In a model developed by me, most of the variables estimates are insignificant at 95% significance level.
This entirely depends on what type of model you are discussing and what object or processes the model is supposed to represent. There are real world problems for which are insensitive to some inputs. I was on a zoom call tuesday when one of the members who works for a large manufacturer was stressing the insensitivity to a particular measurement. This isn't necessarily a bad thing nor does it necessarily invalidate your model but we must have more information in order to adequately address your question. What is the object? What is your approach? What do you hope to learn?
How to explain insignificant results of a model? Is everything OK? For example, are the necessary assumptions fulfilled? The answers to these questions may provide direction on how to proceed.
This means that the results are considered to be „statistically non-significant‟ if the analysis shows that differences as large as (or larger than) the observed difference would be expected to occur by chance more than one out of twenty times (p > 0.05).
- Badges
- Science topic
- Similar topics
- Linguistics
- Composition Studies
- Publication