Chapter 4-Non-experimental Methods Flashcards
Naturalistic observation
involves seeking answers to research questions by observing behavior in the real world. Is the hallmark of qualitative research. Is also used to collect numerical data and answer more focused research questions.
What are the two main goals of naturalistic observation
Two main goals: 1. To describe behavior as it occurs in the natural setting without the artificiality of the laboratory 2. To describe the variables that are present and the relations among them
In naturalistic observation it is important that the researcher does not do what and maintains what?
In naturalistic observation, it is important that the researcher not interfere with or intervene in the behavior being studied. They must remain unobtrusive to avoid influencing or changing the behavior of the participants being observed
It is important that they maintain partial concealment. Or else subjects could be aware of being watched but do not know who or what is being observed (person or video (Hawthorne effect))
Participant observation
the researcher is part of the group
what two types of participant observation are there?
active and passive
active participant observation
Active- have a specific role within the group. Interpreter bias may occur
passive participant observation
Passive- no function or role within the group (Rosenhan)
Contrived observation
manipulate some aspect of the environment and record behaviors
Hawthorne effect (reactivity)
Reactance/reactivity refers to the biasing of the participants’ responses because they know they are being observed.
Example of the Hawthorne effect
Example: At the Hawthorne plant they were trying to gauge the relationship between lighting and productivity. Well. When the lights were dimmed, production was way up compared to normal levels. But this wasn’t because of the light, this was because they knew they were being watched and so produced more because they were paranoid
Time sampling and advantages
Time sampling-involves making observations at different time periods in order to obtain a more representative sampling of the behavior of interest.
Selection of time periods may be determined randomly or in a more systematic manner
This use of time sampling may apply to the same or different participants
Advantages: provides information on the frequency and sequencing of behavior, observer has time to record what they have seen.
A disadvantage is that some behaviors will be missed when outside those intervals-the observation may not be representative
Situational sampling and advantages
involves observing the same type of behavior in several different situations.
Advantages: offers two advantages- 1. By sampling behavior in several different situations, you are able to determine whether the behavior in question changes as a function of the context in which you observed it. 2. Second advantage involves the fact that researchers are likely to observe different participants in the different situations
what is interobserver reliability?
When two individuals observe the same behavior, it is possible, to see how well their observations agree. The extent to which the observer’s agree is called interobserver reliability.
Low interobserver reliability- means the observers disagree about the behavior(s) observed
High- indicates agreement
why is a measure of interobserver reliability important?
It can be important to have more than one observer, because the single observer may have missed or overlooked a certain behavior, and there may be some disagreement concerning what was seen and how it should be rated/categorized.
How can you increase interobserver reliability?
How you can increase it- such factors such as fatigue, boredom, emotional/physical state, and experience can influence interobserver reliability.
If both researchers are well-rested, interest in their task, and in good physical/emotional health, high interobserver reliability should be obtained.
What is a correlational study
involves the measurement and determination of the relation between two variables (hence the term co-relation)
measurement of the relation between two continuous variables.
Used when data on two variables can be measured but not manipulated
Can be used for prediction but cannot determine cause and effect
Positive correlation
as one variable increases, scores on the other variable also increase, perfect = 1, Ex: when you study more you get better grades
Negative correlation
as one variable increases the other variable decreases. Ex: when you drink sun on a hot day your thirst goes down, perfect = -1
Zero correlation
indicate that the two variables under consideration are not related. Even if something is not perfectly zero, but 0.03, let’s say for example, this is still considered zero by researchers
ALWAYS ALWAYS ALWAYS REMEMBER!!! CORRELATION DOES NOT EQUAL CAUSATION
R= 1.0, 0.00, -1.0, 0.6, -0.6
perfectly positive, zero/unrelated, perfectly negative, positively correlated, negatively correlated
Surveys
Surveys typically request our opinion on some topic or issue that is of interest to that researcher. There are two basic types of surveys: descriptive and analytic.
Surveys- gather information from a large group: economical (time, money), anonymity (private, illegal behavior), need a representative sample
Descriptive survey
used when you want to determine what percentage of the population has a certain characteristic, holds a certain opinion, or engages in a particular behavior, then you will use a descriptive survey.
Examples: gallup political poll, Nielsen TV ratings
summarize characteristics
When a researcher uses this type of survey, there is no attempt to determine what relevant variables there are and how they relate to the behavior in question. The end product is a description of a particular characteristic/behavior of a sample with the hope that this finding is representative of the population from which the sample was drawn
Analytic survey
seeks to determine what the relevant variables are and how they might be related
Identify relevant variables and how they are related
Examples: does perception of success or accomplished success better predict self-confidence?
What family qualities best predict moral decisions?
What is an ex post facto study? Give an example
This study is used when we work with variables that we cannot control or do not manipulate. It is a latin phrase meaning ‘after the fact’. When we conduct an ex post facto study we are examining the effects of a variable ‘after the fact’- it has already varied before we arrived on the scene. A great deal of detective work would seem to fall in this category.
Validity
A test or inventory has validity when it actually measures what it is supposed to measure. If your research calls for a test that measures spelling achievement, you want the instrument you select to measure that ability, not another accomplishment altogether, such as mathematical proficiency
There are three different types of validity: content, concurrent, criterion
Content validity
indicates that the test items actually represent the type of material they are supposed to test. Researchers often use a panel of expert judges to assess the content validity of test items
Concurrent validity
can be established only when we already have another measure of the desired trait or outcome and can compare the score on the test/inventory under consideration with this other measure
Is established when a score on a test or inventory agrees with another measure (e.g. aggression score on a test agrees with a clinician’s assessment)
Criterion validity
Criterion validity-
Established when a test score compares favorably with a predicted future outcome (e.g. SAT score and college success)
Random sampling
when every member of the population has an equal likelihood of being selected for inclusion in the sample
Two types of random sampling- random sampling without replacement, random sampling with replacement
random sampling without replacement
when a name is not eligible to be chosen after it is selected
random sampling with replacement
when the chosen name can be returned to the population and be selected again
Stratified random sampling techniques
involves dividing the population into subpopulations or strata and then drawing a random sample from one or more of these strata Ex: freshmen, sophomore, juniors, seniors
An achievement
Achievement- evaluate level of mastery or competence
Example: doctors have to past a series of medical board examinations before they are allowed to practice medicine. Lawyers must pass the bar exam before they can practice law
Aptitude
assess an individual’s ability or skill in a particular situation or job
Example- this Purdue Pegboard test is used to determine aptitude for jobs requiring manual dexterity. It consists of two parts- 1. Tip of the finger dexterity and gross movements of hands/fingers/arms
Open-ended survey question. 3 advantages and 3 disadvantages
open-ended questions are questions that allow someone to give a free form answer describes the steps you took to prepare for your last exam Advantages: Don’t shape/limit responses Questions are easy to write Exploratory, no expected outcome Disadvantages: Time consuming for subject Get irrelevant responses Difficult to score/analyze
Closed-format/ended survey. 3 advantages and 3 disadvantages
questions that can be answered with yes or no, or they have a limited set of possible answers (such as: A, B, C, or all of the above)
Advantages:
Easy to complete, easy to score, get only relevant responses
Disadvantages:
Good questions are hard to write
It shapes/limits the responses
Available answers are based on researcher expectations
