Bias and Ensuring Reliability

Question 1

• Selection bias:

Answer 1

error in the process of selecting participants for the study and assigning them to particular arms of the study.

Question 2

• Attrition bias:

Answer 2

when those patients who are lost to follow-up differ in a systematic way to those who did return for assessment or clinic.

Question 3

Measurement bias:

Answer 3

when information is recorded in a distorted manner (e.g. an inaccurate measurement tool).

Question 4

• Observer bias:

Answer 4

when variables are reported differently between assessors.

Question 5

Central tendency bias?

Answer 5

observed when a Likert scale is used with few options, and responses show a trend towards the centre of the scale.

Question 6

Recall bias?

Answer 6

is a systematic error caused by differences in the accuracy or completeness of the recollections retrieved by study participants regarding events or experiences from the past. It is sometimes also referred to as response bias, responder bias or reporting bias

Question 7

Implicit bias?

Answer 7

• Implicit Bias: an individual has subconscious attitudes and beliefs towards a topic that may influence data collection (e.g. the researcher conducting their own interviews is likely to have already formed views about the topic)

Question 8

Define accuracy?

Answer 8

how close your results are to the true value

Question 9

Define precision?

Answer 9

how close together your repeats are

Question 10

Define validity?

Answer 10

This refers to whether the conclusions drawn from a set of results are credible. Valid results rely on sound experimental design and execution. Results are considered valid if all confounding variables have been controlled, therefore, only the independent variable affected the dependent variable.

Question 11

Define reliability?

Answer 11

This refers to whether a procedure yields consistent results each time it is repeated. Carrying out repeat measurements within an investigation can improve the reliability of the results. A result is considered reliable if it can be re-produced both by the initial researcher and other scientists.

Question 12

Repeats vs replicates?

Answer 12

• Repeats are when you take the measurement more than once, replicates are when you redo the entire experiment.

Question 13

Define construct validity?

Answer 13

how accurately a questionnaire measures what you are trying to measure

e.g. how accurately does a burnout questionnaire actually measure burnout