research methods Flashcards
what is an aim ?
a general statement of the purpose of a study
what is a hypothesis?
a precise statement which clearly states the relationship of the variables being investigated
what are the types of hypotheses?
null, directional or non - directional
when would you write a directional/ non-directional hypothesis?
directional - previous research suggests a particular outcome
non- directional - no previous research/ contradictory
what is the experimental method?
manipulating the IV to have an effect on the DV
what is the IV?
the independent variable - it is manipulated by the researcher.
two different conditions of it (experimental and control) are tested
what is the DV ?
the dependent variable
it is measured by the researcher
describe operationalisation of variables
clearly defining the variables in terms of how they are being measured
what is an extraneous variable?
any variable other than the IV that will affect the DV if not controlled.
eg. participant variables, situational variables, demand characteristics, investigator effects
state the four extraneous variables
- participant variables,
- situational variables,
- demand characteristics,
- investigator effects
what is a confounding variable?
any variable other than the IV that will affect the DV if not controlled.
the difference to extraneous variables is that confounding variables change systematically within the IV.
with confounding variables it’s difficult to claim cause and effect
describe demand characteristics
any cue the researcher or research situation give that could make the participant think they can guess the aim of an experiment.
what are the effects of demand characteristics?
participants may change their behaviour to either behave how they think the researcher wants (please-U) or intentionally underperform to sabotage the study (screw- U)
what are investigator effects?
any unwanted influence from the researcher’s behaviour on the DV measured
investigator effects can influence what 3 factors?
- design of the study
- selection of participants
- interaction with participants
how can you control for extraneous variables ?
- randomisation
- standardisation
describe randomisation
the use of chance methods to reduce the effects of bias from investigator effects
how can randomisation be used?
a computer generator can randomly decide the order of conditions, design of materials, selection of participants etc.
describe standardisation
using the same formalised instructions and procedures for all participants
what type of experiments are there?
- lab
- field
- natural
4.quasi
describe lab experiments
an experiment that takes places in a highly controlled laboratory environment
advantages of lab experiments
high degree of control
results are easily replicable
disadvantages of lab experiments
low ecological validity (artificial conditions)
experimenter bias
describe field experiments
an experiment that takes place in a natural environment but the IV is still controlled by the researcher
advantages of field experiments
naturalistic - higher ecological validity
controlled IV
disadvantages of field experiments
ethical considerations -invasion of privacy and unlikely to have informed consent
lack of control over extraneous variables - unlikely to be replicable
describe natural experiments
an experiment where the researcher studies a naturally occurring IV ( the event would have happened whether the researcher was there or not) and records the effect on a decided upon DV
advantages of natural experiments
provides opportunities for research that otherwise would have been impossible due to ethical or practical reasons
high external validity - real world events
disadvantages of natural experiments
naturally occurring events may be rare so hard to replicate or generalise findings
very hard to randomly allocate participants so extraneous and confounding variables become a problem
describe quasi experiments
an experiment whereby the IV naturally exists and is not brought about by the researcher eg. gender
advantages of quasi experiments
highly controlled conditions - replicable and high internal validity
disadvantages of quasi experiments
cannot randomly allocate participants to conditions so there are likely to be confounding variables. harder to claim cause and effect
target population
the total population a study is intended to research and to watch generalisations from samples are to be made
sample
a subset of individuals from a larger population that will be studied
what are the types of sampling?
random, opportunity, volunteer, stratified, systematic
describe random sampling
all members of the population have an equal chance of being selected. this method uses a random number generator or lottery method
random sampling pros and cons
pros - no researcher bias
cons - time consuming and volunteer bias ( participants selected may refuse to take part)
describe opportunity sampling
participants happen to be available when the study is being carried out so are recruited conveniently
opportunity sampling pros and cons
pros - easy, time saving and not costly method of recruitment
cons - not representative of the whole population so lacks generalisability and there may be researcher bias
describe volunteer sampling
participants self-select, perhaps in response to an advert or when asked to
volunteer sampling pros and cons
pros - easy and not time consuming to find participants. the volunteers are also willing so more likely to cooperate with the study
cons - volunteer bias - may attract a particular profile of person affecting generalisability. also motivations like money could be driving the pps to take part so they may not take the study seriously
describe systematic sampling
every nth member of the population is selected to take part in a study
systematic sampling pros and cons
pros - usually representative and avoids researcher bias
cons - not truly unbiased unless you used a random number generator and then start the systematic sample
describe stratified sampling
the composition of the sample reflects the varying proportions of people in various subgroups (strata) in the wider population
once the number of pps have been decided from each strata they must be selected through ransom methods
stratified sampling pros and cons
pros - generalisation possible due to representative data, no researcher bias
cons - time consuming, complete representation not possible
name the 3 experimental designs
- independent groups
- repeated measures
- matched pairs
describe the independent groups design
the participants only perform one condition of the IV
what are the strengths and limitations of using independent groups design?
strengths - no order effects, participants less likely to guess the aim (demand characteristics eliminated)
limitations - more participants needed, no control of participant variables (extraneous variables)
how to solve the limitations of independent measures design
random allocation to conditions helps to control for participant variables but does not completely remove them
describe a repeated measures design
the same participants take part in all conditions of the IV
what are the strengths and limitations of repeated measures?
strengths - eliminates participant variables and fewer participants needed so not as time consuming
limitations - order effects eg. fatigue/boredom, practice
how to control for the limitations of repeated measures?
counterbalancing - abba - half the participants do the conditions in one order and the other half do them in the opposite order
describe matched pairs design
pairs of participants are first matched on a variable that has been found to affect the DV. one member of the pair does each condition.
what are the strengths and limitations of matched pairs ?
strengths - no order effects, demand characteristics are less of a problem.
limitations - time consuming and expensive to match participants, a large pool of potential participants is needed, it can be hard to know what variable to match participants on.
what is a pilot study?
a small scale version of the investigation before the real thing is carried out to investigate potential problems and get participant feedback to modify any procedures. saves time and money in the long run
what is a control condition?
sets a baseline for results from the experimental group to be compared to (the researcher has not modified the IV in this condition). it allows the researcher to conclude that the effect to the DV from the experimental condition was due to the change in the IV
what is a single blind procedure?
the researcher does not tell the participant whether they are being given a test treatment or a control treatment. this avoids demand characteristics
what is a double blind procedure?
neither the researcher or the participant is aware whether they are completing the experimental or control condition. prevents bias, demand characteristics and the placebo effect. it can also reduce investigator effects
