Research methods (psych year 1)

What is the scientific method based on

Induction and falsifiability

Define bayanism

Beliefs come in degrees, likelihood of future events is based on past knowledge

Outline the hypo-deductive method

Observation/intuition > theory > hypothesis > empirical test > results

Evaluate the hypo-deductive method

Questions of subjective values and morality

Replication crisis & open science

Not enough studies reproducible, open science refers to a set of scientific practises

Difference between reproducibility and replicability

• reproducibility = same analyses and data leads to same results

• replicability = same experiments and methods leads to the same results

Define open access and give an example

Unrestricted access to research, accumulation of knowledge including citation, supports meta research.

E.g. APA requires research to be available with editors for 5+ years , reproducible analyses

Leads to ability for verification and analytical reproducibility

Exploratory research

Generating hypotheses

Confirmatory research

Confirming hypotheses

Replication research

Helps verify findings

Methodological pluralism

Use of multiple methods

Methodological triangulation

Convergence of findings of methodologically varying studies

How are quantitative methods descriptive, relational and experimental?

Descriptive - allow us to describe behaviour, not causality but can make predictions

Relational - prediction, not causality

Experimental - allow us to infer causality because other variables are controlled

Fact

A statement about a direct observation of nature that is so consistently repeated there’s virtually no doubt

Theory

A collection of statements that attempt to explain an observed set of phenomena

Constructs

Causal or descriptive explanations, building blocks of theories

Variables

Any characteristic that can assume multiple values, can be operationalised

Nominal data

Named catagories

Ordinal data

Ranked along a continuum but intervals are not equal

Interval data

Intervals between successive variables but not true 0, e.g. temperature

Ratio data

Equal intervals and a true 0, e.g. height

Factorial designs

Experimental designs with 2 or more IVs

Extraneous variables & solutions

Undesirable variables that add error to our experiments and add error to the measurement of the DV

• research design aims to eliminate or at least control of the influence of extraneous variables - e.g. random allocation or counterbalancing, this results in an even addition of error variance across the levels of the IV

Confounding variables

Disproportionately affect one level of the IV more than the other levels (constant or systematic error at the level of the IV)

• introduce a threat to internal validity of experiments, random allocation/counterbalancing spreads influence of extraneous variables so they don’t become confounding

Outline selection as a threat to internal validity

Bias resulting from the selection or assignment of pps to different levels of the IV

• results if participants who are assigned to different levels of the IV differ systematically in some way that could influence the measurement of the DV (other than manipulation of interest)

• Particularly a problem for quasi-experiment design

outline history as a threat to internal validity

Uncontrolled events that take place between testing occasions

Outline maturation as a threat to internal validity

Intrinsic changes in the characteristic of pps between different test occasions

Outline instrumentation as a threat to internal validity

Changes in the sensitivity or reliability of measurement in instruments during the course of the study

Outline different types of reactivity

• subject related, demand Characteristics

• Experimenter related, experimenter bias

• Counteracting reactivity

• Blind procedures (single/double)

Outline the difference between precision and accuracy

Precision (exactness and consistency)

Accuracy (correctness and truthfulness)

Outline the difference between reliability and validity

Reliability - precision (consistency), the extent to which our measure would provide the same results under the same condition

Validity - accuracy (truthfulness), the extent to which it is measuring the construct we are interested in

Test-retest reliability

Measures fluctuations from one time to another, HOWEVER order effects may incur

Inter-rater reliability

Measures fluctuations between observers

Parallel forms reliability

If we administer different versions of the measure to the same pps would results be the same, different versions can be useful to eliminate memory effects (HOWEVER may incur order effects)

Internal consistency (reliability)

Determines whether all items (e.g. in a questionnaire) are measuring the same construct, can be assessed in a number of ways e.g. split half reliability : questionnaire items split into 2 groups and halves are administered to pps on separate occasions (order effects may incur)

Content validity

Does the test measure the construct fully

Face validity

Does it look like a good test

Criterion validity (concurrent & predictive)

Does the measure give results which are in agreement with other measures of the same thing

• concurrent - comparison of new test with established test

• Predictive - does the test predict outcome on another variable

Construct validity (convergent and discriminant)

Construct validity - is the construct we are trying to measure valid, supported by cumulative research evidence collected over time, can be assessed in terms of=

• convergent validity - correlates with tests of the same and related constructs

• Discriminant validity - doesn’t correlate with tests of different or unrelated constructs

True causation, sufficiency and necessary

True causation = sufficiency and necessity, the point at which we can say that x caused y and make true claims about causality

• sufficient: y is adequate to cause x ; the manipulation of the IV, in the absence of all pother factors will always result in the DV change

• Necessary: y must be present to cause x ; the DV change will not be measured in the absence of the IV manipulation (response to other factors)

Multi factorial causation

Phenomenon is determined by many interacting factors

Stratified sample (proportional/disproportional)

Proportional: specified groups appear in numbers proportional to their size in the population

Disproportional: specified groups which are not equally represented in the population are selected in equal proportions

Cluster samples

Researcher samples an entire group/cluster from the population of interest

Population validity

Is the sample representative

Ecological validity

Does the behaviour measured reflect naturally occurring behaviour

What are factors that influence sample size

• design (subjects design, number of IVs)

• Response rate

• Heterogeneity if population