Exam #2 Lecture Notes - Week of 2/24
Exam #2 Lecture Notes - Week of 2/24 PSY 290
Popular in Intro to Research Methods
Popular in Psychlogy
This 5 page Class Notes was uploaded by Elliana on Thursday February 26, 2015. The Class Notes belongs to PSY 290 at University of Miami taught by Rick Stuetzle in Spring2015. Since its upload, it has received 130 views. For similar materials see Intro to Research Methods in Psychlogy at University of Miami.
Reviews for Exam #2 Lecture Notes - Week of 2/24
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 02/26/15
PSY 290 Exam 2 Lecture Notes 224 Lecture Notes Threats to internal validity Prepost design History Maturation Regression Testing Instrumentation Most susceptible to time Participant problems Participant characteristics can affect the internal validity of a study Subject selection Attrition As time goes on you lose subjects Especialy when studies span a large amt of time participants don39t always complete the experiment they begin Need to know who drops out of the study how are they similar or diff from ppl who continued w the study Certain pp could have been offended by studies too sensitive to measures impatient for retesting Can differential attrition account for your ndings 2 general types of experimental design Betweensubjects or independent groups design Different groups of participants contribute data for different levels of the IV Participants only exposed to 1 level of the IV Depending on your question may be the only way to design the study If IV is a subject variable introverts vs extroverts males vs females etc Or if experience of participating at 1 level of the IV makes it impossible to participate in other levels bias in uence etc Need to create equivalent groups groups that are the same as each other in all important ways except for the levels of IV Strengths Participants don39t know about other levels of IV or IV itself Hard to guess purpose of the study each participant equally naive about procedures Cons Need a large of individuals to ll all IV conditions Even more difficult if conditions call for a speci c type of participant 9th born child etc Difference btwn conditions may be due to IV but could also be due to preexisting differences btwn the groups males amp females Random assignment a method of placing participants into different groups Every participant has an equal chance of being placed in either group Spreads potentially confounding factors evenly throughout diff groups But cannot ensure equal number of participants in each condition PSY 290 Exam 2 Lecture Notes Block randomization Used to ensure an equal number of participants per group Each condition ofthe study has a participant randomly assigned to it before any condition is repeated a 2nd time Matching Participants are grouped together on some trait amp then randomly distributed to different groups Especially useful when there are too few participants available for random assignment to work well 2 conditions needed Good reason to believe that the matching variable is correlated w the DV A good way to measure the matching variable Difficult to match participants on multiple traits amp also narrows down type of participants selected may affect randomness of sample Withinsubjects or repeated measures design Same participants contribute data to all the levels of the IV Participants exposed to all levels of the IV Often used in studies of sensation amp perception IE MullerLyer illusions Strengths Fewer participants needed to ll all experimental conditions Don39t need to worry about equivalent groups Cons Sequenceorder effects Being exposed to one level in uences perception on other levels Progressive effects Practice effect performance improves after several trials Fatigueboredom performance worsens after several trials Ca rryover effects Level A amp then B has a different effect than Level B amp then A Controlling sequence effects Counterbalancing Presenting conditions in more than one sequence Primarily used to minimize progressive effects Types of counterbalancing when testing only once per condition Complete counterbalancing Every possible sequence of conditions is used at least once not always possible Partial counterbalancing A subset of total possible sequences are used only doing some of the orders Ok if only testing 2 diff conditions not so ok if testing for many diff conditions Reverse counterbalancing For each participant present the conditions in 1 order amp then again in the reverse order Block randomization Every condition occurs once before any condition is repeated a 2nd time Within each block the order of conditions is randomized Latin square Experimental research examples IV with levels A amp B IE effects of music volume on studying PSY 290 Exam 2 Lecture Notes Level A quiet music Level B loud music Betweensubjects design Each participant is observed in either level A or B Not both Each grouplevel represents a different condition of the IV Withinsubjects design Each participant is observed in both level A amp B Betweensubjects design example Experiment comparing 2 forms of writing emotional vs control on disease progression in HV patients Matched on the following Time of disease diagnosisstage of HIV progression Age SES Gender Treatment amp type medications Education Exercise Diet Family history Social support quotVariables listed are good bc they are variables that likely correlate w disease progression amp would threaten internal validity if not controlled Can39t match amp randomly assign for all variables must prioritize which traits to match on Each member of matchedpair then assigned to diff methods Control problems in developmental research When IV is age 2 types of designs to consider Cross sectional design Btwnsubjects design 3 4 amp 5 yr olds compared in language performance Problem of cohort effects Children of diff ages have been exposed to diff information Longitudinal design Withinsubjects design Comparing language performance of the same kids at 3 4 amp 5 yrs old Attrition can be a problem Feasibility of collecting data for 3 yrs Testing effects over time ssue of time length Will study conductor live long enough to see end of the study Info collected over time can get lost Study Rosenthal amp Fode 1963 Rosenthal Effect Designed to study experimenter bias using picture perception amp experimenter expectancy Rosenthal had experimenters ask groups of ppl to rate how successful they believed people would be based on their photographs 3 PSY 290 Exam 2 Lecture Notes Tod one group of experimenters to expect many positive ratings Expectancy resulted in many positive scores Tod the second group to expect many negative ratings Expectancy resulted in many negative scores Designed a study for animal subjects as well Randomly assigned groups of rats to 2 experiment groups to learn mazes Tod one group of experimenters their rats were quotmazebrightquot Tod the second group of experimenters their rats were quotmazedullquot Group of quotmazebrightquot rats learned more quickly because the experimenters unconsciously handled them more a factor known to affect learning Ethical violations Omitted reports of contradicting reports Fudged data misrecorded maze errors Study Hawthorne Effect 1927 Will be on the exam Hawthorne effect Belief of participant that they are part of a special group amp focus of attention Regardless of whether changes in IV are positive or negative get positive outcomes Group of 6 female workers selected to be studied while producing telephone relays Changed IV such as rest period schedules work hours bonuses paid Believed that workers remained productive bc they felt quotspecialquot for participating in the group of interest Hawthorne effect the tendency for performance to be affected bc ppl know they are being studied Omitted info 2 workers dropped out 1 new recruit was especially talented amp became a leader contributing to productivity Output per week was recorded rather than per hour thus not counting in extra hours giving workers time to produce more relays Problems with Biasing Bias preconceived expectation about what should happen in an experiment Who would be biased Experimenter bias Experimenters might inadvertently interact with participants in a way that makes them behave in a way that con rms your hypothesis Can be communicated through Ways in which instructions are given Describing anchors on scale Facia expressionsbody language when answers given Participant changes response to try to get quotpositivequot reaction from experiment Personality characteristics Preschoolers perform better on cognitive tasks with quotcaringquot vs quotindifferentquot caregivers Minimizing experimenter bias Minimize contact between experimenter amp participant Computerize assessment Doubleblind procedures Participant bias 4 PSY 290 Exam 2 Lecture Notes Knowing that you39re in an experiment can make you change your normal behavior not always consciously Demand characteristics s part of your experiment revealing your hypothesis More of a problem in withinsubjects design bc they can identify changes in conditions multiple exposures to the IV Efforts to present self as a good subject Evauation apprehension Minimizing participant bias Minimize demand characteristics Use of deception to get participants to behave more neutrally Use of placebo control group Everything the same except content of treatment As much special attention etc Manipulation check Ask participant what they think the hypothesis is Latin Squares True Latin square39s 2 criteria Each condition only occurs in each position once Each condition precedes amp follows each other condition only once A A A B B B B C C X H A D C C D 1 G D Ugtlt 2 Imnrn rngtlt quot3939n 11mm BetweenSubjects single factor designs Independent groups Effectiveness of weightloss programs IV weight loss consequence Level 1 selfreward for weightloss Level 2 selfpunishment for weight loss DV pounds lost over 8 week program Commonality participants are in control of their rewardspunishments
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'