Applied Biostatistics for the Health Sciences. Richard J. Rossi
in a specific range of values. For example, the distribution of a qualitative variable is usually displayed in a bar chart with the height of a bar representing either the proportion or percentage of the population having that particular value.
Example 2.12
The distribution of blood type according to the American Red Cross is given in Table 2.4 in terms of proportions.
Table 2.4 The Proportions of Blood Type and Rh Factor
| Blood Type | Rh Factor | |
|---|---|---|
| + | − | |
| O | 0.38 | 0.07 |
| A | 0.34 | 0.06 |
| B | 0.09 | 0.02 |
| AB | 0.03 | 0.01 |
An important proportion in many biomedical studies is the proportion of individuals having a particular disease, which is called the prevalence of the disease. The prevalence of a disease is defined to be
For example, according to the Centers for Disease Control and Prevention (CDC) the prevalence of smoking among adults in the United States in January through June 2005 was 20.9%. Proportions also play important roles in the study of survival and cure rates, the occurrence of side effects of new drugs, the absolute and relative risks associated with a disease, and the efficacy of new treatments and drugs.
A parameter that is related to a population proportion for a quantitative variable is the pth percentile of the population. The pth percentile is the value in the population where p percent of the population falls below this value. The pth percentile will be denoted by xp for values of p between 0 and 100. Note that the percentage of the population values falling below xp is p. For example, if the 10th percentile is 2.2, then 10% of the population values fall below the value 2.2.
Percentiles can be used to describe many different characteristics of a population including the extreme values in the population, the typical values in the population, and the spread of the population. Commonly used percentiles include the
deciles that are the 10th, 20th, 30th, 40th, 50th, 60th, 70th, 80th, and 90th percentiles.
quartiles that are the 25th, 50th, and 75th percentiles.
quintiles that are the 20th, 40th, 60th, and 80th percentiles.
The 50th percentile is called the median, and the median will be denoted by μ~. The median is a measure of the typical value in the population and is a very important parameter for distributions that have long tails. The median also plays an important role in the following studies:
ID50 study that is designed to determine the median dose to infect a subject.
LD50 study that is designed to determine the median lethal dose of a toxic material.
LC50 study that is designed to determine the median lethal concentration of a toxic material.
IC50 study that is designed to determine the median inhibition value of a drug.
EC50 study that is designed to determine the median concentration of a compound required to obtain the maximum effect in vivo.
Example 2.13
In studies investigating the prevalence of overweight and obesity among adults and children, the body mass index (BMI) is a commonly used measure of obesity. The formula for BMI is
Adults with BMI values exceeding the 85th percentile are classified as overweight. Children are classified according to the BMI breakdown given in Table 2.5.
Table 2.5 The Weight Classifications for Children Based Upon BMI
| Classification | BMI Range |
|---|---|
| Underweight | BMI < 5th percentile |
| Normal weight | 5th percentile ≤ BMI < 85th percentiles |
| At risk for overweight | 85th ≤ BMI ≤ 95th percentiles |
| Overweight | BMI > 95th percentile |
Also, according to the article “Varying body mass index cutoff points to describe overweight prevalence among U.S. adults: NHANES III (1988 to 1994)” published in the Journal of Obesity (Kuczmarski et al., 1997)
The percentage of the population with BMI < 19.0 is 1.6% for men, 5.7% for women; BMI ≥ 19.0 to < 25.0 is 39.0% for men, 43.6% for women; BMI ≥25.0 is 59.4% for men, 50.7% for women. An estimated 97.1 million adults have a BMI ≥>25.0. Additional prevalence estimates based on other BMI cutoff points and ages are presented.
A BMI calculator that computes BMI for any height and weight values and determines the percentile of the resulting BMI value can be found at the website http://www.halls.md/body-mass-index/bmi.htm.
2.2.4 Parameters Measuring Centrality
The two parameters in the population of values of a quantitative variable that summarize how the variable is distributed are the parameters that measure the typical or central values in the population and the parameters that measure the spread of the values within the population. Parameters describing the central values in a population and the spread of a population are often used for summarizing the distribution of the values in a population; however, it is important to note that most populations cannot be described very well with only the parameters that measure centrality and the spread of the population.
Measures of centrality, location, or the typical value are parameters that lie in the “center” or “middle” region of a distribution. Because the center or middle of a distribution is not easily determined due to the wide range of different shapes that are possible with a distribution, there are several different parameters that can be used to describe the center of a population. The three most commonly used parameters for describing the center of a population are the mean, median, and mode. For a quantitative variable X.
The mean of a population is the average of all of the units in the population, and will be denoted by µ. The mean of a variable X measured on a population consisting of N units is
The median of a population is the 50th percentile of the population, and will