2024 Steps in Conducting Community Survey PDF

Figure 1. Steps in conducting a survey 1. Planning survey 2. Gathering the Data Needed 3. Processing and analyzing 4. Documenting the Data Re...

Figure 1. Steps in conducting a survey 1. Planning survey 2. Gathering the Data Needed 3. Processing and analyzing 4. Documenting the Data Results  Formulating survey questionnaire  Pretesting the interview  Final editing of data  Writing survey report  Identifying the community and the schedule/questionnaire and  Coding and encoding data population of the study revising accordingly  Analyzing & interpreting the  Reviewing available information from  Interviewing sample respondents data secondary sources  Supervising interviews  Conducting preliminary interviews with  Field editing of completed village representative or key questionnaire informants and a rapid reconnaissance  Data cleaning of the community  Determining information needed and identifying variables  Designing survey instrument  Selecting sampling techniques  Planning the logistics of the survey  Training interviews  Courtesy call on community officials Topic 2: Basic Concepts in Community Survey Survey questionnaire, focused group discussion, and rapid rural appraisal Sampling design, techniques and data gathering Data processing and analysis Data interpretation and report writing Objectives: 1. Explain community survey as a research tool in generating necessary information for development planning in the community; and 2. Discuss the process of preparing focused questions based on identified problem(s). Steps in Conducting Community Survey PLANNING THE SURVEY 1. Formulating Survey objectives  determine the purpose survey  general questions that the survey is designed to answer  how the findings will be used a. Describe community and analyze the following:  education & training  Income &production  community leadership and participation status of its constituent b. Comprehensive report becomes the basis for a community development plan 2. Identification of the community and population of study  Selection of community – need an interventions project that will improve the living conditions of community members  All community members – compose the population of the study 3. Reviewing available information (Secondary Data)  Socio-economic Profile of the community – available data  Agriculture studies/university studies – as background information on the community 4. Conducting Preliminary Interviews and Rapid Reconnaissance  Short visit to the community for Rural Rapid Appraisal and preliminary interviews  Community leaders are informed , and their permission and participation are solicited  Reconnaissance – is a quick assessment of population distribution, composition and occupation which are useful in preparation of survey instrument to observations on community settlement, crops planted other productive endeavors, etc. 5. Determining information needed, identification of variables, and designing the survey instrument Questions to be asked: a. What basic human needs/services exist/or don’t exist in the target area? Ex. Nutrition center or other facilities that provide basic services b. Which among these require improvement on development?  c. What are the limiting factors/constraints to the improvement of these basic human needs? d. What change elements are appropriate to overcome those constraints? e. How can these change agents be mobilized for the betterment of the target area? Designing the survey instrument  Identification of variables Variables or indicators - measures the progress of an activity against stated targets towards delivering its inputs, producing its outputs and achieving its objectives Example: Input Indicators: Production 1. Delivery of farm inputs 2. Number of visits of extension personnel 3. Construction of farm to market road etc. Output variables 1. Size of the farm area planted 2. Returns/unit area 3. No. of farmers visited 4. Length of farm to market road constructed Impact indicators 1. Increased productivity 2. Available supply of basic food commodities Two basic instruments: 1. Questionnaire - is a research instrument consisting of a series of questions for the purpose of gathering information from respondents. Questionnaires can be thought of as a kind of written interview. They can be carried out face to face, by telephone, computer or post. Questionnaire surveys are a technique for gathering statistical information about the attributes, attitudes, or actions of a population by a structured set of questions. 2. Interview schedule - is the guide of an interviewer uses when conducting a STRUCTURED INTERVIEW. It has two components: a set of questions designed to be asked exactly as worded, and instructions to the interviewer about how to proceed through the questions. What is the difference between interview schedule and interview guide ? The difference lies in the usage; obviously, the interview schedule is used by the interviewer during a face-to-face interaction, while the questionnaire is simply filled out by the respondent.... Essentially, preparing an interview schedule for a structured interview is the same as preparing a questionnaire.  What is the difference between unstructured and structured questionnaire? An unstructured questionnaire is an instrument or guide used by an interviewer who asks questions about a particular topic or issue.... A structured questionnaire, on the other hand, is one in which the questions asked are precisely decided in advance.  NOTE: The more concise the questionnaire, the simple the questions, the more reliable and valid the tool is. Reliable – if it yields consistent results when used to measure similar factors several times Valid - if it measures what is supposed to measure Can be done by dividing into different sections Can be done by providing clear instructions or what data each section wants to gather General Guidelines for Preparing Systematic Interview/Questionnaire include the following: a. Agency conducting the study b. Provide appropriate instructions on how to complete the instrument c. Names and address of the respondent, and interviewer and date when the interview was conducted d. Divide the instruments into sections according to the main variables chosen in the survey: For example: I. Demographic Characteristics II. Production III. Income and expenditures IV. Training needs V. Community leadership and participation Developing Simple Questions a. Always use objectives as guides in deciding what factors or variables to be studied b. Divide the instruments into different sections according to the key factors or variables c. Number every item under each section d. Give instructions under each main section e. Use filter questions to avoid invalid responses. Example: 1. Do you use fertilizers for your crop production? ( ) Yes ( ) No 1.1 If yes, what fertilizer do you used? Please specify: ________________ f. Avoid leading questions Example: Do you listen to this radio program? Change to: What radio programs do you listen to? g. Avoid double barreled questions: Example: Do you read newspapers or magazines?  Change to: Do you read newspapers? Do you read magazines? h. Avoid vague questions Example: How do you feel about what you read? Change to: How satisfied are you with what you read? i. Avoid questions that provide answer and succeeding questions. 6. Selecting sampling technique a. probability sampling methods/techniques b. non-probability sampling methods/techniques TYPES OF PROBABILITY SAMPLING METHODS 1. Simple Random Sampling 2. Systematic Random Sampling 3. Stratified Random Sampling 4. Cluster Sampling 5. Multistage Sampling 1) Simple Random Sampling: In this type of sampling each and every element of the population has an equal chance of being selected in the sample. The population must contain a finite number of elements that can be listed or mapped. Every element must be mutually exclusive i.e. able to distinguish from one another and does not have any overlapping characteristics. The population must be homogenous i.e. every element contains same kind of characteristics that meets the described criteria of target population. Method:  Before taking a sample the population is needed to be defined. In other words, one must know what characteristics constitute the population of interest.  A list of all the elements of population is required.  One needs to prepare the list if the readymade is not available.  The list must be exhaustive i.e. it must contain the name of each and every element of the population.  One method for the selection of participants is lottery method: each element is first given a number and then numbers are individually written on slips of paper.   The slips are put and mixed thoroughly in some bag or bowl. Then the decided number of slips is drawn out of it.  Other methods may be the use of any random table generated through computer or any other resource.  The selected participants are approached and investigation is done. Benefits:  There is not the possibility of sampling biases.  The sample is a good representative of the population.  Crucial Issues/ Draw Backs:  It may be very costly and time consuming especially in those cases when the participants are widely spread geographically and difficult to approach  It needs a lot of efforts especially for a large population.  In many circumstances it is not possible to get or prepare an exhaustive list of elements. Even apparently complete lists may also exclude some of the potential elements. For instance, we randomly select the population of a town using telephone list. Is it sure that everybody in the town has a connection? Example: The owner of Company XYZ wants to know if his employs are satisfied with the quality of food provided in the company. In this case, the target population is every person who works at the company. Thus population is precisely defined, is specific and elements are finite in number. The population is homogenous because people belonging to different groups (age,sect, gender) are not very much likely to be different over the issue. There are 1000 employs in the company. To draw a sample of 100 participants, the researcher uses an exhaustive list of the employs (it means the list contains the names of all the 1000 employs). He allots a number to each name. He now follows a computer generated table containing 100 numbers in between 1 to 1000. The participants whose names are corresponding to the selected numbers are approached and investigated. 2) Systematic Random Sampling This type of sampling is also used for homogenous population. It is a bit different from simple random sampling. Unlike simple random sampling, there is not an equal probability of every element been included. In this type of sampling the elements are selected at a regular interval. The interval may be in terms of time, space or order. For instance, element appearing after every 30 minutes, or present at a distance of two meters, or every 5th element present on a list. Thus this regularity and uniformity in selection makes the sampling systematic. The list of elements may or may not be required before the conduction of research. Sometimes it is not even possible to create a list because of the nature of population. Say, if it is possible to tell who is going to visit the coffee shop today.  Method:  Before taking a sample the population is needed to be defined. In other words, one must know what characteristics constitute the population of interest.  In case where exhaustive list of elements of the target population is available, the list is arranged and numbered in an order 1 to N.  To find an appropriate interval suppose population contains N number of elements and we need a sample of n size.  Divide N by n. the number obtained through this division, say k, is an appropriateinterval size to produce a representative sample.\  For instance if population is consisted of 300 elements and we need a sample of 30 participants, then interval size will be 10 so we need to select every tenth element  Then first element, say 5th, is selected at random then every 10th is selected.  In this way the sample will be composed of 5th, 15th, 25th 35th and so on elements.  Selected numbered elements are then approached and the investigation is done.  In case where the list is not possible to make an interval size is decided and then participants appearing with that interval are approached. Benefits:  It ensures the extension of sample to the whole population  It provides the way to get a random and representative sample in the situation where prior listing up of elements is not possible. Crucial Issues/ Draw Backs:  It may be very costly and time consuming especially in those cases when the participants are widely spread geographically and difficult to approach  It needs a lot of efforts especially for a large population.  If the order of the list is biased in some way, systematic error may occur.  For instance, you are going to select every 15th element from a list compiled of groups of fifteen members where the first name in each group is that of the Prime Minister. Example: Example 1 (when list of elements cannot be prepared)  A super market has been advertised through bill board a few meters away from its existence.  The owner wants to know how much this advertisement has contributed to bring the costumer to the market.  Thus population in this research is constituted by every person who visits the market.  The goal of research does not need population to be divided into groups, so the population is homogenous.  The list is not possible to prepare.  The researcher sets a regular interval in terms of order.  First he includes the third costumer who enters the market.  Now he includes every 10th from the first selection.  In this way he includes 3rd, 13th, 23rd, 33rd, and so on costumer.  Example 2 (when lists are available)  The owner of Company XYZ wants to know if his employs are satisfied with the quality of food provided in the company.  In this case, the target population is every person who works at the company.  There are 1000 (N) employs in the company working in 4 different departments A, B, C, D.  The population is homogenous because people belonging to different groups are not very much likely to be different over the issue.  However the elements are already grouped.  So in order to ensure the extension of sample to the whole population systematic sampling is used  To draw a sample of 100 (n) participants, the researcher uses an exhaustive list of the employs from all the four departments.  He arranges the lists in order and compiles them to one.  There are 234 employs in A, 345 in B, 156 in C, 265 in D.  He allots a number to each name.  In this way the name that was first on the individual list B is now 235th on the compiled list.  Dividing N by n, researcher gets a number for the interval to be used i.e. 10.  Looking into the list, he selects 7th employ at random.  Then every 10th from the 7th is included.  In this way the sample is composed of employs whose names are corresponding to number 7, 17, 27, 37…..997. 3) Stratified Random Sampling This type of sampling method is used when population is heterogeneous. i.e. every element of population does not matches all the characteristics of the predefined criteria. Instead the elements differ from one another on a characteristic. So the sub groups are formed that are homogenous i.e. all the elements within a group contains same kind of characteristics (keep in mind, those characteristics are to be taken into account that defines the target population). The sub groups are called as strata (single stratum) The topic and nature of the investigation tells on what criterion the strata are to be made. Common criterions used for stratification are gender, age, ethnicity, socio-economic status. However, the criterions vary greatly investigation to investigation. This formation of strata can also be called a mini reproduction of population as each stratum consists of elements that are different from other strata’s element in some characteristics. For instance if an investigation is taking young adults into account, so this population may need to be divided (of course, on the basis of what the investigation is about) into sub groups like male young adults and female young adults, educated young adults and uneducated young adults, high income young adults and low income young adults etc. in this way each stratum is a different population. The sample is selected from each stratum randomly. There are two techniques that are used to allocate sample from strata: proportional allocation technique and equal allocation technique.  Using proportional allocation technique the sample size of a stratum is made proportional to the number of elements present in the stratum. Using equal allocation technique same numbers of participants are drawn from each stratum regardless of the number of elements in each stratum. Method:  Before taking a sample the population is needed to be defined. In other words, one must know what characteristics constitute the population of interest.  On the basis of nature and purpose of investigation it is decided which criterion has to be taken into account to make the sub groups (strata).  Then on the basis of decided criterion stratification is done.  A list of all the elements of each strata is required.  One needs to prepare the list if the readymade is not available.  The list must be exhaustive.  The participants are then selected from each stratum through lottery method or using any random table (as in simple random sampling)  Or in case if it is not possible to prepare the list because of the nature of population every nth element is selected from each stratum (as in systematic random sampling) Benefits:  For a heterogeneous population it produces a representative sample as it captures the diversity which otherwise is likely to be undermined through simple random or systematic random sampling. Crucial Issues/ Draw Backs  It needs a lot of efforts.  It is costly and time consuming  If the criterion characteristic/ variable used for classification is not selected correctly, the whole research may go in vain. Example:  The owner of a chain of schools wants to know what percentages on an average have been obtained by his grade 10 students in the Board examination.  He has six branches of his schools.  The target population is every student who studies in grade 10 of any branch of the school.  This population is heterogeneous for the schools are headed by different person and different teachers teach in each.  These factors are likely to impact the quality of education and thus the results of the students.  So the 6 schools are divided into 6 sub-groups or strata.  Students are now randomly selected from each stratum using systematic random or simple random sampling. 4) Cluster Sampling  The group of elements residing in one geographical region is called as cluster. And sampling of clusters is called as cluster sampling. This sampling technique is used when the elements of population are spread over a wide geographical area. The population is divided into sub-groups called as clusters on the basis of their geographical allocation. Usually this division of population is similar to what the standard of division has been used yet. For instance population spread over a country is clustered up into cities, population spread over a city is clustered up into towns etc. The clusters ought to be homogenous among them on the characteristic variable of the research. However for being truly representative sample, the selected clusters must capture the heterogeneity of population. For instance if in the selection of towns only small towns are selected leaving behind the bigger towns, the sample is not going to be a true representative of the population Method  First of all the population is divided into clusters.  The clusters are selected randomly using simple random or systematic random sampling techniques.  The selected clusters are visited.  All the elements (may be individuals, households, schools, markets etc. depending on the nature of investigation) within the selected clusters are investigated. Advantage:  In cases where the population is spread over a wide geographical region, cluster sampling is used to reduce cost as compare to simple random or systematic random sampling.  It consumes less time and efforts than the aforementioned techniques.  For instance the list of elements of the population is not required.  Moreover, instead of going place to place over a widely spread area for randomly selecting elements, you get a group of elements in one geographical region. Crucial Issues/ Draw Backs:  It may sometimes lead to sampling biases and systematic errors.  For instance, in the selection of markets only big markets may be selected, though randomly.  So this selection is likely to impact the results. The results may be different if there were small markets in the selection too.  If clusters are not homogeneous among them, the final sample may not be representative of the population. Example:  Education department wants to inspect quality of education in schools of ABC City.  There are twenty five thousand schools in the city; the researcher wants to take a sample of 1000 schools.  In this case if simple random or systematic random sampling is used it will demand to move around the whole city locating the selected schools that are dispersed.   Of course, it would consume more time, efforts and money.  So, instead the researcher chooses cluster sampling for his research.  He divides the city’s population into 21 towns; thus into 21 clusters.  A number is allotted to each cluster.  Then 7 clusters are selected using simple random sampling.  This is the crucial time of the sampling technique, where systematic errors may occur.  Say, for instance, if the selected clusters are only smaller towns (there is under representation of the bigger town) and/ or if selected clusters only belong to higher economic class (there is under representation of lower economic group).  These variables are likely to impact the results of the present research.  Thus there is a requirement of careful assessment of the selection.  Once the selection is finalized, the researcher goes to the selected clusters and examines each and every element (school) of them. 5) Multistage Sampling It is a sampling technique where two or more probability techniques are combined. It is used when the elements of population are spread over a wide geographical region and it is not possible to obtain a representative sample with only one aforementioned technique. It can be described as sampling within the sample. The final unit or element of population which is used in investigation is obtained after sampling at several stages. Method:  Usually at the first stage target population is divided into clusters.  The clusters are selected randomly.  These clusters are called as first stage units or primary units  These clusters are homogenous among them but may be heterogeneous inside.  To overcome this heterogeneity, homogenous sub groups called as strata are formed.  So the strata are called the second stage units or sub-units.  The formation of these strata can be done using cluster sampling technique or stratified random sampling technique depending on the nature of investigation.  In each stratum the units may need to be further divided, for instance market places into shops, buildings into houses etc.  The final units obtained are investigated. Advantages:  It increases cost and time efficacy.  For instance instead of investigating all the elements within a cluster, if a sample is randomly drawn from each cluster, the results will be similar but with lesser efforts.  This particular sampling method where random sampling is done within the selected clusters is called as two stage sampling.  The technique is also useful in overcoming the heterogeneity problem within the clusters.  Crucial Issues/ Draw Backs:  If the selected clusters do not capture the characteristic diversity of population, the sample would not be representative of the population.  If the characteristic variable used for making strata (in case of heterogeneity) at any stage is not appropriately selected depending on the nature of investigation, the whole research may go in vain. Example:  The purpose of a research is to find out the best seller food products brands of the year in the country.  In this case the target population is constituted by every market where the food products are sold.  So the population is not only spread over a wide geographical region of the country but is also dispersed.  The researcher first divides the country into cities; there is a formation of 150 clusters.  He selects 30 clusters randomly; these form the first stage units.  Care is needed to be taken in the selection so that there must be a representation from smaller as well as bigger cities.  The sale of a food product is likely to be impacted by its price; so there is a possibility that people belonging to lower and higher income groups are different in their preference of food products.  Thus the researcher divides each city into 3 strata: residence of lower class, middle class and upper class; these strata form the second stage units.  Even now it is not possible to take a random sample of elements from each stratum because the strata are spread over a wide geographical region.  So, the researcher makes clusters within each stratum and then randomly selects clusters from each of the 3 strata.  These clusters form the final units of the sample.  Each element (i.e. food products selling shops and markets) within the selected clusters are now approached and investigated. TYPES OF NON-PROBABILITY SAMPLING TECHNIQUES 1. Volunteer sampling 2. Convenient sampling 3. Purposive sampling 4. Quota sampling (proportional and non-proportional) 5. Snowball sampling 6. Matched Sampling 7. Genealogy Based Sampling 1) Volunteer Sampling The members of the sample self-select themselves for being the part of the study.  In other words it is not the investigator who approaches the participants rather participants themselves reach the investigator. Method:  Participants are told about the investigation through advertisements and announcements.  Whosoever is interested contacts the investigator. Crucial Issues/ Draw Backs:  This type of sampling often encounters the problem of generalization.  This technique encounter with systematic errors.  The people who take part in are those who have an interest in the topic and thus they cannot be a representative of the people who are indifferent to it. Advantage:  It is inexpensive.  It is less time consuming.  It helps in gathering a big amount of data in very limited time with small efforts.  The researcher does not need to put any efforts for search of participants. Example:  A T.V program wants to know how many people of the country are in favor of aparticular political ideology.  An announcement is made in the program and the viewer’s respond to the question through phone call or message.  The sample is restricted and non-representative of the country’s population in a way only those people are the respondents who were watching the program at that moment.  People who were busy in some other tasks could not take part. Moreover, the viewers are those who already have an interest in the ongoing topic. 2) Convenient Sampling It is also called as accidental sampling or opportunity sampling. The researcher includes those participants who are easy or convenient to approach. The technique is useful where target population is defined in terms of very broad category. For instance the target population may be girls and boys, men and women, rich and poor etc. Method:  Any member of the target population who is available at the moment is approached.  He or she is asked for participation in the research.  If the person shows consent, the investigation is done. Crucial Issues/ Draw Backs:  It is subjected to sampling biases and systematic errors.   The categories of target population are broader enough to be divisible into infinite number of categories within themselves which are contrastingly different from one another and cannot at any cost be representative of each other. Advantage:  It consumes fewer efforts.  It is inexpensive.  It is less time consuming as the sample is quick and easy to approach. Example:  A student enrolled in school ABC wants to investigate how men and women are different in expression of love.  For his convenience, he selects the sample from the same school.  The problem with this sampling is how these students can be representative of all men and women.  Note: convenient sampling is not always a mutually exclusive category of non-probability sampling techniques rather it is used in various other types of it.  For instance, a researcher wants to investigate difference in aesthetic sense among people belonging to different educational domains. A quota is made for every domain of arts and science faculties in a university.  The researcher reaches every department in the morning and assesses the students who were sitting free in the lawn. In this way the sample is chosen on the convenience of the investigator for he was free in the morning.  Moreover, he approached the students who were free at that time and did not have any classes. 3) Purposive Sampling:  It is not a mutually exclusive category of the sampling technique rather many other non-probability techniques are purposive in nature.  In fact William M. Trochim divided non-probability techniques into two broader categories: convenient and purposive.  Thus all the other types of sampling techniques are described under the heading of purposive sampling.  In purposive sampling the sample is approached having a prior purpose in mind.  The criteria of the elements that are to include in the study is predefined.  So we do not include everyone who is available to us rather those available are included who meet the defined criteria. Example:  The purpose of a research is to investigate which type of clothing middle age women prefer.  The investigator visits a cloth market.  There are many women in the place but the investigator goes to only those women who appear of middle age group and ask them to participate in his research.  It is because the researcher had a purpose of doing such a selection.  He had set the criteria for his elements i.e. they should be women, and should be of middle age. 4) Quota Sampling This type of sampling method is used when population is heterogeneous i.e. every element of population does not matches all the characteristics of the predefined criteria. Instead the elements differ from one another on a characteristic. So the sub groups are formed that are homogenous i.e. all the elements within a group contains same kind of characteristics (keep in mind, those characteristics are to be taken into account that defines the target population). The topic and nature of the investigation tells on what criterion quota is to be set. Common criterions used for quota are gender, age, ethnicity, socioeconomic etc. However, the criterions vary greatly investigation to investigation. The participants are selected non-randomly from each sub group on the basis of some fixed quota. Method:  First of all there is a need to identify the variable which makes the target population heterogeneous.  On the basis of the identified variable sub groups are made.  A quota is set for each sub group.  Then the sample is approached on the basis of set quota Advantage:  It ensures the presence of every sub group of the population in the sample.  There is not the requirement of any lists of the elements of population.  It is less time consuming and low in cost than stratified random sampling. Crucial Issues/Draw Backs:  Like all other non-probability techniques, the sample is not representative and thus encounters the problem of generalizability. Example:  The purpose of a research is to investigate if students of natural Sciences are different from students of Social Sciences in aesthetic sense.  The researcher selects 3 universities where both type of subjects are taught. (a purposive selection it is)  There are two target populations: students belonging to natural sciences, and students belonging to social sciences.  Both the populations are heterogeneous.  Natural science is divided into Biology, Chemistry, Physics, Mathematics and many more; similarly, social science is divided into Sociology, Philosophy, Psychology, Education and many more.  It is important for the research to include representation from every sub group.  So the researcher sets a quota for each of the fields of natural sciences and social sciences taught in the selected universities. Types of quota sampling Proportionate quota sampling In proportionate quota sampling the percentage of every sub group is set on the basis of their actual proportion present in the population. Example: If quota is made on the basis of age and the population comprises of 30% young, 40% middle age, and 30% old individuals, so the quota will be made in the same proportion. In this way the sample of 200 participants will contain 60 young, 80 middle age and 60 old individuals. Non-proportionate quota sampling In non-proportional quota sampling the percentage of quota does not go with the proportion of the sub-group present in the population rather a minimum percentage is set that is to be included. Example: The researcher wants to include all the ethnic minority groups present in the country. So a quota is set like this: at least 3% Hindus, 3% Christians and so on. 5) Snowball Sampling: It is also called as chain sampling. One element of the population is approached at a time and then is asked to refer the investigator to the other elements of the population. Method:  The investigator selects a person who matches the criteria of the research.  The first participant is now asked to refer the investigator to another person who meets the same criteria.  Now the second participant approached is asked to refer the researcher to another one. In this way a chain is made. Advantage:  This technique is useful in approaching the type of population which is not readily available or present in a very small quantity. Crucial Issues/Draw Backs:  It is subjected to sampling biases and systematic errors due to network connection. Example:  The purpose of a research is to investigate what kind of personality billionaires’ possess.  In this case the target population is every person found anywhere in the world who is owner of billions.   The elements of this population, however, are rarely found.  So the investigator find one person, Mr. A, having the required characteristic (i.e.a billionaire) and approach him.  After completing his investigation from Mr. A, the researcher asks him to refer him to another billionaire he knows Mr. A refers him to Mr. B. Then Mr. B let him know about Mr. C.  In this way a sample of population which was very difficult to approach is obtained. 6) Matched Sampling This technique is used in experimental researches. The main purpose of this sampling is to take a control group to assess the effects of an intervention. Two groups of elements that resemble on a variety of variables are selected. Intervention is introduced on only one group. The other group is used to compare with the first one to see what impacts the intervention produced. Method:  First one element is judged to be a part of the research.  Then, another element is explored that resembles the first one on a variety of important variable. Benefits:  The technique makes it possible to examine if an intervention is really useful or not. Draw backs/ Crucial issues:  In the selection of the matching element care must be taken and the elements must be matched on every possible influencing factor so that it may be claimed that the changes in the two elements are due to introduced intervention and not something else. Example:  The researcher wants to see if the presence of a park in an area affects the mental health of its residence.  He chooses one area where the park was not present.  He then finds out another area where not only the park is unavailable but also the noise conditions, environmental pollution, population size, houses and street construction, socio-economic status are same.  Intervention (i.e. the construction of a park) is introduced in one area and the other is kept as control. 7) Genealogy Based Sampling This sampling technique has been mostly used for taking samples from rural areas. Using this technique, instead of selecting household in an area, the members of the entire families are selected (whether or not living in the same house). It gives a reasonable cross section of the community by age and sex. Method:  First a participant is approached and is convinced to take part in the research.   This participant is now asked to refer the researcher to his close relatives who may be living in other areas. Benefits:  This sampling technique is useful in taking the sample from traditional rural areas where there are not much social and economic differences between families; you do not need to persuade each participant to be part of research instead you get the participants through references. Crucial Issues/Draw backs:  There are higher chances of systematic errors in the cases where members from a family tend to be similar in comparison to members from different families. Source: M. H. Alvi (2016): A Manual for Selecting Sampling Techniques in Research 7. Planning the logistics of the survey  allocating funds  printing  transportation  accommodation 8. Training of interviews  train/orient the interviewers on the purpose of the survey  train them on the use of the instrument (role playing, mock interview, etc)  questions are asked and interpreted in a standard manner 9. Courtesy Call on Community Officials  before the start of the actual survey to explain the purpose of the survey and to present the benefits it would provide the community  reinforces the support and cooperation of the local officials as regards the conduct of the survey DATA GATHERING 1. Pretesting the interview schedule a. Pretest the instruments to respondents who have similar characteristics b. Include low literate respondents c. Take note of words that are difficult to understand. Change to simpler words and clearer sentences. 2.Interviewing Sample Respondents a. Interaction between two individuals (2-way flow of communication)  b. Purpose of the interview should be communicated in the opening statements which clearly indicates what will be asked, purpose for collecting the information, and how the information will be handled and used. c. Requires focus, concentration, practice and ability to separate the minor from important. d. Responses should be accurately recorded. e. Interviewers should probe for responses  Useful to clarify a responses and to increase the richness of the data  Common what, where, when, who and how fill-in the blank spaces of a response  Listening carefully to what is said and not said, being sensitive to the feedback needs of the respondent f.Interviewer should always maintain a pleasing facial expression, be courteous, tolerant and voice should be respectful. 3. Data Editing a. clarifying ambiguous entries b. conversion of figures to unit of measurements c. categorizing or coding responses d. coding of open-ended responses Data Processing, Analysis and Presentation The following is a representation of the 3rd phase of the survey as a research method. It consists of 1) introduction to computer 2) data processing and analysis using computers, using statistics 3) methods of data presentation A. Data Presentation 1. Tables (No. and title, with column heading, sub-heading) 2. Figures (graph, drawing, diagram, map, photograph, bar graph, line graph, circle or pie graph, pictograph) Table Graph  Gives precise and more data  Gives approximate data  Requires closer reading to interpret  Provides “quick” interpretation at a  Has lesser visual appeal glance  Requires text for better interpretation  Has greater visual appeal  Requires text for better interpretation B. Data Interpretation 1. Always look at the objectives, hypothesis or conceptual framework of the survey  2. Data in table are normally in percentage. However, may also be described in fraction or ratio to minimize monotony in interpretation. 3. Focus on extreme numbers (highest and lowest) opposite various categories of responses when total no. of respondents is below 100. 4. Focus on extreme percentages (highest and lowest) opposite various categories of responses when the total number of respondents is 100 or more. 5. Write the past tense since the data being interpreted were gathered in the past. 6. Present the interpretation before each table or graph; the data in the table or graph serve as supporting facts to the text. 7. Say the “greatest number or highest percentage of the respondents” instead of the majority if the highest percentage does not exceed 50 percent. 8. To describe in single – response, one- way table either highlighted the highest or the lowest data gathered on one particular variable. For example: Sex of the respondents “The respondents were largely male (70%); only 30 percent were female.” Note: There is a need to indicate the table number where the data came from. 9. To describe a multiple-response, one-way table, give a generalization of the finding first than breakdown major results per variable. For example: “The respondents were more exposed to radio and least exposed to newspapers (generalization). Eighty five percent of them listened to radio and only 40 percent read newspapers. Seventy percent read magazines and 60 percent watched television (Table 2).” 10. To describe a single response and a two-way table, give a generalization of the finding first showing relationship of the dependent variable and independent variables then present details, particularly on the independent variables highlighting either similarity or differences. For example: Sex (as independent variable) and organizational membership (dependent variable) “More male than female were members of formal organizations (generalization). Table 3 shows that 75 percent of the male as compared with only 40 percent of the females were members of formal organizations.” 11. In interpreting cross-tabulated data, compare data relative to the independent variable. For example: Sex (as independent variable) and radio-program preferences (as dependent variable) “Males preferred news over drama radio program while females preferred drama over news broadcast (generalization). Sixty five percent of the males preferred news broadcast and only 35 percent cited drama. On the other hand, 60 percent of the females chose drama and only 40 percent selected news broadcast (Table 4). SAMPLE of Suggested Content of the Field Survey Report: Part I. Introduction A. Rationale B. Objectives (General and Specific) C. Scope and Limitations  D. Significance of the study Part II. Related Literature A. Theoretical Framework B. Conceptual Framework Part III. Methodology A. Population of the survey/study B. Sampling techniques C. Data collection procedures D. Data analysis Part IV. Discussion of Findings A. Generate Description of the Survey Site B. Profile of the respondents C. Findings of……. Part V. Summary, Conclusion and Recommendation Part VI. Insights and Lessons Learned Part VII. Documentations (photos, letters, questionnaire, and other relevant attachments) Source: Lecture Hand-outs by Dr. Gloria B. Osea. CBSUA Professor (Course Guide Data Management for Rural Development, SEAMEO Regional Center for Graduate Study and Research in Agriculture)