Ans. is 'c' i.e., Berksonian bias Selection bias Selection biases are distoion that result from procedure used to select subjects and from factors that influence study paicipation. Groups to be compared are differentially susceptible to the outcome even before the experimental maneuver is performed. Selation bias may be of following types. 1. Surveillance/detection bias A potential aifact in epidemiologic data caused by the use of a paicular diagnostic technique or type of equipment. For example, cancer rates may vary in different regions or periods, not because of an actual difference in the incidence of disease but because of different diagnostic technologies. If diagnostic test is being used in one region is more sensitive than other region, the cancer rates will be high in that region even without the existance of an actual difference. 2. Neyman survival bias (Incidence-Prevalence bias) This type of bias is due to missing of fatal cases, mild cases or cases of shoer duration from the study. For example, in a study of breaset cancer, we can choose two different types of cases : ? Incident cases - All breast cancer patients newly diagnosed during a given time. Prevalent cases - All breast cancer patients who are alive during a given time frame. These can lead to different results, because the probability of finding a case in given time frame is related to moality risk. Those patients who hay a mild form of disease and survive for a relatively long time have a good chance of being around on the date of data collection. Those patients who die quickly are unlikely to be around on that date. 3. Referrel bias or volunteer bias Volunteer or referral bias occurs because people who volunteer to paicipate in a study (or who are referred to it) are often different than non-volunteers/non referrel. This bias usually ors the treatment group, as volunteers tend to be more motivated and concerned about there health. 4. Response bias Occurs when those who respond to a survey differ in impoant ways from those who do not respond. This bias can work in either direction, i.e., if bias occurs, when those who do not respond to a survey differ in impoant ways from those who respond, it is called nonrespondent bias. 5. Berkesonian bias Berksonian bias results from the greater probability of hospital admission for people with two or more disease than for people with one disease. So, it is also known as admission rate bias. For example, If breast cancer is the exposure of interest (diseases are often treated as exposures in hospital based case-control studies) and meningioma is the case disease then people with both breast cancer and meningioma could be hospitalized for either breast cancer or mengioma or both. However, people with only breast cancer or with only mengioma could be hospitalized because of one of these disease. Therefore, a greater propoion of people in the community with both breast cancer and meningioma would be admitted to the hospital than would people with meningioma only. So, Berksonian bias occurs when both exposure (e.g., breast cancer in above example) and disease (e.g., meningioma in above example) affect selection.