Psych 3331 Week 2 Notes
Psych 3331 Week 2 Notes Psych 3331
Popular in Abnormal Psychology
verified elite notetaker
Popular in Department
This 4 page Class Notes was uploaded by Casey Kaiser on Saturday September 3, 2016. The Class Notes belongs to Psych 3331 at Ohio State University taught by Thomas Valentine in Fall 2016. Since its upload, it has received 10 views.
Reviews for Psych 3331 Week 2 Notes
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: 09/03/16
Psych 3331 Week 2 Class on 8/31 Nomothetic captures the idea that researchers are interested in finding general principles that can be applied to the population at large, people in general Can arrive at a nomothetic understanding using the scientific method - same scientific method we have always known Hypothesis: A testable hunch in which certain variables are related in certain ways You cannot pose a hypothesis that is not testable, that would not be science o Testing requires breaking it down into two mini rival hypotheses The null hypothesis - when you test the relationship there would not actually be a relationship, there is no significant relationship between the two variables even if you think there will be Alternative hypothesis - a significant relationship does exist between the two variables Why have these two hypotheses? When we are testing we are trying to determine if we should accept or reject the null and alternative hypothesis o You cannot accept or reject both at the same time, based on your results you will either accept the null and reject the alternative or vice versa We can use three different methods of testing Case study Correlational method Experimental method The Case Study Method A detailed account of a person’s life and psychological problems Refers to one individual You would describe their history, present circumstances, symptoms, etc… taking all of these things and integrating them Could include speculation about their problems and why they developed May describe a treatment plan How are they helpful? Case studies can assist in finding out new ideas about behavior They can support a theory or challenge its assumptions Can show value in new therapeutic techniques or new and unique applications of existing techniques The biggest value is that they allow us to study unusual and unique problems that we do not often get the chance to observe Limitations? Can be biased by observers - because they are run by someone trying to support their own hypothesis they may pick and choose the details that support their theory (intentional or not) Often rely on subjective anecdotal evidence - which can lead to misleading or inaccurate conclusions Provide very little basis for generalization Important Terms: Internal validity: the accuracy with which a study can pinpoint one factor as a cause of a phenomenon o Case studies are very low in internal validity External validity: the degree to which the results of a study may be generalized beyond that study o Case studies are very low in external validity Commonalities between correlational and experimental Methods: You can observe many individuals unlike case studies o More data = stronger conclusions = better internal and external validity (that is good!!) You can apply procedures uniformly o Means that other researchers can replicate a study to see how consistently you get the same findings Use of statistical tests to analyze study results o This helps to justify drawing broad conclusions The Correlational Method A research procedure used to determine how much events or characteristics vary along with each other Involved variables - you cannot draw causation from this method but more general conclusions Describing Correlations Positive Correlation o As one variable goes up so does the other, i.e., x and y go up together o Use the line of best fit to determine the correlation Negative Correlation o As one variable goes up the other goes down, i.e., as x goes up y goes down Zero Correlation o Variables have no relationship with each other o There is no such thing as a TRUE zero correlation, but it is very very close to zero. You cannot look at the graph and determine and correlation or no line of best fit You can also use a correlation coefficient to describe a correlation, r r shows the direction and magnitude of the relationship between variables When Can Correlations be Trusted? Ask yourself… Does the correlation that we found in this sample accurately reflect a real correlation in the general population? What are the chances that this correlation occur by chance? We can figure out if the results are due to chance with Significance Testing!!! If there is a <5% probability that findings are due to chance the findings are statistically significant o We refer to this as p < .05 We want to see p value less than .05 if it is not then we cannot confidently say that the results are found by chance Class on 9/2 Advantages and Disadvantages of Correlational Research: Advantages: High external validity - findings are generalizable Replicable Disadvantages: Low internal validity - CORRELATION DOES NOT EQUAL CAUSATION, these studies do not explain relationships, just describe them o Example of ice cream consumption and murders, there is a correlation between these two but they are not causally related. There is a third variable that effects this relationship, the heat! Epidemiological Study: A study that measures the incidence and prevalence of a disorder in a given population Incidence: the number of new cases of a disorder occurring in a population over a specific period of time Prevalence: the total number of cases (including new and existing cases) of a disorder occurring in a population over a specific period of time Longitudinal Studies: A study that observes the same participants on many occasions over a long period of time It can tell us a lot about the order of events arising. o Temporal order is important in correlational research STILL CANNOT USE THESE STUDIES TO INFER CAUSATION The Experimental Method An experiment is a research procedure in which a variable is manipulated and the effect of the manipulation is observed You must have an independent variable AND a dependent variable You manipulate the independent variable You observe the dependent variable When conducting an experiment it is necessary to try to eliminate ALL confounds (variables other than the IV that also act on the DV) To do this you should include… o A control group - group of participants that are not exposed to the IV o Random assignment - selection procedure that randomly places participants in either the control or experimental group o A blind design - participants don't know if they are in the experimental or control condition Both the experimental and control groups should be treated equally in every way possible If we control for this there is still a chance that the differences are not due to the independent variable ^^^ we test this with statistical significance Clinical vs statistical significance Clinical indicates whether the amount of improvement following treatment is "meaningful"in an individual's life Statistical indicates whether or not a participants improvement in functioning occurred because of treatment Why is random assignment important? Differences in the two groups can confound the results We want to reduce the chances that confounds could cause differences in results Why is a blind design important? It reduces subject bias, meaning participants won't consciously or subconsciously act in a way that differs between each group Also reduces experimenter bias, meaning experimenters may have expectations that they unintentionally transmit to study participants To address experimenter bias? Use a double-blind study! So that neither the experimenter or participant know who receives experimental treatment or a placebo Alternative Experimental Designs Sometimes these designs are needed because… Given some research questions we cannot control for every possible confound Sometimes there are ethical / practical problems with different manipulations Quasi-experiment / mixed design - an experiment in which investigators make use of control and experimental groups that already exist in the world at large Ex: studies comparing children who have been abused vs children who have not been abused Problem: confounds Solution: use "matched control participants" - for each participant in the experimental group you find someone that you can match to them in terms of the confounding characteristics (someone of the same age, sex, race, SES, etc.) Natural Experiment - an experiment designed by nature, in which nature (not an experimenter) manipulates the independent variable Necessary when studying psychological effects of unusual and unpredictable events Problems: cannot be repeated at will, also cannot draw broad generalizations from a single natural experiment
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'