1. Stratified sample
1.1. The population is divided into homogeneous subgroups or strata, based on a common characteristic or criterion, and then a random sample is taken from each of these strata
1.2. Characteristics
1.2.1. The population is divided into subgroups (strata) that are internally homogeneous
1.2.2. A random sample is selected from each stratum
1.2.3. The sample of each stratum can be proportional to the size of the stratum in the population or equal in size
1.3. Advantages
1.3.1. Ensures representation of different subgroups within a population
1.3.2. Improves the accuracy of results
1.4. Disadvantages
1.4.1. If the strata are not defined correctly or are not grouped appropriately, the method could introduce bias into the sample
1.4.2. For large populations or when there are many strata, the process can become logistically complicated and costly
2. Cluster sample
2.1. Involves dividing a population into groups, or clusters, and randomly selecting some of the clusters to study
2.2. Characteristics
2.2.1. The population is grouped into clusters, which generally represent natural subpopulations
2.2.2. The clusters, each representing, in theory, the diversity of the entire population
2.3. Advantages
2.3.1. Often used when population is geographically spread out
2.3.2. Facilitates the organization and execution of the study, especially when the population is not well defined individually but in groups
2.4. Disadvanges
2.4.1. If the clusters are not truly representative of the entire population, biased results may be obtained
3. Balanced sample
3.1. The sample is designed according to a target variable and is forced to have a certain composition according to a predefined criterion
3.2. Characteristics
3.2.1. Ensures sample proportions closely match those of the population
3.2.2. Reduces sampling variability
3.2.3. Minimize bias associated with under- or over-representation of certain groups or characteristics
3.3. Advantages
3.3.1. Allows greater control over the sample structure
3.3.2. Ensures that the sample is more representative of the population in terms of key variables, which improves the accuracy of inferences
3.4. Disadvantages
3.4.1. If the population is very large or the variables are many, it can be difficult to balance all the important characteristics effectively
3.4.2. Data are lost
4. Simple random sample with replacement (SRSWR)
4.1. Involves selecting a smaller group of participants (the sample) from a larger group of participants (the population)
4.2. Characteristics
4.2.1. All elements of the population have the same probability of being selected in each extraction
4.2.2. The selected elements are returned to the population before the next extraction, so that the same element can be selected several times
4.2.3. The selections are independent of each other, since the population remains constant in size and composition.
4.3. Advantages
4.3.1. The size and characteristics of the population are not altered with each extraction
4.3.2. The possibility of bias in the sample is reduced
4.3.3. Maintaining behavior in the data
4.4. Disadvantages
4.4.1. The sample may include duplicates, which may not be useful in some analyses
4.4.2. Inefficient for large populations
5. Simple random sample without replacement (SRSWOR)
5.1. Involves selecting a smaller group of participants (the sample) from a larger group of participants (the population)
5.2. Characteristics
5.2.1. All units in the population have the same probability of being selected
5.2.2. The number of units in the sample is predefined and the available population is reduced as items are selected.
5.2.3. Once units have been selected, they cannot be re-selected for the sample
5.3. Advantages
5.3.1. Biases are minimized and the representativeness of the sample is increased
5.3.2. Generate a representative population sample, facilitating generalizations
5.4. Disadvantages
5.4.1. Can be inefficient for large populations
5.4.2. May not be representative if population has significant subgroups
6. Sistematic sample
6.1. Researchers select members of the population at a regular interval
6.2. Characteristics
6.2.1. Divides the population into intervals and selects one element from each interval according to a fixed sequence.
6.2.2. The sampling interval is calculated by dividing the population size by the desired sample size
6.3. Advantages
6.3.1. By selecting the elements uniformly throughout the population, a more homogeneous distribution is ensured
6.3.2. Low probability of data contamination
6.4. Disadvantages
6.4.1. Overrepresentation or underrepresentation of particular patterns
6.4.2. Greater risk of data manipulation