• Population is the total group of interest target population is the group to whom researchers hope to generalize their findings. – accessible population is the group of potential research subjects who are actually available for a given study. – • • Sampling is the process by which a subgroup of subjects is selected for study from a larger group of potential subjects (population). Sampling methods influence the characteristics of the sample, which in turn influence the generalizability, or external validity, of a piece of research. Once the researcher has defined the accessible population in a general way, you needs to develop more specific inclusion and exclusion characteristics. Simple Random Sampling Drawing a sample from a cage, or even from a hat, may work fairly well when the accessible population is small. The preferred method for generating a simple random sample is to use random numbers that are provided in a table or generated by a computer. Systematic sampling is a process by which the researcher selects every (…th) person on a list. For example: We choose every ninth person or tenth person of a certain population. Or using medical record number, license number, date of birth,…… • • In a stratified sample the sampling frame is divided into non-overlapping groups or strata, e.g. geographical areas, age-groups, genders. A sample is taken from each stratum, and when this sample is a simple random sample it is referred to as stratified random sampling. For example: • • if you were interested in Internet usage you might stratify by age if you were interested in smoking you might stratify by gender or social class. Stratified sampling is used when certain subgroups must be represented in adequate numbers within the sample or when it is important to preserve the proportions of subgroups in the population within the sample. • • • • • • For example: If I want to study the total knee replacement in 8 hospitals Each hospital has different numbers of TKR per year So I need to have an equal and fair representation of each hospital in my sample My sample will be 10% of the population, and the same percent from each hospital. This some time called proportional allocation. • • Cluster sampling is the use of naturally occurring groups as the sampling units. For example, if we wanted to conduct a nationwide study. – – first sample states, then cities within each selected state, then hospitals within each selected city, and then patients within each selected hospital. Each step could be implemented through simple random, systematic, or stratified sampling. Sampling without randomization. The reason is limited funding. subject selection is confined to a available patients Three forms of nonprobability sampling are: 1. 2. 3. convenience Snowball purposive sampling. • • • Samples of convenience involve the use of readily available subjects in certain diagnostic categories at a single clinic. nonprobability method is often used during preliminary research efforts to get a gross estimate of the results Consecutive sampling is a form of convenience sampling. Consecutive samples are used in a prospective study in which the population does not exist at the beginning of the study – all patients who meet the criteria are placed into the study. This continues until a specified number of patients is collected, a specified time frame has passed, or certain statistical outcomes are seen. A snowball sample may be used when the potential members of the sample are difficult to identify or rare. In a snowball sample researchers identify a few subjects who are then asked to identify other potential members of the sample. • • Purposive sampling is used when a researcher has a specific reason for selecting particular subjects for study. A researcher wants to get opinions from nonworking mothers. They go around an area knocking on doors during the day. Their first questions are then about whether there are children and whether the woman has a day job. Assignment is the process by which subjects in the sample are assigned to groups within the study. Random assignment to groups is preferred and is appropriate even when the original selection procedure was nonrandom. assignment process is often to develop groups of equal size. Research MU 1433 Dr. Salameh Al Dajah 1. Random Assignment by Individual – – 2. This could be done with a roll of a die. Disadvantage not equal group sizes. Random Assignment by Block – – to ensure equal group sizes For example, assigning four groups of eight subjects (using random numbers table). 3. • • Systematic Assignment Researchers count off by using a list of the sample and systematically placing subsequent subjects into subsequent groups. For example, The first person was assigned to the 1st group, the second person to 2nd group, the third person to 3rd group, the fourth person to 4th group, the fifth person to the 1st , and so on. 4. • 5. Matched Assignment In matched assignment, subjects are matched on important characteristics and these subgroups are randomly assigned to study groups. Consecutive Assignment