Interpret the Central Measures of a Variable

Interpret the Central Measures of a Variable
Student’s Name
Institutional Affiliation
Interpret the Central Measures of a Variable
Identify the dataset and variables and provide context to the research used to collect the data (in an introduction section).
According to health reports, cancer and heart failure have the highest mortality rates in the world. Over the last 116 years, researchers have compiled a well-detailed dataset that depicts the number of deaths caused by a specific disease (Villiger, 2014a). Scholars can review the compiled data on the United States government website (data.gov). The dataset illustrates the death rates of all the five diseases; stroke, cancer, heart disease, accidents, and influenza. Besides, the data records start from the year 1900 to 2015. In contemporary society, records on death rates are habitually collected through national tallies and sampling methods (Hand, 2008). In the sampling technique, researchers use data obtained from a specific geographic area to represent the larger population than the sampled area. In every census exercise, the government integrates the death rates of various diseases as a variable among mortality rates, birth rates, etc. Research suggests that there are various ways to curb the number of deaths. Some of these techniques include providing better healthcare, quarantining highly affected areas, extensive researching on vaccines and curative medicines, and creating awareness about the disease.
Statistics illustrate that heart failure contributes to 49 percent of death cases in the world (Villiger, 2014b). Physicians assert that there are various examples of heart diseases, which are fatal. Some of these examples include coronary heart disease, arrhythmia, myocardial infarction, congenital heart disease, dilated cardiomyopathy, stroke, hypertrophic cardiomyopathy, and mitral regurgitation. Although some of these types of heart disease occur due to deformities at birth, others are attributed to lifestyle. Example of lifestyles that may contribute to heart diseases includes smoking, obesity, diabetes, generational disease, high consumption of fatty foods. Some of the common symptoms include sweating, chest pains, blue taint of skin, rapid breathing, fatigue, and high heartbeat rates. The above-mentioned diseases can be treated medically through medications or correction surgeries. Additionally, doctors recommend patients to positively change their lifestyles so that they can improve their heart condition. Physicians recommend eating a balanced diet, exercising regularly, reducing the intake of fatty foods and alcohol, and quitting smoking as the best remedies for treating heart disorders.
According to the CDC (Centre for Disease Control and Prevention), heart disease is the leading cause of death in the UK, USA, Canada, and Australia. Every year, heart diseases contribute to the death of 610,000 people. Statistically, every year, 1 in every 4 deaths are a result of heart disease (Crawley, 2014). Additionally, old age exposes one to high risks of heart diseases. In 2009, more men succumbed to heart diseases than women. Statistics quote that 735,000 Americans experience heart attacks annually (Gibson, 2011). First cases reported an account for 525,000 and 210,000 are recurrent. Based on the data provided by NCHS on data.gov, it is evident that the rates of death caused by heart disease over the 116 years are the highest among the other 4 causes of death in the dataset (73.csv). See below in the appendix section.
Identify the analysis performed, pros and cons of calculation, and why they are used (in a method section).
In statistics, descriptive, and inferential statistics are common to come across when dealing with data. In our case, the variable under discretion has a nature of continuity. The rates of death of heart disease can take up any values between 0 and infinity. Seema Singh, a data science aspirant, and journal blogger, descriptively states that for one to understand the distribution of a certain variable, one must first understand these measures. These measures used to describe discrete and continuous distributions entail:
* Measures of dispersion
* Measures of central tendency
* Measures to describe the shape of the distribution
Measures of dispersion expound on the spread of data or the variation of the dataset about the central measure. Examples of measures of dispersion include range, quartile, interquartile range, variance, and standard deviation. The range is simply the difference between the largest and the smallest value of a dataset. A quartile is any real number that divides a distribution f(x) of a certain random variable into two parts. Usually, there are 4 quartiles i.e. Q1 for the first quartile at 25%, Q2 also means or the second quartile at 50%, Q3 is the third quartile at 75% and lastly Q4, the fourth quartile of the data at 100% of the data. The interquartile range is actually equal to Q3-Q1. Half of all values in the dataset are within this range. A large IQR translates to a large spread of values while small IQR means a large number of values in the dataset fall near the center of the dataset (Gibson, 2011). The five number summary comprises of minimum, first quartile, median, third quartile and maximum.
The maximum is the largest value while the minimum is the least value in the dataset. The variance is the average spread of the data about the mean. The larger the variance, the more the data is spread about its mean. The standard deviation is the square root of the variance. It can be incorporated to explain the overall variation of a distribution.
Secondly, measures of central tendency are composed of mean, median and mode. They assist in explaining the dataset using univariate values. The mean is an average of all values which is calculated by adding all values and dividing by the total number of values in the dataset. The median is a value at the center of the dataset; also Q2. Lastly, the mode is described as the value with the highest frequency among all values in the dataset.
Measures to describe the shape of a distribution obviously help us to describe the shape of a distribution. Skewness is a measure of how much the variation differs from a normal distribution. It could be positively skewed or negatively skewed. Positively skewed distribution means that the tail of the curve is towards high values and that the majority of frequent values are few. Negatively skewed distributions are the vice versa. When a distribution is positively skewed, the modemedian>mean. Last but not least, kurtosis measures the peak and combination of weighted tails of the distribution relative to its center (Gibson, 2011). If present, tails ex...