PSYCH 9A Lecture Notes - Lecture 1: Big Bang, External Validity, Scatter Plot
Course CodePSYCH 9A
This preview shows half of the first page. to view the full 3 pages of the document.
PSYCH 9A - LECTURE 1
-People do not use appropriate research methods in psychological research run a high risk of generating BS.
-Example: Journal’s Paper on ESP Expected to Prompt Outrage - precognition (ability to predict the future)
for erotic photos.
-The effect size is rather small (53% vs. 50% guessing rate). However, if there are many human research
subjects with each running many trials, such an effect can reach statistical significance as determined by
standard methods of inferential statistics
-If you keep on running experiments of this sort, you will get something that looks like a result of just by
-The more times an experiment is repeated, the less likely the result is due to chance alone.
-There is no result if it cannot be replicated.
-Basic principles of statistics: The more observations that you make, the more likely it is that you will observe
patterns that “couldn’t possibly occur by chance” - even though they occur just by chance!
-Example: If you keep on running ESP experiments, you are bound to get one that looks as though it is
producing positive results (even though it is just by chance). Proper research methods are needed to interpret
IMPORTANT RESEARCH METHOD: OBSERVATION
-In making the choice about what behavior we should study, we’re usually guided by the questions we hope to
address through our observations. Moreover, we need to formulate the question in a way that leaves no doubt
about how we’re going to link the question to the evidence we collect.
-Induction: on example based on observation of “observed variables”.
-Deduction: apply rules to specific cases.
-Any research projects begins with:
-Testable hypothesis - a specific claim about the facts, framed in a way that will allow an unambiguous test.
(Testability, in turn, is guaranteed by ensuring that the hypothesis is falsifiable).
-Testable hypotheses requires well-defined terms.
-Operation definition - a definition that translates the variable we want to assess into a specific
procedure or measurement.
-We need the operational definition to have construct validity - that is, must truly reflect the variable
named in our hypothesis.
-Example: aggression as an operational action rather than frown - a facial action.
-Untestable hypotheses are ideas that are open-ended or are too general to be interpreted.
-Example: Astrologers predict the future in an open-ended way that we can’t test the claims.
-Scientific method: test a theory by performing an experiment.
*There are many theories out there, based on observation, which do not lead to hypotheses that can be easily
tested by experiment.
-At this time at least, we’re unable to directly manipulate key variables:
-From Physics: Cosmology, original big bang, universe expansion, black hole behavior.
-From Economics: Sunspots cause Economic cycles.
-From Psychology: Darwinian Evolution has played a key role in determining human behavior.
-Independent variable(s) - are directly manipulated by the experimenter.
-Dependent variable(s) - are measured.
-Experimental group - the group that is manipulated by the experimenter.
-Control group - the group that is not manipulated by the experimenter.
-Control variable(s) - these are independent variables that are manipulated in an experiment with the aim of
ruling out explanations for the results other than those that bear directly on the tested hypothesis.
-Subject variable(s): theses are characteristics of the (human) subjects who participate in an experiment.
Because they are not directly manipulated by the experimenter, they are not true independent variables.
-Quasi-experiment: an experiment in which only the effects of subject variables are tested (already-existing
groups - groups that experimenter did not create or manipulate).
You're Reading a Preview
Unlock to view full version