Why do we have cut-off points?
- clinical variables are continuous, but physicians need to make dichotomous decisions
Distribution and range of normal values and cutoff points appropriate for a particular individual often depends on such factors as:
- age
- sex
- race
- occupational and environmental exposure history
- other medical conditions
- other factors that modify risk or response to therapy
Abnormal can be defined as:
- Unusual
- Associated with disease/increased disease risk
- treatment does more good than harm
- >2SD from mean of reference population
The cut-off point for abnormal is typically:
- +/- 2SD from mean of reference population.
Normal distribution:
- classic bell curve
- highest density in middle, tapers off on both sides
- mean, median, and mode all in the same place (dead center of bell curve)
Right skewed distribution:
- tail/outliers on the right of the bell; RIGHT TAIL
- highest density on the left, tapers out toward the tail
- Mode is where the bell peaks; mean is far in the tail. Median in middle.
Left skewed distribution:
- tail/outliers on the left of the bell; LEFT TAIL
- highest density on the right (where the bell is), tapers out toward the tail
- Mode is where the bell peaks; mean is far in the tail. Median in middle.
Bimodal distribution:
- think of breasts - there is a variable (like sex; M/F) under the bimodal curve
- highest density at both bells, tapers off in each direction evenly
- bimodal has two “density centers”
Mean, median, mode in relation to skew:
- Mode is insensitive to skew
- Median moderately influenced
- Mean most sensitive to skew
Standard deviation:
+/- 3SD contains –% of observations
99.7%
Standard deviation:
+/- 1SD contains –% of observations
68%
Standard deviation:
+/- 2SD contains –% of observations
95%
Distributions can be summarized by:
- central tendency
- mean, median, mode
- dispersion
- range, standard deviation, percentiles, and quartiles
A patient’s test result may fall outside the reference range for what reasons (4)?
- Analytic error
- Inter-individual variability
- Intra-individual variability
- Disease process or increased risk of disease
The three types of variables:
- nominal
- categorical: yes/no, male/female, etc.
- ordinal
- ranking (high/low)
- interval
- continuous (any number)
- discrete (counts)
The three types of variation:
- Overall variation:
- measurement variation + biological variation
- Measurement variation:
- instrument variation + observer variation
- Biological variation:
- intra-individual and inter-individual
Overall variation =
measurement variation + biological variation
Measurement variation =
instrument variation + observer variation
Biological variation =
intra-individual and inter-individual
What is considered normal?
- within 2SD of reference population mean
- not at an increased risk for an adverse event
- treatment does more harm than good
- political and cultural values
