Clinical Epidemiology 3 - Abnormality

Question 1

Degree to which the data measure what they were intended to measure

Answer 1

Validity / Accuracy

Question 2

The extent to which repeated measurements of a stable phenomenon by different people and instruments get similar results

Answer 2

Reliability/ Precision

Question 3

The absolute value of the average difference of individual values from the mean

Answer 3

Standard Deviation

Question 4

Measure of central tendency which is well suited for mathematical manipulation

Answer 4

Mean

Question 5

Measure of central tendency not easily influenced by extreme values, good for skewed data

Answer 5

Median

Question 6

Frequency distribution of repeated measurements of the same physical object by the same instrument

Answer 6

Normal Distribution

Question 7

What percent of the observations in a normal distribution fall within 1 standard deviation from the mean? (-1 to 1)

Answer 7

66.66% (2/3)

To be exact, 68%

Question 8

What percent of the observations in a normal distribution fall within 2 standard deviations from the mean? (-2 to 2)

Answer 8

95%

Question 9

What percent of the observations in a normal distribution fall within 3 standard deviations from the mean? (-3 to 3)

Answer 9

99%

Question 10

Statistical definition of normality?

Answer 10

2 standard deviations from the mean

Question 11

Three definitions of abnormality in clinical epidemiology

Answer 11

Unusual (Statistically more than 2 SDF away)
Associated with disease
Treating condition leads to better outcome

Question 12

Phenomenon when abnormal test result is repeated, the second result is often closer to normal?

What is logic behind it?

Answer 12

Regression to the Mean

Abnormal test result is usually “high” (many SD away from mean) so on repeat test, higher probability of being closer to normal value