13 - Research bias

Question 1

Why is it important to understand the effects of bias in research?

Answer 1

Because bias can cause:

• lack of objectivity
• form systematic errors
• create influences: opinions, decisions, conclusions

Question 2

A form of systematic error in the research process that consistently shifts results in one direction:_______________

Answer 2

Bias in research

Question 3

T or F: Bias can occur in all phases of research: planning, data collection/intervention, data analysis and publication

Answer 3

T

Question 4

Some degree of bias is __________ in a published study. However, a study ____________ according to the degree of bias

Answer 4

always present

loses validity

Question 5

T or F: To understand how bias might influence a study’s results and conclusions is essential for evidence-based practice

Answer 5

T

Question 6

Name the types of bias in Research planning:

Answer 6

• Design bias

- Selection bias (self-selection, convenient sample, non-response)

Question 7

A flawed study design is a __________

Answer 7

design bias

Question 8

Selection bias occurs during the identification of a ______________________

Answer 8

study population

Question 9

Individuals are more likely to be selected for a study than others =

Answer 9

selection bias

Question 10

Selection bias is a particular problem in which types of studies:

Answer 10

case control and retrospective cohort study

Question 11

What could be an effect of participants volunteering to participate in a study?

Answer 11

1) Self-selection or convenient sample
- Individuals select themselves into a group
- Characteristics of participants can affect the results
2) Non-response
- Consider the response rate when conducting a study

Question 12

How can we avoid self-selection and convenience sampling?

Answer 12

By doing a random selection or random sampling

Question 13

Each individual is chosen entirely by chance and each member of study population has an equal chance of being included in the sample:

Answer 13

random sampling

Question 14

How can we avoid non-response ?

Answer 14

• Keep survey short
• Provide incentives for completing the survey
• Explain why this survey is important

Question 15

What are the types of bias related to data collection/intervention?

Answer 15

• Measure bias
• Interviewer bias
• Recall bias
• Compliance bias
• Attrition bias

Question 16

Occurs when the measurement tool is not sensitive enough to detect the exposure or outcome of interest:

Answer 16

measure bias

Question 17

How to avoid measure bias?

Answer 17

Using validated measurement tools that have a high sensitivity and specificity to minimize bias

Question 18

Systematic difference between how information is solicited, recorded or interpreted:

Answer 18

Interviewer bias

Question 19

How to avoid interviewer bias?

Answer 19

Ask close-ended questions that are easy to answer vs open-ended questions

Question 20

Other things you can do to minimize interviewer bias:

Answer 20

• Training interviewers
• Standardize protocols for data collection
• Best if the interviews are blind to the experimental group and control groups

Question 21

When measuring the outcome or the exposure requires individuals to remember past events: ____________

Answer 21

Recall bias

Question 22

T or F: Outcome of treatment (good or bad) may change recollections of events

Answer 22

T

Question 23

Give some examples of diet assessment methods:

Answer 23

• Food frequency questionnaire (FFQ)
• 24-hour recall
• Dietary history

Question 24

How can we avoid recall bias?

Answer 24

• Giving the participants enough time to reflect before answering
• Using a well-structured questionnaire that has been validated against direct measures
• Verifying the reported-data by using a reference criterion (ex: medical records, data from another family member)

Question 25

Occurs when some subjects do not adhere to the planned treatment (experimental studies): _____________

Answer 25

Compliance bias

Question 26

How can we avoid compliance bias?

Answer 26

• Designing protocols that are simple and easy to follow and comply with
• Identifying subjects who are unable or unmotivated to comply (with the intervention) during the enrollment process)
• Contacting subjects frequently to maintain interest and motivation

Question 27

Occurs when subjects who leave the study (drop-outs) differ significantly from those that remain (common in cohorts and RCT):

Answer 27

Attrition bias

Question 28

How to avoid attrition bias?

Answer 28

• Using protocols to contact participants by email, post, telephone, etc
• Providing incentives (monetary gifts)
• Keeping the interviews short

Question 29

What are the 2 types of bias in data analysis and publication:

Answer 29

• Confounding bias

- Publication bias

Question 30

Occurs when an estimated association between exposure and outcome is biased by a third factor associated with both exposure and outcome: ___________

Answer 30

confounding bias

Question 31

How can we avoid confounding bias?

Answer 31

• Identified confounders can be controlled with study design (case-control or randomization) and during data analysis (regression analysis)
• Unidentified cofounders can only be controlled with randomization during participants selection and enrollment

Question 32

T or F: positive results are more likely to be reported and accepted for publication in scientific journals, than negative results

Answer 32

T

Question 33

Occurs when researchers and research sponsors are unwilling to publish unfavorable results: ______________

Answer 33

Publication bias

Question 34

It reflects a researcher’s confidence that bias is minimized or eliminated as much as possible so that the results are representative of the outcomes: __________________

Answer 34

Internal validity

Question 35

Need to consider differences between source population and study population: ________________

Answer 35

external validity

Question 36

What is external validity:

Answer 36

Degree to which findings are able to be generalized to other groups or populations