Solve the problem that involves Hypothesis testing and Bin (n,p)

In summary, the conversation discusses the results of a survey where only 73% of respondents reported being satisfied. This raises doubts about Pierre's claim of 90% satisfaction. However, the statistical test shows that there is a possibility that the low satisfaction score is due to random variation, and therefore cannot reject the null hypothesis that 90% of customers are satisfied. This means there is no evidence to disprove Pierre's claim, but also no evidence to support it.
  • #1
chwala
Gold Member
2,753
388
Homework Statement
See attached
Relevant Equations
Hypothesis tests and Binomial distribution
1654088041255.png
1654088113546.png


##p(x≤11)=1-[p(x=12)+p(x=13)+p(x=14)+p(x=15)]##
##p(x≤11)=1-[0.128505+0.266895+0.3431518+0.205891]=1-0.9444428=0.0556##
##⇒p(x>11)=0.9444##
##p(x≤10)=1-[0.042835+0.128505+0.266895+0.3431518+0.205891]=1-0.9872778=0.0127222##

Since, ##p(x≤11)=0.0556> 0.05## then it falls on the Accepted region and further, ##p(x≤10)=0.0127<0.05## then it falls on the Rejected region. We therefore do not reject the Null hypothesis.

Any insight welcome...
 
Last edited:
Physics news on Phys.org
  • #2
Having only 73% of survey respondents say they're satisfied is prima facie evidence that Pierre's claim of 90% satisfaction may be exaggerated (overconfident).
But the test shows that, if Pierre is correct, a survey of 15 people has a greater than 5% chance of returning 11 or fewer saying they're satisfied. So we cannot reject the possibility that the low satisfaction score arises purely from random variation, with 95% confidence of our rejection being correct. Since we set ourselves the target of 95% confidence, we do not reject that possibility, which means we do not reject the null hypothesis that 90% of customers are satisfied.
Note it says there is not evidence that Pierre is correct (ie not overconfident). Lack of evidence to disprove proposition P does not constitute evidence for proposition P. Here P is the proposition: "90% of Pierre's customers are satisfied".
 
  • Like
Likes chwala

FAQ: Solve the problem that involves Hypothesis testing and Bin (n,p)

What is hypothesis testing?

Hypothesis testing is a statistical method used to determine whether a sample data supports or rejects a specific hypothesis about a population. It involves comparing the observed data to an expected or null hypothesis and calculating the probability of obtaining the observed results by chance.

What is a binomial distribution?

A binomial distribution is a probability distribution that describes the likelihood of obtaining a certain number of successes in a fixed number of independent trials, where each trial has only two possible outcomes (success or failure). It is often used in hypothesis testing when the sample data follows a binomial distribution.

How is hypothesis testing used in binomial experiments?

In binomial experiments, hypothesis testing is used to determine whether the observed results are significantly different from what would be expected by chance. This involves setting a null hypothesis (usually that there is no difference between the observed and expected results) and an alternative hypothesis (that there is a significant difference between the two). The data is then analyzed using statistical tests to determine the probability of obtaining the observed results under the null hypothesis.

What is the significance level in hypothesis testing?

The significance level, also known as alpha, is the probability of rejecting the null hypothesis when it is actually true. It is typically set at 0.05 or 0.01, meaning that if the probability of obtaining the observed results by chance is less than 5% or 1%, the null hypothesis can be rejected and the alternative hypothesis can be accepted.

What is the difference between one-tailed and two-tailed tests in hypothesis testing?

In one-tailed tests, the alternative hypothesis is only concerned with one direction of difference from the null hypothesis (e.g. the sample mean is greater than the population mean). In two-tailed tests, the alternative hypothesis is concerned with both directions of difference from the null hypothesis (e.g. the sample mean is different from the population mean). The choice of one-tailed or two-tailed test depends on the specific research question and the direction of the expected difference.

Similar threads

Back
Top