WRITING A RESEARCH PROPOSAL

 

A proposal is a suggestion, intention, plan or scheme to do something. A research proposal is a statement in writing, spelling out ones intentions of carrying out a research in a specified area.

A research project is a combination of inputs managed in a certain way to achieve one or more desired outputs, and ultimately one or more desired impact.

 

THE CONCEPT NOTE

A concept note (or a concept paper) is a BRIEF summary or SHORT VERSION of a research project proposal. The concept note should show the inputs, how they will be managed, a work plan, the output and the impact. A concept note for submission to a donor is ideally between 3 to 7 pages long.

 

How to Prepare a Concept Note

A concept note has a specific format. The final version of the concept note has the following headings:

1. Title

2. Background

3. Objectives

4. Outputs

5. Activities and duration

6. Beneficiaries and impacts

7. Project management (includes monitoring and evaluation) (especially important for donor funded projects)

8. Budget

However, before the concept note is prepared in the final format order, the following order should be followed:

i. Objectives

ii. Inputs

iii. Activities and duration

iv. Outputs

v. Beneficiaries and impacts

vi. Project management

vii. Draft budget

viii. Background

ix. The problem and why it is urgent (for the background section)

x. What has already been done (for the background section)

xi. Title

 

Step 1. Objectives (what do you want to do?)

The objectives tell the reader what one wants to do. They are one of the first parts of the concept note that a reader will look at. They have therefore to be done extremely carefully.

An ideal way to start is to get a small group of colleagues together to brainstorm. Inclusion of colleagues from different disciplines enriches discussions. Project objectives should:

a) correspond to a core problem,

b) define the strategy to overcome the problem, and

c) contribute to the achievement of higher-level development goals.

Before brainstorming the project objectives, one has to reflect on the underlying problems and areas of work which the project is trying to resolve. The problems should be clear.

To explain the objective, the core problem is re-formulated from a negative statement into a positive statement, e.g., if the problem is "low birth weight," the objective will be positively re-formulated as "increased birth weight."

Then the objective will be detailed further. Often, a problem may be overcome by using various strategies to find a solution. For example, the objective "Increased maize yields in drought-prone areas" may be achieved by: a) adopting better maternal nutrition, or b) improving maternal health.

 

The choice of strategy has to be made according to the constraints underlying the core problem, which have been assessed in the field. Considering criteria like: resource availability, time needed, likelihood of success to carry out the work. The project objectives should clearly show which strategy the project will pursue.

A donor may not fund the project unless the project contributes to a development goal. Therefore the statement of the objective has to indicate in what way the project will contribute to development (e.g. food security in the area; improved health).

 

The full hierarchy of objectives, including the contribution to a development goal for the “low maize yield in drought prone areas” is:

· National Development Goal: Increase nutritional health of the population

· Program Objective: Increase average maize yields per hectare

· Project Objective: Drought-tolerant maize varieties adopted

 

Formulated objectives should be SMART!!. Each objective should specify the QUANTITY of achievements (e.g., numbers of beneficiaries, area covered by project), and the QUALITY (e.g., poor farmers, marginal lands, drought-tolerant varieties).

Objectives should also include an indication of TIME when the objective will be achieved (e.g., in January 2018, three years after the start of the project).

N.B: Objectives are more achievable if quality, quantity and time are clarified.

 

Step 2. Inputs (What do you need to achieve the objectives?)

One only needs a list of inputs to prepare the budget. It has to appear in a section of the concept note UNLESS one has substantial inputs (already existing, from another donor or the community). One will need to brainstorm all costs and inputs to arrive at a realistic set of activities and budget.

The inputs you will need to implement your project (i.e. achieve your objectives) may include:

· people (researchers and other partners’ staff-time)

· travel costs (bus tickets, meals allowance)

· vehicles (rental, petrol, driver’s time)

· equipment (tools, office)

· supplies (paper, seed, fertilizer, etc.)

· services (phone, fax, e-mail, etc.)

· facilities (offices, demonstration sites, laboratories)

Some inputs may come from many different partners, e.g. farmer groups, individual farm families, other NGOs, international organizations, donor groups, government agencies, etc.

It is important to remember that all partners will also have travel, supplies, services and other input requirements.

 

Step 3. Activities and Duration (What will be done and how long will it take?)

Describe (in summary only for a concept note) what you and your partners plan to do to achieve the project objectives.

State how long it will take to accomplish each activity

Tips:

· Be brief and clear

· Be positive – use the future tense and the active voice

· Do not use "we" (use "the project")

N.B: Donors are mostly geared up to supporting projects of three years.

        In the full proposal each activities section sentence should explain who will do what, when, and how.

 

Step 4. Outputs (What will have been achieved at the end of the project?)

The outputs of the project should be directly related to the project objectives. Outputs may include:

· events, such as workshops or harvests

· intangible things, like decisions

· tangible things, like new buildings

· information, perhaps in the form of publications or videos

It is worth spending time with colleagues, partners, and friends brainstorming all the possible outputs, as well as those directly related to the objectives.

Key outputs that are achieved during the life of the project may be useful milestones that you can refer to when writing the full proposal.

 

Step 5. Beneficiaries and Impacts (Who will benefit from the project and how?)

Think of all the possible groups who may benefit from project activities and as many different benefits as may occur.

Impact is what the donor is "buying." In making promises about the impact of a project, you need to:

· describe the benefits you expect, how many of them can be expected, and when and where they will occur.

· present your reasoning for why you expect the benefits to accrue to a given group – if necessary, state the assumptions you are making.

· consider whether to suggest that the project will have either an impact assessment component or will be assessed by a separate impact measurement project.

 

Possible beneficiary groups

· Poor individuals (age? sex? location?)

· Farm families (including dependents)

· Refugees

· Poor urban consumers

· Other population groups

Benefits also accrue to NGOs and other organizations, but they are down-played (although not omitted altogether) and play up the benefits to partners such as farmers and their organizations who are the poorest and the target of the donor’s development aims.

Show impact in terms of the Development Goals, such as:

· poverty alleviation

· food security

· preserving the environment

· improved nutrition and health

Develop your own impact checklist

Will the project result in:

· more education for the poor?

· higher family incomes?

· better health for poor families?

· gender-specific or age-specific impact?

· enhanced community participation?

· new use of indigenous knowledge?

· new food source for the urban poor?

· new jobs created?

· other economic benefits? Which sectors?

· improved child nutrition?

· other human benefits?

N.B: Explain how you will measure the above. Impacts that can be quantified are the most impressive, and are more likely to sell your project to the donor.

 

Step 6. Project Management (How will the objectives be achieved? How will the project be managed and evaluated?)

The best objectives in the world can only achieve the desired outputs and impacts if the project can be effectively managed. Your design needs to include a plan covering the roles and responsibilities of the various people who will manage the project. In a concept note you need only to briefly describe who will lead the project and who will be responsible (and when) for the main project tasks including financial management, monitoring and evaluation.

 

Step 7. Budget

Budget preparation skills are an essential tool for all who seek funds to implement good science projects.

This should be based on the list of inputs. If the project will receive funds from other sources (in kind from beneficiaries and partners, from the core program, e.t.c.), they should be highlighted in the concept note and in the covering letter.

Ensure that all project costs are included and labeled, even if not asking for money for them. It is very important for all parties to understand the true and full project costs, and to avoid hidden expenses.

N.B: Remember that nothing is so frustrating as an under-funded project due to a poorly designed budget. For this reason you should develop a budget which is as accurate as possible to include in your concept note.

 

Step 8. Background Material

In the concept note, the background material is organized in two sections.

1. Under "The Problem and Why It is Urgent", the project is discussed in terms of Development Goals of poverty alleviation, food security, preservation of the environment, and nutrition and health. In this section background statistics are provided if available, citing sources, and writing in a general style.

2. Under "What Has Already Been Done", ensure not to focus only on only one organization’s activities. Donors normally want to see acknowledgement of the contributions made by others or are still making; some may be organizations that they are supporting; some may be proposed partners.

(If it is a follow-on project or second phase, the outcomes of the earlier work are described in detail.)

 

Step 9. Selecting a Good Title

Titles need to be catchy, informative, and distinctive. Try using a two-part title. The first part should be short, snappy, catchy; the second part can be more serious and informative. Test out the title with a few colleagues.

EXAMPLE OF A BAD CONCEPT NOTE

 

TITLE: Information about Rice in Blue Land

 

1. Background

Blue Land’s economy is heavily dependent on rice. As the gap between the production deficit and the demand for rice widens, rice-growing represents one of the biggest challenges for Blue Land.

Two types of rice-growing systems exist: - upland rice (rainfed farming), which represents 80% of the total area under rice, and lowland rice (irrigation farming).

Improved varieties of rice have been developed by the national agricultural research center (NARC), but information about these varieties is not available to poor farmers. Farmers may also prefer to plant their traditional varieties but no one has talked to farmers directly about their experiences.

This project aims to strengthen the existing information sharing about rice in Blue Land. A linkage with rural radio stations in Blue Land is proposed to find out more about farmers’ rice cultivation, their traditional knowledge of rice varieties and their reactions to the new varieties.

 

2. Objectives

• Development of information and communication methods (including radio)

3. Expected outputs

• Improved rice-cropping systems.

• Improved grain quality demanded by the market.

• Improved household food security

• New approaches to involving farmers in agricultural information sharing through radio

4. Description of work to be done

Activities

• Identify available rice varieties by talking to local extension workers and possibly visiting NARC.

• Write a radio program about rice and its importance to the national economy and household food security

• Arrange for extension worker and broadcaster to meet with farmers to discuss their rice cultivation and ways to improve productivity and sustain soil fertility.

• Hold a farmer field day in five communities and invite NARC scientists to visit with farmers; tape interviews in the field with farmers and scientists

• Follow up radio program – visit the communities again and invite farmers to ask further questions to send to scientists and extension workers; broadcast their replies to farmers

• Ask farmers to suggest new topics for future farm radio programs (Phase 2 of project)

5. Locations

• Various areas of Blue Land

6. Human resources, materials and financial resources (in ‘000 Blue land Shillings)

	Year 1	Year 2	Year 3	TOTAL
Personnel	60	60	80	200
Training	NA	NA	NA	NA
Equipment
Travel	50	50	50	150
Vehicle maintenance	60	60	60	180
Consumables	50	50	50	150
Contingency (33.3%)	100			100
TOTAL				780

7. Work plan

2005: 

· Start of project:

• Identify farmers’ traditional varieties and rice-cropping systems;

• Meet extension workers to discuss improving rice grain quality.

2006:

• Farmer field days; tape programs

2007:

• Follow up farmer field days.

EXAMPLE OF A GOOD CONCEPT NOTE

 

TITLE: Study of Market information for Yellow Land

 

Background

A study is proposed to help investigate the state of information and communications availability and utilization in Yellow Land. The objective of the study is to determine the demand for specific market information for poultry farming, and to identify existing gaps.

This study builds on research results that helped farmers to increase egg production by using a package of affordable technologies to fight disease, increase nutritional value of local chicken feed and produce using local materials, improved egg storage and transport containers. However, farmers lack sufficient market for their eggs. The farmers value market information, (most especially price information for the export market) and are willing to pay for access to affordable, relevant and timely information services.

A NGO known as “Chickens for Life” proposes a two-year pilot project (2001-02) for delivering price information to farmers using a combination of rural radio and cell phone.

This project has taken into account demand for market information, increased use of mobile phone services in the rural sectors and distortions in the sector where intermediate export buyers connive to fix prices paid to farmers. Simple market studies show that in future the NGO can seek a local agent to take over the information collection and distribution through phone and radio. A new egg producer association for Yellow Land could fund this service.

 

Project Objectives

General objective:

To conduct a study of the information and communication needs of farmers for accurate price information.

Specific objectives:

1. To determine the demand for specific market information for poultry farming

2. To identify existing gaps through participatory farmer needs assessment

3. To respond to these needs with appropriate price information delivered in a timely and effective manner.

 

Project Outputs

The project will produce the following outputs: a database of price information for poultry products, and especially eggs; a network of NGO development workers, researchers and radio broadcasters, radio announcements, and a trained group of farmers who will head a new producers association.

 

Activities

The project will involve the following activities:

1. Collection of price information from individual markets within a 300 km area of producers. Emphasis will be made to work with university researchers and rural radio broadcasters who are based in the region. This partnership will help to recruit research assistants from the local area who can work with farmers in local languages. This will involve participatory methods of gathering information with farmers.

2. The price information will be sent via the mobile telephone to a central database at the NGO Chickens for life. The NGO will relay information directly to rural radio stations.

3. Three rural radio broadcasters operating in the region will include the price information in their daily farm reports.

4. Training for farmers in improved cleaning, storage, packing, and transport of eggs to export markets, and in building a producer’s association and negotiating skills for working with export buyers.

 

Output Indicators to Use for Project Monitoring

1. Price data collected twice a day and sent within 30 minutes from collection time.

2. Number of broadcasts (daily, weekly, monthly, and annually)

3. Listener response

4. Pre-test for training content and frequent spot checks to markets.

5. Number of trainees who applied what they learned.

 

Beneficiaries and Expected Impact

The benefits of this project will be increased income for small-scale poultry farmers in Yellow Land. Women farmers will benefit as they typically they own the laying chickens in the household and are mostly responsible for preparing and selling eggs. It is expected that women will make up most of the participating farmers. Entire families will benefit because income from the sale of eggs is used to pay for school fees, medicines and other household needs. The project is demand driven since the persons querying for information wants to access it.

The project is sustainable in the long run because it will lead to the development of a producer’s association that could fund this project without donor assistance. Training of many farmers (and not only a few individuals) also helps to build capacity and allow continuity.

 

Budget (C$ = Yellow Dollars)

 

Details	2001	2002
Personnel 1. Salaries     – NGO project leader fee (5,000/mo) + 10% in year 2     – Research assistant (3,540/mo) + 10% in year 2     – Consultants without compensation	60,000 42,480	66,000 46,728
2. Wages – Contractual laborer/technician (2,473/mo) + 10% in year 2	29,676	32,644
3. Incentives     – Research center honorarium    – 1,000 bonus/personnel                      Subtotal for Personnel	11,013 3,000 149,169	12,114 3,000 163,486
4. Equipment and other operating costs    – Supplies and materials    – Travelling and expenses    – Sundry expenses        Sub-total for Equipment	55,000 35,000 10,000 100,000	50,000 40,000 10,000 100,000
Summary    – Sub-total for Personnel    – Sub-total for Equipment GRAND TOTAL in Yellow Dollars	149,169 100,000 249,169	163,486 100,000 263,486

 

 STEP 4. PREPARING THE RESEARCH DESIGN

Research design is the conceptual structure within which research would be conducted. The function of research design is to provide for the collection of relevant information with minimal expenditure of effort, time and money. 

Study design is a logical model that guides the investigator in the various stages of the research. Study designs determine the type of data collection method

 

Considerations in preparing research design

1. Objectives of the research study - must answer the research questions; numbered with action verbs

2. Method of Data Collection to be adopted – data is either Primary (being collected for the first time) or secondary (already collected by someone else for another purpose and sometimes analyzed.

    - The method must be appropriate for the type of data and must be appropriate for the study problem;

3. Source of information – who has the information is key. The study population, sample size and sampling design must be thought      

     of seriously. The sample should be representative of the larger population and allow making accurate estimates

4. Tool for Data collection – includes the guide that will be used such as observation checklist, questionnaire or interview guide. Also

the equipment to be used. Reliability and validity of research tool is essential

5. Data Analysis – Data may either be qualitative and quantitative based on the type of research. Processing steps to follow type of research

 

There are several types of research designs depending on research strategies used. They can be subdivided according to approaches into Quantitative and qualitative research designs.

1) Quantitative research designs  

- These try to quantify the relationship between variables and collect count data. They may be divided into:

a). Experimental research designs - may be subdivided into Experimental (true experiments with controls and replication) and Quasi-experimental (without controls and replications)

b). Non-experimental research designs: may be subdivided into Descriptive and Correlational studies

- Quantitative research designs includes the standard experimental method of most scientific disciplines and use traditional mathematical and statistical means to measure results conclusively.

2). Qualitative research designs

- Also called descriptive or non-analytic study research designs

-  Do not try to quantify the relationship but tries to give a picture of what is happening in a population, e.g., the prevalence, incidence, or experience of a group.

- Are non-quantitative, and not necessarily involve informal data collection, but help in formulating hypotheses, and enable deeper/richer understanding of phenomena, interpret organization-specific results

Examples: Surveys (cross-sectional) studies, Case studies, Case reports, Case-series, Interviews, focus group discussions, some observational/archival data, Critical incidents methodology

 

Study designs can also be subdivided into:

1. Non-intervention (Observational) study designs: the researcher just observes and analyses researchable objects or situations but does not intervene

2. Intervention (Experimental) study designs:  the researcher manipulates objects or situations and measures the outcome of the manipulations

 

3. Exploratory studies

• Are small-scale studies of relatively short duration, which are carried out when little is known about a situation or a problem.

• May include description or comparison.

4. Animal Research Studies

• Studies conducted using animal subjects.

• Can also include animal cell lines

 

Generally, study designs have been grouped into;

1. Descriptive Designs - Attempts to describe and explain conditions of the present by using many subjects and questionnaires to fully describe a phenomenon. The aim is to Observe and Describe. They include Descriptive Research, Case Studies, Naturalistic Observation,

2. Surveys – Mostly involve a brief interview or discussion with individuals to obtain information about a specific subject/topic of study. May also involve collecting brief information to give an overview about something.

3. Semi-Experimental Study Designs - Aim to determine causes and includes Quasi-Experimental Designs; Twin Studies

4. Experimental study Designs -  Aim at determining cause-effect relationships. They include True Experimental Design, Double-Blind Experiment

- Directly establishes cause-effect nature of relationship between variables via mmanipulation of cause (treatment), temporal precedence of cause (and no other factor) before effect, and control of all other extraneous factors. They decrease ambiguity

• Procedures are followed to reduce bias and increase reliability

• Appropriate when proof is sought that certain variables affect other variables in some way.

• The researcher must have a working hypothesis or guess as to the probable results.

• Hypothesis is then used to get enough facts (data) to prove or disprove it.

• Involve manipulation of persons or the materials concerned so as to bring forth the desired information.

 a) Field Studies: Studies participants in their natural setting; Give maximizes realism

 b) Laboratory Studies: Are artificial setting with high control over variables, Procedures are followed to reduce bias and increase reliability. The researcher tests hypotheses of causal relationships between variables.  Involves quantitative research methods and analysis.

Methods of data collection include:  Questionnaire, Interview (structured or unstructured), Observation, analysis of documents

5. Correlational Studies - Explore or test relations between variables; determines whether or not two variables are correlated. 

- This means to study whether an increase or decrease in one variable corresponds to an increase or decrease in the other variable, “Rules out” alternative variables that could play a role in relations between variables

6. Case studies – Are qualitative research studies which adopt an interpretive approach to data; uses direct observation to give a complete snapshot of a case that is being studied. They study `things' within their context and considers the subjective meanings that people bring to their situation. The design uses few subjects useful when not much is known about a phenomenon.

- Methods of data collection include Questionnaire, Interview (structured or unstructured), Observation analysis of documents

7. Longitudinal designs -  uses time as the main variable, and tries to make an in depth study of how a small sample changes and fluctuates over time.

-Methods of data collection include Questionnaire, Interview (structured or unstructured), Observation, Analysis of documents

8. Cross-sectional design  - takes a snapshot of a population at a certain time, allowing conclusions about phenomena across a wide population to be drawn.

Methods of data collection include:  Questionnaire, Interview (structured or unstructured), Observation, Analysis of documents

Social surveys

9. Historical Research Design - The purpose is to collect, verify, synthesize evidence to establish facts that defend or refute a hypothesis. It uses primary sources, secondary sources, and lots of qualitative data sources such as logs, diaries, official records, reports, etc. The limitation is that the sources must be both authentic and valid.

10. Prospective studies - Attempts to explore relationships to make predictions. It uses one set of subjects with two or more variables for each.  The aim is to predict. It includes Case Control Studies, Observational Studies, Cohort Studies, Longitudinal Studies, Cross Sectional Studies, Correlational Studies

11. Retrospective Studies

• These studies look backwards and examine exposures to suspected risk or protection factors in relation to an outcome that is established at the start of the study.

• Most sources of error due to confounding and bias are more common than in prospective studies.

12. Cohort studies

• Are usually, but not exclusively prospective.

• The outcome is usually measured after exposure and yields true incidence rates and relative risks.

• They may uncover unanticipated associations with outcome best for common outcomes.

•  They are expensive, require large numbers of participants, and take a long time to complete.

•  They are also prone to attrition bias (compensate by using person-time methods), and bias of change in methods over time.

 

Determining Sampling Design

Researchers usually draw conclusions about large groups by taking a sample A sample is a segment of the population selected to represent the population as a whole. Ideally, the sample should be representative and allow the researcher to make accurate estimates of the thoughts and behaviour of the larger population.

Sampling is the statistical practice concerned with the selection of an unbiased or random subset of individual observations within a population of individuals intended to yield some knowledge about the population of concern,

Sampling is used to;

i) lower the cost - reducing the too high cost of data collection,

(ii) quicken data collection – shorten data collection time,

(iii) obtain smaller data sets – manageable data.

iv) take care of possible change in population dynamics in population individuals over time.

 

 

Designing the sample calls for three decisions:

i) Who/what will be surveyed? (The Sample) - researcher must determine what type of information is needed and who is most likely to have it.

ii) How many item/people will be surveyed? (Sample Size) - Large samples give more reliable results than small samples. However, it is not necessary to sample the entire target population.

iii) How should the sample be chosen? (Sampling) - Sample members may be chosen at random from the entire population (probability sample). The researcher might select people who are easier to obtain information from (non-probability sample). The needs of the research project will determine which method is most effective

 

There are different types of sampling designs which are subdivided into Probability samples and non-probability samples.

Probability sampling:

1. Simple random sampling: Every member of the population has a known and equal chance of being selected. Random numbers can be used. It is the standard against which other methods are sometimes evaluated. A complete sampling frame is obtained and each case is given a unique number, starting at one. Random number tables or computer generated random number are used based on a selected pattern. It is suitable where population is relatively small and where sampling frame is complete and up-to-date.

2. Stratified random sampling: Similar to simple random sampling but every nth item is selected from the sample frame. The population is divided into mutually exclusive groups such as age groups and random samples are drawn from each group. Within each stratum, a simple random sample or systematic sample is selected. Sampling fraction is first worked out by dividing population size by required sample size (total divided by sample). Has disadvantage of effect of periodicity (bias caused by particular characteristics arising in the sampling frame at regular units).

3. Cluster sampling: Involves grouping the population and then selecting the groups or the clusters rather than individual elements for inclusion in the sample. The population is divided into mutually exclusive groups such as blocks, and the researcher draws a sample to interview.

4. Area sampling - Quite close to cluster sampling. Often used when geographical area of interest total is a big one. Total area is first divided into a number of smaller non-overlapping areas (geographical clusters), then a number of these smaller areas are randomly selected, and all units in these small areas are included in the sample.

5. Random Route Sampling: Used mainly for sampling households, other premises in urban areas etc . Address is selected at random from sampling frame (usually electoral register) as a starting point.  Interviewer is then given instructions to identify further addresses by taking alternate left- and right-hand turns at road junctions and sampling at every n^th address (household.) May be saving in time and may reduce bias because interviewer has to call at clearly defined addresses - not able to choose.  Characteristics of particular areas (e.g. poor / rich) may mean that the sample is not representative. However, it is open to abuse by interviewer because it is difficult to check that instructions are fully carried out.

6. Multi-stage sampling- meant for big inquiries extending to a considerably large geographical area like an entire country. It involves drawing several different samples in such a way that cost of final interviewing is minimized. Sample of areas are drawn starting with initially selected large areas then progressively smaller areas within larger area. Eventually, small sample households are then selected, a method of selecting individuals from these selected households is decided. The first stage may be to select large primary sampling units such as states, then districts, then towns and finally certain families within towns. If the technique of random-sampling is applied at all stages, the sampling procedure is described as multi-stage random sampling. 

7. Sequential sampling: A somewhat complex sample design where the ultimate size of the sample is not fixed in advance but is determined according to mathematical decisions on the basis of information yielded as survey progresses. This design is usually adopted under acceptance sampling plan in the context of statistical quality control.

 

Non-probability sampling:

1. Purposive (Deliberate) Sampling - The sample is selected by the researcher subjectively. The researcher attempts to obtain a sample that appears to him/her to be representative of the population and will usually try to ensure that a range from one extreme to the other is included. It is desirable when the universe happens to be small and a known characteristic of it is to be studied intensively.

2. Quota Sampling- The researcher finds and interviews a prescribed number of people in each of several categories.

3. Often used in market research. Interviewers are required to find cases with particular characteristics. Particular types of people only are interviewed. Quotas are organized so that final sample should be representative of population. Interviewers choose who they like (within above criteria) and may therefore select those who are easiest to interview, so bias can result. It is impossible to estimate accuracy (because not random sample)

4. Convenience sampling- The researcher selects the easiest population members from which to obtain information. It is used when one simply stop anybody in the street who is prepared to stop, or when one wanders round a premise to ask questions to willing people. The sample comprises subjects who are simply available in a convenient way to the researcher. There is no randomness and the likelihood of bias is high. You can't draw any meaningful conclusions from the results you obtain.  It is often the only feasible method where resources or other respondents cannot available.

5. Judgmental sampling: The researcher uses his/her judgement to select population members who are good prospects for accurate information.

6. Snowball sampling -- Initially a few potential respondents are contacted and asked if they know anybody with the same characteristics. These are then enlisted into the survey list

7. Self-selection - Respondents themselves decide that they would like to take part in the survey.

 

Sampling errors

  -  Are caused by sampling design, and include:

1. Selection error: Incorrect selection probabilities (sampled and non-sampled pop).

2. Estimation error: Biased parameter estimate because of the elements in these samples.

 

Non-sampling errors

- Are caused by mistakes in data processing and include:

1. Over coverage: Inclusion of data from outside of the population.

2. Under coverage: Sampling frame does not include elements in the population.

3. Measurement error: The respondent misunderstands the question.

4.  Processing error: Mistakes in data coding.

5. Non-response: the respondents do not give feedback. Part of the sample may be unwilling to participate or impossible to contact.

 

Reducing experimental error

This can be done through

· Randomization – ensuring that there is random selection to give equal opportunity to many items/people from the population

• Replication – reduce bias and increasing the number of items/people to ensure true representation of the population

• Increasing the sample size - to ensure true representation of the population

• Repeating experiments – experiments should be repeated to confirm results

• Rejection of data – Data that is doubted should be discarded.

 

STEP 5: COLLECTING DATA

Having formulated the research problem, developed a study design, and selected a sample, the data is collected from which inferences and conclusions for the study will be drawn. Depending upon plans, one might construct research instruments and commence interviews, mail out a questionnaire, conduct experiments and/or make observations.

In inferential research, construction of a research instrument or tool for data collection is the most important aspect of a research project because anything said by way of findings or conclusions is based upon the type of information collected, and the data collected is entirely dependent upon the questions asked to respondents. The famous saying about computers- “garbage in garbage out”- is also applicable for data collection. The research tool provides the input into a study and therefore the quality and validity of the output (the findings), are solely dependent on it. For quantitative research one may conduct experiments and/or make observations.

 

Collecting data through any of the methods may involve some ethical issues in relation to the participants and the researcher:

 - Those from whom information is collected or those who are studied by a researcher become participants of the study.

- Anyone who collects information for a specific purpose, adhering to the accepted code of conduct, is a researcher.

There are many ethical issues in relation to participants of a research activity.

i) Collecting information: putting pressure or anxiety on the participant, relevance of information

ii) Seeking consent: Informed consent implies that subjects are made adequately aware of the type of information

iii) Providing incentives: Giving a present before data collection is unethical.

iv) Seeking sensitive information: Certain types of information can be regarded as sensitive or confidential by some people and thus an invasion to their privacy, asking for such information may upset or embarrass a respondent.

v) The possibility of causing harm to participant: consider whether their involvement is likely to harm them in any way. Harm includes research that might include hazardous experiments, discomfort, anxiety, harassment, invasion of privacy, or demeaning or dehumanizing procedures.

vi) Maintaining confidentiality: Sharing information about a respondent with others for purposes other than research is unethical.

Ethical issues relating to the researcher include:

i) Bias: Bias is a deliberate attempt to either hide what you have found in your study, or highlight something disproportionately to its true existence.

ii) Provision or deprivation of a treatment: It is unethical to provide a study population with an intervention/ treatment that has not yet been conclusively proven effective or beneficial.

iii) Using inappropriate research methodology: It is unethical to use a method or procedure you know to be inappropriate e.g. selecting a highly biased sample, using an invalid instrument or drawing wrong conclusions.

iv) Incorrect reporting: To report the findings in a way that changes or slants them to serve your own or someone else’s interest, is unethical.

v) Inappropriate use of the information: The use of information in a way that directly or indirectly adversely affects the respondents is unethical. If so, the study population needs to be protected.

 

STEP 6: DATA PROCESSING AND ANALYSIS

Analysis of data involves a number of closely related operations which are performed with the purpose of summarizing the collected data and organizing them in a manner that they answer the research questions (objectives). This will depend on the type of research undertaken: qualitative or quantitative.

The data processing operations are followed according to the type of research undertaken

 

Processing and analyzing data involves a number of closely related operations which are performed with the purpose of summarizing the collected data and organizing these in a manner that they answer the research questions (objectives). Analysis of data requires a number of closely related operations such as establishment of categories, the application of these categories to raw data through coding, tabulation and then drawing statistical inferences.

Data Processing operations include:

1. Coding operation - usually done at this stage through which categories of data are transformed into symbols that may be tabulated and counted.

2. Editing- a process of examining the collected raw data to detect errors and omissions and to correct these when possible. It is a procedure that improves the quality of the data.

3. Classification- a process of arranging data in groups or classes on the basis of common characteristics depending on the nature of phenomenon involved.  The researcher should classify the raw data into some purposeful and usable categories.

a) Classification according to attributes: data is analyzed on the basis of common characteristics which can either be descriptive such as literacy, sex, and religion e.t.c. or numerical such as weight, height, income e.t.c

 b) Classification according to class intervals: done with quantitative data relating to income, age, weight, tariff, production, occupancy e.t.c. Such quantitative data are known as the statistics of variables and are classified on the basis of class –intervals.

4. Tabulation -Tabulation is the process of summarizing raw data and displaying it in a compact form for further analysis. It is an orderly arrangement of data in columns and rows (tables) Tabulation is essential because:

i) It conserves space and reduces explanatory and descriptive statements to a minimum.

ii) It facilitates the process of comparison.

iii) It facilitates the summation of items and the detection of errors and omissions.

iv) It provides the basis for various statistical computations.

Tabulation may also be classified as simple and complex tabulation. Simple tabulation generally results in one-way tables which supply answers to questions about one characteristic of data only. Complex tabulation usually results on two-way tables (which give information about two inter-related characteristics of data), three –way tables or still higher order tables, also known as manifold tables. A great deal of data, especially in large inquiries, is tabulated by computers. Computers not only save time but also make it possible to study large number of variables affecting a problem simultaneously.

Data Security - is the process of protecting data from unauthorized access and data corruption throughout its lifecycle.  It includes data encryption, hashing, tokenization, and key management practices that protect data across all applications and platforms. 

Data Analysis:

 After tabulation is generally based on the computation of various percentages, coefficients, etc., by applying various well defined statistical formulae. The researcher can analyze the collected data with the help of various statistical measures. In the process of analysis, relationships or differences supporting or conflicting with original or new hypotheses should be subjected to tests of significance to determine with what validity data can be said to indicate any conclusion(s).

   In analyzing the data, the researcher is in a position to test hypotheses, if any, he had formulated earlier. This enables to know whether the facts support the hypotheses or not. This is the usual question which should be answered while testing hypotheses.  Various tests, such as Chi square test, t-test, F-test, have been developed by statisticians for the purpose. The hypotheses may be tested through the use of one or more of such tests, depending upon the nature and object of research inquiry. Hypothesis-testing will result in either accepting the hypothesis or in rejecting it. If the researcher had no hypotheses to start with, generalizations established on the basis of data may be stated as hypotheses to be tested by subsequent researches in times to come.

a)  Qualitative Data Analysis:

Qualitative data analysis is a very personal process with few rigid rules and procedures. The researcher needs to go through a process called Content Analysis. This is means analysis of the contents of an interview in order to identify the main themes that emerge from the responses given by the respondents. Data can be analyzed either manually or with the help of a computer.

This process involves a number of steps:

Step 1. Identify the main themes -The researcher needs to carefully go through the descriptive responses given by respondents to each question in order to understand the meaning they communicate. From the responses the researcher develops broad themes that reflect the meanings. Since people use different words and language to express themselves, it is important that researcher select wording of the theme in a way that accurately represents the meaning of the responses categorized under a theme. These themes become the basis for analyzing the text of unstructured interviews.

Step 2. Assign codes to the main themes: If the researcher wants to count the number of times a theme has occurred in an interview, he/she needs to select a few responses to an open- ended question and identify the main themes. He/she continues to identify these themes from the same question till a saturation point is reached. These themes are then written and a code assigned to each of them, using numbers or keywords.

Step 3. Classify responses under the main themes: Having identified the themes Next step is to go through the transcripts of all the interviews and classify the responses under the different themes.

Step 4. Integrate themes and responses into the text of the report: Having identified responses that fall within different themes, they are then integrated into the text of the report. While discussing the main themes that emerged from the study, some researchers use verbatim responses to keep the feel of the response. Others count how frequently a theme has occurred and then provide a sample of the responses. It entirely depends upon the way the researcher wants to communicate the findings to the readers.

 

b) Quantitative Data Analysis:

This method is most suitable for large well designed and well administered surveys using properly constructed and worded questionnaire. They are mostly used for experimental data. Data can be analyzed either manually or with the help of a computer.

Manual Data Analysis can be done if the number of respondents is reasonably small, and there are not many variables to analyze. However, this is useful only for calculating frequencies and for simple crosstabulations.

Manual data analysis is extremely time consuming. The easiest way to do this is to code it directly onto large graph paper in columns. Detailed headings can be used or question numbers can be written on each column to code information about the question. To manually analyse data (frequency distribution), count various codes in a column and then decode them. In addition, if you want to carry out statistical tests, they have to be calculated manually. However, the use of statistics depends on your expertise and the desire/need to communicate the findings in a certain way.

Data Analysis Using a Computer needs one to be familiar with the appropriate program. In this area, knowledge of computer and statistics plays an important role. The most common softwares are Excel, XLSTAT, SPSS for windows, GenStat, MiniTab, SAS. However, data input can be long and laborious process and if data is entered incorrectly, it will influence the final results.

 

STEP 7: GENERALIZATIONS AND INTERPRETATION OF DATA

 If a hypothesis is tested and upheld several times, it may be possible for the researcher to arrive at generalizations, i.e., to build a theory. As a matter of fact, the real value of research lies in its ability to arrive at certain generalizations. If the researcher had no hypothesis to start with, he might seek to explain his findings on the basis of some theory. This is known as interpretation. The process of interpretation may quite often trigger off new questions which in turn may lead to further researches.

 

 STEP 8:  REPORTING THE FINDINGS AND DISSEMINATION OF FINDINGS

Writing the report is the last, and for many, the most difficult step of the research process. The report informs the world what one has done, what they discovered and what conclusions have been drawn from the findings.

The report should be written in an academic style. Language should be formal and not journalistic.

 

Report writing must be done with great care keeping in view the following:

 

a). The layout of the report 

It should be as follows:

1) the preliminary pages;

2) the main text, and

3) the end matter.

In the preliminary pages, the student research project report should carry on separate pages:

i) Title, name, registration number and date followed by

ii) Declaration

iii) Acknowledgements

iv) Table of contents,

v) A list of tables and

vi) A list of figures (graphs) and charts (if any).

 

The main text of the student research project report should have the following parts:

i) The Abstract – Summary of findings – Results and recommendations are stated in non-technical language. If the findings are extensive, they should be summarized.

ii) Introduction - Should contain a clear statement of the objective of the research and an explanation of the methodology adopted in accomplishing the research, and the scope of the study, along with various limitations.

iii) Main report/body - should be presented in logical sequence and broken-down into readily identifiable sections.

iv) Conclusion: Towards the end of the main text, the researcher should again put down the results of the research clearly and precisely.

 

The end matter – Appears at the end of the report and carries;

i) Appendices - enlisted in respect of all technical data.

ii) References/Bibliography - list of books, journals, reports, e.t.c. consulted.

iii) Index should also be given especially in a published research report.

 

b). Report Language:

The report should be written in a concise and objective style in simple language avoiding vague expressions such as ‘it seems,’ ‘there may be’,

 

c). Charts and illustrations in the main report should be used only if they present the information more clearly and forcibly. If not useful, they should be left out.