Hypothesis Test

Hypothesis Test Hypothesis is nothing but assumption however it is really interesting to have a closer look at it in terms of Statistics. • The use of hypothesis helps to assume & test concerning fact or result related to the large population data. • Hypothesis testing is about making inference about a population from a small sample data. • We check via sample, whether the test support the statement concerning the population is applicable or not. • Hypothesis is based on sample evidence and probability theory to confirm statements

•

Five steps process for hypothesis testing

• Type of Test: Decide whether the test is two tiled or one tiled test (left or Right tiled), need to state your hypothesis. Select a level of significance appropriate for the decision.

• • Which distribution will be used (t or z) and need to find the critical value for the chosen level of significance as per the business requirement.

• • Calculate the standard error from the sample population data. Use of standard error to convert the observed value of the sample data to a standardize value.

• • Sketch the distribution & mark the position of the standardized sample value & the critical value(s) for the test.

•

A brief on tDistribution t Distribution is used over Z distribution if the

sample size is equal or less than thirty and the standard deviation is not known.

•

• t-distribution is a continuous distribution. • It is bell shaped and symmetrical. • There is a family of t distributions. Each time the degrees of freedom change, a new distribution is created. • As the number of degrees of freedom increases, the shape of the t distribution approaches that of the standard normal distribution. • The t distribution is flat, or more broad, than the standard normal distribution. • •