• organized study: methodical investigation into a subject in order to discoverfacts, to establish or revise a theory, or to develop a plan of action based on the facts discovered.

Hypothesis generated are not typically testable. 

• If scientific tests are reported, methodology is not scientific and validity of data is questionable
• Supportive evidence is anecdotal and does not cite scientific references
• Claims ignore conflicting evidence
• Claims tend to be vague, and appeal to pre-conceived ideas
• Claims are never revised

1. Describe a phenomenon 

2. Predict the phenomenon 

3. Determine the causes of the phenomenon 

4. Explanation of the phenomenon 

Empiricism

Falsifiability

• The use of existing sources of information for research. Sources include statistical records, survey archives, and written records

Observational research

• Research strategy in which people are observed as they go about their lives in the real world. Varies by level of participation in the process from strictly observing to full participation.  In strict observation, you have no contact with the subject population.

Interviews

• A series of questions are read to an individual (interviewee) by an interviewer; interviews are administered in person or over the phone. 

Focus group

• Group interview designed to explore what a specific group of people think about a topic; the advantage of these small group discussions is that the brainstorming and discussion among group members leads to different ideas than would be generated by any one individual him or herself

Survey

• A series of questions that individuals answer about a topic(s) of interest. Questionsare well-written, thematic, often close-ended (choose between options), can be in person, by telephone, by computer/internet or written

Experimental

• A method of determining whether variables are related, in which the researcher manipulates the independent variable and controls all other variables by randomization or by direct experimental control. Two or more groups; groups receive different treatments; randomized to groups; pre-post measurement is desired

Quasi-experimental

• Research strategy for conducting experiment-like studies in the real world where researchers cannot achieve the degree of control that would be necessary for a true experiment (especially situations in which the researcher cannot randomly assign subjects to control and experimental groups). Two or more groups; groups receive different treatments; individuals are not randomized but groups often are; pre-post measurement is desired. 

Basic vs. applied research

Basic: Attempts to answer fundamental questions about the nature of a phenomenon; usually theory based; goal is to advance scientific understanding

Applied: Conducted to address issues in which there are practical problems and potential solutions

Community

• a group of people sharing values and institutions.  Community components include locality, an interdependent social group, interpersonal relationships, and a culture that includes values, norms, and attachments to the community as a whole as well as to its parts. A community may be based on geographical boundaries, ethnicity, sexual orientation, occupation, or other shared interests.

Community-based participatory research

Collaborative approach to research, [CBPR] equitablyinvolves all partners in the research process and recognizes the unique strengths that each brings.  CBPR begins with a research topic of importance to the community with the aim of combining knowledge and action for social change to improve community healthand eliminate health disparities.

CDC ecological framework

Beneficence

research should have beneficial effects while minimizing any harmful effects

Autonomy

(respect for persons): “individuals in research investigations are capable of making a decision of whether to participate” 

Justice

“all individuals and groups should have fair and equal access to the benefits of research participation as well as potential risks of research participation”

Informed consent

Tuskegee Study of Untreated Syphilis in the Negro Male: 

Depression-era U.S. poster advocating early syphilis treatment. Although treatments were available, participants in the study did not receive them. Note the ironic representation of "well" Whites and "infected" Blacks.” 

Rationale: hypothesis that syphilis affects African Americans (cardiovascular damage) differently than whites (neurological)

Milgram Study

• Yale University
• Conformity to authority
• Expected low probability of going all the way
• The design
• Variations

Stanford Prison Study

• Zimbardo talking about prison study.Basement of the Stanford psychology building. Randomly assigned to prisoner vs. guard. Prisoners arrested at home/dorm. Supposed to last 14 days, ended after 6

• Part 1: Observations of men having impersonal oral sex encounters in public bathrooms (ethnographic). He often served as the “lookout” for police to gain trust. 
• Part 2: Captured license plates; looked up addresses. 1 year later, changed his appearance and did in-home interviews with men 

Hypothesis

• A tentative question waiting for evidence to support or refute it. More general – Ex. Two  variables are related

Prediction

• A statement that makes an assertion concerning what will occur in a particular research investigation. More specific – Ex. A certain change in variable X will cause a certain change in variable Y.

Theory

• systematic body of ideas that Organize and explain,  Generate new knowledge, Can be modified by new research

Research question

• Some words a research question might start with….who, why, when, how, under what circumstances, how much….

Construct

an abstraction

Concept

an abstraction that 

describes a portion of reality

A measurable version of a construct or concept

• Variable is an abstract concept that must be translated into concrete forms of observation or manipulation. Studied empirically. Help communicate ideas to others

Situational variables

• characteristics of a situation or environment

Response variables

• responses or behaviors of an individual

Participant or subject variables

• individual differences (characteristics of individuals such as gender, intelligence, personality, etc.)

• psychological processes that mediate the effects of a situational variable on a particular response

Moderator (moderating variable) 

• change the relationship between two variables (sometimes called interaction)

• In general, we think the independent variable is the causal variable

Dependent variable

• In general, we think the dependent variable is the outcome variable

Construct validity

• Adequacy of the operational definition of variables (e.g., if we are examining perceived stress, are we measuring it correctly?)

Internal validity

• Ability to draw conclusions about causal relationships from our data (e.g., if we implement a stress reduction intervention and we see fewer injuries, can we conclude that it was the stress reduction intervention that led to lower injuries?)

External validity

• Extent to which the results can be generalized to other populations and settings (e.g., if we find that a stress reduction intervention works at UF, can we generalize it to other universities – that is, expect it will work at other universities?)

• Draws reasonable conclusions based upon an analysis of the data (e.g., if we find a difference, is it statistically significant?)

third variable problem/confounding

probability

nominal scales

• H₀: Population Means (proportions) are Equal

research (alternative) hypothesis

• H₁: Population Means(proportions) are Not Equal

• Made when the null hypothesis is rejected but the null hypothesis is actually true. 
• you say the populations are different but they are really the same; as a researcher, you are seeing a difference that really does not exist)

Type II error

• Made when the null hypothesis is accepted although in the population the research hypothesis is true. 
• (you say the populations are the same but they are really different – as a researcher, you are failing to detect the difference)

alpha

• Researchers traditionally have used either a .05 or a .01 significance level in the decision to reject the null hypothesis (Type I error)

• One single variable and you want to see if the distribution of your data among the categories of that variable fit your expectations.

Cramer's V

• There is a medium effect size for the relationship between type of car and attractiveness (Cramer’s V)

Chi Square test of independence

• • Test the significance of the relationship between two variables when data are expressed in terms of frequencies of joint occurrence.”
• you want to see if the distributions of two variables are related or independent of each other

critical value of chi square

degrees of freedom

• test for significance of difference between two proportions