GCU Core Quantitative Designs
Design Description General Requirements

Experimental

Designed to demonstrate unambiguous cause-and-effect relationship between variables

Determines if there is an effect/outcome of some form of treatment(s) using random assignment of subjects to treatment and control groups. Includes a manipulation of an independent variable to determine its effects
  • Two or more equivalent groups to receive one or more treatments and a control group
  • Random assignment of subjects to each of the groups
  • Standardization of all aspects of research procedures employed to ensure conditions are the same for all participants (i.e. the control for all variables other than the manipulated variable)
  • Conducted with rigorous control with clearly defined treatments
  • Categorical independent variables and interval or ratio level dependent variables

Quasi-experimental

Designed to demonstrate cause-and-effect relationship between variables.  Does not meet all requirements of an experimental design, thus cannot produce an unambiguous cause-and-effect explanation.

Determines if there is an effect/outcome of some form of treatment(s) using pre-existing groups of subjects assigned to treatment and control groups
  • Two or more nearly-equivalent groups to receive one or more treatments and a control group
  • Typically no random assignment -participants are in pre-existing groups or groups that are naturally formed
  • Inclusion of participants in the control or treatment group is determined by conditions beyond the control of the researcher
  • Conducted with similar rigor and control as experimental studies with clearly defined treatments
  • Requires categorical independent variables and interval or ratio level dependent variables
  • Design contains a confounding variable or factor that prevents the research from obtaining an absolute cause-and-effect answer

Non-Experimental

Attempts to demonstrate associative relationships between variables but does not attempt to produce an unambiguous cause and effect explanation.

 

Descriptive(Survey) Describes the opinions, attitudes, or trends of a population numerically
  • Provides a description of individual variables but not concerned with the relationship between variables
  • Uses a process of surveying a sample to generalize to the population
  • Research may be longitudinal or cross-sectional
  • Returned sample should be hundreds or thousands of surveys in order to generalize to the population
  • Requires at least ordinal or interval level variables
  • Could also be classified as qualitative descriptive depending on the design and collected data
Correlational Determines if there is an empirical relationship between two or more variables on a single group of participants with the intent of predicting or defining a relationship
  • Observes relationships between variables in a naturally occurring setting.
  • Includes two or more variables that can be measured quantitatively
  • Valid approaches to data collection such as validated surveys or databases
  • There is a theoretical or logical explanation that can be used to predict a correlation
  • Requires ordinal or interval level data for variables of interest
  • Variables should not or cannot be manipulated
  • Could also be a quasi-experimental study if designed as such

Causal

Comparative

Determines the causes of differences that already exist between or within two or more groups on two or more variables
  • Identify one or more groups that serve as independent variable
  • Define the dependent variable on which the groups will be compared
  • Requires at least one categorical variable and ordinal or interval level dependent variables
  • Select sample groups that are as homogeneous as possible
  • Could also be a quasi-experimental study if designed as such
Qualitative descriptive A relatively simple phenomenon is described 
  • Does not clearly fit into one of the other designs
  • Phenomenon has been clearly defined
  • Uses two forms of qualitative data collection (typically, interviews a minimum of 15, and may use a second form of data collection such as field notes or questionnaires.
Phenomenology The  essence of a “lived” experiences described by the participants who experienced them are synthesized to describe the phenomenon (from  philosophy and psychology)
  • Phenomenon has been defined to be a “lived” experience and focuses on how the participants find those experiences to be meaningful. Participants must have an experience in common, such as experiencing the death of a child, or living with cancer.
  • Sample has to have the experience in common
  • Focus is on the meaning and description the sample makes of the experience. Must be able to deal with emotional reactions.
  • Reality will be the described phenomenon that results from a conscious experience
  • In-depth interviews are the primary data collection tool, but may use two forms of qualitative data collection (typically 10-15 in-depth interviews); may use essays or other reflective processes); researcher needs to make detailed field notes following each interview
Narrative Stories are told by the participants in an interactive fashion with the researcher with the intent of creating a unified narrative or story  that describes or explains a life episode (from humanities)
  • Phenomenon is defined as a story of an event which will be better understood including causality and relationships
  • Typically uses in-depth interactive interviews with 8-12 individuals who are telling “their individual story”
  • May use other story-telling techniques such as creating timelines of events, etc.
Case Study An in-depth analysis of  a one or more cases which can be a process, program, activity, city event, or person, using a number of data collection approaches (from business)
  • Phenomenon is defined as a process, program, activity, city event, or person studied over a specified time period, which is analyzed
  • Three to five sources of data (forms of data collection) realize triangulation and depth of analysis
  • May include both qualitative and quantitative data collection and analysis.
  • A multi-case study may include up to 10 cases 
  • Typically includes focus groups/interviews with 5 to 15 individuals, and may include observations, document collection, and/or additional forms of data collection
Grounded Theory A theory or model is developed to describe the phenomenon as a concept, process, interactions, components, or actions (from sociology)
  • A theory or model is developed to describe the phenomenon
  • Involves multiple stages of collecting data often using multiple approaches and multiple groups
  • Typically includes iterative interviews, observations, document collection, and questionnaires with various groups. Data are collected until saturation is achieved, denoting lengthy periods of time in the field.
  • May include both qualitative as well as quantitative data collection and analysis.
  • Typically includes collecting a large volume of data either by larger samples or repeated  (iterative) collection from individuals.

 

GCU Recommended Core Research Designs
Quantitative Both Qualitative
 
  • Experimental
  • Quasi-Experimental
  • Non-Experimental
    • Descriptive (Survey)
    • Correlation
    • Causal Comparative
Mixed Methods
(Not Recommended)
  • Descriptive
  • Phenomenology
  • Narrative
  • Case Study
  • Grounded
  • Theory
  • Research designs can be considered along a continuum.
  • Different approaches or sub-designs are possible for each methodology/design.
  • Classification of experimental or quasi-experimental or non-experimental depends how the study is designed.  For example, correlational or causal comparative research could be classified as quasi-experimental, if the study is designed as such.
  • GCU does not recommend using traditional mixed methods because of the extra time and skill development required for this methodological approach.
  • GCU does not support action research because of timing and theoretical foundation issues; a case study of an action research project may be recommended as an alternative.