Principles of Psychological Research Flashcards
rules
principles of good design to set up for data collection
tools
summarising and describing data you’ve collected
theory
math behind rules and tools (stats)
psychology
scientific study of behaviour and mental processes
aristotle and plato
nature and origin of knowledge and thought
locke, hume, descarte and kant
philosophers question mind in 17th-19th century
wilhelm wundt (1879)
psychology became a science and studied structuralism
structuralism
mental events can be broken into components
william james (1890)
psychology is the science of mental life
4 goals of science
description, explanation, prediction and control
authority approach
seeking knowledge from sources thought to be valid and reliable
analogy approach
analogy between some event and a more familiar event
rule approach
try to establish laws or rules that cover a variety of different observation
empirical approach
testing ideas against actual events
hypothesis
an idea or tentative guess
population
members of a specific group
descriptive statistics
summarise the data collected from the sample
inferential statistics
generalise from the sample to the population
dependent variable
measurement taken
operational definition
specification of how the property of interest will be measured
validity
a DV is valid if it measures what it’s suppose to
reliability
DV is reliable if under the same conditions it gives the same measurement
bias
DV is bias when consistently inaccurate in one direction
ceiling effect
too easy task causes all scores to be too high
floor effect
too difficult task causes all score to be low
nominal scale
categorises without ordering (1-women, 2-man)
ordinal scale
categorises and orders categories (1-highlanders, 2-blues)
interval scale
categorises, orders and establishes an equal unit of measurement (celsius)
ratio scale
categorises, orders, establishes an equal unit of measurement and contains a true zero point (no. of items recalled in memory task)
independent variables
experimental factors that distinguish your group manipulated by the experimenter
levels
specific conditions of the IV
manipulated variable
factor directly manipulated by the experimenter
subject variable
factor not directly manipulated. what the experimenter can’t assign
true experiment
manipulated IV so can create a prediction and explanation as involves random assignment
quassi experiment
subject variable so only creates a prediction and can’t state causation
Woolfolk, Castellan and Brooks
Pepsi challenge was confounded by people prefering the letter ‘S’ to ‘L’
control group
comparison group, differs from the experimental group from a lack of treatment
placebo
thinking you’re receiving the treatment altering the results
single blind design
participants not knowing which treatment group they’re in
double blind design
neither experimenter or participants know the treatment group
demand characteristics
cues in a situation that people interpret as demands for a particular behaviour
between subjects design
each participant is tested in only one level of the IV which is easy to confound
within subjects design
subject tested in each treatment where it is easier to detect systematic differences
order effects
the order in which participants experience levels can be a problem (practise effects)
counterbalancing
each treatment condition is equally exposed to practise effects and demand characteristics in the within subjects design.
control variables
any extraneous variables that are held constant
multiple independent variables
sees interaction between IVs and with DV. The relationship between one IV and the DV may change as the levels of other IV(s) change
factorial design
when there are multiple IVs and you collect data in all combinations of the levels of your IVs (crossed)
mixed design
one IV within and one IV between where each participant receives one
main effects
the effects of one IV on the DV ignoring other IVs (one for each IV)
interaction effects
effects of one IV on the DV taking into account other IVs, interaction for every combination of IVs
frequency distribution
lets us see how values are distributed
inferential statistics (variability)
variability affects the kinds of statements we can make and how certain we are about those statements
descriptive statistics (variability)
how we describe the data so variability allows us to model the data
range
largest score minus the smallest score
mean deviation
all the data points minus the mean over n - always ends up being 0
variance
all the data points minus the mean squared over number of participants
standard deviation
approximately the average distance of the scores in a data set
unbiased sd
sd equation but minus one off the number in sample
inflection point
point where the curve begins to bend outward more (at each standard deviation point
within 1 sd
68% of data
within 2 sd
96% of data
within 3 sd
99.7% of data
z scores
tells us how far a score is from the mean which is measured in standard deviations
z score formula
z = data point minus the mean over the standard devation
z distribution
standardised normal distribution to compare things easily where mean = 0 and sd=1
correlation
if two or more DVs are related which can be used to describe and predict behaviour and direct research
bower (1990)
correlation between likeliness of low birthweight and premature birth with stress of mother during pregnancy
Perason’s r
computes a correlation numerically from -1 to 1
Pearson’s r assumptions
only detects linear relationships, have to be measured on the same individuals, must be measured on ratio or interval scale
curvilinear
negative parabola shape (yerkes-dodson curve)
cross lagged panel correlation
assumes that if X causes Y it will be stronger over timer
directionality problem
Y caused X or X caused Y?
