Item construction is a research instrument consisting of a series of questions for the purpose of

gathering information from respondents. They are a kind of written interview and uses both open
and closed questions to collect data. An optimal item construction should be valid, reliable, clear,
succinct and interesting. The following are the procedures for optimal item construction in
survey research:

1.Deciding on the information required

It Should be noted that one doesn't start by writing questions, the first step is to decide what are
the things one has to know from the respondents in order to meet the surveys objectives. It
Should appear in the research brief and research proposal.

2. Define the target respondents

These includes the following;

 Demographic characteristics such as age, sex, religion, urban or rural residents, income
level, social class, education, language status and ethnic group.
 Job or social category such as policy makers, doctors, nurses, factory workers, religious
leaders or University students.
 Other relevant characteristics. Some individuals or groups may be disproportionately
affected by TB such as persons living with HIV/AIDS, imprisoned, homeless people or
drug users.

3. Choose the methods of reaching targeted respondents.

 Face to face interview. These are surveys conducted to the person being interviewed
by the interviewer who always travels to the person being surveyed. It leads to higher
respondent rates but also it is costly and time consuming.
 Telephone interviews. Are always conducted from the central office that places telephone
calls to the selected households or businesses.
 Mail questionnaires. These are the written surveys that are sent through mail to the
population to be surveyed. They give good respondents rates with rigorous follow up
procedures but also they may not reach the targeted respondents.
  Internet questionnaires. These are a form of written survey. Respondents may be invited
to participate in the survey

4. Decide on the question content.

There are a series of questions that should be posed as the researchers develop the survey
questions themselves;
 Is this question sufficient to generate the required information?
 Can the respondents answer the question correctly?
 Are there any external events that might bias response to the question?
 Do the words have the same meaning to all respondents? For example how many
members are there in your family?

5. Develop the question wording.

 Contingency questions or cascade format.
 Matrix questions
 Closed ended questions
 Open ended questions

6. Presentation and layout of the interview form

 Use of booklets
 Simple and clear formats
 Creative which requires the use of space and type face
 Use of colour coding
 Interviewer instructions

7. Piloting and pre-testing the questionnaires. This should focus on the following;
 Whether questions as they are worded will achieve the desired results
 Whether the questions have been placed in the best order
 Whether the questions are understood by all classes of respondents
  Whether additional or studying questions are needed or whether some questions should
be eliminated
 Whether the instructions to interviewers are adequate

A high survey response rate is likely driven by high levels of motivation to complete the survey
or a strong personal relationship between business and customer. A survey response rate of 50%
should be considered excellent in most circumstances. Boosting the survey response rates is
necessary to complete the data gathering process in a survey or a research study. The higher the
response rates, the more data can be analyzed and interpreted. Towards the end of the survey,
this eventually lead to the greater advancement of the object of the survey based on the target
population’s perceptions, beliefs and behaviors. The following are proven strategies that increase
survey response rates:

1. Choose the Appropriate Type of Survey.

Each type of survey differs in terms of their characteristics, advantages and disadvantages. For
instance, the online survey method is ideal if your target population includes people age 13 to 18
years old, but not if the survey requires elderly people since the latter don’t usually have an
access to the Internet. Selecting the right type of survey based on your survey goals is crucial in
achieving your expected survey response rates.

2. Follow the Kiss Principle.

“KISS" stands for “Keep It Short and Simple". Create a questionnaire that is brief and concise
and does not contain complicated questions. Such complex questions include lengthy or too
many open-ended questions. In terms of conducting an interview survey, make the interview as
structured as possible by means of asking thought-out questions and only a few probing ones.
When it comes to the cover page, only include a brief greeting, information about you and your
organization, the purpose of the survey and the pledge of anonymity or confidentiality (optional).
3. Add a Personal Touch to the Invitations.

Studies show that there is an increase of 5% or more in the survey response rates when the
invitations in email, web-based, or interview surveys contain personal salutation pertaining to the
potential respondent. Instead of “Dear Subscriber", respondents prefer to be addressed as “Dear
Mr.Smith" by the researcher or interviewer.

4. Provide Incentives.

Nowadays, people are more likely to respond to surveys if there is a ‘concrete’ benefit from the
survey for their participation and completion. The incentives, which raise response rates by 10%
to 15 %, can be in cash or in-kind. In web surveys, participants are given a cash incentive that
range from $1 to $50. Some give incentives lower than $1 (for example 1-minute surveys) or
higher than $50 (‘VIP’ surveys or those answered by medical professionals, degree holders, etc.).
In-kind incentives can be gift certificates, movie passes, small tokens, prizes, and others.

5. Follow Up and Remind the Respondents.

According to the study conducted by Quintessential, an increase in survey response rates may
come from reminding non-participating recipients or non-completing respondents within 10 days
after sending the first invitation
REFERENCES
 "Standard Definitions - AAPOR". Standard Definitions – AAPOR. AAPOR. Retrieved 3 March
2016.

 "Response Rates – An Overview." American Association for Public Opinion Research (AAPOR).
29 Sept 2008. http://www.aapor.org/Education-Resources/For-Researchers/Poll-Survey-
FAQ/Response-Rates-An-Overview.aspx

 Visser, Penny S.; Krosnick, Jon A.; Marquette, Jesse; Curtin, Michael (1996). "Mail Surveys for
Election Forecasting? An Evaluation of the Colombia Dispatch Poll". Public Opinion Quarterly. 60
(2): 181–227. doi:10.1086/297748.

 Keeter, Scott, Courtney Kennedy, Michael Dimock, Jonathan Best and Peyton Craighill. 2006.
"Gauging the Impact of Growing Nonresponse on Estimates from a National RDD Telephone
Survey." Public Opinion Quarterly. 70(5): 759–779.

 Curtin, Richard; Presser, Stanley; Singer, Eleanor (2000). "The Effects of Response Rate Changes
on the Index of Consumer Sentiment". Public Opinion Quarterly. 64 (4): 413–428.
doi:10.1086/318638. PMID 11171024.

 Holbrook, Allyson, Jon Krosnick, and Alison Pfent. 2007. "The Causes and Consequences of
Response Rates in Surveys by the News Media and Government Contractor Survey Research
Firms." In Advances in telephone survey methodology, ed. James M. Lepkowski, N. Clyde
Tucker, J. Michael Brick, Edith D. De Leeuw, Lilli Japec, Paul J. Lavrakas, Michael W. Link, and
Roberta L. Sangster. New York: Wiley. https://pprg.stanford.edu/wp-content/uploads/2007-
TSMII-chapter-proof.pdf

 Seon Choung, Rok; Richard Locke, III; Schleck, Cathy D.; Ziegenfuss, Jeanette Y.; Beebe, Timothy
J.; Zinsmeister, Alan R.; Talley, Nicholas J. (2013). "A low response rate does not necessarily
indicate non-response bias in gastroenterology survey research: a population-based study".
Journal of Public Health. 21 (1): 87–95. doi:10.1007/s10389-012-0513-z.