TheR-value of 0.21 is between 0.10 and 0.29, which indicates that thereis a weak positive relationship between the length of the time takingdrug x and size of the tumor (Sarantakos, 2012). The P value of 0.001is less than 0.05, which is the significance level (Hauke et al.,2011), and hence we reject the null hypothesis and conclude that itis a significant relationship. Hence the conclusion from this studyis that there is a statistically significant positive weakrelationship between the length of time taking drug x and the size ofthe tumor.

Samplesize affects the outcome because a large sample size increases thechance of finding a significant difference while a small sample sizemight not give reliable, significant results (Faber et al., 2014). Avery small sample size means you have a higher margin of error andlow confidence level that makes the data collected less reliable. Atoo large sample size means that it is expensive to carry out thestudy, and the study could be statistically frivolous. For example,in a population of 1000 people if we take a sample size of 10 people,the results will have a very high margin of error with low confidencelevel and hence the results will be unreliable. If the sample size is900 people, the results will have the too large significantdifference and will be unnecessarily expensive. To calculate theoptimum sample size, one takes into consideration the margin of error(Suresh et al., 2012). Calculating the right sample size beforecollecting data is important because it is crucial to gainingaccurate information because the margin of error and confidenceinterval of the study depends on the sample size.


Faber,J., &amp Fonseca, L. M. (2014). How sample size influences researchoutcomes. Dentalpress journal of orthodontics,19(4),27-29.

Hauke,J., &amp Kossowski, T. (2011). Comparison of values of Pearson`s andSpearman`s correlation coefficients on the same sets of data.Quaestionesgeographicae,30(2),87-93.

Sarantakos,S. (2012). Socialresearch.Palgrave Macmillan.

Suresh,K., &amp Chandrashekara, S. (2012). Sample size estimation and poweranalysis for clinical research studies. Journalof human reproductive sciences,5(1),7.