yet no philosopher has provided a definitive account of how science has proceeded or how it should proceed. The three most important philosophers to follow on from popper were kuhn, lakatos and laudan. All propose that science is best understood in terms of larger units of evaluation than of individual theories. The vast majority of psychological research violates falsificationism. Sometimes that"s psychology"s fault but sometimes it isn"t. We tend to rely too heavily on null hypothesis testing. This results in our developing real hypotheses that aren"t truly risky. Primary analysis: the analysis of data from a single study to test the hypotheses originally formulated.
