Other Hypothesis Tests and Confidence Intervals

Hypothesis testing in statistics is a method used for evaluating statistical evidence from the data and taking a decision about the population based on this data.
Other than the common z-tests and t-tests, there are other types of hypothesis tests such as: Chi-square tests, F-tests and ANOVA tests that are used to compare multiple means simultaneously.
Hypotheses are assumptions about the population that are tested on the basis of sample data. There are two types of hypotheses: Null hypothesis (H0) and alternative hypothesis (H1 or Ha).
A null hypothesis (H0) is an assertion about a population parameter which we presume is true until there is sufficient statistical evidence to suggest otherwise.
An alternative hypothesis (H1 or Ha) is what you might believe to be true or hope to prove to be true. It is the hypothesis that the researchers will usually try to prove in their data.
In hypothesis testing probability, or ‘p-values’, are utilised. If the p-value is small (below a predetermined cut-off, for example 0.05), then the null hypothesis is rejected in favour of the alternative hypothesis.
Confidence intervals are a range of values, derived from a data set, that is likely to contain the value of an unknown population parameter. A common value is 95%, called a 95% confidence interval.
Confidence intervals provide a range of likely values for the population parameter, in contrast to hypothesis tests which test whether a particular value could be the population parameter.
The level of confidence provides the strength of certainty that the actual value lies within the determined confidence interval.
Recall the difference between one-tail and two-tail tests in generating confidence intervals. One-tail tests examine the possibility of the relationship in one direction only, and the two-tail test is interested in both directions.
Always keep in mind the type of data and research question when choosing the right type of hypothesis test. You should have a solid understanding of what each type of test is used for, and the assumptions that need to be met for each test.
Practice various statistical problems to get a good grasp of these tests and concepts. This familiarity is crucial for understanding the statistical inferences that can made from hypothesis testing and confidence intervals.