Saturday, January 26, 2008

SAMPLING SIZE --- Part 15

Sample size for a given population size.
(Read Krejcie and Morgan (1970), ‘Determining sample size for research activities’, Educational and Psychological Measurement, 30, 607-10; and Cohen (1969), ‘Statistical Power Analysis for the Behavioural Sciences, New York, Academic Press.

Number---Size------Number-----Size--------Number------Size
---10-------10----------220-------140----------1200-------290
---15-------14----------230-------144----------1300-------297
---20------19-----------240-------148----------1400-------302
---25------24-----------250-------152----------1500-------306
---30------32-----------260-------155----------1600-------310
---35------40-----------270-------159----------1700-------313
---40------36-----------280-------162----------1800-------317
---45------40-----------290-------165----------1900-------320
---50------44-----------300-------169----------2000-------322
---55------48-----------320-------175----------2200-------327
---60------52-----------340-------181----------2400-------331
---65------56-----------360-------186----------2600-------335
---70------59-----------380-------191----------2800-------338
---75------63-----------400-------196----------3000-------341
---80------66-----------420-------201----------3500-------346
---85------70-----------440-------205----------4000-------351
---90------73-----------460-------210----------4500-------354
---95------76-----------480-------214----------5000-------357
--100------80----------500-------217----------6000-------361
--110------86----------550-------226----------7000-------364
--120------92----------600-------234----------8000-------367
--130------97----------650-------242----------9000-------368
--140-----103----------700-------248---------10000------370
--150-----108----------750-------254---------15000------375
--160-----113----------800-------260---------20000------377
--170-----118----------850-------265---------30000------379
--180-----123----------900-------269---------40000------380
--190-----127----------950-------274---------50000------381
--200-----132---------1000------278---------75000------382
--210-----136---------1100------285--------1000000-----370

Thursday, November 22, 2007

NEED ANALYSIS ........... Part 14

DEFINITIONS:

Every research undertaking will foremost begin with the need to clearly understand what exactly is the cause of the pressing problem or pressing issue and exactly who is affected. Need analysis is the process of identifying and evaluating such needs in the community or other defined population of people. The identification of needs is a process of describing “problems” of a target population and possible solutions to these problems. A need has been described as:

------• A gap between “what is” and “what should be.” (Witkin et al., 1995)
------“A gap between real and ideal that is both acknowledged by community values and potentially amenable to change.” (Reviere, 1996, p. 5)
------• May be different from such related concepts as wants (“something people are willing to pay for”) or demands (“something people are willing to march for”). (McKillip, 1987)

Need analysis usually focuses on the future, or what should be done, rather than on what was done as is the focus of most program evaluations. Some people also use the related term “needs assessment”.

STEPS and EXAMPLES:

The focus here is entirely on “gap” or need analysis. The following steps are suggestions from McKillip, 1998.

1.----First, you identify the audience and purposes for the need analysis (what McKillip, 1998, calls the users and uses).

2.----Second, you fully describe the target population and service environment. Altschuld et al. (2000) point out three levels of target groups and their respective needs:
------------Level 1--- (Primary) targets are the direct recipients of the

--------------------------services;
------------Level 2--- (Secondary) targets include the individuals or groups

--------------------------who deliver the services; and
------------Level 3--- (Tertiary) involves the resources and inputs into the

--------------------------solutions (e.g., buildings, salaries, facilities, etc.).

These researchers emphasize that the focus of the Need analysis should be on Level 1 because that is the reason for the existence of levels 2 and 3, not the other way around.

3. The third step is need identification where descriptions of the problems (beyond the general level noted in step 1) and possible solutions are generated. This is where you illustrate the gaps between expected/ideal and actual outcomes. You want to gather information from more than one level of target, although you should focus on the primary targets.

4. The fourth step is called needs assessment by McKillip (1998). This is the time to evaluate the identified needs. Which are the most important? Do any of the needs conflict with other needs? Is there consistent agreement across levels of target groups about the relevance and importance of the needs?

5. Finally, you communicate your results to the audience identified in the first step.

Wednesday, November 21, 2007

CHOICE OF METHODS ......... Part 13

Choice of research methods to be used is very much determined by how much information you know about the subject at hand.

Little information or----------------------------------------------------------------------Extensive information or
knowledge of situation---------------------------------------------------------------------knowledge of situation
(or research topic)----------------------------------------------------------------------------(or research topic)

<-------------------------------------------------------------------------->
EXPLORATION-------DESCRIPTIVE----------HYPOTHESIS TESTING
* Observation--------* Structured interview---* Structured
* Unstructured-------* Structured focus--------- questionaire
--interview------------ group--------------------* Field Experiment
* Unstructured-------* Questionaire------------* Laboratory
--focus group---------------------------------------experiment

STILL KICKING STRONG towards 2008..................... I HOPE!

It is very rewarding to note that this blog is still being referred to by my postgraduate students since my last posting in 2006. Do not hesitate to post comments, enquiries or request for more info regarding Research Methodology, I'll try my best to answer.

-
Better still, ....... do come and join me naturetracking into the Tropical Rainforest. More exciting Nature's wisdom to be learned and explored!

Monday, August 21, 2006

RESEARCH METHODS ............Part 12

Again and again I've haunted by my students seeking for approval on which method to use in their research proposal. There is no one right answer to this, because it depends very much on your research title and your research hypothesis. If you are seeking for an understanding, an explaination about something not yet known, then the Qualitative method will be your consideration. If knowledge about it is already known, but you need to proof, clarify, validate or predict, than Quantitative Method will be more appropriate. Some research titles might require the application of both methods. Discuss this further with your supervisors.


RESEARCH METHODS

A. QUALITATIVE - DESCRIPTIVE

Survey Research
- A common method used in business, sociological and government. Surveys are used to describe the incidence, frequency, and distribution of certain characteristics in a population.
- Purpose is to explore and describe

Developmental research
- An observational-descriptive type of research that either compares people in different age groups (a cross-sectional study) or follows a particular group over a lengthy period of time (a longitudinal study). Such studies are particularly appropriate for looking at developmental trends.
- includes longitudinal studies (goes forward in time) such as trend (from general population), cohort (random from a group of people) and panel studies (from same selected samples)
- Documentary analysis, and follow-up studies (goes back in time)

Case Studies
- A type of qualitative research in which in-depth data are gathered relative to a single individual, program, or event, for the purpose of learning more about an unknown or poorly understood situation.
- involves direct observation or interviews

Ethnography
- A type of qualitative inquiry that involves an in-depth study of an intact cultural group in a natural setting
- The scientific description and classification of the various cultural and racial groups of humankind. The study of observed behaviour in a natural context

Historical Research
- An attempt to solve certain problems arising out of a historical context through the gathering and examining relevant data
- deals with the past, from informations recorded in the past, in order to draw conclusions about the past and past events.
- Deals with Critical and Interpretive Sciences, and draws conclusions about the past

Philosophical Research
- Ask value questions
- Deals with Critical and Interpretive Sciences.

Action Research
- A type of applied research that focuses on finding a solution to a local problem in a local setting. For example, a teacher investigates whether a new spelling program she has adopted leads to improvement in her student’s achievement scores.
- A deliberate, solution-oriented investigation that is group or personally owned and conducted. The process through which practitioners study their own practice to solve their personal practical problems.
- Characterized by spiraling cycles of problem identification, systematic data collection, reflection, analysis, data-driven action taken, and, finally, problem redefinition.

Content analysis
- A detailed and systematic examination of the contents of a particular body of material (e.g., television shows, advertisements, textbooks) for the purpose of identifying patterns, themes, or biases within that material.

Grounded theory research
- A type of qualitative research aimed at deriving theory through the use of multiple stages of data collection and interpretation.

Observational study
- A type of quantitative research in which a particular aspect of behavior is observed systematically and with as much objectivity as possible.

Phenomenological research
- A qualitative method that attempts to understand participant’s perspectives and views of social realities


B. QUANTITATIVE

Correlational research
- A statistical investigation of the relationship between two or more variables. Correlation research looks at surface relationships but does not necessarily probe for causal reasons underlying them. For example, a researcher might investigate the relationships amongst high school seniors’ achievements test scores and their grade point average a year later when they are first-year college students.
- Compares two or more different characteristics from the same group of people
- Shows how two characteristics vary together (explain), and how well one can be predicted (predict) from knowledge of the other
- Two types:
- Current correlational studies
- Predictive correlational studies

Experimental Research
- A study in which participants are randomly assigned to groups that undergo various researcher- imposed treatments or interventions, followed by observations or measurements to access the effects of the treatments.
- Purpose is to probe cause and effects (“if/then”), establish casualty; its purpose is to control
- Research deliberately manipulates a treatment (independent variables) to see if it causes a change in the dependent variables (effects).
- Two types:
- True experiment research
- Quasi-experimental research
- A method similar to experimental research but without random assignment to groups.


Ex post facto (relational / associational)
- An approach in which one looks at conditions that have already occurred and then collects data to investigate a possible relationship between these conditions and subsequent characteristics or behaviors
- a relational study (explain/predict) which substitute for an experimental study
- Look for natural “cause” without researcher manipulation of the independent variables (treatments)


Phew! That is quite a bit to swallow in one gulp!!!!

Thursday, March 03, 2005

WHERE'S THE DIFFERENCE??? ... PART 11

HOW IS A POSTGRADUATE RESEARCH DIFFERENT FROM A DOCTORAL RESEARCH?

A frequently-asked-question (FAQ) that students bug me all the time. In short, it is a continuation of knowledge enquiry, the first to establish and confirm the significance of the research issue, while the later is to finally develop a tested, proven and novel solution/ knowledge.

No matter what, both requires:-

LITERATURE REVIEW

a) Describe the background work of other researcher in the area, to
establish the 'state-of-the-art' prior to the author's research effort, and

b) To appraise critically previous work undertaken and to put that work in
perspective in relation to its importance



POSTGRADUATE RESEARCH PROPOSAL
Clearly state:

a) WHAT WAS THE PROBLEM?
(I don't know yet but it is about gaining more knowledge)
b) WHAT DID YOU DO?
(Consolidate and synthesis knowledge in a novel way)
c) WHAT DID YOU FIND OUT?
(A new classification of processes, new typology of terms, a new
morphology and a new set of rules that could be applied when teaching
this subject)
d) WHAT IS THE SIGNIFICANCE OF YOUR FINDINGS?
(Professional: increase profitability, improve designs
Educational: new course structure, advice to the profession)


PHD. RESEARCH

A PhD. is said to occur as a result of RIGOUR and SCHOLARSHIP and is usually concerned with:

STUDIES: Analysis, Synthesis, Design, Formal Methods of statistical
analysis, Case studies, Model changes in the target population)

EXPERIMENTATION: Validation of results, Interaction with experts

CONCLUSION: Intellectual property, New knowledge, New insight, New
Rules, Original outcome, Contribution to knowledge, and
applying the results of your research to reality.

COLLECTING THE DATA .... Part 10

DATA COLLECTION:

Just remember this: no research is considered a research if it is NOT DOCUMENTED on paper.

No matter how much books, journals or research papers you have read, or the countless numbers of prominent respondents you have interviewed, if it is still stored in your head, how could convince your supervisor that you have done research. Nobody will ever believe you…….period.

You need to translate all the new knowledge gained during your research into writing, no matter how insignificant, or jumbled-up the grammar is or how topsy-turvy the sequence is, your supervisor still needs to see it on paper, because he is not a mind-reader…… or a clairvoyant. (Today, there is no more excuse, because no matter how busy your supervisor is; you can at any time e-mail him your research data, even at 3 o’clock in the morning.). If you continually make it a practice to submit to him one page of text a day, INSYAALLAH…. you’ld easyly end up with 120 pages of document at the end of the semester withouthout feeling the pinch.

The Data collection methods differs greatly from one type of research methodology to another, and for this it is vital that you familiarize yourself (read from the library), with the specific requirements , (and quote it all into your Methodology Chapter) so that the issue of validity and reliability of the data collected will not be in question later on. It will be a tremendous waste of valuable time if you jump straight to do your field work prior to truly checking that the data collection methodology is not suspected of being BIAS or UNRELIABLE. At the data collection stage, you MUST NOT be seen or be suspected of manipulating or influencing how the final outcome of the research finding will be. Report and analyze the finding as is, do not tamper with the data, because as a researcher it is unethical to do so. As a researcher, leave you personal value judgment aside till the final conclusion chapter; let the data itself reveal to you its true colour. If the final data happens to contradict with your hypothesis, so be it…. that’s the actual truth.

Few research undertakings will fit in exactly as prior planned; but most often the Murphy’s Law will prevail somehow. Report everything that happened during the data collection, including the problem encountered and how you overcome the obstacles…. all that happening is your true research activity that you must share (in writing) with the readers.

Reliability of data through interviews does not rely on hearsay information but comes from the genuine primary source and not from secondhand information. Authentication of manuscript reference in historical research must be verified, and not from photocopied version. When quoting from a person, you must validate the authority and the trustworthiness of the person who says it. All supporting evidence can be incorporated into the appendix section of your thesis for verification if needed.

Make it a habit to record when, what and how the data was collected, and not to procrastinate, because if not done immediately, it is definitely forgotten forever, and I can guarantee you that you will find that to be the most important facts needed to support your thesis writing later. I make it a habit to make sure that all these important data about the source is recorded first before I start copying the quotation from a book. As a researcher, have at all time your tape cassette recorder and your digital camera ever ready in your bag, you’ll definitely need it handy at the most unsuspected moment.

It is a fact that our memory is extremely short-span and you can hardly remember in exact detail the events that happened 4 days ago, let alone one semester from now when you start doing the thesis writing-up. Writing, writing and writing right away, is still the order of the day, and there is no escape from this ever as long as you profess yourself to be a researcher.

Thursday, September 30, 2004

The junction..... PART 9

AT THE CROSSROAD, WHERE TO TURN?

So sorry if it appears to be seen as one-sided, very much in favour towards the quantitative approach so far..... that was not done on purpose. It is also equally important for me to also highlight on the other approach of research method, i.e. the historical, the ethnographic, observational and developmental studies, the action research, and of most recent is the practice-based research specifically geared for us artists and design practitioners.

The Qualitative approach is very much of inductive type where we DO NOT start of with a hypothesis or problem statement, but rather of probing and into the situation and trying to understand the phenomenon. Through induction, we might eventually observe and establish a new pattern or regularities of knowledge that can lead to the development of new theory.

Inductive reasoning works the opposite way to Quantitative by moving from the specific observation to broader generalized theories. Informally, we sometimes call this a "bottom up" approach. In inductive reasoning, we begin with specific observations and measures, begin to detect patterns and regularities, formulate some tentative hypotheses that we can explore, and finally end up developing some general conclusions or theories.


INDUCTIVE REASONING

.................................................................Theory
.........................................Tentative...... /
.......................................Hypothesis -----/
.......................Pattern ----/
Observation ---/


Deductive reasoning works from the more general to the more specific. Sometimes this is informally called "top-down" approach. We might begin with thinking up a theory about our topic of interest. We then narrow that down into more specific hypothesis that we can test. We narrow down even further when we collect observations to address the hypothesis. This ultimately leads us to test the hypothesis with specific data - a confirmation (or not) of our original theories. The disadvantages of deductive approach is that the entry-point begins with an already establish information, which might not opens us up to any possibility of a new insights or a more lateral research to the situation.


DEDUCTIVE REASONING

Theory --\
..............Hypotheses -- \
.....................................Observation ---\
............................................................Confirmation




These two methods of reasoning have a very different "feel" to them when you are conducting research. Inductive reasoning, by its very nature is more open-ended and exploratory, especially at the beginning. Deductive reasoning is more narrow in nature and is concerned with testing or confirming hypotheses. Even though a particular study may look like it is purely deductive (e.g. an experiment designed to test the hypothesized effects of some treatment on some outcome), most social research involves both inductive and deductive reasoning processes at some time in the project.

We could assemble the two flow diagrams above into a single circular one that continually cycles from theories down to observations and back up again to theories. Even in the most constrained experiment, the researchers may observe patterns in the data that lead them to develop new theories.
In short the difference of the Qualitative and Quantitative approaches can be summed up as follows:

QUALITATIVE .................................QUANTITATIVE

‘Complex' rich data.............................. 'Simple' numeric data
Meaning .................................................Measurement
Understanding ......................................Explanation
Interpretation .......................................Prediction
Contextual account ...............................Generalisable account
Purposive/representative, .. ..................Representative,
perspective sample ....................., ...........population sample
Exploratory ............................................Hypothesis-testing
Accepts subjectivity ..............................Claims Objectivity
Open System (ecological validity) .......(experimental control)




A high quality research is characterised by:

1. It is based on the works of others - providing a basis for what and how you might conduct your own.

2. It can be replicated. - produces the same results when replicated, and can serve as a basis for same research in the same area.

3. For Quantitative research, it is generalizable to other setting. - i.e. the result would probably stand up (generalizable) in a different, but related setting. However, a Qualitative is not intended to be generalizable but their finding is only applicable to that specific case study alone. These two distinct differences have to be made very very clear to all researchers.

5. It is based on some logical rational and tied to theory -- No research question ideas stands alone but is more often tied to some guiding theories.

5. It is Doable - it is feasibly done and can be answered in a timely fashion.

6. It generates new questions or is cyclical in nature. - provides the foundation for research question that will be asked again tomorrow.

7. It is incremental. - no research stands alone, instead they stand on the shoulder of others, and contribution takes place in small, easily defined chunks.

8. It is an apolitical activity that should be undertaken for betterment of society. - e.g. Finding a vaccine for AIDS, and is independent of one's personal or political view, but of the truth.


Continuation of the article to come in next episode… please regularly visit this site.
As an indicator to show to me that this site is ever visited and read at all, please do post your comments to my articles. I truely need yourhonest feedback to improve.
It will be seen queer for me to be rambling alone to the brick walls for the past three months and not knowing if it is worth my time doing it. Sometime, I do contemplate on just closing this site for good and thinking of converting it into a book instead.
Chao....

Monday, September 27, 2004

A new chapter....... PART 8

..... AND THE SWEATS BEGINS.


Now that the daunting and nerve-wrecking proposal defense session is over and through, this does not mean that you can already start resting on your laurel. On the contrary, your serious journey has just begun. The proposal defense session you had was intended to get you anchored on some kind of footing, but it is still far far away from being perfect. The proposal you submit is not truly foolproof yet, honestly you still needs to iron out the rough edges and fine tune it further in more detail with your appointed supervisor/s later. Catch, chase or hunt after your supervisor ASAP. You have to make the initiative, rather than waiting for them to come after you because they have many other important things to do than to worry about you.

Although you did mentioned qualitative or quantitative methods during your proposal defense, have you actually sorted out exactly who will be your sampling, and can you provide the justification for why you chose them as your sample? Do you know exactly how big a sampling you will need for your data to be really valid or representative? How do you ensure that the test instrument developed for your study is unbiased and guarantees randomness? How do you design your interview or survey questions to ensure you can get they right data needed to support your hypothesis? And most critical of all is that, have you sorted out how the data will be analyzed?

Most of the answers to the above questions have been explained clearly in many research methodology books that can be obtained in the University library, or at least, try and get hold of a copy of Dr. Sulaiman Samsuri's book on Research Methodology as a starter. Never leave this vital issue unattended until the last minute because this is the sole pillar to your research. This will be your examiner's first line of attack during your Viva Voce.

Start reading and visiting the University library ASAP and start surfing the Internet immediately. Because our memory span is very sort-lived, it is extremely important for you to record immediately the content of what you read into writing, even a bit at a time. At this early stage, worry not about the grammar or the language yet, but to keep constantly writing. Write in Malay if it helps, but make sure to run spell checking on your document, after all Bill Gates has already provided such functionality in his MSWords word processor. There is also built in grammar-checker and Thesaurus for you to use. It could be just in mere point forms, or a simple mind-mapping diagram, or a sketch, just record it to your hard disk or into your logbook. Although it might seem rubbish now, or not quite relevant... do not make judgment yet, just keep filling it into the rubbish dump. Believe me; you'd see the connection and relevance many many months later.

Open a specific folder in your hard disk for this purpose called Research. As a precaution against virus attack or corrupt of your hard disk data, regularly burn all the files to CD-ROM as a backup, and file the printed hardcopy into organized cataloging. This is something extremely valuable, which once corrupted, cannot be replaced ever again.

Your first immediate task now is to rewrite your earlier Research Proposal paper again into a full fledge pages complete with citations, for your Thesis Chapter 1 and hand it to your supervisor for reading and corrections so that both of you are set on the same path together.