As a preliminary to a discussion of the role that theory plays in a sample survey, it is useful to describe briefly the steps involved in the planning and execution of a survey.
The principal steps in a survey are grouped somewhat arbitrarily under 11 headings.
The first step when assessing a sample survey is to well identify the general objectives of the survey. Without a lucid statement of the objectives, it is easy in a complex survey to forget the objectives when engrossed in the details of planning, and to make decisions that are at variance with the objectives.
One of the principal choice is between average values (mean of the population) or total values. In fact, depending on this choice, techniques for the optimal sample size and estimators factors are different.
A number of measures exist that have been used by various agencies to measure the economic significance of fisheries to the regional economy. In addition, a number of performance indicators also exist that can be used to assess the performance of fisheries management in achieving its economic objectives (see chapter 1 and related annexes).
The word population is used to denote the aggregate from which the sample is chosen. The definition of the population may present some problems in the fishing sector, as it should consider the complete list of vessels and their physical and technical characteristics.
The population to be sampled (the sampled population) should coincide with the population about which information is wanted (the target population). Some-times, for reasons of practicability or convenience, the sampled population is more restricted than the target population. If so, it should be remembered that conclusions drawn from the sample apply to the sampled population. Judgement about the extent to which these conclusions will also apply to the target population must depend on other sources of information. Any supplementary information that can be gathered about the nature of the differences between sampled and target population may be helpful.
For example, let us consider the Italian statistical sampling design for the estimation of quantity and average price of fishery products landed each calendar month in Italy by Community and EFTA vessels (Reg. CE n. 1382/91 modified by Reg. CE n. 2104/93). Aim of the survey is to estimate total catches and average prices for individual species. Therefore, the sampling basis consists of the more than 800 landing points spread over the 8 000 km of Italian coasts. It is not however feasible to consider the list of the landing points as the list of elementary units. To overcome these difficulties, a sampled population, distinct from the target population but including units in which the considered phenomenon takes place, has been considered. In synthesis, the elementary units considered are the landings of the vessels belonging to the sampled fleet. Thus, the list from which the sampling units are extracted is constituted by all the vessels belonging to the Italian fishery fleet.
It is well to verify that all the data are relevant to the purposes of the survey and that no essential data are omitted There is frequently a tendency to ask too many questions, some of which are never subsequently analysed. An overlong questionnaire lowers the quality of the answers to important as well as unimportant questions.
The results of sample surveys are always subject to some uncertainty because only part of the population has been measured and because of errors of measurement. This uncertainty can be reduced by taking larger samples and by using superior instruments of measurement. But this usually costs time and money. Consequently, the specification of the degree of precision wanted in the results is an important step. This step is the responsibility of the person who is going to use the data. It may present difficulties, since many administrators are unaccustomed to thinking in terms of the amount of error that can be tolerated in estimates, consistent with making good decisions. The statistician can often help at this stage.
There may be a choice of measuring instrument and of method of approach to the population. The survey may employ a self-administered questionnaire, an interviewer who reads a standard set of questions with no discretion, or an interviewing process that allows much latitude in the form and ordering of the questions. The approach may be by mail, by telephone, by personal visit, or by a combination of the three. Much study has been made of interviewing methods and problems.
A major part of the preliminary work is the construction of record forms on which the questions and answers are to be entered. With simple questionnaires, the answers can sometimes be pre-coded, that is, entered in a manner in which they can be routinely transferred to mechanical equipment. In fact, for the construction of good record forms, it is necessary to visualise the structure of the final summary tables that will be used for drawing conclusions.
Information may be collected using a number of different survey methods. These include personal interview, telephone interview or postal survey. The questionnaire design needs to vary based on the approach taken.
Personal interviews involves visiting the individual from which data are to be collected. The interviewer controls the questionnaire, and fills in the required data. The questionnaire can be less detailed in terms of explanatory information as the interviewer can be trained on its completion before starting the interview process. This type of survey is best for long, complex surveys and it allows the interviewer and fisher to agree a time convenient for both parties. It is particularly useful when the respondent may have to go and find information such as accounts, log book records etc. The personal interview approach also allows the interviewer to probe more fully if he/she feels that the fisher has misunderstood a question, or information provided conflicts with other earlier statements.
Data collectors are usually external to the phenomenon that is being examined and, moreover, they are often part of some public structure, in order to avoid possible influences due to personal interests. However, on the basis of the experience acquired in this field by Irepa, it has been demonstrated (Istat, Irepa 2000) that it is essential to have data collectors belonging to the fishery productive chain in order to obtain correct and timely data. Therefore, data collectors should belong to the productive or management fishery sectors.
During meetings on socio-economic indicators partners involved presented several questionnaires. These questionnaires are aimed to collect the information required to calculate the socio-economic indicators and some of them are reported in appendix C.
There is a variety of plans by which the sample may be selected (simple random sample, stratified random sample, two-stage sampling, etc.). For each plan that is considered, rough estimates of the size of sample can be made from a knowledge of the degree of precision desired. The relative costs and time involved for each plan are also compared before making a decision.
Sample units have to be drawn according to the sample design.
To draw sample units from the population, several methods can be used, depending on the type of the chosen sample strategy:
sample with equal probabilities
sample with probabilities proportional to the size (PPS).
In the first case, each unit of the population has the same probability to take part of the sample, while in the case of a PPS sample each unit has a different probability to be sampled and this probability is proportional to the following measure: Pi = Xi/Xh, where, i = a generic vessel, h = stratum, X= a size parameter, for example the overall length of a vessel.
It has been found useful to try out the questionnaire and the field methods on a small scale. This nearly always results in improvements in the questionnaire and may reveal other troubles that will be serious on a large scale, for example, that the cost will be much greater than expected.
In a survey, many problems of business administration are met. The personnel must receive training in the purpose of the survey and in the methods of measurement to be employed and must be adequately supervised in their work.
A procedure for early checking of the quality of the returns is invaluable.
Plans must be made for handling non-response, that is, the failure of the enumerator to obtain information from certain of the units in the sample.
The first step is to edit the completed questionnaires, in the hope of amending recording errors, or at least of deleting data that are obviously erroneous. The check on the elementary data to eliminate non-sampling errors can be achieved by means of computer programmes implemented to correct the erroneous values and to permit statistical data analysis. These programmes are mainly based on graphical analysis of elementary data.
Thereafter, the computations that lead to the estimates are performed. Different methods of estimation may be available for the same data.
In the presentation of results it is good practice to report the amount of error to be expected in the most important estimates One of the advantages of probability sampling is that such statements can be made, although they have to be severely qualified if the amount of non-response is substantial
The more information we have initially about a population, the easier it is to devise a sample that will give accurate estimates. Any completed sample is potentially a guide to improved future sampling, in the data that it supplies about the means, standard deviations, and nature of the variability of the principal measurements and about the costs involved in getting the data. Sampling practice advances more rapidly when provisions are made to assemble and record information of this type.
Figure 1: The principal steps in a sample survey