Study power can be thought of as how likely your study will find a statistically significant difference between unexposed and exposed groups, if the exposure is actually causing this difference in disease rates. When calculating the study power for a health study looking at the relationship between exposure and disease, epidemiologists estimate the incidence rate for the unexposed and exposed groups.
| Type of Measurement | Description | How to Calculate It | Question It Answers |
| incidence | percentage of a population that develops a particular disease over a period of time | dividing the number of new cases by the number of people in the population at risk over a period of time | how many people have been newly diagnosed with the disease during this period of time? |
| prevalence | percentage of a population that has a particular disease at a given point in time | dividing the number of existing cases by the number of people in the population at risk at a given point in time | how many people have the disease at this point in time? |
Incidence is useful for certain health outcomes that happen as a single episode or event, such as an asthma hospitalization or a cancer diagnosis. Incidence is useful during investigations of diseases with relatively short durations, such as a food borne illness or infectious disease.
Prevalence is useful for measuring how many people have a chronic disease of long duration and relatively stable conditions, such as asthma or diabetes. Prevalence is also applicable for rarer chronic diseases in which it would be difficult to accumulate a large number of new cases developing in a specific time period, such as multiple sclerosis.
Epidemiologists must be careful when comparing prevalence between an exposed and unexposed group, and then trying to draw associations between exposure and disease. With prevalence, it is often hard to distinguish between factors that affect occurrence of the disease, versus those which increase the number of people who survive having a disease. For example, an increase in prevalence of a disease in a population may be due to improved access to optimal care and treatment for this disease, and not due to decreased exposure to a hazardous substance.
| Disease | Specific Population | Annual Incidence: New cases per 100,000 population per year |
Prevalence: Existing cases per 100,000 population |
 |
| brain cancer | US population | 6 | 38 | 01 |
| breast cancer | US population | 128 | 803 | 02 |
| leukemia | US population | 12 | 70 | 03 |
| diabetes (type 2) | US population | 698 | 6,933 | 04 |
| parkinson's disease | US population | 17 | 167 | 05 |
| alzheimer's disease | US population | 120 | 1,667 | 06 |
| chronic kidney disease | US population: over 20 years old |
--- | 8,667 | 07 |
| end stage renal disease | US population: over 20 years old |
34 | --- | 08 |
| infertility | US population: reproductive age |
--- | 10,000 | 09 |
| birth defects or mental retardation at birth |
California population: births |
3,030 | --- | 10 |
| asthma | California population: children |
--- | 8,600 | 11 |
| asthma hospitalization | California population | 100 | --- | 12 |
Data on both prevalence and incidence rates for certain diseases, such as different types of cancers, are routinely collected on a nationwide basis. For other health outcomes, such as infertility, only prevalence data is widely collected for a large population; while for other health outcomes, such as asthma hospitalization, only incidence data is collected.
When calculating study power, epidemiologists predict incidence rates for exposed versus unexposed groups. Epidemiologists sometimes base these predictions on relative risks reported in previous studies.
Epidemiologists must be careful when comparing prevalence between an exposed and unexposed group, and then trying to draw associations between exposure and disease. With prevalence, it is often hard to distinguish between factors that affect occurrence of the disease, versus those which increase the number of people who survive having a disease. For example, an increase in prevalence of a disease in a population may be due improved access to optimal care and treatment for this disease, and not due to decreased exposure to a hazardous substance.
Here are specific examples of how much the rate of disease increased due to exposure according to health studies conducted in the past. The "% Greater Risk" column compares the risk of disease in exposed versus unexposed populations.
| Exposure | Disease | Relative Risk | % Greater Risk | |
| asbestos (household) | mesothelioma | 8 | 700 | 13 |
| asbestos (neighborhood) | mesothelioma | 7 | 600 | 13 |
| smoking | lung cancer (men) | 23 | 2,200 | 14 |
| smoking | lung cancer (women) | 12.7 | 1,170 | 14 |
| secondhand smoke | lung cancer | 1.26 | 26 | 15 |
| secondhand smoke | SIDS | 1.4 | 40 | 16 |
| maternal smoking | SIDS | 4.7 | 370 | 16 |
| benzene (occupational) | leukemia | 3.37 | 237 | 17 |
| benzene (occupational) | multiple myeloma | 4.09 | 309 | 17 |