Research Design

Research Designs. The design used is specified at the start which should be clear and appropriate the design is an arrangement of conditions for collection and analysis of data in amanner that is relevant to and will best address the research purose and with minimum expenditures of effort, money, and time.

Basic Research Designs

1.       Descriptive Studies. They aim to describe the charactereistics of a particular individual, people, situation or group or the frequency with which a phenomenon occure or is related with some other factors.

They are concerned with estimating the frequency of given occurences of the proportion of people holding to certain views or behaving in certain ways.

They are also concerned in discovering, testing, or predicting whether certain factors are related/associated with each other.

2.       Experimental Studies. They seek to test causal relationships often draw from the logic of experiments and attempt to approximate the design of Experimental Studies.

True experimental studies allow the researchers to:

·         Have complete control over the introduction of X, the experimental or independent variable;

·         Randomly assign the research subjects into the study’s experimental and control group;

·         Systematically obtain measures of Y, and other characteristics among subjects in both experimental and control groups and before and after the experiments; and

·         Have control over all other conditions of the experimental study;

·         The experimental design enables researcher to observe closely the X-Y relationship and to rule out with confidence the influence of other factors on the said relationship.

3.       Historical Studies. They seek to establish the veracity of the written records of the past.

The following table may be used in choosing the suitable research design.

Table 1

Matrix of Research Goals and types of Research Designs

RESEARCH GOALS	TYPES OF RESEARCH DESIGN
1.       To understand the nature, characteristics, components, or other aspects of the phenomena	Descriptive Research Examples of this type are: Case study, survey research, Library research, Field Research, Documentary analysis, Content analysis, and Participatory research
2.       To uncover data on phenomen that are not yet fully know; to surface information for possible formulation of hypothesis	Explanatory Research Examples: Library Research, Documentary Research, Survey research, Case Study, Field research
3.       To explain the relationship between variables, between phenomena; -          To test causal relationships; to determine the true cause and true effects; -          To predict the relationship between two variables; the change in one is the cause of or brings about the change in the other.	Experimental Research Examples: Pre-experimental, classical, quasi-experimental, causal-comparative
4.       To initiate and experiment with ta new set-up or system and determine results, this can be replicated-repeated in other situation.	Action Research Example: Experiment, Survey research, case study, Participatory research
5.       To assess the impact, effects, results, outcomes, of operation, policies, programs, behaviour, assessment of the processes or operations involved.	Evaluation Research Policy research, Survey, Case, Field, and Participatory research
6.       To generate information relevant to the development and formulation of policy; assessment of effects, outcomes, impact of policies.	Survey, Field, Library, Documentary, Historical, Descriptive, Experimental, Evaluation
7.       To determine the factors for the success or ciability of a planned course of action	Feseability Research Survey, Library Research
8.       To determine the relationship or association of variables not necessarily in terms of cause and effect.	Correlation Research Case; Field study
9.       Explanatory-causal-non-experimental	Cross-sectional study, Case control

Statistical Treatment of Data

Types of Statistical Tolls/Treatment	When to Use in research
1.       Frequency Count with Frequency Percent	-When certain proportions of the population based on certain variables such age, height, income, etc. are desired to be known.
2.       Measures of Central Tendency (Medium, Mean, and Mode)	-When the typical, normal or average is desired to be known.
3.       Weighted Mean	-When the variable being studied are abstract or continuous such that they can’t be counted indicidually sucj as adequacy, extent, excellence, seriousness.
4.       Measures of variability (range, quartile, deviation, Average Deviation or Standard Deviation)	When the variability of the population is desired to be known such as homogeneity and heterogeneity
5.       Ranking, Quartile or Percentile Rank	When the relative placements of scores or positions are desired
6.       Chi-Square of Equal Probability-single group	When the significance of the trend of reaction or opinnions of persons as a group toward a certain issue, situation, value or thins is desired to be known.
7.       Chi-square of Equal Probability two groups	When the significance of the difference between the reactions or opinions of two distinct groups on which there is neutral position is desired to be known
8.       Coefficient of Correlation	To determine how are variables vary with one another
9.       T-test of Significance	If the significance of the difference between the perceptions of two groups about a certain situation is to be studies
10.   Analysis of Variance (ANOVA) (Comparing two groups)	To determine the relative effectiveness of the different ways of doing things to which different randomized groups are respectively exposed to and only a post test is given to the different groups.
11.   Partial and Multiple-Correlation	To determine the effects of some variables upon a single variable to which they are related.
12.   Chi-square of independence	To determine the association between the two independent variables

Table 2

Matrix on the Use of Statistical Techniques

Variables	Interval	Ordinal	Nominal
Interval	Multiple Correlation Pearson “r”	Spearman’s rho x2 Convert I→0 I→N; 0→N	ANOVA
Ordinal	Spearman’s rho x2 Convert I→0 I→N; 0→N	Spearman’s rho Kendall’s tau	Friedman’s 2 way ANOVA
Nominal	ANOVA	Friedman’s 2 Way ANOVA	X2 test of goodness of fit X2 test of independence

        Procedures. It outlines the reaserch plan. It decribes in detail what will be done; how it will be done, what data will be needed, and what data gathering devices will be used. It decribes the actual steps carried out in conducting the study.

        Sources of Data. The report should include appropriate information on the sample and the sources of evidence. To be valid the investigation must make use of the second hand information which can be exat or incomplete bur of primary source materials.

        Data Gathering Instruments. A description of the adapatation, construction and administration of instruments should be included. Instruments include tests, questionnaires, interview, guides and or schedules. Apparatuses, devised and laboratory equipmenst should be described. In the case of complex or custom made equipment, a drawing or photograph may be useful.

        Collection of Data, according to Source.

        Primary- data coming from the original sources of materials and are collected especially for the task at hand.

        Secondary Data- data or information obtained from the works of other persons who have collected them fof other purposes. Organizations files and library holdings are the most frequent used secondary sources but statistical compendia, movie film, printed literature, audio tapes and computer files are also widely used sources.

        DATA PROCESSING. It is a means of converting information either manually or by machine. This involves the following phases:

        Data Coding. It is a process of grouping the responses to a question into categories and assigning numbers, characters, and/or other symbols called codes.

        Principles of Data Coding

1.       Appropriateness

2.       Single concept

3.       Exhaustiveness

4.       Exclusiveness

5.       Adequacy

Data Matrix- or a roster of data is actually a sheet on which data are written in columns.

Important points to Consider.

1.       If categorical data are being recorded, the number of individual scoring in each category are tallied.

2.       If quantitative data are being recorded, the data are usually listed in one or more columns, depending on the number of groups involved.

Results and Findings

                In this section, summarize the collection of data and the statistical treatment applied to them. The result should be presented in straight forward and unbiased way. The presentation must be geared to the research questions and the research hypotheses.

Summary, Conclusion and Recommendations

                This last chapter contains the overview of the research. It gives a brief statement of the problem, the procedures and findings. In making recommendation, the researcher should avoid making opinionated statements and suggestions not supported by evidence.

SYNTHESIS

1.       The title should be clear and concise.

2.       The problem should be clearly stated and properly delimited. The significance of the problem and the scope and limitation of the study should be clearly stated and hypothesis testable.

3.       The review of theories, literature and studies should create a unified theme to a line of though throughout the review. They must be adequately covered, the findings noted, well organized, effective summary and the literatures, studies and theories cited must be directly relevant to the problem.

4.       The research design must be described in detail, adequate samples described and the relevant variables are recognized. The data gathering technique should be appropriate, the validity and the reliability of the instruments established.

5.       The results should be stated clearly, statistically treated with the appropriate use of tables and figures. There should be a logical perspective and objective analysis and interpretation on the relationships of effects between or among variables. Discussion must be clear and concise.

6.       Bibliographical entries should follow the correct format. E.g. title of books and journal should be highlighted, unpublished theses/dissertations no highlight.

SAMPLES OF BIBLIOGRAPHICAL ENTRIES

BIBLIOGRAPHY

A.      BOOKS

Alano, Patricio, Management of Human Behavior in organizations, Manila, National Bookstore, 1992

Andres, Thomas, Management by Filipino Values, New Day Publishing, Quezon City, 1995.

B.      JOURNALS AND PERIODICALS

Putman, J. J. “Quicksilver and Slow Death” National Geographic, 1972.

Waldichuck, M. “Lead in the Environment” Marine Pollution Bulletin, 1980.

C.      UNPUBLISHED MATERIALS

Alcala D., “Personality Dimensions and Status of Elementary School Principals as Related to their level of Job Satisfaction in the Division of Quezon”, Unpublished Masteral Thesis, PNC, 1988.

Dela Cruz, Vilma C., “Effects of Leaderships Styles and Socio Economic Status of Public High Schools Department Heads on Teachers’ Job Satisfaction and Job Performance”, Unpublished Master Thesis, Bulacan State University, 1996.

DESIGNING RESEARCH INSTRUMENTS

A.      Guidelines in the formulation of questions for a questionnaire.

1.       Make all directions clear and unequivocal

2.       Use correct grammar.

3.       Make all questions unequivocal

4.       Avoid asking biased questions

5.       Call for objective responses

6.       Relate all questions to the topic under study.

7.       Create categories or classes for approximate answers

8.       Group questions in logical sequence

9.       Create sufficient number of response questions.

10.   Word carefully or avoid questions that deal with confidential or embarrassing information

11.   Explain and illustrate difficult questions

12.   State all questions affirmatively.

13.   Make as many questions as would supply adequate information for the study

14.   Add a catch-all word or phrase to options of multiple response questions

15.   Place all spaces for replies at the left side

16.   Make the respondents anonymous.