Lesson 4.2 Finals Comm 18

COMMUNICATION RESEARCH (COMM 18) LESSON 4: FINALS PART IV: THE THESIS PROPOSAL Identifying the Sample, Selecting The Appropriate Sampling Method, & Determining the Desired Sample Size

IMPORTANT CONCEPTS IN SAMPLING



Population or universe refers to the total number of people that we want to study. It is a subpopulation of the total number of people in a given geographical area. Sample refers to the people we choose to represent the population. It is a subset of the population that is taken to be a representative of the entire population. The key term is representative. The representatives of the sample depends upon the sampling scheme used in choosing the sample.

TYPES OF SAMPLING A. Probability Sampling
Provides every member of the population (N) a chance to be chosen as part of the sample (n). 1. Simple Random Sampling – basic type; each subject or unit in the population has an equal chance of being selected.
Random Sampling without Replacement – if a subject or unit is drawn from the population and removed from subsequent selections.
Random Sampling with Replacement – involves returning the subject or unit into the population so that it has a chance of being chosen on another time. 2. Stratified Sampling – when a researcher is interested in a particular characteristic, segment or stratum of the population. Instead of selecting a sample from the population at large, the researcher identifies a significant variable, selects subjects who have this trait and chooses a subsample from this group. The variable of interest might be age, sex, religion, education, income or political affiliation. Incidence is used to describe the frequency with which the desired subjects can be found in the population. Stratified sampling ensures that a sample is drawn from a homogenous subset of the population, that is, from a population with similar characteristics. Homogeneity helps researchers to reduce sampling errors. 3. Cluster Sampling – selecting a sample in groups or categories. (e.g. geographical in nature – state into districts, countries or zip code areas and select groups of people from these areas)

4. Stage Sampling – individual household or persons are selected, not groups. In this type of study, researchers determine which person in the household should answer the questionnaire by using a form of random numbers table. To get a random selection of individuals in selected households, the interviewer simply asks each person who answers the telephone, “How many people are there in your home who are age 12 or older?” 5. Systematic Sampling – every nth subject or unit is selected from the population; randomly selects a starting point and a sampling interval. To add further randomness to the process, the researcher may randomly select both the starting point and the interval. The degree of its accuracy depends on the adequacy of the sampling frame or on a complete list of the members of the population. B. Non-probability Sampling Method 1. Available Sample – is a collection of readily accessible subjects for study such as a group of students enrolled in an introductory mass media course. 2. Volunteer Sample 3. Purposive Sample includes subjects selected on the basis of specific characteristics or qualities and eliminates those who fail to meet these criteria. 4. Quota Sample – subjects are selected to meet a predetermined or known percentage.

USAGE OF PROBABILITY AND NON-PROBABILITY SAMPLE Determinants: 1. 2. 3. 4.

Cost versus value – the sample should produce the greatest value for the least investment. Time constraints Purpose of the study Amount of error allowed

DETERMINATION OF SAMLE SIZE 1. Determine the population to be studied. One way to do this is to ask the project manager to specify the characteristics of the project beneficiaries to be studied. 2. Determine as precisely as possible the population or universe to be covered by the survey. 3. Prepare a sampling frame which is a list of file of all the units in the universe. It might be a list of all regions, provinces, municipalities, and/or villages to be covered by the survey. 4. Determine the desired sample size (n) by: a) using the table of random numbers, b) determining the variables to be studied and c) choosing certain criteria . 5. Select the appropriate sampling scheme depending upon the available time, money, manpower and information.