Samenvatting
Samenvatting - Methods and Statistics 1/Methoden en Statistiek 1
Summary for the methods and statistics course with a clear overview from the book and lectures.
[Meer zien]Voorbeeld 3 van de 21 pagina's
Voorbeeld 3 van de 21 pagina's
In winkelwagengesponsord bericht van onze partner
Verkoper
Volgen
Voorbeeld van de inhoud
Methods and Statistics: A Textbook Summary“Scientific research is systematic, controlled, empirical, amoral, public, and critical investigation of
natural phenomena. It is guided by theory and hypotheses about the presumed relations among such
phenomena.”
Designed so that its conclusions can be believed as they are well-motivated.
Can be repeated by others.
Possible alternative explanations are looked into and excluded by testing so that one final
explanation remains.
Theory = coherent and consistent collection of justified beliefs.
Paradigm = researcher’s outlook on reality.
Empirical-analytical paradigm = focus of this book. Standard approach. Assumption that
lawful generalizations exist that can be discovered; phenomena may be described and
explained in terms of abstractions/constructs (for both sub-categories below)
o Positivism = statements can be made from factual observations towards a theory.
Based on observations, we can generalize towards a general principle by means of
induction. All birds I have seen I perceived to be singing, so all birds sing.
o Critical rationalism = opposition to inductive statements; even if I see masses of
birds sing, I cannot say that all birds sing. Try to show that main hypothesis/general
principle is not true. Mismatch between theory and observations = failing theory.
Critical paradigm = puts emphasis on the role of society. There is no one true reality; our
image of reality is not a final one, and determined by social factors. !Concept of science is
rejected in this paradigm!
Some reasoning might be too simple for all the factors that should be considered.
Causal interference = does one cause the other? A lot of factors have to be taken into consideration
to come to a conclusion of causality.
!A study should be able to be generalized and replicated!
Generalization = from this to all
Replication = from this to next; keep being a problem/difficult. Out of 100 tests, approx. 35
can be replicated. There is a replication crisis due to the used methodology and statistics in
original studies.
Little Albert Experiment (1910s).
Classic conditioning = one is connected and associated with the other in the brain.
Asch Experiment – social conformity (with actors); group pressure.
Instrument validation = concerned with constructing instruments or methods to make phenomena,
behaviour, ability, attitudes, etc. measurable. Ideally, the concept-as-defined
(test/questionnaire/observation) maximally approaches the concept-as-intended (theoretical
construct). Theoretical construct has good approximation = adequate/valid measurement.
1) Instrumental research = giving participants a task, wanting to extract something on different
levels, measuring a concept/construct; e.g. testing spelling skills. !Can be manipulated!
, 2) Descriptive research = measuring, generalizing over subjects towards a single domain; geared
towards describing a particular natural phenomenon in reality. Does not stop when data has
been described, also description of relationships between data points. Causal relationship
between cause and effect cannot be properly established. E.g. national assessments.
3) Correlational research (as r/R) = correlation is found between possible causes and possible
effects; e.g. student motivation – achievements. !Type of descriptive research!
Correlation, not causation.
4) Experimental research = researchers systematically manipulating a particular aspect of the
circumstances under which a study is conducted; making causal inferences, showing an effect
can be tied to manipulation and ONLY manipulation. Oriented towards evaluating causal
relationships.
Randomized experiment/true experiment = experiment with random assignment of
test subjects to conditions. Confound = possible disruptive factor, non-manipulated
but important factor, e.g. sex.
Quasi-experimental research = aspect is systematically varied, but test
subjects/groups are not randomly assigned to experimental conditions.
Hypothesis testing research
Hypotheses that have a connection between cause and effect are often tested through an
experiment.
A variable is a particular kind of property of objects or people that can vary. (See examples on p. 26)
Independent = whatever is presumed to bring about the supposed effect. The aspect that a
researcher will manipulate in a study. Chosen values are not dependent on anything else in a
study. Also: factor, predictor.
Dependent = the variable for which we expect the supposed effect to take place;
independent variable can possibly cause an effect on dependent variable. Or the dependent
variable’s value depends on the independent variable.
Null hypothesis (H0) = the complementary belief to another hypothesis.
Falsification = gaining knowledge by rejecting/falsifying hypotheses, not accepting/verifying
hypotheses. One excludes the other. A proper scientific statement or theory must be possible to
prove wrong.
The Empirical Cycle = Every experimental study can be distinguished by 5 phases of research,
developed by De Groot (1961).
1) Observation = researcher forms an idea of possible relationships between various concepts
or constructs, constructing a problem. Presumptions can result from curiosity in general or
be based on case studies (where one or several cases are studied in depth and described). !
Purely unbiased and objective observation is not possible!
2) Induction = logical step in which a general claim/hypothesis is derived from specific cases.
Presumption from observation is generalized. Not all hypotheses are good for testing,
generally 3 types of hypotheses:
Universal-deterministic = “all…”. If a researchers can show for a single A that it isn’t
B, it is falsified. Can never be verified, only statements about cases that have been
observed/measured can be made. All swans are white.
, Deterministic existential = “there is at least 1…”. If a researcher can show that one A
exists that is B, it is verified. Can never be falsified. There is some swan that is white.
Probabilistic = “there are relatively more…”. Frequent hypothesis type in behavioural
sciences.
!A hypothesis should always be logically consistent, economical & empirical!
3) Deduction = logical step whereby a specific statement/prediction is derived from a more
general statement. Here, specific predictions are deducted from the general hypothesis set
up before. Specific statements can be made for specific samples/experiments/results.
4) Testing = collecting empirical observations + comparing them to worked-out predictions
made if H0 were true. Control group/null condition/placebo/etc. = for comparing old and
new methods to each other and come to a good conclusion. !Usually, the significance is a =
0,05 (5%). H0 is rejected if below this value!
Type I error = if H0 is rejected but there is a small chance that H0 is true, but the
observations happen by chance to strongly diverge from H0’s prediction. E.g. unjustly
sentencing an innocent person.
Type II error = not rejecting H0 even though it should be. E.g. unjustly acquitting a
guilty person.
!Setting a higher significance value means the chance of rejecting H0 is much higher!
5) Evaluation = evaluating the results from the study. Providing a critical review of the way in
which the data were collected, the steps behind it, alternative explanations, and the results.
Results are put in a broader context and discussed. Conclusions recommendations + ideas
for follow-up studies.
Levels of measurement – 4 different levels are distinguished here.
1) Nominal = when a property is categorized into separate categories that have no order
between them, e.g. nationality, boy-girl. Not fit for calculating average.
2) Ordinal = when a property is categorized into separate categories that do have an
order/ranking between them; inherent order, e.g. military rank; clothing size. BUT we do not
know anything about the distance between the categories. Not fit for calculating average.
3) Interval = when a property is expressed as a number on a continuous scale for which there is
no zero point; the distance between measuring points is defined, e.g. Celsius; calendar year
(arbitrary zero points). We do know the distances between categories because of the scale.
Used for calculating an average.
4) Ratio = highest level of measurement. When a property is expressed as a number on a
continuous scale for which there is a zero point. We know, because of the scale, the distance
between categories and what the proportions are, e.g. Kelvin; height. Used for calculating an
average.
Code of Conduct = research should be based on honest, diligence, transparency, independence, and
responsibility. All of these principles have to be implemented in every step of research.
As a researcher you should be honest, accurate, transparent, independent, and responsible.
The efficiency of the study depends on choices regarding how the independent variables are
manipulated. manipulating variables within subjects is better than between subjects. + also
depends on dependent variable.
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 kayleevh1999. Stuvia faciliteert de betaling aan de verkoper.
Zit ik meteen vast aan een abonnement?
Nee, je koopt alleen deze samenvatting voor €5,83. Je zit daarna nergens aan vast.
Is Stuvia te vertrouwen?
4,6 sterren op Google & Trustpilot (+1000 reviews)
Afgelopen 30 dagen zijn er 55534 samenvattingen verkocht
Opgericht in 2010, al 15 jaar dé plek om samenvattingen te kopen