Psychology

quantitative research

quantitative research

• aim is to arrive at numerical expressed laws that characterize the behavior of large group of individuals.

• data comes in forms of numbers

• the orientation on deriving universal laws

• operates with variables

construct

theoretical defined variables, an idea not physical

operationalization

when a construct is expressed in terms observable behavior

experimental studies

one independent variable and one dependent variable and other potential variables are controlled, the experiment is the only method that allows cause-and-effect inferences

(a type of quantitative research)

correlation studies

researchers do not manipulate the variables, variables are measured and relationships between them are quantified

(a type of quantitative research)

descriptive studies

the relationships between variables are not studied, variable are approached separately, often used to conduct a broad investigation of a phenomena

(a type of quantitative research)

random sampling

• ideal approach to make it representative

• sufficient sample size

• easy to generalize

• not always possible for practical reasons

• type of sampling

stratisfied samplinh

• theory driven

• researchers decide the essential characteristics of a sample

• recruit the participants based on the data and proportions as the sample

• type of sampling

convenience (opportunity) sampling

• participants that are more readily available

• university student are a very popular choice because researchers usually are very busy

• type of sampling

self-selecting sampling

• recruiting volunteers through advertisement

• type of sampling

hypothesis

the experimental method is based on hypothesis training

null hypothesis

• a fact that you are set up to disprove

• the hypothesis assumes that there will be no significant difference for a given population under two different conditions

alternative hypothesis

• you guess what will happen

• there is a clear guess as to the outcome of the experiment

• it isn’t acceptable practice to change your alternative hypothesis after you get your results to match your findings

construct validity

characterizes the quality of operationalization

internal validity

characterizes the methodological quality of the experiment

external validity

characterizes generalizability of findings in the experiment

population validity

refers to the extent to which findings can be generalized from the sample to the target population

(type of external validity)

ecological validity

refers to the extent to which findings can be generalized from the experiment to other settings or situations. It links to the artificiality of experimental conditions

(type of external validity)

Threats to internal validity

bias in experimental research comes in the form of confounding factors that may influence the cause-and-effect relationships between the IV and DV decreasing internal validity

selection

occurs in independent measures and matched pairs designs

(threat to internal validity)

history

refers to outside events that happen to participants in the course of the experiment

• they can potentially influence the DV or are not evenly distributed in the comparison groups

(threat to internal validity)

maturity

in the courses of the experiment, participants go through natural development processes, such as fatigue or simply growth

(threat to internal validity)

testing effect

the first measured of the DV may affect the second (and subsequently) measurements

(threat to internal validity)

instrumentation

this effect occurs when the instrument measuring the DV changes slightly between measurements

• the “instrument of measurement” is often a human observer

(threat to internal validity)

regression to the mean

becomes a concern when the initial score on the DV is extreme. extreme scores have a purely statical tendency to become more average on subsequent trials

(threat to internal validity)

experimental mortality

refers to the fact that some participants drop out during an experiment, which may become a problem if dropouts are not random