Lecture 7, 8, 9: Experimental Research and Design Flashcards
A well designed experiment must meet what three requirements?
a.) at least one IV that is manipulated (why?–> important to be able to assess the effects on the participants responses)
b.) Random assignment to a condition (why?–>ensures their initial equivalence)
c.) Control over all extraneous variables
instructional manipulation
vary IV through instructions or information that participants receive
*elaborate instructional manipulation= studies that aim to change peoples thoughts motions or behaviors
invasive manipulation
creating physical changes in the participants body through physical stimulation (drug administration. surgery etc.)
environmental manipulation
experimental modifications of aspects of the research setting
ex: a researcher interested in visual perception might vary intensity of illumination
What are the advantages of a WITHIN SUBJECTS repeated measures design ?
increase in power and the possibility of having a smaller sample size
What are order effects? Describe all three
participants behavior is affected by the order in which they participate in the various conditions of the experiment
practice effects: when participants performance improves merely because they complete the dv several times
fatigue effects: participants become tired bored or less motivated as the experiment progresses
sensitization: after receiving several levels of the IV and completing the dv several times participants within subjects design may begin to deduce what the hypothesis is –> different responses that they did before
What is counterbalancing
used to guard against oder effects by presenting the levels of the IV in different order to the participants
what are carryover effects
effect of a treatment condition persist after the condition ends ; when the effects of one level of the IV is still present when another IV is introduced
What is treatment variance
portion of the variance in participant scores on the DV due to the IV
what is confound variance
portion of the participants variance in dv scores due to extraneous variables that differ between experimental groups
the presence of _____varriables threatens the ________ validity of a study
confounding ; internal
There are a few major common effects to the internal validity of an experiment describe them:
biased assignment:
differential attrition:
pretest sensitization
history effects
biased assignment: participants are assigned to groups in a nonrandom manner –> systematic differences before introduction of the IV
differention atrition : uneven loss of participants from a study–> loss is not random across all conditions
pretest sensitization: completion of a pretest impacts the participants posttest response –> was the response really due to the IV or was it pretest sensitization?
history effects: results of s study being impacted by outside extraneous events
expectations can compromise the internal validity of an experiment; describe the following: expectancy effects, demand characteristics, and placebo effects
expectancy effects: researchers expectations on the outcome of the study effect the participants responses–> the researchers see what they want to see rather than what is actually occurring
demand characteristics: aspects of the study indicate to participants how they should behave causing behavior changes
placebo effects: a change the occurs as a result of mere belief that the change will occur: participants receive a treatment and improve only because they belief they are receiving a valid treatment
what are the main factors that lead to error variance: name, describe, and prevention method
individual differences: preexisting differences between participants when they enter a study
–> solution = use a homogenous sample of participants b/cthe more alike participants are the less error variance is produced by their differences
transient states: current behavior or feeling of a participant on the day of completing the survey
–> avoid creating more differences in transient states throughout the experiment
environmental factors: differences in the environment which the study is conducted. ex: phone buzzing, pen clicking, loud breathing etc.
–> try to ensure setting is as invariant as possible when different participants are being tested
differential treatment: researches not realizing they are treating participants differently
–>automate experiment as much as possible/ record instructions so it can be delivered the same way to all participants
measurement error: the measures that are being used are not accounting for what the researchers want them to account for–> measures could be outdated, falty bc they work well with certain groups than others
External validity is important because it focuses on?
refers to whether the findings of the study can be generalized and replicated
What is a key contributor to external validity ?
random sampling **different than random assignment
what is the “experimenters’ dilemma”?
the greater the internal validity the lower the external validity
the more control the experimenters place on the experiment the less replicable/generalizable the findings become in real world contexts
describe simple random assignment
involves placing participants in conditions in such a way that every participant has an equal probability of being placed in any experimental condition
describe matched random assignment
pretest measure of the DV allows researchers to match participants into homogenous blocks then those blocks are randomly assigned to conditions
it is important that independent variables have ___ or more levels; in other words, this means …
2; independent variable must have 2 or more conditions; ex: 4 levels of caffeine doses
what are the three types of independent variables
environmental, instructional, invasive
describe the experimental group vs the control group ?
the control group consists of participants that receive a zero level of the IV
the experimental group consists of participants that receive the nonzero level of the IV
TRUE or FALSE : researchers always need to include a control group
FALSE; its up to them to decide if it will help them interpret the results
what is a pilot test and why do researchers use it?
a preliminary study that examines the usefulness of manipulations or measures that will later be used in the study
its used to ensure the levels of the IV are different enough to be detected by participants NOT USED to check if hypothesized effects will be produced
what is a manipulation check
a question or set of questions designed to determine whether the IV was successfully manipulated
ex: ask participants to rate brightness of a lightbulb if they can rate the brightness of the lights differently –> differences in brightness is perceivable
participant variables
characteristics of participants non changeable by the researcher
ex: gender race
TRUE or FALSE: most experiments have several dependent variables
true
a one way design is a design in which _____. A two group experimental design is______
only one IV is manipulated
simplest one way design where the IV has two levels/there are two conditions
Randomized group design
participants randomly assigned to one of two or more conditions
within subjects design
each participants serves in all conditions
post test designs are ones that
only measure the DV at the end of experimental manipulation
what is a pre-test post test design
a design that measures the DV before and after the introduction of the IV
what are three major benefits to the pre-test posttest designs
- researcher can verify participants did not differ in respect to the DV at the beginning of the experiment/ can confirm random assignment
- comparison of pre and post test scores allows analysis of the exact change in scores of a participant
- more powerful thus more likely to detect the effects of the IV on the DV–> error variance due to preexisting differences can be ruled out
Drawbacks of pretests include?
pretest sensitization –> sensitize participants responses, they may behave differently than they normally would have
Describe a factorial design
an experimental design in which two or more IV are manipulated
iv-factors
Interpreting factorial designs
2x2 means what
4x2 means what
2x2x4 means what
the design has two independent variables each of which has two levels
the design has two independent variables one with four levels and one with two levels
the design has three IV the first two have 2 levels and the third has 4 levels
whats the primary advantage of factorial designs over one way designs?
they provide information on the separate effects of each IV and the combined effects of them
as well as information on if variability is due to error variance
main effect
ex: in a 2x2 we can examine__ main effects
the effect of a single IV in a factorial design
2 main effects one for each IV
when is an interaction present?
when the effect of one IV differs across the levels of other IV
if variable A has the same effect on participants responses no matter what level of variable B they receive there is no interaction present
describe an expericorr design
used to examine the generality of the IVs effect
allow researchers to determine if the effects of the IV occur for all participants or only for participants with certain attributes
between subjects group design vs within subjects design
participant participates in only one condition
participant participates in every condition
power of an experimental design refers to what?
its ability to detect effects of the IV
how can you combat expectancy effects?
–> can be avoided by the double blind procedure where neither the researcher nor the participants know the full extent of whats being studied
how can one eliminate demand characteristics?
–> conceal the real purpose of the experiment and eliminate any cues that could hint
double blind procedure
General tips for minimizing error variance include
homogenous sample
equal treatment at all times
hold lab conditions constant
standardize research procedures
automate the experiment as much as possible
use only reliable measurement procedures
Higher order factorial designs _______
involve more than two IV
