RESEARCH METHODS Chapter 2 Develop a theory Formulate a Hypothesis Operational definition Select The research various methods; participants Operational Definition Collect the data data collection techniques Analyze the data/draw conclusions Statistics to analyze raw data Report the findings - Journal Steps in Scientific Investigation Two major advantages:

Clarity and Precision provides empirical support Relative intolerance of error Advantages of the Scientific Approach Types of Psychological Research Descriptive Research describing a particular Phenomenon

Correlational Research discovering relationships between variables, whose purpose is to examine whether and how two variables change together Observations Surveys and Interviews Case studies Correlation DOES NOT equal causation

Experimental regulated procedure in which the researcher manipulates one or more variables that are believed to influence some other variable Descriptive Research Naturalistic Observation NO INTERVENING DIRECTLY; BEHAVIOR IS ALLOWED TO UNFOLD NATURALLY Strength - Systematic observation in

natural setting Example You might observe student class attendance in order to predict grade success Limitations The main drawback is observer bias The presence of an observer may alter the

participants behavior Hawthorne Effect Descriptive Research Surveys Questionnaires or interviews, such as polls

prior to an election Strength - Can generate a lot of information for a fairly low cost Limitation - Questions must be constructed carefully so as to not elicit socially appropriate answers Socially desirability Bias Accuracy depends on ability and willingness of participants to answer questions accurately Descriptive Research Case Studies

Detailed description and analysis of one or a few people Phineas Gage Prominent in psychology Strength - Gateway for further research Limitation - Observer bias is a problem

Limitation - Unable to make generalizations past person being studied Low population validity Correlational Research Correlational Research

Research technique based on the naturally occurring relationship between two or more variables Often used to make predictions, such as the relation between SAT scores and school success Cannot be used to determine cause and effect Correlational Research Correlation does not equal causation Example The more people study, the less people sleep

The less people study, the more people sleep Other factors affect sleep videos , social media Newspaper headline: Psychologists Discover Relationship Between Religious Faith and Good Health Correlational Example

There is a correlation between domestic violence (violence between a family members) and bowling As more people bowl in the US, more domestic violence occurs. Does that mean that bowling causes domestic Or domestic violence causes bowling? One does not cause the other to occur, but they are

related- for every time people bowl, I can predict that domestic violence will go up, and every time domestic violence goes down I should be able to find a lane at the local bowling alley. There is a hidden variable that links both of them together. In this case it is winter time. In the winter more people bowl and more people stay in their homes (which increases the chances of domestic violence). Statistics and Research Correlation

Positive Correlation Two factors that follow the same direction I.e., - High SAT scores predict Increased school success I.e., - Low SAT scores predict Decreased school success The studious student who studies is more likely to score a higher score on their test. Students who don't study much are less likely to score as high as those who do. Positive Correlation Scatter Plot

SAT Scores School Succe ss Positive Correlation Scatter Plot Amoun t/ Smoke Lung CA

Negative Correlation. Two factors that do not follow the same direction I.e., - High SAT scores predicts Decreased school success I.e., - Low SAT scores predicts Increased school success The studious student who does not study is more likely to score a higher score on their test. Students who do study are less likely to score as high as those who dont.

Negative Correlation Scatter Plot SAT Scores School Succe ss Negative Correlation Scatter Plot Hours/ Study

Sleep Statistics and Research Correlation association between 2 variables correlational coefficient (r) numerical index of relationship between two variables Positive and Negative correlation Closer the correlation to either -1.00 or +1.00 the stronger the relationship. Coefficient near zero indicates no correlation. The size of the CC indicates the strength of the

relationship Strength The following guidelines are useful when determining the strength of a positive correlation:

1: perfect positive correlation .70 to .99: very strong positive relationship .40 to .69: strong positive relationship .30 to .39: moderate positive relationship .20 to .29: weak positive relationship Strength

The following guidelines are useful when determining the strength of a negative correlation: -1: perfect negative correlation .-70 to .-99: very strong negative correlation .-40 to .-69: strong negative correlation .-30 to .-39: moderate negative correlation .-20 to .-29: weak negative correlation Third variable problem

Pg 33 Correlation between Ice Cream and Violent Crime Heat DESCRIBE PATTERNS OF BEHAVIOR AND DISCOVER ASSOCIATIONS BETWEEN VARIABLES ADVANTAGES EXPLORE QUESTIONS NOT ABLE TO BE EXPLORED BY EXPERIMENTS DISADVANTAGES

CORRELATION DOES NOT MEAN CAUSATION LESS CONTROL OVER VARIABLES Correlational Research Experiment-manipulates a variable under carefully controlled conditions and observes whether any changes occur in a second variable Cause and effect independent variable manipulating Always consists of 2 groups (experimental and control) dependent variable measuring Always the results (always a behavior or mental process) experimental group - receive manipulation/treatment Control group - do not receive manipulation/treatment

Experimental Psychology Experimental Psychology Population the entire group N=population Sample the subset of the population Experimental Psychology

Random sample selecting participants from the population and allowing for a representative sample Random assignment each participant has an equal chance Experimental Psychology Extraneous Variables any variables other than the IV that is likely to influence the DV (less control) Confounding of variables Two

variables linked together that make it difficult to sort out their specific effects (more control) A Type of Extraneous Variable Example - Confounding Variable For example, say you're doing a study of depression meds during counseling. You randomly assign people diagnosed as depressed into a control and experimental groups. The control group is given placebo pills by Nurse A and talks to Counselor A for one hour every week. The experimental group is given your test pills by Nurse

A but sees Counselor B for one hour every week. You find that the experimental group feels better at the end of the study. Unfortunately, you're study is not valid because the two groups saw different counselors. We can't say Student Activity Using colored paper rather than plain old white paper can improve learning and performance. One teacher suggested that printing text on green paper helps

students read better, while another claimed that yellow paper helps students perform better on math exams. How accurate are these claims? Does the color of the paper really have an impact on how much a student learns or how well they perform on an exam? Student Activity Theory Hypothesis

IV DV Experimental Control

Oper. Def. IV DV Sample Target Pop.

How to Random Assign. Extraneous Variable Confounding Variable ADVANTAGES OF EXPERIMENTS:

CAUSE AND EFFECT RELATIONSHIPS AVAILABILITY OF CONTROL DISADVANTAGES OF EXPERIMENTS: ARTIFICIAL The artificiality of the lab setting may influence subjects behavior Low Ecological Validity UNEXPECTED AND EXTRANEOUS VARIABLES MAY CONFOUND RESULTS NOT ABLE TO GENERALIZE Low Population Validity CANT EXPLORE SOME RESEARCH QUESTIONS

Unethical Experimental Psychology Cont Activity Psychological Inquiry pg 44 Answer all six questions

Descriptive statistics organize and summarize data Central Tendency typical or average score Mean-average sensitive to extreme scores Median-middle of distribution Mode-most frequent score Statistics and Research Statistics and Research Variability scores vary from each other standard

deviation measure of dispersion that tells us how much scores in a sample differ from the mean of the sample Understanding Standard Deviation https://www.youtube.com/watch?v=MRqt XL2WX2M Normal Distribution Z-Scores

Z-Scores: - The distance of a score which is away from the mean. - Measured in Standard Deviation. - A scored below the mean has a negative Z score. Test has mean score of 80 with a standard deviation of 8. Terence has a score of 72, so he has a z score of -1. Maria has a score of 84, she has a z score of +0.5.

Inferential statistics - interpret data and draw conclusions Statistically significant research results are unlikely to be due to chance Inferential Statistics Probability Value P Value: - It is used to determine the Statistical Significance. - The smaller the P value, the more significant

the results. Cannot equal Zero. P value of 0.05 means that a 5% chance exists that the results occurred by chance Inferential Stats Are the differences occurring by chance or due to the changes in the IV A level of significance is the probability that

it was the independent variable that caused the change in the DV and not chance Significance levels are reported as p<.05 representing 5% error, p<.01 representing 1% error Inferential Stats Most often, psychologists look for a probability of 5% or less that the results are due to chance, which means a 95% chance the results are "not" due to

chance. When you hear that the results of an experiment were statistically significant, it means that you can be 95% sure the results are not due to chance...this is a good thing. :>) Statistical Significance This is determined by the degree of difference between the performance of the two groups If the difference is large enough, then it

is unlikely that the difference is due to chance. You are more likely to find statistical significance if: The sample group contains a large number of people or data points There is a large difference between the

mean of the control group and the mean of the experimental group Sample groups are representative of the population The groups are very similar or have little variability within each group as well as between groups Replication (Triangulation) repetition to see if earlier results are duplicated Sampling Bias sample is not representative of the population Sample-subjects selected population-from where the sample is drawn Placebo effects participants expectations lead them to experience some change; ineffectual treatment Self-Report data:

Social desirability bias socially approved answers response set response to questions in a particular way/unrelated to content of question Hawthorne Effect - individuals modify an aspect of their behavior in response to their awareness of being observed Flaws In Evaluating Research Experimenter Bias researchers expectations influence the results obtained Double-blind procedure neither subject or experimenter know experimental or control group

Flaws In Evaluating Research Cont Ethics Informed consent Confidentiality

Anonymity Debriefing Disclosure Inform purpose and methods utilized Deception Deception used to avoid or reduce problems due to placebo effect, the unreliability of self-reports Lying

Undermine trust in others Produce Distress Animal Research Behavior of a specific type Laws of behavior expose/treatments/unacceptable/humans Ethics