BME100 s2015:Group17 12pmL2
|BME 100 Spring 2015|| Home |
Lab Write-Up 1 | Lab Write-Up 2 | Lab Write-Up 3
Lab Write-Up 4 | Lab Write-Up 5 | Lab Write-Up 6
Course Logistics For Instructors
Wiki Editing Help
LAB 2 WRITE-UP
For the statistics portion of this experiment, the t-test was chosen to describe the rat experiment and ANOVA was chosen for the human experiment. This is because, the t-test is only for two data sets, whereas the ANOVA is for multiple data sets.
Experiment with Rats: T Test: 0.867403497
The trials involving the rats yielded a P-value of 0.867, which is greater than 0.05, the data is not statistically significant. The sample size is not large enough which creates a variance in the data set. Such a great variance can not be used to draw an accurate conclusion as to whether the LPS drug was effective in the rats. To decrease the P-value of the data, the data sample needs to be larger.
An ANOVA test revealed that the P-value of the human trials was blank. An accepted P-value for an ANOVA test is <0.0083 which was found by dividing the normal p-value of .05 by the number of comparisons we did for the Bonferroni correction. This value attained from the human trials shows that the sample size is not large enough as seen by the big variance in data. With such a small sample size and large variance, the data is insignificant to the study of whether LPS can produce effective amounts of inflammotin. Raw data also shows that a larger dosage of LPS yields a larger amount of inflammotin.
The trials between the rats and humans displayed a stark difference in variance of the data. The large variance in collected data from each experiment can be attributed to the sample size of the rat trials and human trials. In the rat trials, only 10 subjects were administered the LPS. After performing a T-Test with the raw data from the rats, a P-value of 0.867 was obtained. With an accepted P-value of 0.05, the raw data from the rats can not be significant to the research of the influence of LPS on inflammotin. In comparison the human trials had a large sample size of 40 subjects. An ANOVA test was performed using the raw data from the human trials, all the P-values were obtained. Accepted P-values for ANOVA tests is a value less than 0.0125. A Bonferroni correction showed that the data was insignificant and could not be used to further draw conclusions for the purpose of the experiment. This large P-value gained from the human trials shows that there was not a correlation between the dosage of LPS and the yield of inflammotin. In order to correct the variance in data between the rat and human trials, more subjects in the rat trials is needed in order to decrease the variance in the two sets of data.