Descriptive research design

DESCRIPTIVE REASEARCH DESIGN: -
SURVEY AND OBSERVATION

Survey method: -

A structural questionnaire given to a sample of population and designed to elicit specific information from respondents.

NATURE OF SURVEY RESEARCH.

q Survey researcher must be concerned with
a. Sampling
b. Questionnaire design
c. Questionnaire administration
d. Data analysis.

q The administration of questionnaire to an individual or group of individuals is called an interview.

q Conditions for successful interview
1. The respondent must have the information, which is sought by the interviewer.
2. The respondent should understand what is required and expected.
3. The respondent should feel motivated to answer questions accurately.
4. The respondent should be serious about the matter and answer the question throughout.

q Task of interviewers.
1. Locating the respondents Ex Probability sampling of area sampling requirements.
2. Initiate the interview.
3. Give idea about the interview & its purpose.
4. Interviewer should be patient & courteous.
5. Assure of confidentially.
6. Ask only necessary questions.
7. Ask questions in same phrase & sequence.
8. Don’t influence the ideas.
9. Understand customer responses.
10. Don’t emphasize on any words.
11. Note down the responses properly.
12. Use technology wherever necessary.

q Selection of interviewer.
1. He should possess good health to do hard work.
2. The person should be extrovert.
3. The person should be well-behaved and good personality.
4. Knowledge of local language is essential.
5. He should have proper education to handle research.
6. He should be capable of handling he communication process.

q Training of interviewers: -

1. Specify the guidelines for conducting interview.
2. Make aware of technical specifications.
3. The initial training should be given to explain his role in the research.
4. Train them on research methodology.
5. Have a rehearsal research in the organization.
6. Provide background information.

q Supervision of interviewers: -

1. Gathering & training interviewer on fundamentals of interviewing.
2. Allocation of territory.
3. Carefully study first day’s work & correcting errors.
4. Editing all work.
5. Keeping careful production records.
6. Reviewing time sheets.
7. Reducing detailed bill for work.

q Types of interviews.

A. Structured interviews.
1. The amount of freedom the interviewer has in altering the questionnaire to meet the unique situation posed by each interview.
2. Interviewer bias is less.
3. It is possible to use less skilled interviewers because their main job is to read question and record the responses.

B. Unstructured interviews:
1. Used when the knowledge about variables is less.
2. This method used in he exploratory surveys.
Directness: - The extent to which the respondent is aware of the underlying purpose of the survey.

C. Direct interview:
1. Asking the questions such that the respondent is aware of the underlying purpose of the survey.
2. Usually the name of the firm is kept confidential.
3. It is easy to answer for the respondents.
4. The responses can be easily interpreted.
5. These are also known as non-disguised interviews.

D. Indirect interview:
1. Disguised interviews.
2. Involves asking questions such that the respondent does not know what the objective of the study is. Ex: Attitude measurement.

q Types of surveys:

Survey methods

Telephone interview Personal interview Mail interview Electronic interview


Traditional Computer assisted In home Mall intercept Computer assisted


Mail Mail Panel E – Mail internet


I. Traditional telephone interview:

Ø Phoning a sample respondent and asking them series of questions.
Ø Uses the paper questionnaire and records the responses with a pencil.
· Computer assisted telephone interview.
Ø Computerized questionnaire administered to respondents over the telephone.
Ø Uses the CRT and headset in the research.
Ø Data collection flows naturally & smoothly.
Ø Time is reduced and quality is enhanced.
Ø Data processing easy.



















STEP 3:

OVERCOMING INABILITY & UNWILINGNESS TO ANSWER.


1) Inform the respondent.
2) If respondents are not likely to be informed filter questions that measure familiarity, product use and experience should be asked before questions about the topic themselves.
3) Can he respondent remember?
4) Questions that do not provide the respondent with cues can underestimate the actual occurrence of an event.
5) Can the respondent Articulate?
6) Minimize the effort required of the respondents.
7) Check whether question asked is appropriate.
8) If the information is sensitive.
a. Place sensitive topics at the end of the questionnaire.
b. Preface the question with a statement that he behavior of interest is common.
c. Ask the question using third person technique.
d. Hide the question in-group of other questions that respondents are willing to answer.
e. Provide response categories rather than asking foe specific figures.
f. Use randomized techniques.












STEP 7:

FORM & LAYOUT OR PHYSICAL CHARACTERSTICS.

Divide the questionnaire into several parts.
Questions in each part should be numbered.
The questionnaire should be precoded.
The questionnaires themselves should be numbered serially.





STEP 8:

REPRODUCTION OF QUESTIONNAIRE.


The questionnaire should have a professional appearance.
Booklet format should be used for long questionnaires.
Vertical response column should be used.
Grids are useful when there are a number of related questions that use the same set of response categories.
The tendency to crowd questions to make the questionnaire look shorter should be avoided.
Directions or instructions for individual questions should be placed as close to the questions as possible.








STEP 9:

PRESENTING & FINAL DRAFT.


1. Always pretest.
2. All aspects of the questionnaire should be tested including question content, working, sequence form and layout & instructions.
3. The respondents in the pretest should be similar to those who will be included in the actual survey.
4. Begin the pretest by using personal interview.
5. Pretest should also be conducted by mail, telephone or electronically; if those methods are to be used in the actual survey.
6. A variety of interviewers should be used for pretests.
7. The pretest sample size is small, varying from 15 to 30 respondents for the initial testing.
8. Use protocol analysis and debriefing to identify problems.
9. After each significant revision of the questionnaire another pretest should be conducted, using a different sample of respondents.
10. The responses obtained from the pretest should be coded and analyzed.










STEP 4:

CHOOSING QUESTION STRUCTURE
OR
DECISION ABOUT THE RESEARCH RESPONSE FORMAT
OR
TYPE OF QUESTIONS.


Questions


Structured Unstructured


Multiple Choice Dichotomous Scale Open end


Structured questionnaire.

Questions that prespecify the set of response alternatives and the response format.

A. Multiple choice questions:
The researcher provides choice of answers and respondents are asked to select one or more of the alternatives given.

Ex 1: Do you intended to buy a new car
Ø Definitely will not buy.
Ø Probably will not buy.
Ø Undecided.
Ø Probably will buy.
Ø Definitely will buy.






Ex 2: What was the brand name of the last soft drink you purchased?

Pepsi Seven-up mountain dew

Coco-cola Thumbs Up Sprite

Maaza Mirinda Others


Advantages of multiple-choice questions:

1. Easier for both respondent & researcher.
2. They reduce the interviewer bias.
3. Tabulation & analysis are much simpler.
4. Can use maximum number of choices.

Dis-advantages of MCQ:

1. It requires considerable effort to generate variables.
2. It may cause distortion.
3. It may result in order bias or position bias (choosing one without knowledge).
4. Respondent will have some other alternative.

Issues with multiple-choice questions.

a. Number of alternatives.
b. Balanced or unbalanced alternatives.
c. Position bias.

Split ballot technique.

Dichotomous Questions:

o Extreme form of multiple choice.
o Example.
a. Yes or No
b. Agree or Disagree.
c. Male or Female

Advantages:

1. Researcher can ask clear-cut questions.
2. Researcher should think whether response will be dichotomous or not.
3. It is easy to codify and analyze.

Dis-advantages:

1. Entire research result may be biased or may have negative answers.

Issue:
1. Adding of neutral alternative.

UNSTRUCTURED QUESTIONS:

Open-end questions that respondents answer in their own terms & words.

Examples:
1. What is your occupation.
2. What is your favorite political personality.
3. What brand of cigarette do you generally smoke.

Advantages.

ü They do not influence respondent.
ü They generate wide variety of response.
ü Researcher can judge actual values.
ü Respondent have opportunity to express his variables.

Dis-advantage:

1. Respondent
2. Interviewer effects.
3. Necessity of precoding.

Open end Questions Classification.



Free response Probing Projective technique
STEP 5:
DETERMIE OF THE QUESTIONNAIRE
OR
DECISION ABOUT QUESTUION PHRASING
OR
CHOOSING QUESTION WORDING

IMPORTANCE QUESTION WORDING.

1. These translate question into more understanding way.
2. It determines the success of the response.
3. Data analysis complexity depends on type of words used.
4. Poor wording results in response error.

DEFINE THE ISSUE.


Where
Who

What
Why
Way
WhenSix W’s






Find out customer choice of shampoo brand?
Which brand of shampoo use? (Incorrect).

Six W’s:
When is not clear.
Where is not clear.
What is semi answered.

ü Which brand /brands of shampoo have you personally used at home during the last month? In case of more than on brand, please list all the brands that apply. (Correct)

USING ORDINARY WORDS.

§ Simple words are necessary because education level of people varies.
§ Don’t use technical and management jargon.

Ask question to find out availability of Pepsi is enough.

Do you think the distribution of Pepsi is adequate. (Incorrect).

ü Do you think Pepsi is readily available when you want to buy them. (Correct).

AVOID AMBIGUOUS WORDS.

1. The words in a questionnaire should have a single meaning that is known to respondents.
2. Certain words have different meanings to different people.
3. Don’t use “usually”, “frequently”, “often”, “regularly”, “occasionally”, & “sometime”.
4. Ask following question before using such words.
a. Does it mean what we intended.
b. Does it have any other meanings.
c. If so, does the context make the intended meaning clear.
d. Does the word have more than one pronunciation.
e. Is there any word of simpler pronunciation that might be confused with this word.
f. Is a simpler word or phrase suggested.

Prepare a question to know the frequency o shopping in a month in Bangalore Central,

In a typical month, how often do you shop in Bangalore Central.

a. Never
b. Occassionally
c. Sometimes.
d. Often. Regularly (Incorrect)



In a typical month, how often do you shop in Bangalore central.

a. Less than once.
b. 1 or 2 times.
c. 3 or 4 times.
d. More than 4 times. (Correct)

AVOID LEADING QUESTIONS.

A Question that gives the respondent a clue as to what the answer should be.

Do you think that patriotic Indians should buy imported computers when that would hit Indian domestic computer manufacturers.

Yes, No, Don’t know, (Incorrect).

Do you think that Indians should buy imported computers.

a) Yes.
b) No.
c) Don’t know. (Correct)

AVOID BIASED QUESTIONS.

§ Biased phrases are difficult to deal with because phrases that are neutral to one group may be emotionally charged to another.
§ These are also called as loaded questions.
Prepare a question to find out what promotional activities Hyundai is doing to increase its sales using its Euro III pollution norms.

Do you think that Hyundai is doing everything possible to increase its sales using Euro III pollution norms. (Incorrect)

Do you think Euro III pollution norms of Hyundai will increase its sales. (Correct)
AVOID IMPLICIT ALTERNATIVES.

§ An alternative that is not explicitly expressed.
§ Making an implied alternative explicit may increase the percentage of people selecting the alternative.
Find answer for mode of transport in short distance.
Do you like to fly when traveling short distance. (Incorrect).
Do you like to fly when traveling short distances o would you rather drive.(Correct Partially).

Please mention the mode of transportation do you use for short distance.

a. Air.
b. Rail.
c. Road.


AVOID IMPLICIT ASSUMPTIONS.

§ Question that contain implicit assumption.
§ These are not stated in the question.
§ Answer depends on assumption about factors outside the question itself.

Construct question to know whether people prefer advertisement in movie theatres though there is increase in ticket prices by Rs.2/-

Q : Do you favor ban on commercial in movie theatres even if it meant
Rs. 2/- increase
in ticket prices. (Incorrect).

Do you favor ban on commercial in movie theatre. (Correct).

· To find out the impact of service tax on IT industry in the current chidambaaram budget.

Q : Are you in favor of service tax on IT industry. (Incorrect)

Are you in favor of service tax which may decrease its sales. (Correct).


AVOID DOUBLE BARRALLED QUESTIONS OR COMBIAING QUESTIONS.

§ A question that calls for several responses

Find out Kellogg Cornflakes spiciness & tastiness.

Q : Do you consider Kellogg Cornflakes spicy & tasty. (Incorrect)
a. Do you consider Kellogg cornflakes spicy
b. Do you consider Kellogg cornflakes tasty. (Correct).


BE SPECIFIC OR AVOID GENERALIZATION.

§ General results generate meaningless data.

What kind of car do you own.

Answers will be based upon.
1. Brand (Indica, Zen, Santro)
2. Type (Passenger, MUV, SUV)
3. Gasoline (Petrol or Diesel)
4. Model (V2‑ V2 deluxe, V2 New)




AVOID LENGTHY QUESTIONS.

a. It may discount the mood of respondent.
b. Respondent may confuse.
c. Respond may not answer.

































STEP 6:
A. DETERMINE ORDER OF QUESTION
OR
DETERMINE ABOUT THE QUESTION SEQUENCE
OR
DETERMINE QUESTION STRUCTURE.

Question sequence:
The specific order in which the respondent receive the questions.

v The sequence of the questionnaire should start with statement of problems and topic’s purpose. It will be more attractive if it contains a formal request.

OPENING OR LEAD IN QUESTION:

Ø Introduce yourself.
Ø It should be easy to answer.
Ø It should be objective & interesting.
Ø It should not contain biasing question or leading question for rest of the part.

Dear Sir/Madam,
We are carrying out a study on buying behavior of households in television purchase. We would appreciate if you will please convey your views on the different question referred to in this schedule. On the behalf of the sponsors of this research study. I thank you for sparing your valuable time and co-operation.

(Signature)

Q 1: a) Do you own a television

a). Yes b). No

b). If yes please mention the brand /brands name. ---------------------

c). If No please go to question 7.

IInd Example.

Q 1: When did you last paint your house.

Less than 1 year back.


Between 1 – 2 years back.

More than 2 years back.


IIIrd Example.

Q I: How would you classify your hair.

Natural

Dry.

Oily.

IVth Example.

Q 1: Do you use toothpaste.

Yes

No



TYPE OF INFORMATION.

Ø Basic information: relates to basic formula
Ø Classification information: socio economic & Demographic character used to classify respondents.
Ø Identification information: Questions regarding, have address & phone number.

Basic.

Classification.

Identification.


QULIFYING QUESTIONS:

It is practical importance to confine the interview to people who have the background or are type for meaningful responses.

Example 1:

a. Do you use any toothpaste

Yes

No

If no stop asking question or Go to general questions.








Example 2:

Have you ever used any of the diabetic’s injection of these following companies.

a. Novo Nordisk

b. Ranbaxy

c. Cipla

d. Others

WARM UP QUESTION:

Example 1:

How many brands of toothpastes have you used in your lifetime. Please specify.
Example 2: Please rank the following attributes of toothpaste on a five-point scale ranging from most important to less important.

i. Taste.
ii. Foam.
iii. Freshness.
iv. Prices.
v. Packaging.
vi. Manufacturer name.






DIFFICULT QUESTION:

These are sensitive, embarrassing, complex or dull should be placed late in the sequence.
Research Bangalore central brand equity analysis.

ü Credit Card information should be asked at the end of the basic question.
ü Income should be he last question in classification section.
ü Telephone number should be at the end for identification number.

IDENTIFICATION QUESTIONS:

Name,
Age,
Telephone
Number,
Address,
Habits,
Occupation.

Funnel approach: or Flower pot Approach.

A strategy for ordering questions in questionnaire in which the sequence starts with the general questions, which are followed by progressively specific question, in order to prevent specific questions from biasing general questions.