EBP: Research Design

Independent variable

A variable that stands alone and isn't changed by any other variables being measured; in an experiment, the variable that is being manipulated.

Dependent variable

The variable that is being studied and measured; in an experiment, it changes when the independent variable is manipulated.

Categorical variables

Variables categorized according to a trait or characteristic that does not have inherent numerical value.

Continuous variables

Variables that measure a characteristic with inherent numerical value.

Nominal scale

Classifies variables or scores into two or more mutually exclusive categories based on a common set of characteristics; the lowest level of measurement.

Ordinal scale

Classifies and ranks variables or scores in terms of the degree to which they possess a common characteristic; intervals between ranks are NOT equal.

Interval scale

Classifies and ranks variables or scores based on predetermined equal intervals; does not have a true zero point.

Ratio scale

Classifies and ranks variables or scores based on equal intervals and a true zero point; the highest, most precise level of measurement.

Cross-sectional research

Data are collected on an individual or groups of individuals at a single point in time.

Retrospective research

Research that looks back at data collected in the past.

Prospective research

Research that follows individuals over time to collect data.

Levels of Measurement

The classification of data based on the nature of the information being collected, including nominal, ordinal, interval, and ratio scales.

Statistical analyses

Methods used to describe, associate, predict, or compare phenomena based on the level of measurement of the data.

Problem statement

A clear description of the issue that needs to be addressed in research.

Research question

A specific question that guides the research process.

Data collection

The process of gathering information for analysis in research.

Data analysis

The process of inspecting, cleansing, transforming, and modeling data to discover useful information.

Interpretation of results

The process of making sense of the data collected and analyzed in research.

Discussion of findings

The section of research where the implications of the results are explored in relation to existing evidence.

Biomedical research

Research that can be described by the time-frame used to collect data and/or by the goal of the research design.

Visual analog pain scale

An ordinal scale used to measure pain intensity.

Manual muscle test grades

An ordinal scale used to assess muscle strength.

Frequency

The number of times a particular value occurs in a dataset.

Percentage

A proportion expressed as a fraction of 100.

Median

The middle value of a dataset when it is ordered from least to greatest.

Mode

The value that appears most frequently in a dataset.

Range

The difference between the highest and lowest values in a dataset.

Mean

The average value of a dataset, calculated by dividing the sum of all values by the number of values.

Variance

A measure of how much values in a dataset differ from the mean.

Standard Deviation

The square root of the variance, representing the average distance of each data point from the mean.

Skew

A measure of the asymmetry of the probability distribution of a real-valued random variable.

Kurtosis

A measure of the 'tailedness' of the probability distribution of a real-valued random variable.

Chi Square

A statistical test used to determine if there is a significant association between categorical variables.

Phi coefficient

A measure of association for two binary variables.

Point biserial

A correlation coefficient used for measuring the relationship between a binary variable and a continuous variable.

Rank biserial

A measure of correlation used for ordinal and continuous variables.

Spearman's Rank Order Correlation

A non-parametric measure of rank correlation that assesses how well the relationship between two variables can be described using a monotonic function.

Kendall's Tau Correlation

A measure of correlation that assesses the strength and direction of association between two variables.

Pearson's Product Moment Correlation

A measure of the linear correlation between two variables, giving a value between +1 and -1.

Logistic Regression

A statistical method for predicting binary classes based on one or more predictor variables.

Discriminant Analysis

A statistical technique used to classify a set of observations into predefined classes.

Simple Regression

A statistical method that models the relationship between two variables by fitting a linear equation.

Multiple Regression

A statistical technique that uses multiple variables to predict the outcome of a dependent variable.

Descriptive Research

Research that involves collecting data about conditions, attitudes, or characteristics of subjects or groups.

Correlational Research

Research that attempts to determine the presence and magnitude of relationships between two or more variables.

Correlation Coefficient

A statistic that measures the presence and magnitude of a relationship between variables, ranging from -1 to +1.

Positive Correlation

Occurs when the correlation coefficient is greater than 0, indicating that as one variable increases, the other variable also increases.

No Correlation

Occurs when the correlation coefficient is 0, indicating that the variables are not related.

Inverse Correlation

Occurs when the correlation coefficient is less than 0, indicating that as one variable increases, the other variable decreases.

Coefficient of Determination

The square of the correlation coefficient, describing how strong the linear relationship between the variables is.

Regression Equation

Predicts how much the dependent variable will change given a specific change in the independent variable.

Retrospective Research

An investigation of data collected in the past.

Prospective Research

Recording and investigation of present data.

Descriptive Research

An investigation of several variables at once to determine existing relationships among them.

Predictive Research

Research useful to develop predictive models.

Experimental Research

Attempts to define a cause-and-effect relationship through group comparisons.

Independent Variable

The alleged cause or treatment that is manipulated in an experiment.

Dependent Variable

The effect or difference that is determined in an experiment.

True Experimental Design

Includes random assignment into experimental or control groups, with all other experiences held similar.

Cohort Design

A quasi-experimental design where subjects are identified and followed over time for changes/outcomes following exposure to an intervention.

Within Subject Design

A design where subjects serve as their own controls, randomly assigned to treatment or no treatment blocks.

Between Subject Design

Comparisons made between groups of subjects.

Single Subject Experimental Design

Involves a sample of one with repeated measurements and design phases.

A-B Design

Involves two phases: a pretreatment or baseline phase followed by an intervention or treatment phase.

A-B-A Design

Involves three phases: a baseline phase, a treatment phase, followed by a second baseline phase.

A-B-A-B Design

Includes baseline, treatment, and additional baseline and treatment phases.

Factorial Design

Refers to the number of independent variables utilized (e.g., single factor, multifactor).

Causal-Comparative Research

Attempts to define a cause-and-effect relationship through group comparisons.

Ex Post Facto Research

Research where the cause or independent variable has already occurred and cannot be manipulated.

Epidemiology

The study of disease frequency and distribution in a community.

Hypothesis

A tentative and testable explanation of the relationship between variables.

Null Hypothesis

States that no relationship exists between variables; any relationship found is the result of chance or sampling.

Statistical Significance

Occurs when the null hypothesis is rejected, indicating that a significant difference was observed between groups or treatments.

Null hypothesis

Accepted meaning that no significant difference was observed between groups or treatments.

Research hypothesis

States that a relationship between variables exists and manipulating the independent variable will bring about a change in the dependent variable.

Nondirectional hypothesis

Predicts that the dependent variable will change when the independent variable changes, but does not specify if the change will be an increase or a decrease in magnitude.

Directional hypothesis

Predicts that the change will occur in a specified direction (increase or decrease).

Selection of Sample

The selection of individuals for a study from a population. The sample represents the larger group from which they were selected.

Random sampling

All individuals in a population have an equal chance of being chosen for a study.

Systematic sampling

Individuals are selected from a population list by taking individuals at specified intervals (e.g., every tenth name).

Stratified sampling

Individuals are selected from a population from identified subgroups based on some predetermined characteristic (e.g., by height, weight, or gender).

Double-blind study

An experiment in which the subject and the investigator are not aware of group assignment.

Effect size

The size (quantity, magnitude) of the differences between sample means, allows a statistical test to find a difference when one really does exist.

Generalizability

The degree to which a study's findings based on a sample apply to an entire population.

Instrumentation Selection

Instruments are chosen with established validity and reliability.

Gold standard

An instrument with established validity can be used as a standard for assessing other instruments.

Informed Consent

A document that includes consent of an individual prior to participation in a study with full disclosure of risks and benefits, ethical disclosure.

Control

The researcher attempts to remove the influence of any variable other than the independent variable in order to evaluate its effect on the dependent variable.

Control group

The group in a research study that resembles the experimental group, but which does not receive the new or different treatment; provides a baseline for interpretation of results.

Experimental group

The group in a research study that receives a new or novel treatment that is under investigation.

Intervening variable

A variable that alters the relationship (intervenes) between the independent and dependent variable, may not be directly observable or easy to control (e.g., anxiety).

Validity

The degree to which a test, instrument, or procedure accurately measures what it is supposed to or intended to measure.

Face validity

The assumption of validity based on the appearance of an instrument as a reasonable measure of a variable; may be used for initial screening of a test instrument but psychometrically unsound.

Internal validity

The degree to which the observed differences on the dependent variable are the direct result of manipulation of the independent variable and not some other variable.

External validity

the degree to which the results are generalizable to individuals (general population) or environmental settings outside of the experimental study.

Content validity

the degree to which an instrument measures an intended content area.

Concurrent validity

the degree to which the scores on one test are related to the scores on another criterion test with both tests being given at relatively similar times; usually involves comparison to the gold standard.

Predictive validity

the degree to which a test is able to predict future performance.

Construct validity

the degree to which a test measures an intended hypothetical abstract concept (non-observable behaviors or ideas).

Sampling bias

the researcher introduces systematic sampling error (e.g., a sample of convenience) instead of random selection of subjects.