Summary Research Methodology:
Chapter 1:
-Psychology is based on empiricism: using evidence from the senses or from instruments
that assist the senses as the basis for conclusions.
-Evidence-based treatments: therapies that are supported by research.
-Cupboard theory: mother is valuable to a baby because she’s a source of food.
-Contact comfort theory: mother is valuable because she gives comfort of cozy touch.
-Harlow: investigated these theories, made a wire mom with milk and a cozy mom, the
outcome was that the baby monkey’s spend a lot more time with the cozy mom.
-Theory: set of statements that describe general principles about how variables relate to one
another.
-Hypothesis: the specific outcome the researcher expects to observe if the theory is
accurate.
-Data: set of observations, data may support or challenge the theory.
-Good theories are supported by data, the more the
better.
-Good theories are falsifiable: a theory must led to hypo-
theses, when tested, it could fail to support the theory.
-Good theories have parsimony: theories are supposed
to be simple.
-The word prove isn’t used in psychology, nothing can
prove a theory.
-Scientists evaluate their theories based on the weight
of the evidence, for and against.
-Applied research: done with a particular problem in mind.
-Basic research: not intended to address a specific problem.
-Translational research: use basic research to develop and test applications.
-Researchers write a paper and submit it to a scientific journal, the articles are peer
reviewed. The paper get’s send to some specialists in the field, the peer-reviewers are
anonymous.
-Journalism: news and commentary mostly read on the internet or watched on tv. Sometimes
journalist chose the sensational news over the important news.
-Mozart effect: example of over-sensation of scientific news; research -> you get a short
lasting and very small advantage on some intelligence tests when you listen to Mozart for 10
minutes, headline -> ‘’You get smarter when you listen to Mozart.
Chapter 2:
-3 ways to obtain knowledge:
1) Personal experience; important for generating new ideas, there is no control
possible, has confounds (there are alternative explanations), it treats validity (do we
measure what we want to measure).
2) Intuition; gut feeling, can be important to do important scientific inventions, the
problem is that you feel something, who’s feelings are right? Is biased, has availability
heuristic; what pops up easily in our mind tends to guide our thinking, people
overestimate how often something happens.
3) Authority; they try to convince us to accept their claims, which authorities can we
, trust (research based) and which we can’t (experience/intuition based)?
-Confederate: actor playing a specific role for the experimenter.
-Research is probabilistic: the findings aren’t expected to explain all cases all of the time.
-Present/present bias: failure to consider appropriate comparison groups.
-Confirmation bias: only look at information that confirms your theory.
-Bias blinds spot: believe that we’re unlikely to fall prey to biases, the sneakiest one, because
we less initiate the scientific-theory cycle.
-Empirical journal articles: report, for the first time, the results of an (empirical) research
study.
-Review journal articles: provide summary of all published studies that have been done in
one research area, are sometimes used as meta-analysis; combines the results of many
studies and gives a number tat summarizes the magnitude/effect size of a relationship.
-Edited books: collection of chapters on a common topic, each chapter is written by a
different contributor.
-Language trade book: on the bookshelves in stores, more comprehensible language than in
psychological books and show everyday applies.
-Abstract: concise summary of the article, about 120 words long.
-Introduction: first paragraph explains topic, middle paragraph the background, final
paragraph states research question and goals/hypotheses.
-Method: detailed explanation how the researcher conducted the research, you can do the
method in principle without asking question to the researcher.
-Results: describes relevant quantitative and qualitative results of the study, including the
statistical tests used to analyze the data.
-Discussion: first paragraph is a summary, second paragraph the importance of the study,
third paragraph gives alternative explanations and other interesting research questions.
-References: full bibliographic list of all the sources the author used cited in the article.
-2 important questions when reading and empirical journal article; what is the argument, and
what is the evidence to support the argument?
Chapter 3:
-Variable: something that varies, so it must have at least two levels/values.
-Constant: something that could potentially vary, but has only one lever in the research.
-Measured variable: levels are simply observed and recorded, even abstract variables
(depression or stress) can be measured (but not with something like a ruler).
-Manipulated variable: is controlled by the researcher, e.g. 10 mg or 15 mg medicines, or
some people have to do in a room with people and others in a room alone, some variables
can’t be measured (e.g. age or IQ), some variables are unethical to be manipulated (e.g.
what the effect of eating different kinds of plastic is).
-Some variables can either be manipulated or measured, depending on the goal of the study.
E.g. you can measure what hair color people have, or manipulate it by painting their hair.
-Conceptual variables: abstract concepts such as spending time socializing and school
achievement. Are elements of a theory, are sometimes called a construct. These variables
have to be carefully defined at the theoretical level, these definitions form the conceptual
definitions. E.g. car ownership
-Operational variables/operational definitions: to operationalize means to turn a concept into
, a measured or manipulated variable. Are used to study them. E.g. having a car yes or no.
-Claim: argument someone is trying to make. E.g. 72% of the world smiled today.
-Frequency claim: described a rate or a degree of a single variable. E.g. just 15% of all
Americans smoke. It claims how frequent or common something is. The best way to identify
is to focus on only one variable, such as smoking. A report/research can have multiple
different frequency claims.
-Association claim: one level of a variable is likely to be associated with a particular level of
another variable, they are said to correlate (when one variable changes, the other tends to
change too). E.g. people with higher incomes spend less time socializing. There have to be
at least 2 variables to make a frequency claim. The study is called a correlational study.
-Positive association: high goes with high and low goes with low. The correlation
coefficient (r) has to be between 0 and 1. The higher the stronger the association.
-Negative association: high goes with low and low goes with high. The correlation
coefficient (r) has to be between -1 and 0. The more negative the stronger the
association.
-Zero association: there is no correlation between variables, correlation coefficient (r)
of 0.
-Associations can be used to make predictions. When you know one variable you can
predict the other. The stronger the relationship between the variables, the better the
prediction. Zero correlation can’t do predictions.
-Causal claim: one of the variables is responsible for the change of another variable. Has at
least 2 variables. Start with negative/positive association (sometimes on zero association
e.g. vaccines don’t cause autism). Go beyond a simple association between 2 variables, it
claims that one variable causes the change of another. Even when worlds like, maybe/could/
sometimes are used, there is a causal claim made. They make a stronger statement than
association claims. There must be no other explanations for the correlation of the variables.
-Investigating frequency claims:
-Validity: appropriateness of a conclusion or decision and in general, a valid claim is
reasonable, accurate and justifiable.
-Construct validity: how well a conceptual variable is operationalized. When evaluation the
construct validity of a frequency claim, the question is how well the researcher investigated
their variables. How well a study measured or manipulated a variable.
-External validity: how generalizable is a claim. Does it represent the whole population/group
of interest. Did the researcher chose the correct subject group? Does it apply to other
situations?
-Statistical validity: extent to which a study’s statistical conclusions are reasonable are
accurate and statistical important. Usually accompanied by a margin of error of the estimate,
that tries to include the true value in the population. E.g. +/- 2,6 percentage points.
-Investigating association claims:
-Construct validity, external validity, statistical validity (strength and significance)
-Type I error: there is an association between 2 variables, but no association in the
population. Also called false positive.
-Type II error: there is no association between 2 variables, but there is an association
in the population. Also called a miss.
-Important for making frequency, association or causal claimsf
-Investigating causal claims:
-Covariance: the extent to which two variables are observed to go together.