Hypothesis testing

When we are conducting hypothesis testing, there will be four possible outcomes can occur:

i. We accept Ho, and Ho is in fact TRUE

ii. We accept Ho, and Ha is in fact TRUE

iii. We reject Ho, and Ho is in fact TRUE

iv. We reject Ho, and Ha is in fact TRUE

In practice, it is impossible to prove the Ho (null hypothesis) is TRUE. Therefore, if we ACCEPT Ho, then we have actually FAILED to reject Ho!

If Ho is TRUE and Ho is accepted, or if Ha is TRUE and Ho is rejected, then the correct decision has been made. Therefore, if we accidently rejecting Ho when Ho is actually TRUE, or if Ha is TRUE but now Ho is accepted, then an ERROR has been made. So now the two concepts of ERROR will then be introduced and need to be treated differently.

Comments

Type of errors

There are two types of ERROR that we will dealing during conducting hypothesis testing; TYPE I ERROR: The probability of rejecting the Ho when Ho is TRUE. TYPE II ERROR: The probability of accepting the Ho when Ha is TRUE. TYPE I ERROR is serious form of error thus, it is denoted by alpha and is commonly referred as the SIGNIFICANCE LEVEL. TYPE II ERROR is usually denoted by beta where 1-beta is the POWER OF THE TEST. POWER OF THE TEST is the probability of rightly rejecting Ho when it is FALSE. In order words, we are RIGHT on deciding to accept Ha as our decision. There are some factors need to be considered when looking into the power of the test; When the significance level or a is made smaller, then the power will be decreases. In condition where the standard deviation of individual observation increases, the power will be decreases. By increasing sample size, then the power will be increasing too. The power of the test will be increases if the alternative me...

Final test 2017

Randomised controlled trial

I like to turn to the basic study design therefore used to confirm or refute the hypothesis. The first type of study, randomised trial also called as randomised clinical trial because it often use to testing new therapy. What is the design showing here? We begin with a study population and we randomly assign the study population into current treatment or new treatment. We then follow up both groups of patients and determine how many dies from the disease in current treatment and how many dies from the disease in new treatment. If the new treatment is more effective than the current treatment we would expect to see fewer people die from the disease in the new treatment than we see in current treatment. So the design of randomised trial is basically a simple one. And it is very desirable type of study. The act can be carried only if we looking at a potentially beneficial prevention. If we have toxic or potentially toxic substances or putative carcinogens clearly we cannot r...

Statking

Search This Blog