## Expert Answer

a. In order to measure how far the data from the mean is, one can use the prominent measures of Mean deviation and Standard deviation. In case of mean deviation, it helps in finding out the absolute average of all the data available to us and the figure is termed as the mean. The degree to which the given data are away from the mean could be measured using the formula of mean deviation which takes the sum of all the numerical data available to us and dividing it by the number of data available. For example, for a simple set of data given with the values: 1,2 and 3, the addition of all the values would be 6 and dividing it by number of values, here it is 3. Hence 6 divided by 3 will give us the value ‘2’ as the mean deviation. Accordingly, one can measure how far each of the value from the mean value of 2.

Next measurement is Standard deviation. This could be used to measure the dispersion in the set of data given to us from its mean value. If the data figures are farer from the mean value, it could be termed that the data has higher level of deviation from the mean and vice-versa. The absolute mean value itself forms the basis of the standard deviation. Later, the gap of each point from the mean is squared, added and subsequently averaged to determine the overall variance in the given data.

b. When an unprocessed raw data is to be converted into some useful data purpose, the data needs to be processed and classified first. However, it is to be noted that at individual level, if data is processed then while segregating the overall data, the complexities in the same reduces considerably. The deconstruction analysis techniques may also come into rescue in order to classify and analyze the raw data more efficiently.

c. Variables are any attributes which are prone to alteration in terms of bearing more than one value as its characteristics such as intelligence, age, gender, etc. It could be basically classified as two types: Dependent and Independent variables, when it comes to Research. The dependent variable is such a variable that is impacted by an Independent variable while the independent variable is such a variable that is expected to have an influence over other variable. Variables could further be classified as Nominal variable or ordinal variable, Ratio variable or dummy variable, Intervening variable or Orgasmic variable, Control variable or Interval variable, Preference variable or Multiple response variable, etc.

In the case of Hypothesis testing, univariate and bivariate variable analysis play a significant role. In case of univariate data, it involves only single variable while that in case of bivariate data, it involves two variables for the purpose of hypothetical tests. Univariate data is not based upon the cause and effect relationship as it has only one variable under its study while in case of bivariate data, it is possible to establish a cause and effect relationship owing to the possibility of comparison between two variables. The general purpose of undertaking univariate data analysis is basically to determine the values of central tendency such as mean, median or mode or to measure the dispersion by way of range, variances and standard deviation concepts or to prepare various types of statistical graphs such as histogram, bar graphs, pie charts, etc. On the other side, univariate data analysis is performed in order to study the correlation of two given variables, the explain the cause and effect relationships, to prepare a list where one variable acts as a contingent to the values of other variables and also has one variable as a dependent variable while the other as independent.