INTRODUCTION TO SURVEYS

 

TABLE OF CONTENTS

Introduction
What is a survey?
What kinds of questions are asked?
When is a survey conducted?
How is survey information used?
Types of surveys
Concerns when using survey data
SALDRU data Information

 

INTRODUCTION

Prior to analyzing survey data, in an attempt to answer questions relating to the social and economic conditions of a given population, we must first understand: where the survey data comes from, how it is collected, and what concerns, if any, a researcher should have in using survey data.

In the following module, you will be given a basic introduction to surveys which will hopefully enable you to use household survey data in future research.

WHAT IS A SURVEY?

Have you ever been asked to fill out a customer satisfaction questionnaire? Or asked to give your opinion about a political issue? If you answered "no" to both of these questions, congratulations! You have just taken part in your first survey. If you answered "yes," then you are already an expert.

In general, a survey usually involves the collection of data by interviewing a sample of people. Often times, however, the group of interest is too large to interview completely. It would take too much time and money to question everyone in China, each farmer in South America, or each car owner in Europe. In these cases, a smaller selection, excerpt, or sample of the larger population is selected for questioning. The group of people, households, towns, villages, cities, or countries that participate in the survey is called the survey sample. Each person in the selected sample is asked the same series of questions, and the responses are then organized so that conclusions can be drawn from them.

WHAT KINDS OF QUESTIONS ARE ASKED?

Survey questions may ask about a wide range of topics such as people's behavior, attitudes, how and where they live, and information about their economic and social backgrounds (demographic data).

Behavior - Many survey questions relate to people's actions or behavior in various social areas. In economic research, for example, patterns of spending and saving have been studied intensively using surveys. Other types of projects examine such behaviors as voting, reading, visits to the doctor, geographical movements, and recreational habits.

Attitudes - Some survey questions concern people's beliefs, opinions, attitudes, or expectations. These are areas in which it is unlikely that data would be available from non-survey sources.

Environment - In many surveys it is important to have data on the circumstances in which respondents live in order to interpret their responses more accurately. This includes information about the neighborhood, the adequacy of living quarters, membership in groups and organizations, and so on.

Personal Descriptive (demographic) - Surveys always include questions regarding personal-social characteristics of respondents such as sex, age, occupation, income, and education. This kind of information helps researchers interpret the opinions people express in surveys, since people who share particular demographic characteristics also tend to share opinions on social issues. For instance, we can find out how many people aged 20-29 own cars and how car owners in this age group compare with those in other age groups. Certain kinds of demographic data, however, are more significant and useful in some areas of research than in others. For example, in an election study, a respondent's nationality or where he or she grew up would be more important to know than in an economic study.

WHEN IS A SURVEY CONDUCTED?

Surveys are conducted when the desired information cannot be obtained in a more accurate and less expensive manner. For example, it would be inefficient and too costly to conduct a sample survey to determine the number of automobiles in use in the United States. This information can usually be obtained more quickly and more reliably from state licensing bureaus. On the other hand, a survey would be required to obtain information about automobile users. For instance, no recorded information is available on the occupations, buying intentions, driving habits, or other characteristics of automobile owners. In this case, interviewing each individual car owner in the United States would be prohibitively expensive and time consuming, thus it would be far more feasible, efficient, and less expensive to collect information on only a small representative sample of car owners.

HOW IS SURVEY INFORMATION USED?

After gathering various kinds of information, the study director is then in a position to analyze the data and consider the problem in light of these data. He or she will be concerned with such matters as how many, who, how, and why. A survey on the use of public libraries, for instance, might be designed to answer questions like these:

The answers to such questions are of interest to many people. For example, librarians, educators, and publishers would find them useful when they consider the practical problems of improving facilities. They might also be useful to theoretical researchers interested in studying the manner in which the public is reached and influenced by information from various sources. After the survey data have been analyzed, a paper or report is usually prepared which is generally published and made available to the public. The survey results can then be used as a basis for changing, improving or even discarding existing procedures. Survey data are also used by other researchers to increase their knowledge of a field or to define new areas for investigation.

TYPES OF SURVEYS

Today, surveys are being used in public opinion polling and other types of social research, market research, and census taking. These types of surveys and the various ways in which they are used are described briefly below:

Descriptive Statistical Survey - This kind of survey is conducted largely by governments to obtain major descriptive information about their population and its density, the composition of their labor force, national health statistics, and so forth. From early on, governments have taken inventories of their human resources for taxation, military, and legislative purposes. In addition, democratic procedures in government brought forth a need for better communication between people and their officials. Government agencies such as the U.S. Census Bureau conduct or sponsor a wide variety of surveys designed to collect information on many aspects of life in this country.

Survey for Social Research - The social survey is a major research method used by social scientists to gather and analyze information about the social and economic conditions of a population or segments of a population. This information leads to a better understanding of human beings in their social setting.

Market Research Survey - Another type of survey activity is carried on by businesses in consumer market research. Each year, many surveys are conducted by market research groups to determine consumer needs and the effectiveness of marketing programs. Market surveys focus on consumers' attitudes toward current products as well as on possible demand for new products.

CONCERNS WHEN USING SURVEY DATA

Up to this point things may seem a bit simple, but there are several aspects related to surveys one must consider carefully prior to using any survey data.

Does the survey design introduce bias into the data?

Both the phrasing and the manner in which questions are asked can introduce bias into a survey. Bias occurs when the results obtained in a survey are systematically skewed and thus do not accurately reflect the real state of the world. With bias in the data, we cannot develop accurate predictions using descriptive or inferential statistics.

A Potential Bias - "What does this question really measure?"

One concern is related to the actual survey questions themselves. It is quite possible that the information respondents are providing for a given question is not what the researcher was looking for. For example, if we are interested in how much a respondent earns in a year, does it matter how we ask our questions? Is it satisfactory to ask someone "How much do you make?"

This again may seem quite straight forward, but given the tremendous variation in the background and circumstances of the respondents, wording of questions can have a significant impact on the qualtiy of information received.

Returning to our example, does asking "How much do you make?" accurately assess what we are trying to measure? That is, by asking this question will the respondent give us the amount he or she earns in a year? What would you guess?

Given our question, it is quite possible that the respondent would provide us with his or her hourly, weekly, or monthly earnings. It is also possible that the respondent would provide us with the earnings from one job, even though he or she is employed at two or three jobs. Finally, the respondent could accurately provide us with the earnings received in the last year, but instead of providing this information for him or herself alone, the answer could reflect the entire household or family earnings for that year.

In general, the wording of a question can play a tremendous role in the information respondents provide, thus when using survey data it is important to understand what the information truly represents. Further, it is important to consider the ordering of questions in a survey, who asks the questions, and how the survey questions are asked, as each of these are also potential sources of bias in the data.

What level of information are you interested in?

Responses can be measured for any unit of analysis. Example units of analysis are: individuals, households, neighborhoods, businesses, provinces, or even countries. For this reason, you need to determine at which level you wish to conduct your survey, or if someone else has conducted the survey, at which level you are going to analyze the data.

For example, a survey may collect information at the household level, meaning the responses are in terms of the respective household. Thus, a question related to income would reflect the income of the entire household; a question related to the amount of food eaten would reflect the amount eaten by the entire household.

It is also possible for a survey to ask questions that will result in numerous levels of information. For example, a survey may have questions relating to the amount of money earned by the entire family (which would produce a "family" level variable), while at the same time have questions relating to how much the individual earns (which would produce an "individual" level variable).

Given this added complexity, it is important to determine early on in the research process - at what level is the survey conducted. From here, one can decide the types of analyses and the level of information to use.

SALDRU DATA INFORMATION

Throughout this workshop, we are going to use the statistics program STATA and the SALDRU data set to examine questions in areas such as education, health care, and quality of life. Below is a brief introduction to the SALDRU data set which should prove useful in your future analyses.

What is the SALDRU data set?

The South Africa Integrated Household Survey (SAIH) was developed and conducted by the South Africa Labour Development Research Unit (SALDRU) in the School of Economics at the University of Cape Town in collaboration with the World Bank. The survey was designed to provide broad measures of South Africa’s living standards for policy makers to enable them to create strategies for combating poverty.

Development of the survey’s questionnaire was a crucial phase of the data collection process. Determining what information would be needed and how to phrase questions on the survey were issues that were discussed extensively. After twelve drafts of the questionnaire, collaborators decided to include questions pertaining to:

For more information on the collaborating partners, visit their home pages:

University of Cape Town SALDRU
UCT - School of Economics The World Bank

 

BACK TO TOP