In statistics bias means ‘a tendency of an estimate to deviate in one direction from a true value’. This systematic deviation from the true value can result in either underestimation or overestimation of the effects of an intervention [7]

There are many types of bias:
Selection bias occurs when selection of the study participants results in a difference between the characteristics of those selected and those not selected. For example, if an RCT examining the effectiveness of a parent promotion program on child sleep problems recruits children and parents via volunteers responding to an advertisement, participants included in the study may be different to the general population i.e. they may be more health conscious and better educated.

Measurement or information bias occurs when measuring or collecting information. This can occur due to the participant, the study team or the measuring tools. For example in a study that needs to measure infant hearing loss, the investigators who will be measuring hearing loss will need to be trained in the same manner and follow the same protocols to ensure hearing loss is measured uniformly and accurately for all participants.

A methodological strategy to reduce the risk of bias. Blinding represents any attempt made by the investigators to keep one or more of the people involved in the trial unaware of the intervention that is being given or evaluated.
Blinding can be implemented on many levels; participants, investigators or clinicians who administer the intervention, the investigators or clinicians who take care of the participants during the trial, the investigators who assess the outcomes of the interventions, the data analysts and the investigators who writes the results of the trial [7]. If a participant is not blinded to the fact that they are taking the placebo or the intervention drug they may report their outcomes, for example pain levels, differently.

Is used in RCTs to prevent selection bias. Allocation concealment is a critical mechanism that prevents foreknowledge of assignment to the intervention or control group and thus shields those who enrol participants from being influenced by this knowledge.[8]

A provisional supposition put forth to account for a cause or an effect. For example, Socioeconomic status, maternal education and maternal vocabulary level influences children’s language development.[9]

Exposures are factors that may influence the size or occurrence of the outcome. Examples include: Will a mother smoking during pregnancy (yes, no) influence birth weight of a baby? Does duration of exclusive breastfeeding (weeks) affect development of egg allergy?

The study involves an active attempt to change a disease determinant – such as an exposure or behaviour – or the progress of a disease through treatment.[4]

The investigator measures. The investigator does not intervene and has no control over events.

Is the probability that the disease event occurs during a specified period. Estimated by the number of new cases of a disease during a specified period of time divided by the number of persons initially disease-free and therefore at risk of contracting the disease. eg. the risk of vertical transmission of HIV during pregnancy or childbirth in HIV-infected mothers given antiretroviral therapy during pregnancy.[10]

On most occasions the term intervention refers to treatment however, it can also refer to any health care element that is offered to the study participants that may have an effect on their health status. For example, preventative strategies, screening programs, diagnostic tests, educational models or the setting in which health care is provided.[7]

The people who design and carry out the study and analyse the results.[7]

The outcome is the focus of the study’s attention. It is the disease or condition of interest eg. cow’s milk allergy in children.
We are seeking to understand the outcome’s variance or occurrence eg. baby born with low birth weight (yes,no), survival time (months) following diagnosis of cancer.[10]

Sample size is calculated according to ‘power’ when the research question involves a specific comparison eg. exposed vs non-exposed. If a study is powered appropriately it will be able to detect any clinically important differences as statistically significant.[10]

Prevalence represents the burden of disease at a particular time (rather than the chance of future disease). It is based on the total number of existing cases among the whole population, and represents the probability that any one individual in the population is currently suffering from the disease [10] eg. the prevalence of asthma among children in Queensland.

is the document that outlines the study plan for a clinical research project.

RCT study participants are assigned to the intervention or the control group by chance alone. By allocating randomly, the characteristics of the participants are likely to be similar across groups at the start of the study/comparison/baseline. This allows the investigators to be more able to isolate and quantify the impact of the interventions they are studying, while minimizing effects from other factors that could influence the outcomes.[7]

Except when a full census is taken, we collect data on a sample from a larger group called the population.[10]

Sampling is the process of selecting units (eg., people, organizations) from a population of interest so that by studying the sample we may fairly generalize our results back to the population from which they were chosen.[11]

An aspect of an individual that is measured, like blood pressure, sex or age. [10]

[4] Bonita, R, Beaglehole, R, Kjellstrom, T. 2006, Basic epidemiology, 2nd Ed, WHO, Switzerland.

[7] Jadad, A, Enkin, M, W. 2007, Randomised Controlled Trials: Questions, Answers and Musings, 2nd Ed Blackwell Publishing, Carlton, AUS.

[8] Moher, D. Hopewell, S. Schulz, K. Montori, V. Gotzsche, P. Devereaux, PJ. Elbourne, D. Egger, M. Altman, Consort 2010 Explanation and Elaboration: updated guidelines for reporting parallel group randominsed trials. 2010, BMJ; 340:c869.

[9] Reilly, Sheena, Bavin, Edith L., Bretherton, Lesley, Conway, Laura, Eadie, Patricia, Cini, Eileen, Prior, Margot, Ukoumunne, Obioha C. and Wake, Melissa(2009)'The Early Language in Victoria Study (ELVS): A prospective, longitudinal study of communication skills and expressive vocabulary development at 8, 12 and 24 months',International Journal of Speech-Language Pathology,11:5,344 — 357

[10] Kirkwood, B. Sterne, J, 2008, Medical Statistics 2nd Ed, Blackwell publishing, Carlton.

[11] Trochim, William M. The Research Methods Knowledge Base, 2nd Edition. Internet WWW page, at URL: < )