Psychology 7 - Intro Experiment Psychology Reading Notse
Psychology 7 - Intro Experiment Psychology Reading Notse
Popular in Course
verified elite notetaker
Popular in Psychlogy
This 21 page Document was uploaded by Kaley jorgensen on Tuesday April 15, 2014. The Document belongs to a course at University of California Santa Barbara taught by a professor in Fall. Since its upload, it has received 294 views.
Reviews for Psychology 7 - Intro Experiment Psychology Reading Notse
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: 04/15/14
41514 955 AM Chapter 1 The scientific approach many ppl rely more on intutition and authority instead of the scientific approach intuition intuition causes us to draw conclusions about cause and effect that aren39t true illusory correlation when two events happen adoption amp pregnancy and we assume they are caused by each other authorty we believe whatever they say bc they seem credible skepticism ideas must be evaluated on the basis of logic and scientific investigations empiricism knowledge is based on observations data plays a central role scientists are credited by other scientists pseudoscience fake science because it is based off of false info and conclusions goals of behavioral science 1 describe behavior how are two things related why are some ppl attracted to others 2 predict behavior once we look at behavior we can predict it anticipate events 3 determine the causes of behavior it is hard to determine a cause of something without evidence to conclude causation 3 things must occur temporal precedence the cause precedes the effect watch violent tv THEN aggression occurs covariation of cause and effect comparing two sitations kids who watch violent tv behave aggressively and those who do not watch violent tv do not behave aggressively alternative explanations there should be no other explanation for the relationship 4 to understand or explain behavior why does the behavior occur what is the true cause of the behavior Must look at all options basic research tries to answer fundamental questions about the nature of behavior applied research conducted to address issues in which there are practical problems and potential solutions chapter 2 hypothesis a type of idea or question a statement that may be true a tentative idea or question that needs evidence to supportrefute it prediction 030 researcher makes predictions about the outcome of an experiment 030 when results of a study confirm a prediction the hypothesis is only supported and not proven 5 sources for ideas 1 Common Sense Testing commonsense can be valuable to prove that our commonsense isn39t always correct 2 Observation of the World around us 030 ex storing something in an unfamiliar place is a bad idea 030 Pavlov observed dogs and salivation 30 Observing music and the effects it has on behavior 3 Theories 030 a theory consists of a systematic body of ideas about a topic 030 they organize and explain a variety of specific facts or descriptions of behavior 030 theories generate new knowledge 030 theories are living and dynamic 030 ex females and males differ in their attachment and jealousness 4 Past Research 030 research from the past helps with new research 030 you can apply past research or question it and make another study 30 facilitated communication for children with autism to help them communicate o scientists proved this to not work fully bc the facilitator could have been guiding the child to press a certain button 5 Practical Problems Method no details can be omitted the method section is divided into subsections details allow the reader to know how the study was conduced and provides info on how to replicate the study Resuks Researcher presents findings narrative form statistics tables and graphs Discussion This section the researcher looks at the research form various perspectives researcher discusses how the results compare with past research results on the topic suggestions on research for the future Chapter 4 Fundamental Research Issues Validity Construct validity concerns whether our methods of studying variables are accurate Internal validity refers to accuracy to conclusions about cause and effect External validity concerns whether we can generalize the findings of a study to other settings Variables variable any event situation behavior or individual characteristic that vanes has to have 2 levels of values categorizing ppl 0 extraversion and introversion examples of variables depression intelligence reaction time stress age sef esteem etc Operational Definitions of Variables aggression cognitive task performance pain sef esteem word length operational definition of a variable is the set of procedures used to measure or manipulate it variable must have this to be studied empirically easy to study things with numbers but hard to study things like pain pain very general and abstract subjective and cannot be directly observed we can use a scale from 15 need to be able to define what each level means so others can use it have to agree on what aggression means Construct Validity adequacy of the operational definition of variables Relationships between variables when using variables that are numeric we can focus on 4 common relationships 1 positive linear relationship 2 negative linear relationship 3 curvilinear relationship 4 no relationship we have to know the size of the correlation between the variables correlation coefficient a numerical index of the strength of relationship between variables important so we know how strongly two variables are correlated random variability uncertainty that there is randomness in events 9 research reduces random variability by looking for relationships btwn variables 030 2 methods to study relationships among variables Nonexperimental method 030 making observations or measures of the variables 030 EX ppl with jobs tend to have lower grades 0 They vary together both variables are measured with the nonexp Method Whereas with the exp Method only the first variable is manipulated ex testing anxiety levels with exercise 0 those who exersice more have lower levels of anxiety 9 the variables correlate with each other 030 AKA correlational method problems with making causal statements 1 reverse directiong of causality hard to know what is causing what ex cant really say that excersize causes reduction in anxiety 0 maybe high anxiety causes ppl to exercise less 2 third variable lurking variable 030 maybe no direct causal relationship between variables 030 extraneous to the two variables being study 0 another explanation for the relationship the reason could be income level 0 those with more can exercise more and have lower levels of anxiety 0 if this is the case there is no relationship between anxiety and exercise but instead with income level they reduce the overall validity of a study Confounding variable when a third variable is operating as a relationship this limits the nonexp Studies Experimental method involves manipulating a variable variables do not just vary together but 1 variable is introduced first to determine whether it affects the 2quot variable EX when looking at anxiety and exercise exercise would be manipulated 030 one group exercises or a week and the other does not 030 if ppl who exercise have less anx then you can say something about direction of causality 030 exercise came first so anxiety level could not influence amt of exercise ppl engage in 030 experimental method eliminates confounding variable 0 do this by holding everything constant except the manipulated variable Experimental Control 030 all extraneous variables kept constant 0 if it39s constant it cannot be responsible for results 0 Aka cannot be a confounding variable 0 Treat all participants equally Randomization eliminates extraneous variables income that can be confounding variable makes the two groups exercise vs non independent variable the cause manipulated variable dependent variable the effect the measured variable independent variable 9 dependent variable Internal validity ability to draw concl About causal relationships from the results of a study high internal validity strong inferences about one variable causing change to another variable eliminating alterative explanations gives higher internal validity External Validity extent to how these results can be generalized to other pop s can the results be replicated Alternative methods Field experiment independent variable is manipulated in a natural setting Use nonexperimental methods to observe things like alcohol effects on children and punishment with child39s anger group children based on their experience growing up kids who are spanked vs those who aren39t chapter 3 ethic research Milqram obedience experiment teacher and a learner and punishments experiment used to see how well ppl obeyed authority even when they were hurting someone 65 of ppl continued to deliver shocks could be related to Nazi39s beneficence the need for research to maximize benefits and minimize any possible harmful effects of participation risk benefit analysis see notes from class this section mainly explains the risksbenefitsdeceptions chapter 5 reliability of measures consistencystability of a measure of behavior true score real score on a variable measurement error unreliable measure of intelligence contains measurement error 0 greater variability test retest reliability measure two ppl at 2 different times high reliability high correlation coefficient showing that two scores are similar should be at least 80 testing intelligence intelligence remains the same usually so the test retest should be high 0 however mood could change and therefore change outcome of the second test internal consistency reliability the assessment of reliability using responses t only one point in time spit haf reliability correlation of the score on the 1st half combined with 2quot half score reliability increases with more questions items interrater reliability have at least two raters observe the same behavior how aggressive kids are on the playground how these two raters agree in their obs Construct validity recall how it concerns whether our methods of studying variables are accurate does the measure actually measure what it is intended to face validity the evidence for validity that the measure appears on the face of it to measure what it is supposed to measure content validity Chapter 6 Observational Methods Qualitative approach Focuses on ppl behaving in natural settings and describing their world in their own words Few ppl in limited setting Quantitative Focus on specific behaviors that can be easily quantified counted Larger samples Naturalistic observation aka field observation collect data of ppl in their natural environment researchers do not attempt to influence what occurs goal to provide accurate picture of what happens in natural settings o Qto test a hypothesis Analyze what has been observed Primarily qualitative Issues with naturalistic obs Whether to be a participant or non participant Participant observation allows the researcher to be in the studied environment and experience events like the natural participant o Researcher might lost objectivity remember naturalistic obs Requires accurate desc amp objective interpretation w no prior hypothesis Presence of observer may influence natural participants Systematic observation Careful observation of one or more specific behaviors in a particular setting Only interested in a few behaviors Prior hypothesis amp quantifiable 1 observing kids playing video games 3 things make it systematic study specific behaviors quantifiable hypothesis driven Codinq systems Measures behaviors Reactivity The possibility that the presence of observer will affect pp s behaviors Can be reduced by letting ppl get used to equipment Sampling Taken over a long period of time gives more accurate and useful data than a single short observation Case studies Describes an individual Sometimes called a naturalistic observation Psychobiography researcher applies psychological theory to explain the life of someone usually important historical figure The man called S Genie Valuable for looking at rare cases Chapter 7 Survey Research Survey research Questionnaires and interviews ask ppl to provide info about themselves attitudes beliefes demographics Study relationships between things and how they change overtime Complements experimental research Response set Bias responses Tendency to respond to all questions from a particular perspective rather than to provide answers that are directly related to the ques ons o Answering in a socially acceptable way Types of questions Attitudes and beliefs Facts and demographics Behaviors Question workinq problems with questions unfamiliar technical terms vague or imprecise terms phrasing that overloads working memory embedding the question with misleading info Simplicity Ppl should be able to understand the question easily Doublebarreled questions Asking two questions in one should senior citizens be given more money for recreation centers and food assistance programs Loaded questions Lead ppl to respond in one way Do you favor eliminating the wasteful excess in public school budget 0 can influence what ppl will say Chapter 8 experimental design Confoundinq variable Varies along with the independent variable Eliminate these so there are no alternative explanations Internal validity 0 Draw consl About cause and effect Posttest ony desiqn 1 Obtain two groups of participants 2 Introduce the independent variable 3 Measure the effect of the independent variable on the dependent variable selection differences 0 the ppl selected cannot differ in any systematic way repeated measures desiqn having ppl participate twice in different groups advantages fewer participants needed sensitive to differences within groups individual differences can be explained more likely to detect effect of independent variable on the dependent variable disadvantages 0 order effect the order of presenting the treatments affects the dependent variable 0 practice performance on the second task could improve because of practice on the first task practice effectlearning effect 0 fatigue effect become tired from the first to the second poor performance 0 carryover effect effect of the first treatment carry over and influence the response to the second counterbalancinq all possible orders of presentation are included in the experiment OOOO choosing between repeated measures and independent groups repeated measures have 2 advantages over independent a reduction in number of participants needed greater control over participant differences gt detect effect of the independent variable matched pairs desiqn match ppl on a particular variable match ppl based on scores or cognitive ability ensures that groups are 0 important for small samples costly and time consuming chapter 9 conducting experiments reminder external validity when the results from a study can be generalized to other populations or settings straightforward manipulations manipulates variables with instructions and stimulus presentations most memory research benefits of being an expert are limited staged manipulation used to ensure the independent variable is being manipulated successfully confederate appears to be another participant but is actually part of the manipulation o proves how easily it is for ppl to conform based on what others are doing self report measures used to measure attitudes liking for someone judgements behaviors emotional states rating scales strongly disagree strongly agree behavioral measures direct observations of behaviors rate of behavior reaction time how quickly a response occurs after stimulus duration how long the behavior lasts physiological measures recordings of responses of the body galvanic skin response 0 emotional arousal and anxiety 0 measures electrical conductance in skin which changes when sweating occurs electromyogram 0 measures muscle tension 0 measure of stress or tension electroencephalogram 0 measure electrical activity of brain 0 record brain arousal as a response to different situations MRI 0 Image of brain structure 0 fMRI same thing but ppl are doing something while they scan the brain sensitivity of the dependent variable 0 sensitivity important when measuring human reaction time o vary in difficulty ceilinq effect the independent variable appears to have no effect on the dependent measure because participants quickly reach the maximum performance level floor effect opposite of ceiling when no one can do well controlling for participant expectations demand characteristics researchers do not want to tell ppl what the hypothesis of their experiment is the participants will try to confirm the hypothesis becomes bias how to control for demand characteristics 0 deception o filler items on the questionnaire that has nothing to do with the study just to throw ppl off experimenter bias when the experimenter develops expectations about how participants should respond manipulation check attempt to directly measure whether the independent variable manipulation has the intended effect on the participants provide evidence of construct validity two advantages 0 if the check shows that your manipulation was not effective you save the expense of running the actual experiment 0 if you get no significant results there is no relationship between the independent and dependent variables interactions and simple main effects simple main effects examine mean differences at each level of the independent variable treat as separate experiments factorial designs independent groups design different ppl are assigned to each condition in the study repeated measures same ppl participate in all conditions mixed factorial design combination of independent groups and repeated measures independent groups between subjects design 2x2 design and you want 10 participants in each condition need 40 different ppl repeated measures withinsubjects design same ppl in all conditions Mixed factorial design using combined assignment Increasing the of levels of an independent variable 0 Incr of levels incr complexity 2x3 design 2 independent variables A has two levels and B has 3 levels 6 conditions factorial design with independent variables easy hard and anxiety level low moderate high 0 dependent var performance on task increasing of ind Variables in a factorial design 2x2x2 contains 3 variables each with 2 levels 0 8 conditions 2x2x3 design 12 conditions factorial 2x2x2x2 there are 16 conditions chapter 11 quasiexperiments singe case experimental designs operant conditioning determine whether an experimental manipulation has an effect on a single research participant behavior is measured overtime using a baseline control period manipulation is then introduced problem there could be many explanations for change in behavior reversal designs determines reversibility on the manipulation A baseline period 9 B treatment period 9 A baseline period 0 Children getting stars for homework Multiple baseline design Used for things that cannot ethically be reversed Effectiveness of a treatment is demonstrated when a behavior changes only AFTER the manipulation Must be observed under multiple circumstances Replications in singe case designs Hard to generalize to everyone because some people will perform the same no matter what Everyone is different Quasi experimenta designs Address the need to study the effect of an independent variable in settings in which the control features of true experimental designs cannot be achieved Allows us to see impact of ind Var on dep Var but hard to see causal inferences Lack random assignment One group posttest only design Ex want to see if sitting close to strangers will make them move Participants 9 sit next to stranger 9 measure time until stranger leaves 0 Cannot draw conclusions because there could be other reasons they get up No control group One group pretest posttest design Can measure change Probems 0 Ex want to see if relaxation training will result in reduction in smoking 0 Participants 9 smoking measure 9 training program 9 smoking measure 0 If smoking did decrease cant say it was because of the program 0 Could be alternative explanations History Any event that occurs between the first and second measurement but is not apart of manipulation Ex famous person dies of lung cancer during time between first and second measures This could be responsible for lack in smoking not the training program 0 Can be confounding variable that occurs at the same time as exp Manipulation Maturation Any change that occurs systematically overtime Testing Pretest can effect the posttest instrument decay basic characteristics of measuring instrument change overtime overtime an observer may gain skill become fatigued or change the standards on which observations are based Regression towards the mean Happens bc ppl are selected when they are extremely high or low on a measure When they are measured again they seem to go back to the mean Basketball example from class Nonequivalent control group design Employs a separate control group but the participants in the two conditions the experimental and control group are not equivalent Differences confounding variable Selection differences selection bias 0 Occurs when participants who form the two groups in the experiment are chosen from existing natural groups Participants 9 training program 9 smoking measure Participants 9 no training program 9 smoking measure Nonequivalent control group pretest posttest design Most useful quasi design Participants 9 measure 9 treatment 9 measure Participants 9 measure 9 no treatment 9 measure Not a true exp Design bc no random assignment But closest thing to it Propensity score matching Matching ppl on more than just one variable Combined scores are called propensity score matching Interrupted time series design Suggests that overtime something can change not necessarily due to an independent variable 0 Car crashes decreasing overtime Chapter 12 understanding research results Statistics Describe data draw conclusions Scales of measurement Nominal scale No numerical quantitative properties Categories or groups Ppl differ but not in a quantifiable way gender eye color Ordinal scale Rank from lowest to highest No interval rank in between Ranking favorite songs Interval scale Intervals are in size Same diff between 1 amp 2 as 2 amp 3 Ranking happiness from 1 7 No absolute 0 Ratio scale Have intervals and an absolute 0 Time weight length Comparing group percentages Compare percentages for yesno questions because it is nominal Correlating individual scores No distinct group of subjects Instead measured on 2 variables Do ppl who sit in the front of the class get higher grades Frequency distribution of ppl who receive each possible score on a variable central tendency 3 measures mean median mode effect size strength of association between variables pearson r correlation coefficient inferential statistics used to assess how confident they are that their results reflect a larger population assess likelihood that their findings will occur if it was repeated null hypothesis population means are observed difference is due to random error independent variable had NO effect research hypothesis means are NOT equal independent variable DID had an effect statistical significance reject the null hypothesis when there is a low probability that results can be due to random error probability likelihood of occuranceoutcome alpha level 05 the probability of incorrectly rejecting the null hypothesis sampling distributions based on assumption that null hypothesis is true are results consistent with the null T test Sees whether 2 groups are significantly different form each other Ift has low probability of occurrence 05 or less then reject the null hypothesis 0 T group diffwithin group variability F test More general than t test Used for more than two groups factorial design Chapter 10 complex experimental designs Curvilinear relationships need 3 levels to determine a relationship sometimes you might want to compare more than two things factorial designs increasing number of independent variables more than one independent variable in a single experiment info from factorial designs 1 main effect the effect each variable has by itself average the two independent variables interaction an interaction between two independent variables indicates that the effect of one independent variable is different at different levels of the other independent variable independent variable x participant variable IV x PV designs PV age gender ethnic group personality characteristics Use one independent variable with two levels and one participant variable with two levels See page 204 when studying Moderator variable Influences the relationship between two other variables Can be situations or characteristics
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'