4931notes

WHAT IS FIELD RESEARCH

Research conducted in the field versus laboratory

Field: Setting in which phenomenon naturally occurs

Laboratory: Setting chosen by researcher to study phenomenon where it doesn’t normally occur

Example: Classroom is field setting to study learning, but laboratory to study personality

Field Common setting

Clinical Clinic

Consumer Home

Educational School

Medicine Hospital

Political Science Voting Booth

RESEARCH PROCESS Choose topic
Develop question
State hypotheses
Choose design
Collect data
Analyze data
Interpret results
Disseminate results

PHYSICAL SCIENCE VERSUS SOCIAL SCIENCE Question: Does amount of fertilizer affect yield of tomatoes?
Physical Scientist
Take plot of land a divide it into 10 equal sized parts
Plant the same number of tomato plants on each part, maintaining equal distance
Randomly assign amounts of fertilizer to each part
Wait 90 days
Count number of tomatoes in each part
Social Scientist
Identify sample of tomato farmers
Administer questionnaire asking how much fertilizer they use and how much yield they get

VALUES AND SCIENTIFIC RESEARCH Values: Things we consider to be good or important
Values are
    Cultural
    Personal
    Related to religion
    Related to self-interest
Values influence
    What we choose to study
    Our methods of study, e.g., ethical use of human and animal subjects
    How we analyze data
    Interpretation of our results

Facts are the enemy of truth
Junk science

BASIC CONCEPTS OF SCIENTIFIC RESEARCH Variable: Characteristic of something that can take on different values
Independent variable: Variable presumed to be the cause of the dependent variable
Dependent variable: Variable presumed to be the effect of the independent variable
Construct: Theoretical characteristic of something
Theory: Explanation for a scientific phenomenon or for the relations among constructs
Hypothesis: Statement of expected outcome of a study
Operationalize: Procedure for measuring a construct
Construct validity: Evidence in support of the interpretation of a measured variable
Control: Procedures used to eliminate or systematically vary the effects of variables
Randomization: The assigning of subjects to levels of a variable in a nonsystematic way so that every subject has an equal chance of being in each condition
Causality: A relation among variables in which one can be said to determine the other. Cause must precede effect in time.
Internal and External Validity
Internal validity: Appropriate conclusion about relations among variables in a study
    Example: Income as a predictor of GPA
    Subjects: College students
    Valid method: Survey and ask income and GPA
    Invalid method: Observe shoes to estimate income and performance on one test to estimate GPA
External validity: Ability to generalize conclusions from study to broader population, e.g., from lab to field
    Example: New therapy technique reduces depression
    Subjects: College students
    Valid: Compare new technique to old technique with depressed students in counseling center
    Invalid: In lab show sad film clip, then apply treatment, and assess depressed mood CORRELATION Extent to which two variables are associated, i.e., you can predict one from the other

r = SP / sqrt(SS_X x SS_Y)
Sum of products: total amount of covariation between variables
SP = sumXY - (sum X sum Y)/n

Sum of squares: total amount of variability between variables
SS = sum X² - (sum X sum X)/n
SS = sum (X - M_X)²

Correlation Example

X Y X Y X Y

1 1 1 4 1 1

2 2 2 3 2 4

3 3 3 2 3 3

4 4 4 1 4 2

SS_X = 5

SS_Y = 5

SP = 5 SP = - 5 SP = 1

Field	Common setting
Clinical	Clinic
Consumer	Home
Educational	School
Medicine	Hospital
Political Science	Voting Booth