psych 203 exam 2
what is cluster sampling ?
- randomly sample a group or cluster of individuals. ex: school kids in wv 1) choose a random 10 schools in the state 2) randomly sample kids from each school
what is simple random sampling ?
- you identity all members of a population of interest. - you assign everyone in the populations a number - and you use random numbers for the sample.
What does the Likert Scale look like?
-Captures agreement/disagreement with statements I plan to wait until I'm at least 30 years old to get married for the first time. strongly agree- agree- idk - not agree - for sure not
how do you choose the best measure
-Ensure construct validity -Examine interrater reliability ( use more than one observer and train them well) -Think about measurement scale
how do you minimize relativity
-Keep observer unobtrusive( you are hidden but they know) -Partial concealment: Participants do not know what is being observed. -Wait it out -Consider alternative measures:( not ideal) - Use knowledgeable informants.( eg. teachers) -Look for traces of previous behaviors.(eg. marks on floor)
what is a Semantic differential scale:
-Participants report where their behaviors/thoughts/opinions fall between two opposite points. Please rate your marriage along the following dimensions: easy ___:___:___:___:___:___:___ difficult hostile ___:___:___:___:___:___:___ harmonious amicable ___:___:___:___:___:___:___ rancorous stable ___:___:___:___:___:___:___ unstable
what are some Other Approaches to Descriptive Research
-demographic research -epidemiological research - archival research
What is observational research?
-observing relevant people, actions, and situations -systematic observation of behavior - natural or lab - leads to frequency claims - lead to a lot of external validity
what is a Multi-item scales
-often are necessary to measure more complex constructs. EX: anger How likely are you to lose control of your emotions? 1 2 3 4 5 6 7 8 9 10 high or not who often does ur anger interfere with sleep not at all 1 --- a lot 5 ....... ....
what sampling techniques use meaningful categories
-quota -stratified random sampling - over sampling
what is convenience sampling
CONVENIENCE SAMPLING: Sample from "accessible population."( easy acess) Example: If we want a sample of WVU undergraduate students, we could... - Use this class. -Stand in front of the Mountainlair at 9 am and interview the first 30 undergrads who walk by and agree to participate.
what is a Successive independent sample
Carry out same study at several times with different samples. - its like cross- sectional bit do it several different times. - you have two different groups maybe
what are the benefits of using a multi item scale ?
Content validity Statistical advantage
Seo-yeon and her research assistants are told that the children participating in their study are particularly lively and friendly. what should you do
Correct label: Use a clear codebook.
what is demographic research
DEMOGRAPHIC RESEARCH: Describes patterns of basic life events and experiences. Examples: birth, marriage, divorce, employment, death, -Provides sociological context for understanding psychological phenomena. ( like why age of marriage is increasing or age of having kids is increasing)
Decision #3: Disguised or Undisguised Observations?
DISGUISED OBSERVATION: Participants unaware they're being observed. -Advantage: Produces the most natural behavior. o Disadvantages: 1)Ethical concerns 2)May not be possible in all situations( like ion a classroom there are no one way mirrors) UNDISGUISED OBSERVATION: Participants know they're being observed. -May trigger REACTIVITY - People behave differently in presence of observer. Variations: Participant expectancy Participant reluctance Evaluation apprehension
what is a cross- sectional design
Describes sample at ONE point in time
What are open-ended questions?
Essay-type questions with no fixed answer. - can be very informative and get you rich data But: it's difficult to score because everyone is not gonna write the same thing.
how do you minimize observer bias ?
Explicit operational definitions and careful training of observers Using multiple observers Masked design ( have the research assistant not know what the research is about.)
what is JUSTICE:
Fair distribution of risks (and individual benefits) from research participation.• - All groups that might benefit from research share equitably in the potential "burdens." - race, gender, ses, age
How many participants should we recruit (N)?
Larger samples lead to less sampling error( the average will be more representative) and more statistical power.( the more data the more confident int data) BUT: Larger samples are NOT more representative! - its not about size of sample its about how you obtain the sample
Respondents are asked to choose a number corresponding to how much they agree or disagree in ______________ questions.
Likert scale
what is a longitudinal design
Longitudinal design: Follow the same sample of people and observe/survey/measure them more than once.
Seo-yeon and her research assistants notice the children are sitting awkwardly throughout the study. what should you do .
Make unobtrusive observations
decision #2 Natural or Contrived Setting?
NATURAL SETTING: Observe behavior where it occurs in the "real world" - Jane Goodall - observation of chimpanzees in Tanzania - "Territoriality" over parking spaces (Ruback & Juieng, 1997) -Advantage: Maximizes external validity ( applies to real world) • CONTRIVED SETTING: Observe behavior in environment that mimics natural context, but is better controlled. -"The Strange Situation"( what infants do w/o parents) - Piaget's stages of development: Conservation of volume. ( how children see tall glass or water or short) - Advantage: Allows study of infrequent events ( you might scarifies external validity but you are studying things that are not always seen)
what does a basic scale look like?
On a scale of 1-10, how often do you think about getting married? never 1 2 3 4 5 6 7 8 9 10 All the time
For good quantitative research, we need... what ??
Operational definitions. Be specific about how you will measure the construct(s) of interest. - Frequency measures: Number of times behavior occurs in time period.( how many times a behavior occurs) - Interval measures: Number of time intervals during which behavior occurs - Timing measures: Reaction time, task completion time, duration of behavior( how long does the head lock last?) - Rating scales: Intensity or quality of behavior.( how intents is the hit it bite)
what is Rating scale response:
Participants report frequency or intensity of behaviors/thoughts/opinions. - Easy to summarize data. - More informative than simple fixed-alternative.
what is nonresponse bias ?
People who agree to participate in a study often differ from those who don't. -In other words, nonresponses bias the sample, and reduce its representativeness. Examples: - Mail-in survey ( only old people do it) -Survey of stress levels in college students( no stressed people will do it) Solution: Attempt to obtain data from as many members of sample as possible.
what is BENEFICENCE:
Potential risk to participants must be minimized. • • • -Risk-benefit analysis: Potential benefits must outweigh potential harm. -Studies categorized as no risk, minimal risk, or greater-than-minimal risk. -Considerations include psychological and physical risks. - always give them new treatment and keep it -Important question: How much distress is ethical?
what is power calculations
Power calculations allow us to determine the necessary sample size, based on: -the variability/diversity of the population. -the predicted size of the effect we're trying to detect.
what are the non probability and probability samples
Probability Sampling Simple random sampling Stratified random sampling Cluster sampling Systematic sampling Non-probability sampling Convenience sampling Quota sampling Snowball sampling
what are the types of sampling
Probability sampling: Every member of population has EQUAL chance of being included in the sample. Non-probability sampling: Probability that any particular individual will be chosen is undefined. ( its unknown you are getting what you can get)
decision #1 qualitative or quantitive design?
QUALITATIVE DESIGNS: Record non-numeric data Goal: Create full narrative of participant behavior. ( everything that occurs will be recorded) - Often focus on case studies ( one person) so its difficult to generalize data. QUANTITATIVE DESIGNS: Describe observations numerically -Allow researchers to summarize patterns across multiple observations.
what is RESPECT FOR PERSONS:
Research participants must be "autonomous agents." you have free will and can decide . don't disclose their info • Informed consent - Participant given info that might affect willingness to participate before study begins. - Includes potential risks and benefits • Debriefing - After study concludes, participants given complete information. Mitigating harm: - Any misconceptions cleared up; questions answered. - All reasonable steps taken to address any harm. • Voluntary participation and protection from coercion -Participants must consent without coercion or undue influence. -Special protections for those with reduced autonomy... - e.g., prisoners, patients with dementia, children Privacy -Participants have the right to privacy. - Research results must be treated with confidentiality, and anonymity when possible.
more things to know
Retrospective reports: Asking people about events, behaviors, or feelings from the past. "What feelings did you have when you began classes during freshman year?" : might not be accurate Write-revise-pretest: Write a bigger pool of questions than needed. Revise questions, thinking carefully about bias and ambiguity. PRETEST!!! Assessing the scale: Is it reliable?o Test/retest reliability - Internal consistency Does it have construct validity? - Convergent (and discriminant) validity o Criterion validity
what is quota sampling
Sample created to represent key subsets of population. -Divide population into 2+ subgroups based on some common characteristic. -Take convenience sample from within each subgroup. Example: Sample of WVU students...
what is systematic sampling
Sample every ex:9th individual encountered from population. Example: Investigating alcohol consumption among people seeking treatment in E.R. -Strategy: Starting with person #3, interview every 8th person who enters E.R. until desired sample size (n) is reached.
what is sampling bias ?
Sampling bias. Occurs when sampling procedure favors certain groups of individuals -> non-representative sample. ALWAYS problematic with convenience sampling. Also potentially problematic for random sampling methods. - To develop sample, we rely on "sampling frame." - However, the frame may not include everyone and may be biased Example: Sample of adults living in Morgantownàuse driver's license records
what is snowball sampling
Sampling method used to identify a "special" population that is... -Difficult to find, and/or -Reluctant to be identified. Examples: prostitutes , illegal immigrants Researcher enlists help of early participants in identifying other potential participants.
what is generalizability
The degree to which results from a sample apply to the population of interest. • The more representative your sample, the more generalizable your study findings. • Example: Let's say we're investigating the effectiveness of different study techniques... Population GPA = 3.12 Sample GPA = 3.57
what is Fixed-alternative:
True/false or multiple-choice questions.
Decision #4: Unobtrusive or Interactive Observer?
UNOBTRUSIVE OBSERVER: Observes behavior without interference - Goal is not to change behavior in any way. ( an observer quiet in the corner) INTERACTIVE OBSERVER: Interact with group/individuals under study -Observer's presence may be disguised or undisguised - Advantages: 1) Access to situations of that would otherwise be closed. 2) Insight into subjective experiences of group members. -Disadvantages: 1)-Observer's presence may alter group's behavior. 2)More difficult to avoid observer bias. •3) Ethics
What is participant reluctant
When you guess the hypothesis and you do the opposite because you don't like being watched or observed.
what is participant expectancy
When you guess what the hypothesis is during the study
What is evaluation apprehension
You feel uncomfortable but you're being evaluated. .concern for how others are evaluating us
If respondents continually select "yes," they are participating in _______________
acquiescence.
La'ei is conducting an online survey that asks participants many different questions about personality and takes nearly an hour to complete. After collecting some pilot data, La'ei notices toward the end of the survey that participants are choosing "strongly agree" for every question. What is the best strategy La'ei can use to improve her survey?
add reverse worded question
what principle is this -The researcher must give the control group the opportunity to receive a new treatment if and when the study has found it to be effective.
beneficence
what principle is this -To prevent sensitive participant data from being revealed, researchers should not collect any potentially identifying information.
beneficence
are these biased or unbiased -purposive sampling snowball sampling convenience sampling
biased
bias or unbiased -Ami randomly selects phone numbers for a telephone survey and then asks the people she calls to recruit additional participants.
biased
bias or unbiased -Dr. Lin recruits participants from her psychology class and then randomly assigns them to one of three conditions.
biased
is this a biased or unbiased sample - democratic in Texas - recruiting only ones outside a convention
biased sample
A(n). __________ is conducted when a researcher investigates the entire group of people they are interested in
census ( all the members of population)
What is fence sitting?
choosing middle response options to avoid reporting controversial or oversimplified opinions. removing neutral or middle response options may help.
Scenario 1: A researcher at a nearby university wants to look at what teachers in a certain school district think about new policy changes. The researcher makes a list of all the schools in the district and uses a random number generator to select five schools from the district. Then the researcher interviews every teacher at each of those five schools. The researcher is using ______________ in this study
cluster sampling
what kind of sampling is this -Karim could randomly select five hospitals from his county and recruit all of the health care workers from those five hospitals.
cluster sampling
What type of validity is most important to consider when creating a poll or survey?
contract validity -Being certain that a poll or survey is measuring a construct well is essential to obtaining reliable results.
what is a structured observation
contrived setting with and interactive observer
One of Seo-yeon's research assistants unintentionally cues the children to share as he passes out cookies. what should you do
do a masked design
what is wrong with this How often do you walk your dog? (2+ times per day never)
do you even have a dog
what is wrong with this -What kinds of substances do you take?
do you even take substances
And researchers cannot be sure which part of the question people are responding to in a ________________—a question that poses two questions.
double barreled
what is wrong with this -Do you agree that campus traffic is a problem and that the administration should be working diligently on a solution? (Strongly disagree Strongly agree)
double barreled
what type of question is this -Should the school preserve the tree and cancel plans for the new bike path?
double barreled
If respondents select all middle options, they are participating in _________________
fence sitting.
_________________ questions ask respondents to choose between two or more options.
forced choice
what is representativeness ?
he extent to which a sample reflects characteristics of the population. • A representative sample... - leads to unbiased estimates of population characteristics. - allows us to generalize results from the sample to the population. 30 males 40 female and 20 others * you need to get the same
what is considered a severe or poll
if you are asking someones questions at all that is a survey or poll ex: the CDC asking questions over the telephone filling out a customer feedback form online interviewing someone who has been clinically committed
What is naturalistic observation?
in a natural setting and an unobtrusive observer
what principle is this -Researchers must recruit participants who are representative of the population that would benefit from the results of the study.
justice
what principle is this -To study a sample of participants from only one ethnic group, researchers must first demonstrate that the problem being studied is especially prevalent in that ethnic group.
justice
a question with wording that encourages a particular response is called a
leading
what is unobtrusive
making yourself less noticeable
what kinds of sampling is this -Karim could randomly select five hospitals from his county and then randomly select 50 health care workers from each of the selected hospitals.
multistage sampling
Scenario 2: The campus safety committee has asked Professor Ibrahim to study bicycling on his campus. He trains two observers to rate the safety behaviors of cyclists at various locations around campus. He randomly selects 10 observation locations from the places where bicycles can be ridden on campus and randomly selects five 1-hour durations for each location. He has his observers make observations at each of the 10 places for each of the five durations. Dr. Ibrahim is using ____________________
multistage sampling.
what is a participant observation
natural setting with a interactive observer
A _________________ question using phrases such as "should never not" can be cognitively difficult and confusing to respondents.
negatively worded
what type of question is this ? - there is never a reason to be late for work 1 agree, 2 kind of 3 idk 4 no 5 noooo
negatively worded
Researchers interpret prisoners' behavior as more aggressive than college students' behavior even though the behavior is actually identical.
observer bias
When observers' knowledge of the research hypothesis influences how they record their observations, ________________ occurs
observer bias
what is this Based on the researcher's body language, a participant guesses that the study is about politeness in intergroup interactions, so he acts politely to align with the researcher's expectations.
observer effect
When participants change their behavior based on perceived expectations from the observer, it is called __________________.
observer effects.
masked design
observes are unaware of the purpose of the design and the conditions that participants are in.
Respondents can provide as much or as little information as they would like in ___________________.
open-ended questions,
what kind of sampling is this -Karim is concerned that 15 physicians might not give him a precise statistical estimate, so he could recruit more physicians and then adjust the results later.
over sampling
_________________ is often used to select participants to represent, in an unbiased way, subsets of the population that are not large enough to be accurately measured
oversampling
Scenario 2: Dr. Saetang is conducting a study on the experience of being a racial minority on a college campus. He goes to the Asian Student Association, Black Student Union, and Hispanic Student Group on his campus to recruit Asian, Black, and Hispanic participants for his study. Dr. Saetang is using_______________.
purposive sampling
what type of question is this 1. Do you think that trees should be preserved on campus, or not?2. Should the school reconsider the route for the new bike trail, or should they reconsider the plan?
question order
what kind fo sampling is this -Karim could visit a local hospital and pass out his survey to health care workers that walk by until he reaches his goal of 15 physicians, 50 nurses, and 35 administrative staff.
quota sample
what kind of sampling is this ? Researchers conducting an online survey collect 50 men and 50 women in order to have equal gender representation.
quota sampling
what is this Small children stop and stare at the experimenter who is in the room taking notes on their behavior.
reactivity
When people change their behavior based on the presence of someone else, this is known as ______________.
reactivity.
what principle is this - To avoid undue influence, researchers should carefully consider whether the compensation is appropriate for the participants they are recruiting.
respect for persons
what principle is this -Researchers should take care to study only participants who are able to understand the procedures, risks, and benefits of the study.
respect for persons
f respondents become fatigued or are unengaged in a survey, they may answer questions in a general pattern without really considering their honest responses. This is known as using a(n) _____________
response set.
The student government at a college is interested in determining how important intercollegiate sports are to the students. Because all students have e-mail accounts, the student government can send a survey to all the students at the college. About 50% of the students respond. What is the most likely bias in this sample?
self selection
what type of scale is this how would you rate yourself ? very submissive 1 ___________________ 5 or dominate
semantic differential
Scenario 1: Jada is working on a study focused on attention span in children and notices that 11-year-old boys are underrepresented in her sample. After her 11-year-old brother participates in her study, she asks him to distribute flyers about the study to his male classmates and soccer team. Jada is using ______________.
snowball sampling
With sensitive topics, sometimes respondents answer in a way that aligns with what they believe everyone else thinks, in a way that makes them look good, or in a way they think the researcher would like them to answer. This is called ____________________
socially desirable responding.
what kind of sampling is this -Karim could randomly select 15 physicians, 50 nurses, and 35 administrative staff for his sample of 100 participants.
stratified random sampling
Scenario 1: A college administrator knows that 30% of the students at her college are from out of state, and she wants to make sure that she maintains this proportion in her survey about admission practices at the college. She has a list of all the out-of-state and in-state students and randomly selects 30 students from the out-of-state list and 70 students from the in-state list. She is using _________________
stratified random sampling.
what is epidemiological research
study of occurrences of disease and illnesses. - relevant to health psychology imprint measures : prevalence: total populations with this disease at one point incidence: rate how many new cases occurs over time ex: depression prevalence by state. autism spectrum overtime
what is a reverse worded question
they ensure fuller measurement of an attitude or opinion, (2) they keep respondents from answering carelessly, and (3) help correct for agreement bias
what is the goal of a descriptive study ?
to describe systematically the characteristics, behaviors, and/or experiences of a population. - you describe what occurs and not explain why is occurs . - its focus on getting info not testing it .
are these biased or unbiased : -systematic sampling -stratified random sampling -probability sampling -cluster sampling -multi stage sampling -over sampling
unbiased
bias or unbiased -Nasir selects telephone numbers from a random-digit dialer and then asks for the youngest male in the house who is at least 18.
unbiased
what is archive al research
use previous collected data and analyzing it in a different way to get new info from that old data. useful for studying: - changes over time - rare events limitations : you didn't collect it so it might not include everything you want . and might have some flaws .
what do you need to consider when creating survey questions
use simple words -avoid jargon - avoid vague terms ex: lately. is that one week or 2 ? - minimize negative words / confusing - provide more context to question that can be misinterpreted - consider putting other in your questions - don't make assumptions: fav place to workout?? you don't know if they like working out -avoid double barreled questions -avoid check all that apply - DO mix reverse questions in there ( helps with response set) -avoid leading questions - be thoughtful when probing sensitive issues - wonder the order of the questions - say its annonnmous