exam review Flashcards
what are the steps of the research process?
- choose a research question
- conducting a literature review
- making a hypothesis
- designing the study
- conducting the study
- analyzing the study
- reporting the results
3 ways to find a research topic
- informal observations
- practical problems
- previous research (most common)
informal observations
from the world around you, other or own behaviour
practical problems
seeing an issue and applying research
previous research
look at journals from areas of interest
theory
cohesive explanation about a set of events that has not yet been shown to be untrue
- used to explain phenomena
- uses variables
hypothesis
specific prediction about an event or phenomenon that is testable
- often derived from theories
inductive hypothesis
many observations for a theory
hypothetico-deductive model
says that you can get new hypotheses from derived theories
what makes a good hypothesis?
- it is testifiable and falsifiable
- logical
- positive
- replicable
variable
a quantity or quality that varies across people or situations
quantitative variable
a quantity that is typically measured by assigning a number to each individual (height, number of siblings)
categorical variable
a quality that is typically measured by assigning a category label to each individual (occupation, university major)
operational definition
a definition of the variable in terms of precisely how it is to be measured
population
large group of people about whom researchers want to draw conclusions about
sample
smaller portion or subset of the population that is studied
simple random sampling
every member of the population has an equal chance of being selected for the sample ( hard to do in practice)
convenience sample
sample consists of individuals who happen to be nearby and willing to participate (more likely used)
independent variable
variable manipulated by the experimenter (x)
dependent variable
variable the experimenter measures (y)
extraneous variables
any variables other than the IV/DV
confounds
specific type of extraneous variable that systematically varies with the variables under investigation
non-experimental research
researcher measures variables as they naturally occur without manipulation
what does non-experimental research allow for?
description and prediction but NOT for making causal conclusions
laboratory study
conducted in the laboratory environment and usually has high internal validity
field study
conducted in the real world and usually has high external validity
internal validity
the degree to which we can confidently infer a causal relationship between variables
external validity
the degree to which we can generalize the findings
descriptive statistics
used to summarize the data
inferential statistics
used to generalize the results from the sample to the population of interest
what are types of descriptive statistics?
measures of central tendency and measures of dispersion
measures of dispersion
describes the spread of the scores in a distribution (range and standard deviation)
range
the difference between the highest and lowest scores in a distribution
standard deviation
a computed measure of how much scores vary around the mean
correlation coefficient
a statistical measure of the relationship between two variables
when are differences statistically significant?
when calculations indicate that research results are not likely to be result of chance
type I error
you rejected the null hypothesis when you should have failed to reject it (false positive)
type II error
you failed to reject the null hypothesis when you should have rejected it (false negative)
morality
principles set by a group or individual that determine right from wrong
ethics
branch of philosophy that questions moral principles and determines the appropriate code of conduct within a field
moral principles to consider in scientific research
- weighing risks against benefits
- acting responsibly and with integrity
- seeking justice
- respecting peoples rights and dignity
unavoidable ethical conflict
when something arises you deal with it in a responsible way
measurement
the assignment of scores to individuals so that the scores represent some characteristic of the individuals
constructs
variables we want to measure that are seemingly not straightforward or simple to measure (personality, attitudes)
how do we measure our variables?
must use an operational definition
self-report measures
participants report on their own thoughts, feelings and actions
behavioural measures
some other aspect of participants behaviour is observed and recorded
physiological measures
involve recording any of a wide variety of physiological processes
four scales a variable can be measured on
- nominal
- ordinal
- interval
- ratio
nominal scale
categorical (qualitative)
ordinal scale
rank order, discrete, difference between rank is NOT equal
interval scale
numeric scale with NO true zero point and each point is equal distance between each other
ratio scale
numeric scale with TRUE ZERO
what do the levels of measurement determine?
the type of statistics you can do and conclusions you can make
reliability
ability to obtain consistent scores
validity
ability of a test to measure what it’s supposed to
test-retest reliability
a measure’s consistency over time
internal consistency
consistency of people’s responses across the items on a multiple item measure
what is used to test internal consistency?
split-half correlation
inter-rater reliability
the extent to which different observers are consistent in their judgements
how is inter-rarer reliability assessed?
Cronbach’s alpha when judgements are quantitative and Crohen’s Kappa when judgements are categorical
face validity
how accurate a measure looks on the surface
criterion validity
the extent to which scores on a measure correlate with other variables that one would expect them to be correlated with
concurrent validity
criterion is measured at the same time as the construct
predictive validity
criterion is measured at some point in the future
convergent validity
when new measures are correlated with existing established measures of the same construct
content validity
the extent to which your test accurately measures the behaviour you are trying to measure
discriminant validity
the extent to which scores on a measure DO NOT correlate with other UNrelated variables
socially desirable responding
doing or saying things because they think it is the socially appropriate thing to do
demand characteristics
subtle cues that reveal how the researcher expects participants to behave
experiment
carefully controlled scientific procedure that manipulates variables to determine cause and effect
single factor two-level design
experiments involving a single IV with 2 conditions
single factor multi-level design
experiments involving a single IV with more than 2 conditions
two features of an experiment
- manipulation of the independent variable
- control of extraneous variables
treatment
any intervention meant to change people’s behaviour for the better
treatment condition
the group receiving treatment
control condition
the group not receiving treatment
randomized clinical trial
an experiment that researches the effectiveness of psychotherapies and medical treatments
types of control conditions
- no treatment control condition
- placebo control group
- wait list control condition
no treatment control conditions
zero treatment (most simplistic)
placebo control group
given a placebo
wait-list control condition
delayed treatment, they are told they need to wait before receiving treatment
between-subjects experiment
- each participant tested only once
- relies on random assignment
matched group design
participants are matched on the DV or extraneous variables prior to manipulating the IV
within-subjects experiments
each participant tested in all conditions
- order effects and counterbalancing
carryover effect
an effect of being tested in one condition on participants behaviour in later conditions
practice effect
participants perform a task better in later conditions because they have had a chance to practice it
fatigue effect
participants perform a task worse in later conditions because they become tired or bored
context effect
being tested in one condition changes how participants perceive stimuli or interpret their task in later conditions
order effects
- carryover effect
- practice effect
- fatigue effect
- context effect
counterbalancing
testing different participants in different orders (does not allow for order to become confounding effect)
complete counterbalancing
an equal number of participants complete each possible order of conditions
random counterbalancing
the order of the conditions is randomly determined for each participant
when is between subject design better?
when you only get one shot
when is within subject design better?
if the participant has time and don’t think carryover is an issue
mundane realism
when the participants and the situation studied are similar to those that the researcher wants to generalize to and the participants encounter everyday
psychological realism
where the same mental process is used in both the laboratory and in the real world
construct validity
the research question is clearly operationalized by the study’s methods
operationalization
the specification of exactly how the research question will be studied in the experiment design
statistical validity
concerns the proper statistical treatment of data and the soundness of the researchers statistical conclusions
subject pool
an established group of people who have agreed to be contacted about participating in research studies
experimenter expectancy effect
when the experimenter’s expectations about how participants should behave in the experiment affect how the participants behave
double blind study
when neither the participant nor the experimenter knows to which condition the participant is assigned
manipulation check
separate measure of the construct the researcher is trying to manipulate to confirm that the IV was successfully manipulated
pilot test
a small scale study conducted to make sure that a new procedure works as planned
when to use non-experimental research?
- you only have single variable
- have non-causal relationship between variables
- there is causal relationship but can not randomly assign participants
- asking a broad or exploratory question
types of non-experimental research
- correlations research (most popular)
- observational research
correlational research
measures 2 variables with little or no attempt to control extraneous variables and assesses the relationship between them
observational research
researcher makes observations of behaviour in a natural or lab setting without manipulating anything
when Pearson’s r can be misleading
when there is restriction of range
restriction of range
means that one or both of the variables is truncated and does not vary enough to detect a correlation
complex correlational research
involves measuring several variables and assessing the statistical relationships among them
factor analysis
a complex statistical technique in which researchers study relationships among a large number of conceptually similar variables
regression
statistical technique that allows researchers to predict one variable given another
predictor variable (x)
the variables used to make the prediction
outcome variable (y)
the variable that is being predicted
simple regression
involves using one variable to predict another
multiple regression
involves using several variables to predict an outcome variable
partial correlation
says correlation between two variables while controlling for others
what is qualitative research?
- begins with less focused research question
- collects large amounts of unfiltered data
- describes data using non-statistical methods
strengths of quantitative research
- provides precise answers to specific questions
- draws general conclusions about human behaviour
weaknesses of quantitative research
- does not give detailed descriptions of behaviour in particular groups or situations
- does not communicate what it’s like to be member of particular group or situation
strengths of qualitative research
- helps generate new questions
- detailed descriptions of human behaviour in real world contexts
- can convey what it’s like to be member in particular group or situation
weaknesses of qualitative research
- lack of objectivity
- difficult to evaluate statistically
- does not allow for generalization
triangulation
use both quantitative and qualitative methods simultaneously to study same general questions and compare the results
naturalistic observation
involves observing people’s behaviour in the environment in which it typically occurs
disguised naturalistic observation
when researchers make their observations as unobtrusively as possible so that participants are not aware they being studied
undisguised naturalistic observation
when the participants are made aware of the researcher presence and monitoring of their behaviour
participant observation
researchers become active participants in the group or situation they are studying
structured observation
researcher makes careful observations in a particular setting that is more structured
coding
clearly defining the set of target behaviours so different observers code them in the same way
case study
an in depth and often longitudinal examination of an individual
archival research
involves analyzing archival data that have already been collected for some other purpose (may involve content analysis)
cross-sectional studies
compare two or more pre-existing groups of people
cohort effect
differences between the groups may reflect the generation that people come from rather than a direct effect of age (issue of cross-sectional studies)
longitudinal studies
one group of people is followed over time as they age
cross-sequential studies
people in different age groups are followed over a smaller period of time
survey research
quantitative and qualitative method with two important characteristics:
1. variables are measured using self reports
2. considerable attention is paid to the issue of sampling
item-order effect
when the order in which the items are presented affects people’s responses (context effects)
open-ended items
simply ask a question and allow participants to answer in whatever way they choose (qualitative)
closed-ended items
questionnaire items that ask a question and provide a limited set of response options for participants (quantitative)
rating scale
an ordered set of responses that participants must choose from
unipolar scales
where only construct is tested (five point scales)
bipolar scales
where there is a dichotomous spectrum (seven point scales)
BRUSCO model for writing effective items
Brief
Relevant
Unambiguous
Specific
Objective
non-probability sampling
occurs when the researcher cannot specify the probability that each member of the population will be selected for the sample
convenience sampling
the sample consists of individuals who happen to be easily available and willing to participate in
snowball sampling
existing research participants help recruit additional participants for the study
quota sampling
subgroups in the sample are recruited to be proportional to those subgroups in the population
self selection sampling
individuals choose to take part in the research on their own accord without being approached by researcher directly
probability sampling
occurs when the researcher can specify the probability that each member of the population will be selected for sample
sampling frame
a list of all the members of the population from which to select the respondents
simple random sampling
each individual in the population has an equal probability of being selected for the sample
cluster sampling
larger clusters of individuals are randomly sampled and then individuals within each cluster are randomly sampled
stratified random sampling
the population is divided into different subgroups and then a random sample is taken from each “stratum”
proportionate stratified random sampling
used to select a sample in which the proportion of respondents in each subgroup matches the proportion in the population
disproportionate stratified random sampling
used to sample extra respondents from particularly small subgroups
sampling bias
occurs when a sample is selected that is not representative of the entire population
non-response bias
occurs when there is a systematic difference between survey non-responders from survey responders
quasi-experimental research
research that resembles experimental research but is not true experimental research
characteristics of quasi-experimental research
an IV is manipulated but it is not possible to include either a control group or random assignment to groups
one group design
no control group
non-equivalent groups design
no random assignment
one group posttest only design
a treatment is given to just one group and an outcome is measured just once
one group pretest-posttest design
a treatment is given to just one group and an outcome is measured twice
why are control groups so important?
- history
- maturation
- testing
- instrumentation
- regression to mean
- spontaneous remission
history
something else happened during the course of the study (9/11)
maturation
participants matured or developed over the course of that time
testing
measuring the DV at pretest affected responses at posttest
instrumentation
the measurement of your device has changed
regression to mean
extreme scores tend to normalize to the mean over time
spontaneous recovery
things would have improved over time anyway
interrupted time series design
measurements are taken in intervals over a period of time (difference is number of pretests and posttests)
posttest only nonequivalent groups design
participants in one group are exposed to a treatment, a nonequivalent group is not exposed to the treatment and the two groups are compared
pretest-posttest nonequivalent groups design
a treatment group is given a pretest, recieves treatment and is given a posttest
at the same time a nonequivalent control group is given pretest, does not get treatment and is given a posttest
interrupted time series design with nonequivalent groups
involves taking a set of measurements at intervals over a period of time both before and after an intervention of interest in two or more nonequivalent groups
pretest-posttest design with switching replication
- nonequivalent groups given pretest of the DV
- one group gets treatment and the other doesn’t and the DV is assessed again
- then treatment is added to control group and DV is assessed again
switching replication with treatment removal design
the treatment is removed from the first group when it is added to the second group
factorial design
experiments that include more than one IV in which each level of one IV is combined with each level of the others to produce all possible combinations
between-subjects factorial design
- all factors are between subjects
- no one person recieves both conditions of a factor
within-subject factorial design
each subject recieves all conditions
mixed factorial design
one factor is between subjects while the other is within subject
non-manipulated IV’s
an IV that is measured but is non-manipulated
why do you have to be careful when inferring causation from non-experimental studies?
- directionality
- a potential third variable
main effects
- the effect of one IV on the DV
- they are independent of each other
interactions
when the effect of one IV depends on the level of another
three results from factorial designs
- main effect
- interactions
- simple effects
spreading interaction
there is an effect of one IV at one level of the other IV and there is either a weak effect or no effect of that IV at the other level of the other IV
cross-over interaction
the IV has an effect at both levels but the effects are in opposite directions (most valuable outcome)
simple effects
an interaction means that the effects of at least one IV depend on the level of another IV
when are simple effects used?
to break down the interaction to figure out precisely what is going on
single-subject research
type of quantitative research design involving a small number of subjects
single-subject research
type of quantitative research design involving a small number of subjects
reasons for single subject designs?
- important to focus intensively on behaviour of individual participants
- important to discover causal relationships
- important to study strong and consistent effects that have biological or social importance
social validity
treatments that have substantial effects on important behaviours and can be implemented reliably in the real world
steady state strategy
the researcher waits until the participants behaviour in one condition becomes fairly consistent before moving on to the next condition
reversal design
- most basic
- researcher measures DV in three phases (baseline, after treatment, return to baseline)
multiple treatment reversal design
the baseline phase is followed by separate phases in which different treatments are introduced
alternating treatments design
two or more treatments are alternated relatively quickly on a regular schedule
problems with reversal design
- if treatment is working it may be unethical to remove
- DV may not return to baseline when treatment is removed
multiple baseline design across participants
a baseline is established for each participant and the treatment is then introduced for each one at a different time
multiple baseline design across behaviours
multiple baselines are established for the same participant but for different DVs and the treatment is introduced at a different time for each DV
multiple baseline design across settings
multiple baselines are established for the same participant but in different settings
