Randomized field trials (RFTs) are “situations in which individuals or entire organizations are randomly assigned to one or two or more interventions” (Mosteller, Frederick, Robuch, & Robert F., 2002, p. 2). The assigned groups do not differ from each other and do not have hidden factors that would influence the research to sway in any way. By choosing RFTs, researchers know that the comparison of the relative effectiveness of the interventions will be fair. Furthermore, the results will be unbiased if this method is followed correctly. An example of when to use RFTs would be when looking at programs or services. One could ask the question: “Is one service more effective than another?” and do a randomized trial to determine an unbiased answer. In education, RFTs are used to usually review policies. The benefits of RFTs is that they permit an objective and unbiased answer in relatable language (p. 183). The disadvantages are that they are costly, and as with many other types of research, there are ethical issues connected to working with participants (p. 187).  

Mosteller, F., & Boruch, R. F. (2002). Evidence matters: Randomized trials in education research. Washington, D.C: Brookings Institution Press.
By: Natasha

A randomized-controlled study (RCT) is a study design that randomly assigns participants to an experimental group or a controlled group in order to assess the effectiveness of interventions (Fortin & Gagnon, 2016, p. 233).  In other words, RCT refers to experimental studies in which examine the effects of interventions on participants.  Researchers therefore measure and compare the results between the control and experimental groups during a study.  RCT is considered as “the gold standard of many educational researchers, as it purports to establish controllability, causality, and generalizability” (Cohen, Manion & Morrison, 2007, p. 277).  RCT and randomized trials are occasionally used synonymously; however, a RCT has a control group whereas it is absent in a randomized trial (Fortin & Gagnon, 2016, p. 233).

 

            A comparison study measuring the effects of contacting parents or not when students have incomplete homework assignments (experimental group / control group). Will contacting parents (intervention) increase or encourage homework completion?

 

References

 

Cohen, L., Manion, L., & Morrison, K. (2007)  Research methods in education (6^th ed.) [Electronic version]. New York, NY: Routledge Publishing.

 

Fortin, M.-F., & Gagnon, J. (2016). Fondements et étapes du processus de recherches : méthodes quantitatives et qualitatives (3rd ed.). Montreal, QC : TC Média Livres Inc.

True randomization refers to the way in which participants (or subjects) are assigned to a study group.  It is used to minimize selection bias by using, for example, statistical computer programs to assign participants to groups.  When participants are assigned to study groups using randomization, there is equal probability for each individual to have the same chance at being placed in any of the groups within the study. 

Suresh. K.P. (2011). An Overview of Randomization Techniques: An Unbiased Assessment of Outcome In Clinical Research. Journal of Human Reproductive Science. 4(1): 8-11.
By: Sheela

 

- Participants are chosen to be in a study but not necessarily random as to where they are placed

- Quasi means “resembling” so this resembles a true experiment

Bad à Risk of selection bias / Researcher knows who is where

Good à Easier to make generalizations about a sample

 

http://www.bandolier.org.uk/booth/glossary/RCT.html   

Candace

By: Sheela

The limitations of this study is that it does not allow for complete randomization, or a full and complete representation of all of a population, since only a certain portion of the population are of interest. [2] However; in many cases, especially in the field of health and education, there are specific parameters that participants must meet in order to actually be able to contribute to the data collection in a study. Purposive sampling is also a more cost effective way of sampling, you can specifically look for individuals willing to participate with a certain set of desired requirements, rather than take large numbers of random participants. [2]

[1] Etikan, Ilke, Abubakar Musa, Sulaiman, Sunusi Alkassim. Rukayya. (2016)  Comparison of Convenience Sampling and Purposive Sampling. American Journal of Theoretical and Applied Statistics.  5(1): 1-4

 

[2] Hoeven, Loan R., Janssen, Mart, Roes, Kit, and Koffiber, Hendrik. (2015) Aiming for a respresentative sample: Simulating random versus purposive strategies for hospital selection. BMC Medical Research Methodology. 15 (90): 1-9 
 By: Keri

A limitation to convenience sampling is that strong generalizations cannot be made about a study’s findings, and it would obviously also pose some issues with bias. [1]  Convenience sampling also may eliminate unique cases, or “outliers” from the data trends. [1] However, convenience sampling is more financially feasible, and not as time consuming as other methods of sampling that may be more randomized. [1]

[1] Etikan, Ilke, Abubakar Musa, Sulaiman, Sunusi Alkassim. Rukayya. (2016)  Comparison of Convenience Sampling and Purposive Sampling. American Journal of Theoretical and Applied Statistics.  5(1): 1-4

By: Keri

Participants recruit more participants to be involved.

The snowball keeps “rolling” until a sample size is found.

Good – Finding participants for sensitive or unacceptable topics (cheating or illegal substances, religion, politics)

Bad – Relies on referrals and can have ethical concerns

 

 

Crossman, Ashley. "What Is a Snowball Sample in Sociology?" ThoughtCo, Jul. 12, 2017, thoughtco.com/snowball-sampling-3026730

By: Candace

 

- The researcher uses their own judgment to select participants

- The researcher deliberately chooses based on the participant’s profile

- Participants can be chosen for their expertise, unique characteristics, viewpoints, age or gender

Good à Easy for making generalizations

Bad à Others may find it bias / not representative

 

https://research-methodology.net/sampling-in-primary-data-collection/purposive-sampling/

By: Candace

Sheela

Definition: The control is a group that does not receive any treatment or intervention by the researchers. The control group is used as a benchmark to examine how the experiment measures up to and can be compared to the group that was tested on. 

Example: Literacy support intervention could be an example of how to incorporate a control group. The experiment could be looking at the impact of literacy support among students of similar level and ability. One group would be the control group and one group would be the experimental group. After the literacy support intervention is complete with the experimental group, the results are compared to the control group.

By: Sara

It is a process by which the population is subdivided into smaller homogeneous groups (strata) in order to acquire more accurate sample representation (Fortin and Gagnon, 2016, p. 267).  That is, the population is divided into subgroups or strata according to common attributes or characteristics.  Certain characteristics, such as age, sex, racial origin, geographic location or socioeconomic status, may provide a basis for choosing a stratified sample (p. 267).  However, it is important to note that the characteristics must be clearly identifiable in the study population. This method of sampling selection is therefore used when the population is heterogeneous.   

A school district superintendent would like to assess teachers’ attitudes towards N.B. Policy 322: inclusive education.  It is possible that the teaching level (elementary, middle, and high school) is an important variable to consider as elementary teachers may feel differently towards inclusive education than teachers at the middle or high school levels.  The superintendent would therefore want a sample that reflects a representation of the three teaching levels.  Stratified sampling would allow this to happen as the population can be divided into subgroups (elementary, middle, and high).

Reference

Fortin, M.-F., & Gagnon, J. (2016). Fondements et étapes du processus de recherches : méthodes quantitatives et qualitatives (3rd ed.). Montreal, QC : TC Média Livres Inc.

BY: James