x Turn on thread page Beta
 You are Here: Home

# Can your null hypothesis and experimental hypothesis be the same? watch

1. I want to predict that there will be no significant difference between gender and consumption of alcohol. Am I allowed to do this? Because I can't tell what my null hypothesis would be then
2. Your null hypothesis would then be there is a significant difference between gender and consumption of alcohol.
3. (Original post by Izu)
I want to predict that there will be no significant difference between gender and consumption of alcohol. Am I allowed to do this? Because I can't tell what my null hypothesis would be then
It's important, first of all, to make sure that the word "significant" is interpreted properly - as there is often an ambiguity between "statistically significant" and "scientifically sigfificant". I take it that you are trying to show that any difference between the genders with regard to consumption of alcohol is too small to matter (i.e. we're looking at scientific significance).

So you would want to start off by looking at

H0: There is a difference between the genders in alcohol consumption.
H1: There is no difference between the genders in alcohol consumption.

The problem with this is that it is rather hard to come up with a test statistic that will do this for you. Strictly speaking you would end up needing an infinite ssample size. So what is typically done (and you may like to look up the notion of an "equivalence trial" or a "non-inferiority trial" is that you set up your hypotheses like this:

H0: The difference between the genders in alcohol consumption is greater than or equal to d.
H1: The difference between the genders in alcohol consumption is less than d.

The way you typically then proceed is to calculate an estimate of the difference in consumption betwen the genders, together with a 95% confidence interval, and you reject the null hypothesis if the 95% confidence interval lies entirely between -d and +d.

Be warned, the sample size required for such a test can be pretty large!
4. (Original post by lovecupcakes)
Your null hypothesis would then be there is a significant difference between gender and consumption of alcohol.
Nope. A null hypothesis is no sig effect found whatever the experimental hypothesis is. So yes OP, they would be the same.

TSR Support Team

We have a brilliant team of more than 60 Support Team members looking after discussions on The Student Room, helping to make it a fun, safe and useful place to hang out.

This forum is supported by:
Updated: March 14, 2016
Today on TSR

### I've studied the wrong subject

...Should I go back to school?

### Should I complain about my supervisor?

Poll
Useful resources

Can you help? Study Help unanswered threadsStudy Help rules and posting guidelines

## Groups associated with this forum:

View associated groups

The Student Room, Get Revising and Marked by Teachers are trading names of The Student Room Group Ltd.

Register Number: 04666380 (England and Wales), VAT No. 806 8067 22 Registered Office: International House, Queens Road, Brighton, BN1 3XE