Measurement; the basics

As explained previously, when asking questions you have to take into account the respondent’s willingness to answer those questions.  In some cases you will have the risk of a social desirable effect, in other words the answers will reflect what the person thinks should be, rather than what they truthfully are.

This is an inherent issue with every survey performed but there are ways to minimise this.

First of all you have to set up your questions based on the following criteria:  

  • Standardisation – use similar ways of answering the questions, for example when asking for a response on a scale from 1 to 5, whereby 1 is very negative and 5 is very positive, this scale has to be the same across the survey
  • Reliability 
  • Consistent – ask questions in present or past tense, refer to participant as you or I
  • Validity – measure what you want to measure

Setting up a successful questionnaire is key to a successful survey. Any errors or discrepancies in your questionnaire will mean that any conclusions may be invalid. Spending extra time at setting up the questionnaire and testing it to a small group of people, is of great value for the rest of your research.

A successful questionnaire will have clear questions, standardised format and can be coded efficiently and effectively for analysis purposes

In future blogs I will go into more detail about statistical analysis, which will support the validity and confidence levels of the data.

master research

Technorati Tags: consistent, measure, questionnaire, reliable, SPSS, standard deviation, standard error, standardisation, statistics, validity

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>