Psychology 100-Chapter Two- Research Methods
Psychology 100-Chapter Two- Research Methods Psychology 100
Popular in Psychology 100-Introduction to Psychology
Popular in Psychology (PSYC)
This 19 page Class Notes was uploaded by Obioma Azie on Sunday September 4, 2016. The Class Notes belongs to Psychology 100 at University of Illinois at Urbana-Champaign taught by Megan Davis in Winter 2016 2016. Since its upload, it has received 27 views. For similar materials see Psychology 100-Introduction to Psychology in Psychology (PSYC) at University of Illinois at Urbana-Champaign.
Reviews for Psychology 100-Chapter Two- Research Methods
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: 09/04/16
Chapter Two: Research Methods (Source: Psychology: From Understanding to Inquiry (13th Edition)) Highlighting and Underlining Explained If a term is underlined and highlighted, it is a key term that you should know come exam day. If a term is just underlined it is an important person or concept that would be good to remember. Phrases in bold are key ideas. Topics Covered Why We Need Research Designs How We Can Be Fooled: Two Modes of Thinking Naturalistic Observation: Studying Humans “In the Wild” Case Study Designs: Getting to Know You SelfReport Measures and Surveys: Asking People about Themselves and Others Correlational Designs Experimental Designs Placebos Ethical Issues in Research Design Descriptive Statistics: What’s What? Inferential Statistics: Testing Hypotheses How People Like with Statistics Evaluating Psychological Research Why do we need research designs? We need research designs to conquer naive realism and prevent confirmation bias. o What are naive realism and confirmation bias? Naive Realism The belief that we see the world precisely as it is. Confirmation Bias The tendency to seek out evidence that supports our beliefs, and deny, dismiss, or distort evidence that contradicts them. Even the smartest of people can be fooled by the absence of research designs. o Examples Facilitated Communication(FC) Was put into use in the early 1990s The aides who worked with Jenny Storch were so sure that FC worked. Their naive realism led them to see children’s abuse allegations “with their own eyes”, while their confirmat n bias created for them a selffulfilling prophesy, causing them to see what they wanted to see. Prefrontal Lobotomy It was believed to be an effective treatment for schizophrenia and other severe mental disorders. Surgeons would severe the neural fibers that connect the brain’s frontal lobes to the underlying thalamus. Scientists all around the world took lobotomy as a breakthrough, and awarded its developer. Egaz Moniz He received a Nobel Peace Prize for the development of lobotomy in 1949. Astonishing reports of effectiveness were based almost entirely upon subjective reports. Lobotomy may have been effective, but it failed to target specific behaviors associated with schizophrenia Deception by naive realism and confirmation bias Lobotomy has been replaced with medications and other treatments that have firmer groundings in science. These are alternatives that have been systematically tested, and have the backup of experimental design. How We Can Be Fooled:Two Modes of Thinking “The same psychological processes that serve us well in most situations also predispose us to errors in thinking.” Mode One o Intuitive Thinking Mode Our brains for the most part are on autopilot We use this when we meet someone new and form an immediate impression of him or her. Relies a lot on heuristics What are heuristics A heuristic is a mental shortcut or rule of thumb. When we move out of the way of a moving car headed right in our direction, and decide to move out of its way We need intuitive thinking. Why? Without it we would be in serious trouble, because much of everyday life requires snap decisions. o Mode Two o Analytical Thinking Mode Slow and analytical We engage in analytical thinking whenever we try to reason through a problem. In some cases, thinking analytically helps us to override intuitive thinking Does not rely on heuristics What are research designs? Systematic techniques developed by psychologists and other scientists to harness the power of analytical thinking. o Why? “Research designs force us to consider alternative explanations for findings that our intuitive thinking overlooks(pg.47).” Research designs can help us to avoid the pitfalls that can result from an overdependence on intuitive thinking and using heuristics. The Scientific Method The scientific method is a myth. o Why? The techniques that psychologists use are very different from those that are used by physicists, chemists, and biologists. The scientific method is a toolbox of skills designed to counteract our tendency t ofool ourselves. Advantages and Disadvantages of Research Designs Case Studies o What is a case study? When researchers examine one person or a small body of people o Advantages of case studies Allows us to study rare phenomena Can offer insights for later systematic testing Can prove existence proofs What is an existence proof? An existence proof is a demonstration that a given psychological phenomenon can occur o Disadvantages of case studies Are usually anecdotal Do not allow us to infer causation Case studies almost never lend themselves to systematic tests of hypotheses about why a phenomenon occurred. Why? Even though case studies can be helpful in generating hypotheses, they tend to be pretty limited when it comes to being tested. o There is no recipe for a case study. One can simply: Observe a person overtime Administer questionnaires Conduct repeated interviews Naturalistic Observation o What is naturalistic observation? Naturalistic observation is the act of watching participants’ behavior in realworld settings without trying to manipulate their actions o What can one gain from doing naturalistic observation? By doing naturalistic observation, we can come to a better understanding of the range of behaviors displayed by individuals in the real world. o Advantage(s) of naturalistic observation High in external validity External Validity Relevance to the real world o Disadvantages of naturalistic observation Low in internal validity Have no control of variables If your subject knows that they are being watched, that could cause some problems. What is internal validity? The extent to which we can draw cause and effect inferences. The ability to assert cause and effect Wellconducted laboratory experiments are high in internal validity, because one can manipulate the key variables him or herself. Correlational Designs o What happens in a correlational study? Psychologists examine the extent to which two variables are associated. What is a variable? A variable is anything that can vary amongst individuals, like impulsivity, creativity o When we think of the word correlate, we should think about how two variables relate to each other statistically, not interpersonally. o Advantages of correlational designs Can lead us to predict behavior o Disadvantage(s) of correlational designs Do not allow us to infer causation Knowing one variable tells us nothing about the other variable. Lack in internal validity o Conclusions from correlational research are limited. Why? One cannot be sure why predicted relationships exist. o The strength of a correlation is dependent upon the strength of the absolute value of the correlation coefficient. o What is the correlation coefficient? Correlation coefficients are the statistics that psychologists use use to measure correlation. They range from 1 to +1. Values lower than +1 or 1 indicate an imperfect correlation coefficient The strength of a correlation coefficient is dependent upon its absolute value. What is the absolute value? The absolute value is the size of the coefficient without the plus or minus sign. o Correlational designs use scatterplots. What is a scatterplot? A scatterplot is a grouping of points on a twodimensional graph. o Illusory Correlation(s) What is an illusory correlation? The perception of a statistical association between two variables where none exists. A statistical mirage Illusory correlations forms the basis of many superstitions. Why do we fall victim to illusory correlation? We’re not too good at remembering nonevents. “The phenomenon of illusory correlation explains why we can’t rely on our subjective impressions to tell us whether two variables are associated, and why we need correlational designs.” o Correlation vs Causation Even though a correlation can sometimes result from a causal relationship, we cannot tell from a correlational study alone whether or not the relationship is causal. SelfReport Measures and Surveys: Asking People about Themselves and Others o Advantage(s) of selfreport measures and surveys They are really easy to administer. o Disadvantage(s) of selfreport measures and surveys We make the poor assumption that the respondents possess enough insight into their personality characteristics to report them accurately. Selfreport questions usually assume that participants are honest in their responses. Some respondents engage in response sets. What are response sets? Response sets are tendencies of respondents to distort their answers to questions, often in a way that paints them out in Some respondents engage in malingering What is malingering? Malingering is the tendency to make ourselves seem psychologically disturbed with the aim of achieving a clear cut personal goal. o Random selection is crucial if we want to generalize to a broader population What happens in random selection? Every person in the population has an equal chance of being chosen to participate. o Obtaining a random sample is usually more important than having a large sample, if we want to generalize our results to a grander population. Nonrandom selection can lead to misleading conclusions o Evaluating measures Reliability What is reliability? Consistency of measurement A reliable questionnaire yields similar results This type of reliability is called test reliability Reliability also applies to interviews and observational data. Interrater Reliability The extent to which different people who conduct an interview , or make behavioral observations, agree on characteristics they are measuring. Validity The extent to which a measure assesses what it purports. Reliability is needed for validity. We need to measure something consistently before we can measure it well. Reliability does not guarantee validity A reliable test can be completely invalid We should not assume that people responding to survey questions even understand the questions they are being asked. Rating Data Another way to ask people about themselves is to ask others who know them to give you ratings on them. o Why? Observers may not have the same blindspots as the people they are rating. What is the drawback of data rating? o The halo effect The tendency of ratings of one positive characteristic to influence the ratings of other positive characteristics. Experimental Designs o In experimental designs, researchers manipulate variables to see whether these manipulations produce differences in participant’s behavior. In correlational designs, the differences among participants are measured. In experimental designs, they are created. o What makes an experiment and experiment? Random assignment of participants to conditions Manipulation of an independent variable What is the independent variable? The variable that an experiment manipulates o What do experimental designs have? Experimental group The group that receives the manipulation Control group The group that does not receive the manipulation Independent variable(IV) Variable that an experiment manipulates Dependent variable(DV) Variable that an experimenter measures to see whether the manipulation has an effect. Operational definition(OD) A working definition of what a researcher is measuring We define this when we define our IVs and DVs. Confounds: A Source of False Conclusions For an experiment to have internal validity, the level of the IV must be the only difference between the experimental group and the control group. Confounding Variable(Confound) o The difference between the EG and the CG that is not the IV. The Placebo Effect o Improvement caused by the mere expectation of improvement. To control this effect, experiment administrators should make sure that participants do not know which supplement they are getting, the placebo or the real supplement. The Nocebo Effect o Harm caused by the mere expectation of harm The Experimenter Expectancy Effect o Phenomenon in which researchers hypotheses lead to unintentionally bias the outcome of a study. The DoubleBlind Procedure o When neither researchers nor participants are aware of who is in the experimental group Demand Characteristics o Cues that participants pick up from a study that allow them to generate guesses about the researcher’s hypotheses. This can prevent researchers from getting an unbiased view of the participants’ thoughts and behaviors. To combat this, researchers may disguise the purpose of their study, and maybe add some distracting fillers Ethical Issues in Research Design Protection of the rights of human subjects Every major American research college and university has at least one institutional review board. o What do institutional review boards do? They review research carefully with the hope of protecting participants from abuse. The Tuskegee Experiment o No informed consent(The participant being informed about what he or she is getting him or herself into) 128 out of the 399 subjects died. Some researchers use deception o They deliberately mislead participants about the study’s design or purpose. This prevents the generation of obvious demand characteristics. The APA says that deception is only justified when: o Researchers could not have performed the study without deception o The scientific knowledge to be gained from the study outweighs its cost Debriefing: Educating Participants o Institutional review boards may request that this be done at the end of research sessions. o What is debriefing? Debriefing is a process in which researchers inform participants about what the study was about. By debriefing, the study becomes a learning experience for both the investigator and the subject. Ethical Issues in Animal Research It is invasive research. o Researchers cause harm to animals. The goal of animal research is to generate ideas about how the brain relates to behavior in animals, and how those findings generalize to humans, without inflicting harm on people. Without animal research, we would know little about the physiology of the brain. There are no good alternatives to using animals. o Without animals, we’d be unable to test the safety of drugs Statistics: The Language of Psychological Research Descriptive Statistics o What are descriptive statistics? Descriptive statistics are numerical descriptions that describe data. o There are two major types of descriptive statistics. Central Tendency What is central tendency? Central tendency is the measure of the central scores in a data set, or where the group tends to cluster. There are 3 measures of central tendency. Mean: Average Mean is the best statistic to report when a set of data forms a bellshaped or “normal” distribution Median: The middle score in a set of data Mode: The most frequent score in a set of data Median and mode are the best statistics to report when the data is skewed to one side or another. Why? Median and mode are less affected by extreme scores on both sides of the graph. Outlier A score that is outside of the range of the rest of the scores Variability o Gives us a sense of how loose or tight the scores are o Range is the simplest measure of variability. Range can be deceptive. Two data sets with the same range can display a very different distribution of scores across the range. This is why standard deviation is used. Standard deviation is less likely to be deceptive, because it takes into account how far each point is from the mean, rather than how widely scattered the most extreme scores are. Inferential Statistics o Allow us to determine how much we can generalize findings from a sample to the full population o Statistical Significance 0.05 level of chance o 5 in 100: The finding occurred by chance. o If it is less than 0.05, then the finding probably did not occur by chance. o Sample set in this case is very important The larger the sample size, the greater the odds will be that the result will be statistically significant. o Practical Significance Realworld importance Evaluating Psychology in the Media Sharpening o The tendency to exaggerate the gist, or central message of a study Leveling o The tendency to minimize the less central details of a study Balanced coverage sometimes creates pseudo symmetry (The appearance of a scientific controversy where none exists).
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'