Descriptive Method - Group 3.Docx

Descriptive Method

DESCRIPTIVE METHOD Concerned with the description of data and characteristics about a population Characterized as a survey or normative approach to the study of conditions GOAL: acquisition of factual, accurate and systematic data Focus on answering 5Ws

Values of Descriptive Studies1. Descriptive studies are of great value in providing facts on which professional judgements may be based. 2. Descriptive studies contribute to science because they afford penetrating insights into the nature of what are dealt with and perhaps what to study. When there is a need or wish to develop more complex forms of scientific understanding, these descriptive facts are fitted into more complex frames of relationship.

Values of Descriptive Studies3. Descriptive studies provide essential knowledge about the nature of objects and persons and they contribute again and again at recurring intervals as science grows from one cycle or level of insight to another. 4. Descriptive studies help fashion many tools for science. Specifically in the development of measuring instruments for quantitative research.

TerminologyDESCRIPTIVE RESEARCH Studies that imply to present facts concerning nature and status of anything. Best (1963) defined descriptive research as something that describes and interprets what is. NORMATIVE STUDIES Those which establish standards through the study of what is prevalent.

TerminologySURVEY The common way of gathering data. Good (1973) defined Normative Survey as an investigation designed and conducted to ascertain the facts concerning the present status.

Descriptive Survey

Descriptive Survey The general procedure employed in studies. Its significance lie in the possibility of investigating the status of conditions at any given time and repeating the survey at a later date, thus providing descriptions or cross-sections at different periods of time in order that comparisons may be made. Many survey-status studies emphasize present conditions with an implication that things will change.

Descriptive Survey An adequate survey requires a carefully pretested questionnaire, group of interviewers trained in its use, a sample carefully selected to ensure that the respondents are representative of the population to be studied, and appropriate methods of data analysis so that the results are properly interpreted.

Relation of Survey Studies to Other Techniques Survey and Case Studies may serve complementary and supplementary purposes the survey approach fits appropriately into the total research scheme

Descriptive Survey Studies as Research carries forward the particular project does not only provide answers to questions but also furnish excellent illustrations in the areas represented main purpose is to describe, explain and validate findings

Causal-comparative Study type of research which discovers what, how and why a phenomenon happens compares the similarities and differences to find out what factors or circumstances seem to contribute to the occurrence of such event

Sampling Process

SAMPLING the process of choosing a representative part of the population under study.

Typical or representative of the population means that a part of the population is chosen in such a manner that the characteristics and variations are reflected.

SAMPLE a limited but representative subset of a population. It must be adequate in size in order to be reliable. Population may consists of attributes, qualities or behavior of people, the behavior of inanimate objects such as dice or coins, cities or city blocks, households or dwelling structures, the days output of a factory, or opinions of the electorate of an entire nation.

SAMPLING FRAME is a population list from which the sample is to be chosen.

Why Use Sampling? The researcher can gain accurate knowledge about a population by measuring only a portion or sample of it.

Cost limitations in terms of effort, time, and money are usually important considerations in social research.

Two Types of SamplingPROBABILITY SAMPLING is one in which every element of the population has a chance of entering the sample. NON-PROBABILITY SAMPLING that is, the accidental and the quota sampling does not give any knowledge as to the probability of any person in the population being included in the sample.

Probability Sampling

SIMPLE RANDOM SAMPLING Each person in the population has an equal probability of being included. When Should Simple Random Sampling Be Used? When one wants to generalize as to the whole population from which the sample is drawn or if the population is not scattered, that is, it is more or less homogenous with respect to the characteristics under investigation and a good frame is available or can easily be constructed.

STRATIFIED RANDOM SAMPLING The researcher or analyst divides the population into two or more strata on the basis of one or more characteristics. Each stratum then is treated like a different population, and simple random samples are drawn from each. These subsamples are then combined to form the total sample. When Should Stratified Random Sampling Be Used? When it is known in advance that a special segment of the population would not have

TWO TYPES OF STRATIFIED RANDOM SAMPLING 1.Proportionate Sampling Sample sizes are proportional to the population size 2.Disproportionate Sampling Sample sizes are NOT proportional to population size

SAMPLING BY REGULAR INTERVAL Is the selection of cases at regular intervals from a series, alphabetical list, or any other arbitrary arrangement.

CLUSTER SAMPLING When the population from which a sample is to be drawn is very big and is distributed over a large area. This means that the population is the same at it is when individuals are being sampled. When Should Cluster Sampling Be Used? When the population to be sample is very large. It requires a population list or a dwelling-unit map of the city or town but not for the entire country.

Tools for Sampling

The most common assumptions in sampling theory and practice are the availability of census data such as population lists, residence lists, or dwelling-unit maps. Another problem of sampling on the basis of population lists is ending up with respondents who live great distances apart. If population or residence lists are not available the most obvious solution is for the researcher to draw up his/her own list.

One alternative is to use dwelling-unit maps of the area although there are some areas where obtaining a map is not a simple matter. If dwelling- unit maps are not available, the researcher who has time and money to spare can draw accurate maps from a survey of area. Once a map is obtained or drawn each residence is given a number, a list of the numbers drawn up and the sample of dwelling-units is arrived at as in simple

The type of person to be interviewed in a particular dwellingunit must be chosen beforehand. It may be better to limit the individuals to be interviewed to those who represent the household.

Size of the Sample

The size of a sample must likewise strike the appropriate balance. It must be large enough to do the job but small enough to be workable. Cost and accuracy should be considered when determining the size of the sample. The researcher must consider the cost of the entire survey, not only the cost of data collection.

The sample size must take into account the usable resources of the person who is conducting the survey. In sampling, greatest precision will be achieved when the entire population is tested and inversely, as the proportion sampled gets smaller, so will the precision of the results be diminished. The researcher must achieve a balance between the cost and accuracy.

Non- Probability Sampling

ACCIDENTAL SAMPLING This type of sampling has no system of selection. Accidental Sampling is the easiest to use but it is usually not representative of the population from which it is drawn. Only individuals met by the researcher are included.

When Should Accidental Sampling Be Used? Almost never, or only when no alternative is available. If is method is used, one must kept in mind its lack of representativeness.

QUOTA SAMPLING Each interviewer is given a number of persons of a specific type to interview. The person who will be interviewed is decided upon the interviewer in the field. Problem associated with this sampling technique: Consider the representativeness of a sample drawn. The way in which the interviewer obtains the sample (major threat to representativeness)

When should Quota Sampling be used? When the analyst knows exactly what type of person he wants to interview. Used only when probability sampling is not possible.

Advantages Interviewer is designed to include desired numbers or proportions of different types of persons. Doesnt require population lists or dwelling-unit maps. Disadvantages Doubts about the representativeness of the population.

CONVENIENCE SAMPLING Process of picking out people in the most convenient and fastest way Contacts people and asks them what their reactions are to the issues at hand.

Certainly biased and not representative

PURPOSIVE or DELIBERATE SAMPLING Also called judgemental Determining the target population or those to be involved in the study. (Respondents) chosen on the basis of their knowledge of the information desired Deliberate selection of individuals based on certain pre-defined criteria.

SNOWBALL SAMPLING This type of sampling, also called networking, involves asking subjects to provide names of others who may meet study criteria. It is often used when researchers do not have access to a population.

Difficulties in Sampling1. If the sampling plan is not correctly designed and followed. 2. If the characteristics or distinguishing feature to be observed occurs only rarely in the population. 3. When detailed classification of the sample data is called.

Difficulties in Sampling4. When sampling requires expert advice. 5. There are characteristic limitations for each type of sampling. 6. Complicated sampling plans.

Planning a Sampling Survey1. Statement of the purpose of the survey 2. Definition of the population or universe 3. Selection of the sampling unit and the unit of tabulation 4. Location and selection of the source list

Planning a Sampling Survey5. Deciding on the type of sampling to be used 6. Determining the size of the sample or the sample ratio 7. Testing of the sample in pilot or exploratory surveys 8. Interpretation of the data in the light of the reliability of the sample

Light, et al. (1989) point out that; Random sample is far more important than a large sample.

Small random samples almost always give more accurate results than large but nonrandom samples.

Descriptive MethodThank You for Listening!