Table 1

Types of research bias

Design biasPoor study design and incongruence between aims and methods increases the likelihood of bias. For example, exploring HIV testing using a survey is unlikely to obtain in-depth rich data about individuals’ experiences. Bias can occur when a researcher's personal beliefs influence the choice of research question and methodology. For example, a researcher working for a pharmaceutical company may choose a research question which supports the usefulness of the drug being investigated
Selection/participant biasSelection bias relates to both the process of recruiting participants and study inclusion criteria. Successful research begins with recruiting participants who meet the study aims. For example, recruitment bias could occur if participants were invited to participate in a survey posted on the internet, which automatically excludes individuals without internet access
Inclusion bias in quantitative research typically relates to selecting participants who are representative of the study population, and where applicable allocation of participants to ensure similarity between comparison groups. In addition, accounting for the differences between people who remain in a study and those who withdraw may be important in some study designs. For example, an evaluation of a weight loss programme may be affected by participant withdrawal; participants who become disillusioned because of not losing weight may drop out, which may bias the findings towards more favourable results. Confounding bias can also occur because of an association between ‘cause’ and ‘effect’. For example, comparing treatment outcomes for similar conditions between general and specialised centres may find higher mortality rates at specialised centres yet patients referred to these centres are more likely to have high-risk factors and more complex needs
In qualitative research, it is usual to recruit participants with a range of experiences in relation to the topic being explored; therefore, accounting for biases in relation to the sampling strategies is essential. For example recruiting parents from a parent and toddler group is likely to be biased towards mothers; the findings are unlikely to represent both mothers’ and fathers’ perspectives
Data collection bias and measurement biasData collection bias can occur when a researcher's personal beliefs influence the way information or data is collected
In quantitative studies, measurement bias can occur if a tool or instrument: has not be assessed for its validity or reliability (eg, using a shared decision-making tool that measures patient satisfaction rather than decision-making); is not suitable for the specific setting or patient groups (eg, using an adult verbal pain assessment tool with young children); an instrument not calibrated properly may consistently measure inaccurately (eg, weighing babies with poorly calibrated weighing scales)
In retrospective studies, for example, when completing questionnaires about eating habits when data collection relies on recall, participants may not remember and report events accurately
In qualitative research, interviewing is a commonly used method of data collection; how questions are asked will influence the information elicited. For example a leading question, “Do you find the health service poor?”, is likely to receive a closed yes or no response, and not gain insight into participants experiences and could be replaced with; “Please describe your last visit to hospital?”
Analysis biasWhen analysing data, the researcher may naturally look for data that confirm their hypotheses or confirm personal experience, overlooking data inconsistent with personal beliefs
Publication biasPublished studies nearly always have some degree of bias. For example, in quantitative research, studies are more likely to be published if reporting statistically significant findings.5 Non-publication in qualitative studies is more likely to occur because of a lack of depth when describing study methodologies and findings are not clearly presnted6