Biostatistics Case Studies



CASE 2: Variables


Clinical History:

A 62-year-old impoverished man living on a subsistence income has never received regular health care. He participates in a health screening program conducted by medical students and is found to have a random serum glucose of 201 mg/dL. On followup of this, his hemoglobin A1C is 10.3%. Based upon these findings, he is referred for vision testing.

Funduscopic Pathology:

He has a diabetic background retinopathy with extensive hard exudates as a result of microangiopathy that is associated with edema and retinal exudates that are "soft" microinfarcts or "hard" yellowish waxy exudates which are deposits of plasma proteins and lipids. The hard exudates are more a feature of older persons with type II diabetes mellitus. Also with background retinopathy leakage from small vessels leads to edema and swelling. If swelling occurs in the area of central vision (macula) then decreased visual acuity is marked.

Questions:

  1. If a study were to be performed to determine risk factors for ocular problems with this man's underlying disease, what kind of variable would be used to record demographic information?

  2. Demographic data are recorded as nominal variables. Categorical variables can be nominal or ordinal. A nominal variable is assigned (not measured) and could be a demographic characteristic such as sex or race. An ordinal variable is a ranking, such as mild, moderate, or severe.

  3. What kind of variable would be used to record his laboratory findings from a blood specimen?

  4. Quantitative variables are measured values. A discrete quantitative variable has a finite number of possible measurements. A continuous quantitative variable has an infinite number of possible measurements within a range, as would be typical for a serum chemistry test such as glucose.