10: Data Interpretation

Question 1

Components of Validity

Answer 1

• Internal Validity

- External Validity

Question 2

Internal Validity

Answer 2

When there has been proper selection of study groups and a lack of error in measurement. Goal is to be able to link observed effect to exposure.

Question 3

internal validity is concerned with the appropriate measurement of…

Answer 3

exposure, outcome, and association between exposure and disease

Question 4

External Validity

Answer 4

implies the ability to generalize beyond a set of observations to some universal statement

Question 5

Sources of Error

Answer 5

• Random Errors

- Systematic Errors

Question 6

Random Errors

Answer 6

reflect fluctuations around a true value of a parameter because of sampling variability

Question 7

Factors that contribute to Random Error

Answer 7

• poor precision
• sampling error
• variability in measurement

Question 8

Systematic Errors

Answer 8

measurement bias

Question 9

Poor Precision

Answer 9

Occurs when the factor being measured is not measured sharply. Can be increased by increasing sample size or the number of measurements.

Question 10

Sampling Error

Answer 10

Occurs when the sample selected is not representative of the target population. Arises when statistics obtained for sample differ from values of parent population. No way to prevent a non-representative sample from occurring, but increasing the sample size can reduce the likelihood of sampling error.

Question 11

Variability in Measurement

Answer 11

The lack of agreement in results from time to time reflects random error inherent in the type of measurement procedure employed. Goal is to obtain data that is objective, reliable, accurate and reproducible.

Question 12

Systematic Errors (Bias)

Answer 12

Deviation of results or inferences from the truth, or processes leading to such deviation. Much more serious problem for validity than random errors. Can be introduced at any point in an investigation.

Question 13

Systematic Errors grouped into…

Answer 13

• Selection Bias
• Information Bias
• Confounding

Question 14

Selection Bias

Answer 14

Distortions that result from procedures used to select subjects or influence participation in the study. Arises when the relation between exposure and disease is different for those who participate and those who would be eligible for study but do not participate.

Question 15

Information Bias

Answer 15

Can be introduced as a result of measurement error in assessment of both exposure and disease.

Question 16

Types of Information Bias

Answer 16

• Recall Bias
• Interviewer/Abstractor Bias
• Prevarication (lying) Bias

Question 17

Recall Bias

Answer 17

Better recall among cases than among controls

Question 18

Interviewer/Abstractor Bias

Answer 18

Interviewers probe more thoroughly for an exposure in a sase than in a control. Avoided through blinding.

Question 19

Prevarication (lying) Bias

Answer 19

Participants have ulterior motives for answering a question and thus may underestimate or exaggerate an exposure.

Question 20

Confounding

Answer 20

The distortion of the estimate of the effect of an exposure of interest because it is mixed with the effect of an extraneous factor. An independent variable that varies systematically with the hypothetical variable under study. Occurs when the crude and adjusted measures of effect are not equal. (Difference of at least 10% between crude and adjusted measures)

Question 21

Confounding errors can only be controlled for in the….

Answer 21

data analysis

Question 22

Criteria of Confounders

Answer 22

1. Be a risk factor for the disease
2. Be associated with the exposure under study in the population from which the cases derive.
3. Not be an intermediate step in the causal path between exposure and disease.

Question 23

Simpson’s Paradox

Answer 23

Demonstrates that association can be reversed when confounding factors are controlled.

Question 24

Reducing Selection Bias among Cases

Answer 24

• Develop explicit (objective) case definition.
• Enroll all cases in defined time and region.
• Strive for high participation rates.
• Take precautions to ensure representativeness.

Question 25

Reducing Selection Bias among Controls

Answer 25

- Compare prevalence of exposure with other sources to evaluate credibility. - Attempt to draw controls from a variety of sources.

Question 26

Reducing Information Bias

Answer 26

- Use memory aids; validate exposures - Blind interviewer, provide training, and use standardized data collection forms - Blind participants as to study goals and classification status

Question 27

Prevention Strategies

Answer 27

Attempt to control confounding through the study design itself. (Randomization, Restriction, and Matching)

Question 28

Randomization

Answer 28

Attempts to ensure equal distributions of the confounding variable in each exposure category.

Question 29

Randomization Advantages

Answer 29

convenient, inexpensive, and permits straightforward data analysis

Question 30

Randomization Disadvantages

Answer 30

need control over the exposure and the ability to assign subjects to study groups in Intervention Study, and works well with only large sample sizes.

Question 31

Restriction

Answer 31

May prohibit variation of the confounder in the study groups. Provides complete control of known confounders.

Question 32

Restriction Disadvantages

Answer 32

- unlike randomization, can't control for unknown confounders. - may shrink pool of subjects to unacceptable level. - findings may not be generalizable.

Question 33

Matching

Answer 33

Matches subjects in the study groups according to the value of the suspected or known confounding variable to ensure equal distributions. Frequency vs. Individual

Question 34

Frequency Matching

Answer 34

The number of cases with particular match characteristics is tabulated.

Question 35

Individual Matching

Answer 35

The pairing of one or more controls to each case based on similarity in sex, race, or other variables.

Question 36

Matching Advantages

Answer 36

- Fewer subjects required than in unmatched studies of same hypothesis. - May enhance validity of a follow-up study

Question 37

Matching Disadvantages

Answer 37

- Costly due to extensive searching and record keeping required to find matches. - May introduce confounding rather than control for it.

Question 38

Analysis (Statistical) Strategies to Control Confounding

Answer 38

- Stratification | - Multivariate Techniques

Question 39

Stratification

Answer 39

Evaluate the effect of an exposure with levels (strata) of the confounder. Define homogeneous categories or narrow ranges of confounding variable. Then, combine stratum-specific efforts into overall effect by statistics

Question 40

Stratification Advantages

Answer 40

- performing analyses within strata is direct and logical - minimum assumptions must be satisfied for analysis to be appropriate - computation procedure is straightforward

Question 41

Stratification Disadvantages

Answer 41

- small numbers of observations in some strata - variety of ways to form strata with continuous variables - difficulty in interpretation when several confounding factors must be evaluated - categorization produces loss of information

Question 42

Multivariate Technique

Answer 42

Computers used to construct mathematical models that describe simultaneously the influence of exposure and other factors that may be confounding the effect. Able to use continuous variables vs. categoric data.

Question 43

Multivariate Technique Advantages

Answer 43

- continuous variables don't need to be converted to categorical variables - allow for simultaneous control of several exposure variables in a single analysis

Question 44

Multivariate Technique Disadvantages

Answer 44

- potential for misuse | - people don't understand the different models and misapply multivariate techniques

Question 45

Publication Bias

Answer 45

Occurs because of the influence of study results on the chance of publication. Positive results more likely to be published than negative results. May result in preponderance of false-positive results in literature. Bias compounded when published studies are subjected to meta-analysis.

Question 46

Meta-analysis

Answer 46

combining several studies that address a set of related research hypotheses