Confidence is another term for probability in statistics. For instance, if we construct a confidence interval with a 96% level of confidence, we may be sure that 96 out of 100 times the estimate will fall inside the upper and lower values suggested by the confidence interval. An example of this can be a dataset for testing the effectiveness of a drug produced for the treatment of lung cancer. As this is a testing drug it can either cure the disease by an amount or won't affect the patient at all which is basically the effectiveness of the drug. If we have a model showing a 90% level of confidence with 80% - 90% of the effectiveness of the drug on lung cancer patients. This means there is only a 10% chance that the drug's effectiveness is less than 80% or more than 90% in any lung cancer patient. The confidence interval is crucial to test the validity of this dataset. The population here is all lung cancer patients. The dataset should contain the data of only those patients with lung cancer and no other disease which will give better accuracy. The parameter that I will be using are: the total number of lung patients, smoking history, and amount of testing drug taken. I will choose an 85% - 95% confidence interval as there can be lung cancer patients with any inheritance history or can get lung cancer without smoking so the effectiveness will not be 100% accurate. When the sample size increases the confidence interval decreases. As there are a lot of lung cancer patients around the world so the sample size that will be taken will be huge which will give better confidence