Lecture 4 Research Methods

Goals of Psychology

-Description: identify and classify different behaviors and mental processes -Explanation: try to provide a reason for why it occurs -Prediction: what conditions need to happen for this behavior to occur -Influence: allows us to apply what we know to solve a real world problem

Examples of Case Studies

-Patient H.M.: can't remember any new memories -Phineas Gage: railroad worker got a pipe through his skull; frontal lobe functioning

Theory

-a tentative explanation that tries to integrate and account for the relationship of various findings and observations -tries to incorporate a bunch of different findings, observations, phenomenon into one explanation

Why is it important to operationally define your variables?

-allows other researchers to try to replicate your study or add to it

Survey

-ascertains self-reported attitudes and behaviors of a particular group by questioning a representative, random sample of the population to attempt to avoid sampling bias -try to avoid wording effects -manipulation checks -social desirability bias

Experimental Designs

-between subjects design -within subjects design

Advantages of Experimental Method

-demonstrate causal relationships -avoid directionality problem

Methods to test hypotheses

-descriptive methods -correlational methods -experimental methods

Positive Correlation

-directly related -r values = 0 through +1

Hypothesis

-empirically testable prediction, often implied by a theory -describes how events are related -allows us to test, reject, or revise a theory -can have more than one

Disadvantages to Observation

-errors in observation can occur because of observer's expectations (observer bias) -observer's presence can change the behavior (reactivity)

Case Study

-examines one individual or group in depth in hopes of revealing the truth in us all -uses interviews, observations, and written records

Research

-gather evidence to test the hypothesis -variables -operational definitions -examine, describe, and analyze the data -draw conclusions from the data

Characteristics of a good theory

-general: summarize many different observations -falsifiable: we know its not correct going into it/can be unsupported -parsimonious: needs to be simplest explanation -drive future research: either supported or not supported; not proven right or wrong

Negative Correlation

-inversely related -r values= -1 through 0

Operationally define stress

-loss of appetite -cortisol levels in their bloodstream

Operationally define anger

-measure blood pressure -hormones -heart beats per minute -how many times they hit someone -number of times they curse

Correlation

-measure of the extent to which two factors vary together -measured using the correlation coefficient (r)

Effect of outliers on measures of central tendency

-mode: doesn't change -mean: very susceptible -median: not as susceptible

Descriptive Methods

-objective and systematic way to describe observations/behavior 1. case study 2. naturalistic observation 3. surveys/interviews -no manipulation of variables -can usually do without consent

Observation

-observing and recording behavior in naturally occurring situations without trying to manipulate and control the situation -naturalistic and participant

Experimental Methods

-research method in which an investigator manipulates one or more factors (ie variables) to observe the effect on some behavior or mental process -by random assignment of participants, investigator aims to control other factors -assessment of causality

Naturalistic Observation

-researcher doesn't interact with subject; just observe in natural habitat -ex. chimpanzees and tools

Participant Observation

-researcher is part of the group/interacting with group -ex. doomsday cult

Operationally define happiness

-smiling and laughing -level of endorphins

Disadvantages of Experimental Method

-take place in artificial settings (laboratory settings)

Measures of Variation

-tells how similar or diverse the data are -range -standard deviation

Internal Validity

-the degree to which a study is logically sound and free of confounding variables -achieved if effect on DV is due only to variation in IV

Zero Correlation

-there is no relationship between x and y

Why use the scientific method?

-to conduct research in a systematic way -used for the development, replication, and revision of theories and hypotheses

Advantages to Observation

-valuable in early stages of research, especially when determining if a phenomenon exists -takes place in a real-world setting

Do correlations prove causation?

NO -causal ambiguity -third variable problem

Which of the following might be used as an operational definition of "assertiveness"? 1. The number of times a person makes requests or states his or her feelings over the course of a one-hour interaction. 2. An appearance of confidence and at ease in social situations without appearing aggressive.

The number of times a person makes requests or states his or her feelings over the course of a one-hour interaction.

Aspects of an Experiment

Variables: 1. Independent Variable 2. Dependent Variable 3. Confounding Variable Groups 1. Experimental Group 2. Control Group

Variable

a factor or measure that varies within an experiment

Within Subjects Design

a single group of subjects is exposed to all conditions (all levels of IV, all levels of treatment)

a test CAN be reliable without being valid

a test CANNOT be valid without being reliable

Population

all the cases in a group you're interested in surveying

Quasi-Experimental Design

can't randomly assign certain variables (ex. male/female; age; height)

Operational Definition

definition of a variable based on the procedures or operations used to measure it; describe the property in concrete, measurable terms

Inter-rater reliability

different raters assigns similar scores

Representative Sample

drawn from a population of interest and has demographics and characteristics that match those of the population in as many ways as possible

Between Subjects Design

each group of subjects is exposed to a different condition (level of IV, treatment)

What happens after we conduct research?

either support or not support our theory

Random Assignment

every member in the sample has an equal chance of being in either group

Random Sample

everyone in the population has an equal chance of being surveyed

Independent Variable (IV)

experimental factor(s) being manipulated

Validity

extent to which a measure assesses what it claims to measure (ex can't measure tennis ability by spaghetti cooking ability)

Confounding Variable

factor(s) other than IV that might produce an effect in an experiment

Experimental Group

group exposed to treatment

Control Group

group that does not receive treatment

What is a good measure of psychological processes?

high validity AND high reliability

Convenience Sample

made up of people who are easy to reach

Test-retest

similar scores of tests at different time points

Measures of Central Tendency

single measure to represent a whole set of scores -mode -mean -median

Negatively Skewed

tail pulled left

Positively Skewed

tail pulled right

External Validity

the ability to generalize the results from an experiment to different tasks, settings, or larger population

Reliability

the consistency of the measurement -test-retest -inter-rater reliability

Normal (no skew)

the normal curve represents a perfectly symmetrical distribution

Counterbalancing

the systematic manipulation of the order of conditions

Dependent Variable (DV)

the variable that changes in response to manipulations