Sampling

The Nature of Sampling

Sampling is the process of choosing a representative portion of a population or some elements in a population that will represent the entire population.

It is assumed that the characteristics of the chosen elements, called sample, reflect the characteristic of the entire population.

In the study of sampling, it is important to distinguish the following concepts: population, sampling population, sampling frame and sample.

Population, this refers to the total number of elements (e.g. items, objects, areas, or individuals) to be studied. For example: in the study: “ Sexual Attitudes and Practices of Students in Public High School of Province A”. What’s the population?----all student.

Population Element. This pertains to an item, an object, an area, or an individual on which data will be taken. It is considered the unit of study. ---a student

Sampling Population. This is the population from which a sample is actually drawn

Sampling Frame. Is the lists of all the elements or sampling units in a population. The sample is drawn from a sampling frame.

Sample. This refers to an individual, an element or a group of individuals or elements on which information is obtained. The sample is drawn from a population to which the research results are generalized.

Basic Types of Sampling

• Non-probability Sampling is arbitrary and is generally subjective
• Probility Sampling is based on the concept of random selection, a procedure that assures that all elements in the population are given equal chance of being selected as a sample unit

Non-probability Sampling examples

Accidental Sampling. the investigator selects the sample as they become available. Say a researcher want to interview 25 students about their study habits. He may stand by the door of a class room and interview the first 25 student. What’s the bias?

Purposive Sampling. The investigator uses a specific purpose in selecting a sample. Example, a researcher wants to know how grandparents feel about their grandchildren. He may select men and women who are 65 years old and above. Younger grandparents are excluded.

Probability Sampling Procedures

A. Simple Random Sampling is the process of selecting sample cases or subset of sample cases from a population, giving all the sampling unit equal chances of being included as a sample. Best example is “drawing of lots”

B. Systemetic Sampling with Random Start. Is a method of selecting a sample from a population by taking the kth units from an ordered population

Say for a study on “ Risk Behavior of Insulin-Dependent Diabetic Patients Admitted in X Hospital in Bacolod” suppose you wish to draw a sample of 15 insulin-dependent patients from 30 illegible patients (from the hospital record)

Procedure:

Population: 30

Sampling frame: List of names of eligible patients

Sampling unit: an insulin-dependent patient

Step 1: Prepare the list numbered 1 to 30 in alphabetical order

Step2: Determin the Sampling interval (K) by dividing the population by the

number of sample desired 30/15=2

Step3: Select a random Start say number 10

Step 4: from the random start take every second (interval=2) name in the list.

When you reach 30 go backto number one until you have drawn

15 numbers

C. Stratified Random Sampling. Is the process of selecting a random sample from

subgroups or strata into which a populationhas beensubdivided.

Say if I want to conduct a study examining the average annual income of adults in Talisay, by definition, my population is “adults in Talisay” this population includes a number of subgroups( e.g. men, women, retired adults, diabled adults, parent adults and single adults, etc.) These different subgroups may be expected to have different incomes. To get a n accurate picture of the income of adults in Talisay, I will selects a sample that represents the population well. This is by matching the percentage of each group in my sample that I have in my population. Say if 15 p% of the population of adults is retired, I will select a sample in a manner that included 15% retired adult. If 55% of the total population is male, 55% of my sample should be male.

D. Cluster Sampling

· a method of selecting a sample of groups of clusters of elements.

· clusters are usually exclusive sub-populations, which together comprise a population. Each cluster consists of heterogenous elements and each is typical of the population.

· for instance in a school where students in each grade level assigned to a heterogenous rather than homogenous sections, each section is considered a cluster.

· The number of clusters in the population represents the size of the population of clusters, while the number of elements in a cluster is called cluster size.

· The sample clusters can be drawn using simple random sampling or systematic sampling with a random start.

“Attitudes Towards Cheating of College Freshmen In a Private School”

· Population: 100 students divided into 10 heterogenous groups each with 10 members

· Desired Sample Size: 50 students, 5 sample clusters need to be drawn at random

· Sampling Frame: List 10 clusters / groups

· Sampling Unit: One group / cluster with10 members

E. Multistage Sampling

· a method where the selection of sample is accomplished in two or more stages.

· the N is first divided into a number of first stage units from which a sample is drawn. Then, divided further into second stage units. More stages may be added, if desired, by dividing the population into a hierarchy of sampling units corresponding to the different sampling stages.

· This process is usually used when the population in each hierarchy is considered one stage.

• “Men’s Participation in Child Care”

· Population: All the men with 0 to 6 year-old children in the province

· Desired Sample Size: 135 married men with 0 to 6 year-old children in the province

· Sampling Frame: List of men with 0 to 6 year-old children

· Sampling Unit: A man with 0 to 6 year-old children