Ch. 4 Observation Flashcards
External validity
the extent to which a study’s findings may be used to describe people, settings, and conditions. the goal is to obtain representative sample of behavior
Situation sampling
choose different settings, circumstances, and conditions for observations.
enhances external validity
use subject sampling to observe some people within a situation
Time sampling
choose time intervals for making observations; systematic, random
don’t use time sampling for observing behavior during rare events
Naturalistic observation
observation in natural (real-world) settings without attempts to intervene or change the situation
Participant observation
observer is an active participant in the natural setting they observe (undisguised or disguised)
Structured observation
set tup (structure) specific situations in order to observe behavior
Field experiment
manipulate independent variable in natural setting and observe behavior
Reactivity
when people change their usual behavior because they’re being observed
Confederates
assistants to the researcher that help set up a situation by acting without the participants awareness
Narrative records
complete reproduction of behavior (video, audio, field notes) - comprehensive record
made during or soon after behavior begins
Selected behaviors
checklists, electronic recording; requires decision regarding how to measure behavior (e.g., frequency, duration)
What do methods of recording behavior determine?
how results are measured, summarized, analyzed, and reported
Nominal
categories, many demographics
ex. gender, eye color, hair color, political preference
Ordinal
ranked category
ex. satisfaction, socioeconomic status, degree of pain
Interval
clear distance between options, not real “0”
ex. temperature, credit scores, SAT scores
Ratio
clear distances between options, real “0”
ex. height, weight, length
Qualitative analysis
comprehensive, narrative records, data reduction (abstracting and summarizing behavioral data), choose representative examples
Quantitative analysis
selected behaviors, method of data analysis depends on measurement scale used to record behavior
nominal or ordinal: summarize behavior using relative frequency
interval or ration: summarize behavior using central tendency (mean) and variability (standard deviation)
Reliability
refers to consistency
ex. do two or more observers agree in their observations?
Factors that affect interobserver reliability
characteristics of the observers
- bored, tired, amount of experience, train observers and provide feedback
clearly define events and behaviors to be observed
- provide examples
Observer bias
- systematic errors in observation that result from expectations (also called expectancy effects)
- observers often have expectations about behavior
- reduce bias by keeping observers “blind” to aspects of the study: reasons for observations, goals of the study, hypotheses
Controlling reactivity
conceal observer (ethics: privacy issues), disguised participant observation (privacy), use indirect (unobtrusive) observation
Unobtrusive measures
learn about behavior by looking at evidence of people’s past behavior, not directly observing when the behavior happens
nonreactive: people can’t react to being observed because they’re no longer present
Categories of unobtrusive measures
physical (products, used) and archival (running records, fixed records)