Treatment-Controlled Comparative Experiment

A Treatment-Controlled Comparative Experiment is an interventional experiment that involves an experiment population division into MECE experiment groups (including a control group) and performs a comparison evaluation.

• Context:
  • It can (typically) attempt to control for Extraneous Variance, such as by confounding variables and measurement error.
  • It can (typically) involve a Controlled Experiment Analysis.
  • It can (typically) have a Null Hypothesis (that the differences are due to chance alone).
  • It can range from (typically) being a Randomized Comparative Experiment to being a Non-Randomized Comparative Treatment.
  • It can range from being a Placebo-Controlled Experiment (with negative control groups) to being an Active Treatment-Controlled Experiment (with positive control groups).
  • It can range from being a Two-Group Comparative Experiment to being a Multi-Group Comparative Experiment.
  • It can range from being a Subject-level Assignment Controlled Experiment to being a Group-level Assignment Controlled Experiment.
  • It can range from being a Posttest-Only Comparative Experiment to being a Pretest-Posttest Comparative Experiment.
  • It can range from being a Blocked Comparative Experiment to being an Unblocked Comparative Experiment.
  • It can range from being a Stratified Comparative Experiment to being an Unstratified Comparative Experiment.
  • It can range from being a Bivariate Controlled Experiment to being a Multivariate Controlled Experiment.
  • It can range from being a Blind Controlled Experiment (such as a Double-Blind Controlled Experiment) to being a Non-Blind Controlled Experiment.
  • It can range from being a Therapeautic Interventional Study (e.g. of an anti-biotic) to being a Preventive Interventional Study (e.g. of a vaccine).
• Example(s):
  • a Scientific Treatment-Controlled Comparative Experiment, such as:
    • Louis Pasteur's Spontaneous Generation Disproof Experiment [1].
    • James Lind's Scurvy Cure Experiment, 1747 [2]
  • a Organizational Treatment-Controlled Comparative Experiment, such as a:
    • a Controlled Direct Marketing Campaign.
    • an Online Controlled Experiment.
  • …
• Counter-Example(s):
  • a One-Group Experiment, such as a pretest-posttest one-group experiment.
  • an Observational Study, such as a Retrospective Cohort Study.
  • a Thought Experiment.
• See: Scientific Control, Experiment Question, Multivariate Testing, Evaluation Procedure.

---

---

References

2013

• (Wikipedia, 2013) ⇒ http://en.wikipedia.org/wiki/Control_group
  • In comparative experiments, members of the complementary group, the control group, receive either no treatment or a standard treatment.

2012

• http://prsinfo.clinicaltrials.gov/definitions.html
  • Interventional: studies in human beings in which individuals are assigned by an investigator based on a protocol to receive specific interventions. Subjects may receive diagnostic, therapeutic or other types of interventions. The assignment of the intervention may or may not be random. The individuals are then followed and biomedical and/or health outcomes are assessed.

2011

• (Wikipedia, 2011) ⇒ http://en.wikipedia.org/wiki/Scientific_control
  • QUOTE: When performing an experiment creating a unchanged and normal specimen. This includes variables i.e. environmental changes, temperature changes, and biological variation. Scientific controls ensure that data are valid, and are a vital part of the scientific method.

    An experiment which uses controls is called a controlled experiment, and usually separates research subjects into two groups: an experimental group and a control group. The control group is practically identical to the experimental group, except the fact that the experimental group is tested on using variables while the control group remains constant during the experiment.

• (Wikipedia, 2011) ⇒ http://en.wikipedia.org/wiki/Scientific_control#Controlled_experiments
  • QUOTE: There are many forms of controlled or designed experiments. A relatively simple one separates research subjects or specimen into two groups: an experimental group and a control group. The control group is practically identical to the experimental group, although the experimental group is changed according to some key variable of interest, while the control group remains constant during the experiment. Each field develops their own specific, important controls.

2010

• (Tang et al., 2010) ⇒ Diane Tang, Ashish Agarwal, Deirdre O'Brien, and Mike Meyer. (2010). “Overlapping Experiment Infrastructure: More, Better, Faster Experimentation.” In: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2010). doi:10.1145/1835804.1835810
  • QUOTE: An experiment in web search diverts some subset of the incoming queries to an alternate processing path and potentially changes what is served to the user. A control experiment diverts some subset of incoming queries, but does not change what is served to the user.

2008

• (Bailey, 2008) ⇒ Rosemary A. Bailey. (2008). “Design of comparative experiments." Vol. 25. Cambridge University Press. ISBN:1139469916

• http://www.biology-online.org/dictionary/Controlled_experiment
  • A scientific investigation in which both the control group and experimental group(s) are kept under similar variables apart from the factor under study so that the effect or influence of that factor can be identified or determined.

• http://www.drcath.net/toolkit/intervention.html
  • Intervention studies differ from observational studies in that the investigator assigns the exposure. They are used to determine the effectiveness of an intervention or the effectiveness of a health service delivery. They can also be used to establish the safety, cost-effectiveness and accceptability of an intervention. In contrast, analytical observational studies (i.e. cohort and case control studies) look at the relationships between risk factors or characteristics of patients and their likelihood of getting a particular disease. There are two types of intervention studies: randomised controlled trials and non-randomised or quasi-experimental trials.

2005

• (Freedman, 2005) ⇒ David A. Freedman. (2005). “Statistical Models: theory and practice." Cambridge University Press. ISBN:0521854830
  • QUOTE: a controlled experiment is a study where the investigators decided who will be in the treatment group.

2003

• (Jones & Kenward, 2003) ⇒ Byron Jones, and Michael G Kenward. (2003). “Design and Analysis of Cross over Trials." CRC Press.
  • QUOTE: This book is concerned with a particular sort of comparative trial known as the cross-over trial in which subjects receive different sequences of treatments.

2001

• http://www.stat.berkeley.edu/~stark/SticiGui/Text/gloss.htm#c
  • Controlled Experiment: An experiment that uses the method of comparison to evaluate the effect of a treatment by comparing treated subjects with a control group, who do not receive the treatment.

1992

• (Keppel et al., 1992) ⇒ Geoffrey Keppel, William H. Saufley, and Howard Tokunaga. (1992). “Introduction to Design and Analysis, 2nd edn." W.H. Freeman and Company. ISBN:0716723212

---