2.0 SCIENTIFIC APPROACH TO GEOGRAPHIC RESEARCH:

2.1 STAGES THROUGH WHICH GEOGRAPHICAL APPROACHES AND METHODS DEVELOPED

2.1.1 EXPLORATION PARADIGM

This was dominated by Ancient Greeks especially Plato who used the deductive method and Aristotle who used the inductive method. Their main concern was to answer the question what is where? They gave descriptions of places and different phenomena. They did not answer the questions: Why are the phenomena where they are located? And why do they behave that way?

2.1.2 ENVIRONMENTAL DETERMINISM PARADIGM

Why are the phenomena located where they are? They believed that the environment dictates the kind of activities to be done at a certain place.

This paradigm developed much in Europe.

It failed to answer the question; what is the influence of man in the environment.

The environment provides different options or alternatives to which you can put it; human beings make decision on what alternatives to take.

The environment does not dictate decision making.

It failed to realise the interrelations between human beings and the environment

2.1.3 REGIONALISM (ARERIAL DIFFERENTIATION)

They believed that the phenomena behave as they are behaving due to regional differences.

Climate, soils and vegetation were taken as some of the criteria to define the region.

This paradigm divided the world into natural regions which are unique.

This uniqueness was rejected by some geographers: they claimed that it was difficult to demarcate regions which are permanently unique; it did not come with a clear testable way of assessing human impacts on the environment.

Regionalism changed into spatial analysis of geographic phenomena.

2.1.4 QUANTITATIVE REVOLUTION

It started in the US. It is an attempt to make Geography systematic science which can make laws and theories. It aimed at making geography scientific by using scientific methods.

In previous paradigms there were no laws and theories. The approaches were descriptive

The scientific approach uses the philosophy of mathematics and statistics to arrive at conclusions

2.1.5 ORIGINS AND NATURE OF QUANTITATIVE REVOLUTION

Regionalism in its various forms was the dominant geographical paradigm used in teaching and research in geography after replacing the environmental determinism and possibilism paradigm in 1930s and 1940s. However many geographers blamed it for the low self esteem of the discipline in the 1950s and argued that it did not afford the necessary balance between regional and systematic studies. They also argued that uniqueness of places that regionalism emphasized tended to ignore the search for generalization that would offer better explanations and allow for wider application and insight into geographical phenomenon. They believed that their approach and adoption of quantification by the wider geographical community would make geography to be more respected and recognised academically as capable of contributing worthy knowledge to solve the many problems that the society was facing in the 1960s as opposed to its then status that they considered to be intellectually weak, being held in low esteem by other discipline and being descriptive and lacking in theory. The main difference with the regional school was the greater faith geographers had in their ability to produce laws and work within the accepted scientific methods that were increasingly defining social science research.

2.2 THE CHARACTERISTICS OF GEOGRAPHIC RESEARCH

Any research is the logical process, i.e. appears logically. It possesses the following characteristics:
The research begins with the question in the mind of the researcher. This question should be intelligently asked in the presence of the phenomena that the researcher has observed and which disturbs him. The question may involve unresolved and confusing situation around you.
Research requires a plan: It is not aimless, undirected activity. It requires a definite plan direction and design. To ensure a good plan there should be:

A clear statement of the problem
Development of hypothesis
Data gathering and interpreting design
Test of hypothesis and an arrival at factually based conclusion

A research requires a clear statement of the problem: Here unanswered questions that the researcher finds indigenous to the research situation must be put clear at the very beginning of the research. Before we begin we need to understand the problem. We look at it objectively.
Any research deals with the main problem through sub problems. Most researchable problems have within them other problem areas of lesser breadth and importance
Research seeks direction through appropriate hypothesis or research questions, having set the research problem and the sub problems. The sub problems are then viewed through logical constructs. “ A hypothesis is a logical supposition, a reasonable guess, an educated assumption which may give direction to thinking with respect to the problem and thus aid in solving it.
Research deals with facts and meanings: Having isolated the problem, subdivided it into appropriate sub problems, and formulated hypothesis or research questions which will suggest the direction in which the facts may lie, the next step is to collect whatever facts which may seem to be pertinent to the problem and to organize them into meaningful aggregates capable of being interpreted
Research is circular

2.3 TENETS/PILLARS OF SCIENTIFIC RESEARCH

Science is an objective activity undertaken within very strict rules, and it involves the continuous excitement of search for new discoveries under a certain set of values universally subscribed to within academics.

The main tenets of academic research

Originality: Original work intends to discover new knowledge, addition of knowledge on existing knowledge, comparing of things and it is not duplicate.
Communality: Sharing of information with the public is expected after work. It can be done I publication, seminar, workshop or forum.
Disinterestedness: Objectivity not being guided by your opinions; use of scientific procedures

Universalism: if a research is done in one area it should bring the same results on other areas with similar characteristics
Constructive criticism be ready to receive constructive criticism.

2.4 Steps in Scientific geography

Problem identification: A problem is anything that requires some explanation. A problem must be clearly defined. A problem can cover anything, e.g. population growth and plan, population movement, Dynamics of human settlements, Urbanization process, economic growth, etc.
Gathering available information or data: You need to read widely what has been written about that particular problem. Relevant information that is available must be collected. This data is available in statistical publications, books, journals, News media, census reports, Historical documents, research documents, etc
Primary data or original data collection: Secondary data may not suffice the problem. The research has to collect original data. This is the data one collects from the field. A research advantageously collects from the field data that is relevant to the problem using different data collection techniques.
Classification or summarization of data: Data or facts that are collected must be organized or grouped to suit the study. The process is known as data classification. Items with similar characteristics are arranged in classes. Summarization is done so as to reduce bulkiness. Summarisation is done through techniques that give use of numerical descriptive values which come up with measures of central tendency, Deviation
Data analysis: Data is analysed so as to come up with explanations and conclusions. You derive meanings from the data through analysis and interpretation
Data presentation: The summarised data is presented using tables, values graphs, charts, diagrams, maps. Qualitative and quantitative measures help to understand the relationship between values.

2.5 Research process is circular

A point that needs to be stressed here is that research is hardly conclusive. This is because in exploring one area a researcher comes up with one or several problems that need resolving.

Research needs no to be seen as one time act static and an end itself. Genuine research is dynamic. It creates more problems than it solves. In deed reading through a number of research report you will notice that researchers point to areas of further research a suggestion that their studies uncovered many issues that need to be considered by themselves or other researchers. Such is the nature of the discovery of truth. In this way therefore research is a circular process.

2.5 Nature of geographic data

What is data? Data is the body of information mostly presented in numerical form (sometimes found in a textual form)

Before any statistical analysis can take place data must be collected (Raw data

2.5.1 Characteristics of data:

Data are precise numerical facts: The information they give is quantitative rather than qualitative. They can therefore be manipulated statistically, they can be stored in digital forms e.g. tapes, CD-ROMs etc

Data is usually collected for a definite purpose. Collection of data must therefore take time, involve measurements and surveys of various types. The justification to collect data is to test a theory or hypothesis

2.5 2 Quality of data: The quality of data depends on reliability and accuracy of a researcher. Care must be taken during data collection. To maintain the quality of data certain things must be avoided in data collection: These include: Making mistakes, Subjectivity, biasness. The collection of data and methods/ techniques must suit the purpose of research. Data should be valid and reliable. To have good data you need to be objective rather than subjective.

2.5.3 Types of Geographical data:

Davis (1974) Insisted that the common feature of geographical data is the fact that it is spatially distributed over time and space. Geographical data have time and space.

The values of geographical data have been related to points, areas and lines. For instance when dealing with population data, the points can be used to represent the population density.

2.5.4 Forms of geographical data

Geographical data can take various forms including:

Altitude: Heights of landscapes, always presented in Metres. This data can be presented in form of contours.

Rainfall: A rain gauge is used to get the amount of rainfall in mm. This data can be presented in the form of isohyets.

Temperature: Presented in the form of isolines

Population statistics: Presented in the form of dots

Traffic flows: Presented in flow line map forms\

The aim of collecting all these data is to solve geographical problems

2.5.5 Types of Data:

Geographical data can be;

2.5.5.1 Individual or grouped data:

Individual data provides precise and specific values of every item in the sample population. This data is very informative, thus very difficult to tabulate if the data set is too large. It is suitable if the population is small.

Grouped data: This represents the grouped/class values information. The groups are formed arbitrary e.g. age groups. It is convenient when large numbers are involved in research

2.5.5.2 Discrete or continuous data:

Discrete data: Data presented in whole numbers due to their nature e.g. Human beings, cars, etc

Continuous data: Presented in the value over a given range, temperature, rainfall, height, etc. It is the type of data where you can get fractions.

Primary and secondary data:

Primary data: Information acquired directly from the field

Secondary data: The kind of information obtained from other people’s findings

2.6 Why use statistical/ Quantitative methods in Geography?

They help to facilitate DESCRIPTION: Summarising or converting information into mathematical language enables one to easily understand and interpret the phenomena. It enables easy comparison of results. Enables the understanding of the phenomena. It enables the reduction of massiveness of data. It is good for the manageability of information. Enables the researcher to quantify data by giving numbers to data in a way t

Statistical methods enable facilitation of induction/ making of inferences. Generally the whole information is very difficult is very difficult to study. Statistical methods make it easier to generalise information about population from the sample. It enables to make inferences about the whole population leading to objective decisions.

hat data becomes objective and look scientific.

Statistical methods enable researchers to test the significance of the results. They test the relationships between sample data whether they are significant or a result of chance.

Statistical methods allow the making of predictions: Predicting what may happen in future. This requires understanding of past events. The past events on the context of geography are spatial. They may be past while existing. With this knowledge prediction of the future is possible

2.7 Problems of geographic data collection

Limited time: the amount of time available to a researcher determines the research design, the type of data to be collected, analysis strategy, etc
Reliability and accuracy. This mostly concerned with stability and consistency. If not acquired the data collected can not be reliable. Lack of reliability and accuracy leads to biases and invalidity. Highly unreliable measures can not be valid.

Inability to reach certain populations (inaccessibility). Certain populations may not be accessible e.g. due to remoteness (topography)
Data disaggregation
Introduction of errors

4.0 PURPOSES OF RESEARCH

Research involves carrying out a diligent inquiry or critical examination of a given phenomenon such as a critical analysis of existing conclusion or theories visa vies newly discovered facts.

The purpose for any research include all or some of the following

To discover new knowledge ie new ideas or new facts

To identify and describe new phenomenon

To make predictions and make estimation of a phenomena

Offer explanation of a phenomenon based upon described characteristics ( give a critical reasons why something is happening) for example there is a very high drop out rate whyWhy there is low crop production or why road accident or impacts of rainfall variability or what can maintain price of a particular crop in the market.

Enable theory development or confirmation, validation of existing theories (basic research) or develop new ideas that strengthen a theory.

Solve a specific problem i.e. in agriculture genetically modified food (GMF)

5.0 TYPES OF RESEARCH

Research is classified according to

Data collection
Analysis
Purpose

5.1. 1 Classification of research according to purpose

Applied research
Basic research
Action research
Evaluation research

5.1.2 Classification of research according to data analysis

· Qualitative research

· Quantitative research

5.1.3 Classification of research according to data collection methods

· Survey research

· Historical research

· Descriptive research

· Case study research

· Experimental research

6.0 How do we identify a specific research problem?

·From existing literature ie systematic reading of previous research work and or published books
·Existing theories
·Opinion/ insights from experts/ peers
·Media reports ( things which are frequently reported ie news papers, radios, TV
·Personal experience/ practical issue ( the work related experiences ie technological change and experience.
·New policy

7.0 Strategies used in social science research

Survey
Case study
Experimental strategy
Ethnography

7.1 Survey strategy

It is characterised by one common thing wide and inclusive coverage, Bringing things up to date. Getting snapshot of how things are at a specific time during the survey.

7.2 Case study

It is an in-depth study of a particular situation or event

7.3 Experimental strategy

Manipulation of circumstances, identifying significant factors, introducing or excluding some factors from the situation, observing effects (manipulation and control)

7.4 Ethnography

Here is not an interview to people for little time but one need to spend a lot of time with people whose culture you want to understand.

Example why people prefers this? Why they live there and how they passive life.

8.0 Which strategy is most suitable

There is no one right strategy or correct strategy in doing a research.

There is no best strategy but the one which can help to solve a problem is the best.

The strategy should be taken prio for the research so choose the best suited according to the purpose.

9.0 How do we know that this strategy is good?

There are a number of criteria to consider and these include

Relevance
Feasibility
Accuracy
Objectivity
Coverage
vEthics

9.1 Relevance

Does the research you intend to carry out address current issue in a society

Current – commonly talk about and affect people ie environmental degradation, governance
(Corruption) the impact of governance on management and sustainable utilization of natural resources (disease environment and poverty)
Will your research build upon existing knowledge? Is it going to make a contribution on what is being known?
Are you going to use the existing theory? are specific theory being tested
Is your research coming with new theory?

9.2 Feasibility

Is the question about be done? (Can your research be done?)

Criteria for feasibility

Time – is there sufficient time for you to do a research, i.e. to collect data, analyse and come up with results. How much time are you locating in design, analyse and writing a report.
Resources – do you have enough resources to cover your research (i.e. financial resources)
Accessibility – information can be available but not accessible. The research design should make sure that information is accessible. Ie one is doing a research in rain season when roads are not passable. Or assume the information available is for nationals and not for foreigners.

9.3 Accuracy

Criteria for accuracy

Will the research you want to carry out provide true and honest findings

Precise and detailed data ( full and honest answer to questions)
Do you as a researcher focus on vital issue

9.4 Objectivity

Criteria for objectivity

Will the research give you a fair and balanced picture
Will the research provide an option of free for personal values, believes and background
Will the researcher maintain an open mind about the findings as well as be able to recognise limitations about the approach taken.

9.5 Coverage

· You need to question whether the all right things have been included

· All the questions should cover the issues being investigated ie people and events. The extent of responses ( the response rate)

9.10 Ethics

Ethics has to do rights and feelings affected by research that you conduct.
(Because of money respondents can give or not give or exaggerate the information)
Avoid deceiving people who are going to give you data use an informed concent ( truth information)
Avoid misrepresentation
Protect the identities of people whom you are conducting a research on.

TOPIC 2: GEOGRAPHIC DATA COLLECTION METHODS

10.1 OVERVIEW OF TYPICAL GEOGRAPHIC METHODS OF DATA COLLECTION

Geographers use specialized research methods to study earth features and human activities. These methods include;

Field study: A technique that relies on direct observation as the means of learning about the earth’s surface and the patterns resulting from human activity. Geographers travel to regions to answer specific questions about the area or to learn about unfamiliar geographic relationships.
Mapping: This is one of the geographers’ most basic activities. Many aspects of geographic research can be shown on maps. Maps present in a simplified form complex pieces of geographic information. They can easily describe the location, characteristics and patterns of geographic elements.
Interviewing: Observation alone can not answer all geographic questions. At times geographers want to study the attitudes people have towards certain places or how their surroundings is affected by their beliefs and activities. This information can be obtained by interviewing groups of people. Researches often do not interview the entire group, instead they interview a portion of the group scientifically selected to represent the entire population (Sampling).

Interviews can be formal when guided or informal when guided by a topic.
There are face to face and telephone interviews
Advantages of interviews:
Enable discussion among the researcher and the correspondent
Help to have information on certain groups through telephone interviews
Disadvantages of interviews
Time consuming and costly
Inaccuracy of information due to forgetfulness, shy, or biasness
The researcher may employ research assistants who are not competent.
Lack standards during evaluation.

Focus groups: Acquiring information from a group of 10–20 people. It helps them to understand and voice some of the geographic problems they face. A group should be representative of the whole population. A focus group enables people with different views to discuss their differences, challenge assumptions and come to a collective understanding of the geographic problems. This method gives give a very brief precise and specific information about the problem. They create new knowledge which was not obtained through other methods.
Quantitative methods: With the aid of the computer geographers often test their research by using quantitative (mathematical and statistical) methods. These methods help to simplify complex information and to present it in a form that is more easily understood. They also help geographers find the patterns in geographic elements and determine which factors affecting a particular element are the most important.
The use of scientific instruments: This is very crucial to geographic research. Geographers use remote sensing devices to identify and study hard to reach or very large physical features. Such devices are instruments that observe and record information from a distance. These devices include aerial and satellite cameras, infrared (heat sensitive) films, and radar. These devices record information about weather systems, patterns of vegetation growth, the existence of pollution, etc. Some instruments measure environmental characteristics such as weather gauges, which measure and record temperature, humidity, wind speed and direction and air pressure.

10.2 FIELDWORK IN GEOGRAPHIC RESEARCH

Geography is a field study subject, concerned with accurate observation, recording and interpretation of the variable nature of the human and physical landscapes.

The geographers’ laboratory is in the field, the local environment.

Types of field work:

Field excursion (Field trip): Refers to the trip round the locality or further a field in order to visit places of geographical interest. Students (researchers) observe, listen to lectures by experts (resource persons). Although it is difficult to structure it has the advantage of bringing students into reality of the environment. They are given the opportunity to identify problems of development for later class discussion.
Field study: Refers to the practice whereby students are taken to permanent field centres or laboratories, chosen and maintained by geography departments, for purpose of studying geographic patterns and processes. Students may closely examine and analyse a piece of landscape to understand spatial variations. It involves intensive investigation.
Field research: Refers to fieldwork organized in the context of problem solving approach. A problem of study is stated. A hypothesis put forward for testing; data collection; analysis; hypothesis testing, Conclusion.

10.3 Historical background of Fieldwork in Geography
Change has been present throughout the long development of geography.

v There have been a number of different phases or trends in the discipline.

v Throughout all this change over the centuries, however, a few things have remained constant.

v the subject matter of geography hasn't really changed

Since the time of the ancient Greeks, geographers have been concerned with the Earth's surface as the home of mankind

Something else that has not changed is the fact that geography has always been a discipline of observation

v Observation is simply the most basic way of understanding the fundamental components of geography

-geographers have been observers for centuries

-Homer and other Greeks who observed their surroundings and wrote about them are today recognized as geographers as much as they are by other disciplines

v Fieldwork has evolved from its traditional, observational-based origins to a diversity of learning and teaching processes that, since the 1960s and 1970s, have been characterised by increased orientation around study of geographical processes (cf observation of form) and research and problem-solving approaches. Such approaches have necessarily demanded development of subject-specific technical skills, but also the opportunities provided by fieldwork for developing transferable skills (for example teamwork, leadership) and student employability were recognised in the 1980s when such skills became explicit learning objectives of fieldwork (Kent et al, 1997).

v Observation has formally been incorporated into geography through fieldwork.

v fieldwork is nothing more than systematic observation by a geographer of his or her subject matter

v anyone can do fieldwork, and every good geographer does

virtually anyone can do it because fieldwork is, at its most fundamental, just going out and looking at the land

-all the training you need is knowing what to look for

-knowing what to look for involves training in your respective area

-physical geographers, for example, need to understand geomorphology before going out to research the erosion pattern of a slope

-economic geographers need to understand land use types before going out to chart economic patterns in American cities

10.4 The importance of Field Work to Geography

Fieldwork is important to geography because it contributes so fundamentally to geographical research and to our basic understanding of the Earth's surface.

· To understand history in its fullest sense, one cannot just read books about past events or what are commonly called secondary sources

· To understand geography or do geographic research, one must consult primary sourcesin this respect, geographers certainly make use of some of the same primary sources as researchers in other fields do

· Geographers doing research spend much time in the archives looking at original documents like census manuscripts

· Geography, however, has another primary source that is quite different from those used in other fields; this, of course, is the landscape

· The landscape is the primary source of the geographer, whether he or she is a physical, cultural, or economic geographer

-it can be rural or urban

-it contains all of the essential facts of geography and, many would say, the means of explaining those facts

10.5 For Field Work to be Precise and Valid a Geographer has to:

1. Be curious and observant

-you must want to do fieldwork, and you must keep your eyes open

2. Take clear, organized notes

-fieldwork is just sightseeing unless you can use the information later

3. Pay careful attention to your location, making good use of maps

-no matter how detailed your observations are, they are of little value in geography if you cannot link them to a location

-this is where maps come in handy in the field

-making notes about a site at its location on a good map lends precision to your fieldwork

-increasingly, you can note your location accurately by using GPS

-Global Positioning System receivers are lightweight and portable

-they are also becoming quite accurate

-better models can even record and store data for sample locations; you can later download that data directly into a GIS

4. Be consistent: fieldwork is literally data collection, whether it is soil or plant types or religious patterns, so consistency is important for accurate results

The value of good fieldwork will not usually be seen in the field, but will instead show up later . . . when you analyze your field observations.

o remember, fieldwork is data collection

o your observations are thus raw data

o if you have observed things systematically and recorded these observations consistently, your analysis of the data will go smoothly

o you will also be able to do something with your data

-most basic is mapping similar observations

-then, interpret and explain the pattern

-finally, compare the pattern to other patterns

Approaches to Field Work

Historically, two views have tended to dominate fieldwork, at least in American geography (Deductive and Inductive Methods).

Deductive Method

o one of these was common at the University of Chicago

-in this view, geographers studied a particular problem in depth and then went into the field to look for answers to the problem

-this involved the deductive method

-this method can obviously work, but it is very easy to go into the field and simply look until you find what you are looking for

Inductive Method

o another view was held by Carl Sauer at the University of California, Berkeley

-Sauer was probably the strongest advocate of fieldwork in American geography

-he made all of his students to fieldwork, mainly in Mexico and South America

-he himself conducted fieldwork almost every year of his professional life

-he reputedly once said that any mode of transportation faster than a mule was too fast for fieldwork, and he preferred walking

-Sauer's fieldwork philosophy was just the opposite of the Chicago view

-Sauer felt geographers should identify vague topics

-they should then conduct thorough, unbiased fieldwork and simply see what problems and answers the landscape yielded

-this involved the inductive method

-more sound logically and scientifically, in many ways

-the upshot if this was that Sauer send his students into the field with little more than a notebook

-students were not told how to do fieldwork, for everyone does it differently

-they were certainly not told what to look for

-it was really on the job training

-they include step-by-step instructions on a wide range of techniques and skills

-they also include a series of exercises on each of the major topics related to fieldwork

-there is also a superb reading list attached to this site

11. SAMPLING

It is not possible to observe the all population, so we observe the sub set of population which is called sample.

One major characteristics of population is that thjey are never homogeneous. Population is always heterogeneous. And therefore the value of attributes of which we want to collect information from is also heterogeneous. So we get a representative sample to make inferences about a population. And this inference influences the decision making processes. Example what Tanzanians regional division should be based on?

11.1 SAMPLING TECHNIQUE

There are two major sampling techniques these are

· probability sampling

· non probability sampling

A. PROBABILITY SAMPLING

1. RANDOM SAMPLING

Simple random sampling
Stratified random sampling
Systematic sampling
Mult stage sampling

B. NON RANDOM SAMPLING

i. Cluster sampling

ii. Judgemental sampling

iii. Accessibility sampling

iv. Quarter sampling

11.2 SAMPLE SIZE

Perhaps the most frequently asked question concerning sampling is, "What size sample do I need?" The answer to this question is influenced by a number of factors, including the purpose of the study, population size, the risk of selecting a "bad" sample, and the allowable sampling error.

This paper reviews criteria for specifying a sample size and presents several strategies for determining the sample size.

11.3 SAMPLE SIZE CRITERIA

In addition to the purpose of the study and population size, three criteria usually will need to be specified to determine the appropriate sample size: the level of precision, the level of confidence or risk, and the degree of variability in the attributes being measured (Miaoulis and Michener, 1976). Each of these is reviewed below.

The Level of Precision

The level of precision, sometimes called sampling error, is the range in which the true value of the population is estimated to be. This range is often expressed in percentage points, (e.g., ±5 percent), in the same way that results for political campaign polls are reported by the media. Thus, if a researcher finds that 60% of farmers in the sample have adopted a recommended practice with a precision rate of ±5%, then he or she can conclude that between 55% and 65% of farmers in the population have adopted the practice.

The Confidence Level

The confidence or risk level is based on ideas encompassed under the Central Limit Theorem. The key idea encompassed in the Central Limit Theorem is that when a population is repeatedly sampled, the average value of the attribute obtained by those samples is equal to the true population value. Furthermore, the values obtained by these samples are distributed normally about the true value, with some samples having a higher value and some obtaining a lower score than the true population value. In a normal distribution, approximately 95% of the sample values are within two standard deviations of the true population value (e.g., mean). In other words, this means that, if a 95% confidence level is selected, 95 out of 100 samples will have the true population value within the range of precision specified earlier (Figure 1). There is always a chance that the sample you obtain does not represent the true population value. Such samples with extreme values are represented by the shaded areas in Figure 1. This risk is reduced for 99% confidence levels and increased for 90% (or lower) confidence levels.

Degree of Variability

The third criterion, the degree of variability in the attributes being measured refers to the distribution of attributes in the population. The more heterogeneous a population, the larger the sample size required to obtain a given level of precision. The less variable (more homogeneous) a population, the smaller the sample size. Note that a proportion of 50% indicates a greater level of variability than either 20% or 80%. This is because 20% and 80% indicate that a large majority do not or do, respectively, have the attribute of interest. Because a proportion of .5 indicates the maximum variability in a population, it is often used in determining a more conservative sample size, that is, the sample size may be larger than if the true variability of the population attribute were used.

11.4 STRATEGIES FOR DETERMINING SAMPLE SIZE

There are several approaches to determining the sample size. These include using a census for small populations, imitating a sample size of similar studies, using published tables, and applying formulas to calculate a sample size. Each strategy is discussed below.

Using a Census for Small Populations

One approach is to use the entire population as the sample. Although cost considerations make this impossible for large populations, a census is attractive for small populations (e.g., 200 or less). A census eliminates sampling error and provides data on all the individuals in the population. In addition, some costs such as questionnaire design and developing the sampling frame are "fixed," that is, they will be the same for samples of 50 or 200. Finally, virtually the entire population would have to be sampled in small populations to achieve a desirable level of precision.

Using a Sample Size of a Similar Study

Another approach is to use the same sample size as those of studies similar to the one you plan. Without reviewing the procedures employed in these studies you may run the risk of repeating errors that were made in determining the sample size for another study. However, a review of the literature in your discipline can provide guidance about "typical" sample sizes which are used.

Using Published Tables

A third way to determine sample size is to rely on published tables which provide the sample size for a given set of criteria. Table 1 and Table 2 present sample sizes that would be necessary for given combinations of precision, confidence levels, and variability. Please note two things. First, these sample sizes reflect the number of obtained responses, and not necessarily the number of surveys mailed or interviews planned (this number is often increased to compensate for nonresponse). Second, the sample sizes in Table 2 presume that the attributes being measured are distributed normally or nearly so. If this assumption cannot be met, then the entire population may need to be surveyed.

GE: 249: RESEARCH METHODS IN GEOGRAPHY