You are on page 1of 23

MODULE IV

Data Collection Field Force

Field Procedures
Fieldwork involves the selection, training, supervision, and evaluation of individuals who collect data in the field. The twin objectives of the field work are •To maximize the flow of pertinent , accurate data, and • To minimize the errors committed by the interviewers.

. Interviewers read the questions and either type in the answers or use “light pen” to mark the answers on the video screen.When telephone interviewing is computer-assisted. Data are entered in the computer directly so that at any time the results can be summarized quickly.• • • • Several means of gathering primary data areTelephone interviewing Personal interviewing Mail surveying Observation Telephone interviewing. the paper questionnaire is replaced with a video screen.

Sometimes recruitment is done with the help of local sources such as newspapers and educational institutions. . The sampling sites are matched against these files and qualified workers are selected.Most fieldwork organizations keep a file of fieldworkers by geographical location.Personal Interviewing Recruitment .

Since most field-work must be done within a limited time period and interviewers are widely dispersed. .When the interviewers commence the field-work.Training. training is usually done by mail. at least to the extent of ensuring they are proceeding on schedule and their work is satisfactory. On some projects the training is given by supervisors in person at one or few central locations.After field-workers are selected they have to be trained. Supervision. they need to be supervised.

• Observation plans can specify the details of who. • When the plans are carefully administered. where. when. the observers well trained. instructions adhered to.Observation – • Some form of systematic procedures would be valuable in observation research situations. observational research can be fruitful. and observers supervised. . and how to observe an object or individual. what.

stuff them with the questionnaire and other materials and mail them.Mail Survey In this medium of data collection there is no field worker and no personal interface. Edit the questionnaires returned and prepare them for data processing. All the functions are shifted to persons in some central office location. whose tasks are of these typeCompile or purchase address lists of the desired kinds of respondents who are located within the sampled areas. Address envelops. To those not responding by a selected cut off date. • • • • . mail follow-up entreaties and questionnaires.

Nonresponse error 3. Interviewer cheating . Errors in selecting respondents 2. Errors created by the method of seeking data 4.Common sources of error in fieldwork Five common sources of error in fieldwork are1. Errors resulting from interviewers misinterpreting or misrecording answers 5.

2. 5.Minimizing Fieldwork Errors To improve the overall quality of fieldwork . Administrative procedures for handling projects in the field. Supervision of field-workers and the datacollection process. Validation of fieldwork. . Quality and cost control procedures. 4. most research organizations pay attention to five factors 1. 3. Selection and training of field workers – interviewers and observers.

Tabulation Tabulation means sorting of the data into different categories and counting the number of cases that belong to each category. Tabulation is another way of summarizing and presenting the given data in a systematic form in rows and columns. The major objectives of tabulation are•To simplify the complex •To economize space •To depict trend •To facilitate comparison •To help as a reference .

Parts of a table :• • • • • • • Table number Title of the table Caption/Column head Stub/Row head Body of the table Foot Note Source .

Caption column Stub Row head Row head Row head column column Body of the table Foot note………… Source…………… .Example Table number ……….Title……….

This is called univariate tabulation. Univariate tabulation.The simplest way to tabulate is to count the number of responses to one questions.Types of tabulation1. .

of respondent 9 15 13 10 8 5 60 Percentage of respondent 15 25 22 17 13 8 100 0 1 2 3 4 5 . of movies Seen per week No.• ExampleNo.

This is also known as cross.It may often be necessary to tabulate responses to two or more questions simultaneously. Such tabulations are known as Bivariate or multivariate tabulation .2. Bivariate or multivariate tabulation. depending on whether two or more than two variables are involved. .tabulation.

Example – Preference for shopping center by income level of households Income level Shopping center (A) Shopping center (B) Total no. 10.000 Rs.000+ Total 100 120 220 200 80 280 300 200 500 .10.of households Up to Rs.

(2) Marital status (3) Gender .(1) high or low categories based on their purchase of fashion clothing.Example of Multivariate tabulation Purchase of fashion clothing by Marital status and Gender: Purchase of Fashion clothing High Low male marital status female Marital status married unmarried married unmarried 35% 65% 40% 60% 25% 75% 60% 40% Three variables are.

• The second problem in a two.way tabulation is which base should be used for 100 percent. One simple rule is. percentage should be computed in the direction of the causal factor.Problem in Cross-Tabulation • One has to first determine which data should be given primary emphasis and which should be given secondary emphasis. . Whichever is relatively more important. Data with primary emphasis are normally given in columns while those with secondary emphasis are shown in rows. as the data may be percentaged in either dimension. Percentage should be based on totals of rows or column.

the following information was received. Town B: Males were 55%. Represent this data in a tabular form. Total coffee drinkers were 45% and male non-coffee drinkers were 20%. Male noncoffee drinkers were 30% and female coffee drinkers were 15%. Town A: Female were 40%.In a sample study about coffee drinking habits in two towns. .

out of a total of 4000 workers in a factory. 3300 were members of a trade union. . Present the following information in a suitable form : In 2003. The number of non-union workers was 760 of which 330 were women. the number of workers in the union was 3450 of which 3200 were men.Q. The number of women workers employed was 500 out of which 400 did not belong to any union. In 2004.

Study Health Foods Ltd. as the company is a small one. . It is interested in testing a newly developed protein snack. However. The Health Foods Ltd. it is not in a position to hire the services of a marketing research firm.Case. is a small private limited company which manufactures nutritious snacks especially for children.

Desai.e. to invite a group of 10 to 15 women to test the new snack. Desai was also told that if she so liked she could invite her friends and neighbours. i. She was advised to invite only married women with children belonging to three major categories. Mrs. high. one of its senior employees.The company management has asked Mrs. . middle and low income groups. provided they fitted the above requirements.

Questions:1. specify it. . 3. specify them. Is it possible to use a better sample design? If yes. Are there any factors that may distort the results? If so. What sample design is being used by Mrs. Desai? 2.