Samenvatting
Summary MCRS part 2- Y
- Instelling
- Universiteit Van Amsterdam (UvA)
This summary gives a clear overview of the lectures and book together, provided by an honours student.
[Meer zien]Voorbeeld 3 van de 17 pagina's
Voorbeeld 3 van de 17 pagina's
In winkelwagengesponsord bericht van onze partner
Verkoper
Volgen
Voorbeeld van de inhoud
Summary MCRS second examThere are 2 types of validity: measurement and research: research validity
External validity (outside research):
o Population validity sample needs to be best representant as possible
o Ecological validity where you experiment takes place, in which circumstances
Internal validity (inside research): causality co variance, time order, non-spuriousness
High control = high interval validity (certain about conclusions) experiments low external validity
Low control = low interval validity (uncertain about conclusions) high external validity: results are
applicable beyond the experimental setting
Attempts to increase internal validity can lower external validity (and vice versa)
SAMPLING
A sample is a selected segment of a population presumed to represent that population
o Probability sampling: random selection very unit has equal chance of being selected, the
researcher has no control
o Non-probability sampling: based on judgment of the researcher does not permit
generalization to a wider population
Sample size depends on:
o Purpose of the research
o Desired level of statistical confidence
o Homogeneity of the population
o In practice, the time and resources aviable for research
Probability sampling:
Random sampling: e.g. throwing dice, drawing names out of a hat, lotteries
Multistage cluster sampling: population is divided into clusters, then a random selection is
selected and all the participants in the chosen clusters are selected
Stratified random sampling: to ensure that all the groups of interest are represented in a
sample, the population is divided into separate groups (strata) and then the random selection
Systematic Sampling: means sampling every nth person on a list- for example, taking every 10th
or every 100th person listed in a phone book the interval you select is the sampling interval
Non-probability sampling:
o Convenience sampling elements are selected that are the most easy
o Snowball sampling form of convenience sampling that occurs when you rely on members of a
network to introduce you to other members of the network
o Purposive sampling based on the idea that a specific person or media content will meet
specific criteria the researcher may have
o Quota sampling based on attempts to replicate in a sample the features that the researcher
thinks are important in the population
o Volunteer sampling form of sampling that researcher directly recruits volunteers
Sample: the bigger the better (until a certain point)
However, a bigger sample never makes up for a bad sampling produce
Partial non-response: respondent stops halfway
Unit non-response: selected respondent does not participate in your study
Unreachable/ speaks different language/ he or she does not want to participate
,Consequences:
- You need a larger sample
- External population validity lower, you may not have reached specific subgroups
Wat to do:
- Start over (most of the time not possible)
- Be transparent about sample and non-response and reflect on generalizability of results
(especially in case of non-probability)
- Check representativeness of your sample
SURVEYS: PUTTING NUMBERS ON OPINIONS
Survey: captures public opinion at a point in time (several surveys in a row can capture opinion over
time) and use formatted standardized rather than open-ended questions
Advantages: Disadvantages:
Relatively low cost o Provides information more than understanding
Relatively fast delivery o Increasing public resistance
Rapid data processing o Difficult to explore issues in depth
Can research large populations o No control over response rate
o Generally limited to scaled or check-list questions
Types of survey:
- Cross-sectional at one point in time capturing the publics opinion
Disadvantage: could produce remarkably different results on another time
Least expensive but cannot determine cause and effect
- Longitudinal over time, with several surveys
More expensive, but provide a better sense of cause and
effect, different types:
Trend study
Measures the same items over time using the same questions but drawing different samples
from the population each time
Not clear why change occurred because one is not collecting information from the same
individuals over time
Examines trends in public opinion
Example: comparing public opinion regarding gun control in 2010, 2015, 2020
Cohort study
Collects data from different individuals within the same cohort
Provides more detail than a trend study, but determining cause and effect is still a problem
because the same persons are not studied over time
Examines changes in a cohort across time
Example: students communication science international track who started their studies in
September 2021
Panel study
The same individuals are retained to answer questions over time
Examines changes in individuals across time
Surveys do not necessarily include same questions
Panels can also be used for cross-sectional surveys (one point in time)
Example of a panel: 5000 respondents who were randomly selected form the general Dutch
population. They receive surveys: survey at wave 1, survey at wave 2, survey at wave 3
, Cross-lagged panel survey
The best form of survey for “determining” cause and effect (still only indication)
You measure independent and dependent variable at several time points (hence surveys need
the same questions at each wave)
You need panel data
Prevent social desirability bias
o Indirect questions (third party reference)
o Show that it is ok to answer in a way that is not socially desirable
Item non-response
o Respondent does not understand a question
o Respondent does not want to answer a question (to intimate, threatening)
Consequence: external validity lower when item non-response is associated with characteristics of
the respondent (e.g., with demographics)
What to do? change questions/ pre-test questions/ change answer format
How to pre-test:
Ask respondents to fill in questionnaire and add evaluation question (ask for feedback)
Cognitive interviewing: use think-aloud method and ask respondents what they think when
filling in the questionnaire
EXPERIMENTAL DESIGNS
Surveys are a correlational design (not sure of causality)
You need to use experiments when you have a causal hypothesis
Randomization: eliminates all systematic differences between participants in different conditions
Control group: independent variable is absent
Based on level of control: pre-experiment quasi-experiment true experiment
Types of experimental designs
One-group pretest-posttest design O1 X O2
Type of a pre-experiment
Measure same people once before and once after manipulation
Low internal validity (cannot rule alternative explanations)
Two-group pretest-posttest design X O2
Quasi-experiment (because no random assignment) O2
Two different groups
Measure before and after manipulation
Problems: what if groups were different anyway?
Quasi-experiment: Two-group pretest-posttest design O1 X O2
o Independent variable cannot be randomized (e.g. personality characteristic) O1 O2
o No random assignment at individual level, but at group level
o Inclusion of control group
True experiments maximize internal validity essential ingredients:
Manipulation: ensures that cause precedes the effects
Comparison: ensures effect does not occur naturally
Random assignment: ensures there are no other explanations for the effect (replication required)
Voordelen van het kopen van samenvattingen bij Stuvia op een rij:
Verzekerd van kwaliteit door reviews
Stuvia-klanten hebben meer dan 700.000 samenvattingen beoordeeld. Zo weet je zeker dat je de beste documenten koopt!
Snel en makkelijk kopen
Je betaalt supersnel en eenmalig met iDeal, creditcard of Stuvia-tegoed voor de samenvatting. Zonder lidmaatschap.
Focus op de essentie
Samenvattingen worden geschreven voor en door anderen. Daarom zijn de samenvattingen altijd betrouwbaar en actueel. Zo kom je snel tot de kern!
Veelgestelde vragen
Wat krijg ik als ik dit document koop?
Je krijgt een PDF, die direct beschikbaar is na je aankoop. Het gekochte document is altijd, overal en oneindig toegankelijk via je profiel.
Tevredenheidsgarantie: hoe werkt dat?
Onze tevredenheidsgarantie zorgt ervoor dat je altijd een studiedocument vindt dat goed bij je past. Je vult een formulier in en onze klantenservice regelt de rest.
Van wie koop ik deze samenvatting?
Stuvia is een marktplaats, je koop dit document dus niet van ons, maar van verkoper flipsejans. Stuvia faciliteert de betaling aan de verkoper.
Zit ik meteen vast aan een abonnement?
Nee, je koopt alleen deze samenvatting voor €8,99. Je zit daarna nergens aan vast.
Is Stuvia te vertrouwen?
4,6 sterren op Google & Trustpilot (+1000 reviews)
Afgelopen 30 dagen zijn er 60281 samenvattingen verkocht
Opgericht in 2010, al 14 jaar dé plek om samenvattingen te kopen