T test limitations explained PDF

Preview

Summary

ASIEJVCIDKSPCOSAKJCFR...

Description

MAARYA

UNIT 8 ASSIGNMENT 3

NAME: SANNAH HANIF

D3) EXPLAIN WHAT TYPE 1 AND TYPE 2 ERRORS ARE IN THE CONTEXT OF STATISTCS, DESCRIBE THE LIMITATIONS OF THE T TEST AND EXPLAIN IF THESE APPLY TO THE DATA ANALYSED. COMMENT ON THE VALIDITY OF THE CONCLUSIONS AND SUGGEST HOW THE INVESTIGATION CAN BE IMPROVED. In statistical hypothesis testing a type I error is the rejection of a true null hypothesis whereas a type 2 error is the failure of rejecting a false null hypothesis. Type 1 error is occurred when we reject the null hypothesis when we should have retained it. That means that we believe we found a genuine effect when in reality there isn’t one. The probability of a type I error occurring is represented by α and as a convention the threshold is set at 0.05 (also known as significance level). When setting a threshold at 0.05 we are accepting that there is a 5% probability of identifying an effect when actually there isn’t one. For type 2 error, this error occurs when we fail to reject the null hypothesis. In other words, we believe that there isn’t a genuine effect when actually there is one. The probability of a Type II error is represented as β and this is related to the power of the test (power = 1- β). Cohen (1998) proposed that the maximum accepted probability of a Type II error should be 20% (β = 0.2). A limitation of the t test was that the amount of data that was provided was slim and therefore Samples of larger amount of values would more accurately represent the population. In the data that I analysed, there were three different types of data, therefore this limitation does not apply as there was a variety of different data. Another limitation of the t test is that it could have been through random sampling, this is when the data is collected from a representative, randomly selected a portion of the total population. This limitation does agree with the data that I analysed as the data is about measuring the resting pulse rate and a handful of patients were chosen to carry this investigation out. A limitation for the t test would be the scale of measurement as the assumption is that the scale of measurement is applied to the data collected which follows a continuous or an ordinal scale. This limitation does apply to the data that I analysed because the measurement is the same throughout the investigation at (bpm) because pulse rate is being monitored. Another limitation of the t test would be that the two population have the same variance. This limitation does apply to the data that I analysed because the data is similar in both white, green and red colours. This can be adjusted though. Two final limitations for the t test would be that you can only use one factor at a time and you can only use two levels at a time. This does apply to the data that I analysed because to carry out the t test, I could only choose two of the three colours. The final limitation would be the fact that You have to watch out for the Type 1 error because it increases with simultaneous tests. This limitation does not apply to my data as it is not a simultaneous test. Therefore, the validity of my conclusion is reasonable. There are ways in which the investigation could be improved: There could be more data that is not hand-picked from a random sample of people. The scale of measurement could be changed. The data that was analysed could have been more spread out and the data could be different and not the same values for different colours. Another way the investigation could be improved is through being able to use all the data and not just a part of it to carry out the t test. The ideal experiment where there have been improvements would be where one thing is changed, and one result is looked at and Everything else is remained the same. The more you keep the same, the more likely it is that the result will be valid. References: https://www.students4bestevidence.net/type-i-and-type-iierrors/ https://stats.stackexchange.com/questions/304046/what-are-the-limitations-involved-in-a-twosamples-independent-t-test https://www.answers.com/Q/What_are_the_Limitations_of_the_t-test_in_statistics

MAARYA

UNIT 8 ASSIGNMENT 3

NAME: SANNAH HANIF...