Revision of quantitative research

Positivist
Quantitative methodology
Deductive reasoning
Make prediction from a general principle
A researcher try to address a problem of interest by extrapolating the implication of a theory or conceptual framework
Develop a hypothesis and test it by collecting evidence in real life

Concepts
Research involves abstractions, e.g. the terms pain, anxiety, and quality of life are all abstractions of particular aspects of human behavior and characteristics
These abstractions are called concepts

Construct are abstractions that are deliberately and systematically constructed by researchers for a scientific purpose, e.g. self-care, health locus of control, etc. The terms construct and concept are sometimes used interchangeably, although by convention, a construct often refers to a more complex abstraction than a concept

Study variable is a well defined and measurable form of concept to be studied in a research

Conceptualization (conceptual definition)
A process of defining or refining an abstract ideas
By generalizing about particular manifestations of human behavior and characteristics

Operationalization (operational definition)
Specifies the procedures and tools required for measurement of a concept

Theory
An abstract generalization that presents a systematic explanation about how phenomena (concepts?) are interrelated
Consists of:
A set of interrelated concepts
A set of propositions that systematically explain the relationships of the concepts

Framework
An explanation, based on the literature, of how the variables in your study are expected to related to each other and why
Theoretical framework underpins (supports) the relationship between study variables with a theory
Conceptual framework underpins the relationship between study variables, with information from literature, but not a theory

Independent variable
The variable that is believed to cause or influence the dependent variable
In experimental research, independent variable is a variable which the researcher manipulates

Dependent variable
The variable that depends on or be caused by independent variable

Cause-and-effect (causal) relationship
One variable caused the other

Functional (associative) relationship
One variable changes values in relation to changes in the other variable

Experimental hypothesis
Statement of expected relationships between the independent and dependent variables

Null hypothesis
Hypothesis which state that there is no relationship between independent and dependent variables
For the purpose of statistical testing and for interpreting statistical outcomes

Manipulation
Researcher does something to some subjects, e.g. introduces an intervention or treatment

Randomization
Also called random assignment
Researcher assigns participants to groups at random

Control
No intervention
Alternative intervention
Usual care
Placebo

Experimental (randomized controlled trial)
Manipulation of independent variable
Control group
Randomization

Quasi-experimental
Manipulation of independent variable
May not have control group or randomization

Non-experimental
No manipulation of independent variable

Data collection frequency
Cross-sectional: data are collected at one point in time
Longitudinal: data are collected at two or more points in time over an extended period

Retrospective
Study begins with dependent variable and looks backward for cause or influence

Prospective
Study begins with independent variable and looks forward for the effect

Non-experimental designs
Correlational (ex post facto ~ from after the fact) designs
- Prospective designs (Cohort studies)
- Retrospective designs
Descriptive designs

Generalizability
It relates to the extent that the results can be applied to other groups of people who are outside the study sample

Sample / Accessible population / Target population

Stratified random sampling
Process of selecting a sample to identify subgroups in the population that represented in the sample at random
(Proportionate / Disproportionate)
e.g. RN ~ Baccalaureate graduates / Diploma school graduates

Cluster (Multistage) sampling
A successive random sampling of units (clusters) from large to small which meet sample eligibility criteria

Systematic sampling
The process of selecting every kth case from the list

Convenience sampling
Subjects are chosen on the basis of availability

Consecutive sampling
Taking the complete accessible population within a defined period of time in the study

Snowball sampling
Relies on early sample subjects to refer others who meet the study eligibility criteria, to participate in the study

Quota sampling
Identify population strata of the population and then determine how many subjects are needed for each stratum to meet a quota according to the subjects' availability

Reliability
The consistency and accuracy with which an instrument measures the attribute

Validity
The degree to which an instrument measures what is supposed to be measuring

Statistical significance is a term that indicated the results obtained in a research study are unlikely caused by chance

Type I error
Wrongly rejecting a true null hypothesis

Type II error
Wrongly accepting a false null hypothesis

Crossover design
The exposure of the same subjects to more than one experimental treatment

Blocking / Stratification
Identify the possible confounding / extraneous variable, e.g. gender

Factorial design
Manipulate two or more independent variables simultaneously

External validity
The extent to which the results of a study can be generalized from the study sample to the larger population

Internal validity
The extent to which the change in the dependent variable (outcome) is truly due to the influence of independent variable, but not the other factors

History threat
The change in dependent variable is due to the occurrence of events concurrent with the independent variable
When external events affect one group more than another

Selection threat
The study result is due to the pre-existing differences between study groups before the manipulation on the independent variables (lack of randomization)

Maturation threat
The change in the dependent variable is due to any kind of change that occur as a result of time, but not only related to the independent variable

Attrition is not at random -> mortality threat

Hawthorne effect
Subjects respond in a certain manner because they are aware that they are being observed

Experimenter effect
Occur when the researcher characteristic or behavior influence subjects response to treatment / a questionnaire

Double-blind technique
A technique in which the subjects, the researcher who administer the interventions, or the data collector, are unaware of which subjects are assigned to the experimental and control group

Measurement effect
When a pretest and posttest are used, measurement effect occurs when subjects have been sensitized to the treatment through taking the pretest

Systematic reviews
The use of a rigorous method to summarize the findings of all methodologically sound studies that address the same research question

Meta-analysis
Statistically combining the data produced by individual studies

The odd ratio is a way of comparing whether the probability of a certain event is the same for two groups

Evidence-based nursing
The process by which nurses make clinical decisions using the best available evidence, their clinical expertise and patient's preferences