A research into the perception and attitude of pregnant women to drugs. I want to use likert scale to assess the attitude and perception of pregnant women to drugs
There is difference between Likert-score items and scales that are made up of several Likert-scored items. If you are using a multi-item scale, then it is quite common to treat that as interval-level data that yous can assess through parametric statistics.
As a first step, you would want to use Cronbach's alpha to asses the reliability of the scale.
Use parametric test whenever appropriate or when the conditions for the use of parametric test were met.
Thank you Castillo, please explain what conditions need to be met before using each of the tests.
Please see the following stat book by Andy Field. See page 132 for parametric assumptions
http://www.soc.univ.kiev.ua/sites/default/files/library/elopen/andy-field-discovering-statistics-using-spss-third-edition-20091.pdf
Dear Ikenna: You may also look at the following link.
http://www.psychology.emory.edu/clinical/bliwise/Tutorials/CHTESTS/choose/assump.htm
You may also read the answers in a similar question provided in the link below.
https://www.researchgate.net/post/What_are_the_specific_rules_for_the_use_parametric_and_nonparametric_tools
What should I used to analyse a likert scale, a parametric test or a non parametric test?
When your Dependent Variable (DV) is in ordinal scale e.g. Likert scale, you should use non-parametric statistics. When your DV is in interval / ratio scale, you can use parametric statistics.
Some scholars still debating Likert scale can be treated as interval scale & hence handled by parametric statistics e.g. Lubke & Muthen (2004). However, some argue the other way round i.e. Likert scale should use non-parametric statistics e.g. Jamieson (2004).
If your DV is in Likert scale & based on common observations, you can change your Likert to interval scale data through modifying the survey questionnaire before data collection i.e. converting Likert scale questionnaire (e.g. 1=Effective, 2=Some How Effective, 3=Moderately Effective, 4=Neutral, 5=Moderately Not Effective, 6=Some How Not Effective, 7=Not Effective) to Semantic Differential scale using Bipolar Adjectives (e.g. Effective1, 2, 3, 4, 5, 6, 7 Not Effective) so that parametric tests can be applied. The rationale claimed is that the intervals between the scale values can be treated as equal intervals, making it an interval scale which justified for parametric tests.
Use parametric approach specially if your sample more than 30 individual.
It is safer to treat Likert scale as ordinal scale. Ordinal data should be analysed using non-parametric tests. But in certain cases, e.g. scales which are sum of several Likert scales and medium to large N, you may be able to use parametric test without any concerns.
There are debates among researchers--as well as practitioners--about this issue.
You can refer to this concise and brief article that summarizes both sided arguments: Article Parametric Tests for Likert Scale: For and Against
- Badges
- Science topic