PSYC 3100 1st Edition Lecture 7 Outline of Last Lecture I. Correlational Vs. Experimental Research II. Two Types of Studies A. Correlational B. Experimental III. Correlational Studies IV. Pearson r V. Correlational Studies VI. Casual Possibilities VII. How can one know VIII. An Experiment: What is it IX. Experiment X. Causal Inference XI. Confounding Variables XII. Trait-Confounded Experiment XIII. Situation Confounded Experiment XIV. Confounds Problematical for Two Reasons XV. Situation Confounded Experiment XVI. Situation Confounded Experiment These notes represent a detailed interpretation of the professor’s lecture. GradeBuddy is best used as a supplement to your own notes, not as a substitute.XVII. Situation Confounded Experiment XVIII. Avoiding Confounds XIX. ExamplesOutline of Current Lecture I. An Experiment: What is it? II. Causal Inference III. Confounding Variables IV. Avoiding Confounds V. Examples VI. Video Current Lecture I. An Experiment: What is it? - Investigator manipulates the value of some variable (independent variable).- Investigator measures the value of some other variable (dependent variable).II. Causal Inference - If an experiment is properly conducted, then one has potential for making a causal inference.- “Properly conducted” means that the experiment has no confounding variables. - Make causal inferences if there is not a confound variable. III. Confounding Variables - Confound: A variable whose value has been allowed to co-vary with the value of an independent variable.- Two types: (1) trait (e.g., hair color), and (2) situational (e.g., room temperature). - Co-vary with independent variable - Can have a counter-valuing effect which will weaken or eliminate the effect. IV. Avoiding Confounds - The chance of trait confounds can be minimized (not eliminated) through random assignment of participants to experimental condition. - There is no magic procedure that will allow one to avoid situational confounds. One simply has to attend carefully and make sure that conditions are distinguished only by the value of the independent variable. - Trait- use random assignment, or your results will be inaccurate. Random assignment will give every person an equal chance at each condition. - Random assignment is the key to avoid trait confounds. V. Examples- Marriage and happiness Common law married- couple has been dating since middle school and the man finally wants to get married. The woman does not want to unlessshe is certain that they will be happier. The woman is a grad student and conducts a research thesis over the effect marriage has on happiness. Shemakes a scale of happiness and gets random samples of married couples and non-married couples to participate in her study. The results conclude that married couples are ten times happier than non-married couples. Are there any confound variables? She ended up not conducting an experiment, but a correlational study instead. She did not manipulate a variable to receive an outcome. Therefore, she just measured marital status and measured happiness. Since the study is correlational there are three possibilities. - University and learning A mom cannot decide whether to send her daughter to Texas A&M University or Harvard University so she decides to conduct a study on which school will better educate her daughter. The mom researches Harvard education and Texas A&M education by randomly selecting freshmen from both schools. She then makes a measure of knowledge scale and gives it to the students during their freshman year and four years later after they graduate. The results concluded that Harvard students received a better education. However, the mom did not assign each person to each college, so she could not manipulate the university treatment. Therefore, there are confounding variables and not an experiment. - Alcohol and vertical stability An investigator conducts an experiment where either an individual drinks a six pack of coke or a six pack of beer. The participants waited for 30 minutes and were then brought to a room to walk along a straight line. There were censures to detect when the individual walked off the line. The people who drank beer walked less stable than the group who drank coke. There is a situational confound variable. Each group knew what theywere drinking; therefore, this study cannot be considered an experiment. VI. Video - During the film watched in class, an experiment was conducted where individuals rated the appearance of individuals by looking at pictures on a computer screen. There was a Group A and a Group B. Group A was placed in a normal environment and Group B was placed in an environment that was smelly, hot, noisy, and uncomfortable. The independent variable is theenvironment the groups were given to complete the task of grading the appearances of the pictures provided because this variable was manipulated. The results concluded that Group B gave lower grades of attractiveness. The environment was the influence and it caused each group to give different results. - Field experiments take usual research methods out into the real world. Field experiments are great to use because you get to see how people react in a natural environment, but there is also a lack of control and confounding variables. - Ethics in research include making sure that you care about your participants and that they are getting something out of the research