Evaluating Normality

EvaluatingNormality

InstitutionAffiliation

Thedata of the patients with cancer at different ages is normallydistributed (Weiss, 2016). Various reasons explain the normality ofthe data.

Thefirst reason is that once the curve for the distribution issuperimposed onto the histogram, the result shows a symmetrical curve(Weiss, 2016). The symmetry is around the mean which is about 59.64.Also, the mean, median and the mode of the data presented are allequal showing that the data is normally distributed (Weiss, 2016).The curve is also denser at the center and less dense at its sidesshowing that the data is normally distributed (Weiss, 2016). 68% ofthe area under the curve lies within one unit of the standarddeviation of the mean value and 95% of the area under the curve lieswithin two units of the standard deviation from the mean (Weiss,2016). The curve also extends indefinitely by approaching the x-axisbut not touching it. The variable used is also a continuous randomvariable and not discrete because the distances between the valuesare not equal. It is random since the likelihood of a subject havingcancer is not determined by any factor. Random continuous variablesare used in normal distribution curves (Weiss, 2016). The Skewnessand Kurtosis values are -0.3478 and -0.5841 respectively and are verylow showing that the data is normally distributed (Weiss, 2016). Thepvalue is 0.9399, and since it is greater than 0.05, it indicates thatthe data is normally distributed (Weiss, 2016). Another evidence thatproves the normality of the data is found in figure 2 that shows theage of patients against the normal quantile. The data points arerandomly scattered around the line of best fit. This characteristicindicates that the data is normally distributed (Weiss, 2016).

References

Weiss,N. A. (2016). IntroductoryStatistics(10thEd.).New York, NY: Pearson Education.