UW-Madison PSYCH 225 - Final Exam Study Guide (35 pages)

Previewing pages 1, 2, 16, 17, 18, 34, 35 of 35 page document View the full content.
View Full Document

Final Exam Study Guide



Previewing pages 1, 2, 16, 17, 18, 34, 35 of actual document.

View the full content.
View Full Document
View Full Document

Final Exam Study Guide

491 views

Lectures 18-23 including book readings


Pages:
35
Type:
Study Guide
School:
University of Wisconsin, Madison
Course:
Psych 225 - Experimental Psychology
Edition:
1
Unformatted text preview:

Psych 225 Exam 3 Study Guide Lectures 18 23 Book Readings Exam 3 Chapter 8 Control The Keystone of the Experimental Method scientists increase certainty by creating an artificial situation the experiment in which important factors can be controlled and manipulated control technique used to reduce the effects of extraneous variables on results and to ensure greater certainty that the changes in the DV result from the IV emphasize control as control as related to participant assignment control as related experimental design and the assurance of internal validity control as related to the logic of experimentation Control Achieved Through Participant Assignment and Selection one class wants to study how accurately people can measure time don t want to use girls vs guys because then gender can be a cofound don t want to call all friends or people that are in on a certain night could be different using all P s from one school college can affect external validity best way is to use random sampling Random Sampling most common technique is called random number tale random number tale table of numbers created so that their occurrence cannot be predicted from a mathematical formula to avoid sex confound someone suggests using only participants of one sex called an elimination procedure but would limit the generality of the finding because only pertains to one sex equating procedure use same number of men and women matching P s are matched in terms of a pre test example in book chose to use equating method equating does not eliminate sex difference but controls for any sex difference someone else says they can assign first 5 women and first 5 men to one condition and second 10 to the other but this may introduce another cofound may be some correlation between tardiness promptness and ability to tell time another wants to assign them ECECEC but this can create bias so needs to use counter balance counterbalancing procedure like simple alternation this ensures that each condition appears equally often and it has the additional advantages that each condition precedes and follows the other condition an equal number of times Randomization the most powerful technique we have for eliminating unintended participant assignment confounds from the design of experiments is randomization randomization compilation of P s assignments solely on the basis of chance ex flipping a coin random sampling selection of P s in an unbiased manner so that each potential participant has an equal possibility of being selected for the experiment random assignment occurs when participants chances of being assigned to each group in an experiment are equal Random Sampling helps constitute a representative sample Random Assignment after randomly selecting the P s then we randomly assign them to experimental and control groups randomization controls for both known and unknown potentially confounding variables Control Achieved Through Experimental Design experimental design must provide a logical structure and help rule out confounds must allow us to determine effect of IV on DV and rule out alternative hypotheses Post test Only Control Group Design Random Assignment Group A Treatment Measurement Random Assignment Group B Treatment zero level Measurement Pretest Post test Control Group Design Random Assignment Group A Measurement Tx Measurement Random Assignment Group B Measurement Tx Measurement this allows us to determine the effects of the IV on the DV and to control for threats to internal validity history maturation and testing would affect both groups similarly be controlled for also controlled for participant selection and statistical regression by random assignment mortality not expected to occur more often in one group than the other random assignment controls for participant maturation interaction Pretest measurement occasion that occurs prior to the introduction of the IV Posttest measurement occasion that occurs at the conclusion of the presentation of the treatment or IV controlling a factor in experimentation is the same as holding the effect of that factor constant for all groups throughout a research study designs serve their function only if used correctly because giving a pre test and post test can have affects themselves it is suggested that people consider using the Solomon four group design Solomon four group design have an experimental and control group that receive pretest and posttest and an experimental and control group that receive only the posttest can determine not only the effects of the Tx but also the interaction of the Tx with the presence or absence of a pretest can also use to look at maturation and history three designs presented posttest only pretest posttest and Solomon four group are considered true experiments true experiment 1 P s assigned randomly to groups 2 at least two levels of the IV one level can be zero 3 control for the major threats to internal validity such as history and selection 4 compare two alternative theoretical positions Control as Related to the Logic of Experimentation F 1 if groups equal no change group a and b for example if groups unequal the F ratio would be greater than 1 before the IV is ever introduced might find ourselves rejecting the null and drawing an inappropriate conclusion Chapter 11 The Ecology of the Experiment The Scientist and Research Participant in Relation to Their Environments cultural perspectives play a large role in studies focus more on witness and witness interpretation Two historical model have influence psychological research in the US according to Danziger 1 Leipzig model Wundt makes little differentiation between the participant and the experimenter in terms of expected roles or social status 2 The Paris Model clear distinction between roles of the scientist and the research participant Ecology ecology scientific study of the relationship of living organisms with each other and their environment all parts of nature are closely interconnected and its impossible to make environmental changes without affecting the entire system at least to some extent Examples dust in Africa affect Asthma in US atomic explosion in China led to cows giving bad milk that got to Philadelphia similarly ecology of a psychological experiment involves the experimenter the research participant and the experimental situation Bronfenbrenner has written about the importance of including the ecological perspective in human development research context where study


View Full Document

Access the best Study Guides, Lecture Notes and Practice Exams

Loading Unlocking...
Login

Join to view Final Exam Study Guide and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Final Exam Study Guide and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?