# Tutor profile: Bob L.

## Questions

### Subject: US Government and Politics

In a short paragraph, explain the role of the state in the distribution in the distribution of power to the poor and disadvantaged?

Taken as a whole, who gets what is at least partly a function of government policy. Policies can, for example, be designed to ensure that poor families receive a greater share of the economic pie than they would if the market was left completely untouched. By contrast, policies can be designed to ensure that the rich are allowed to maintain or even increase their share of wealth. These policies, known as tax and transfer policies, are especially important for the distribution of income and wealth. There are many specific examples of how states impact who gets what in any society. (1) States set and can alter the rules of the game. Policies can favor big business, small business, farmers, or workers and unions, but not all at the same time. (2) States allocate resources through various kinds of spending programs. (3) States decide who pays for public spending programs primarily through tax policy. (4) States make life-and-death decisions. They decide when to go to war and whether the death penalty is legal.

### Subject: Sociology

What is "inequality of opportunity" and how is it measured?

Inequality of opportunity refers to the ways in which inequality shapes the opportunities that children and young adults have to maximize their potential. If an individual’s chances to do well in life depend on the advantages or disadvantages of birth and early childhood, then we say opportunity is unequally distributed. However, measuring opportunity in any society is not a simple research question. Because there is no one obvious way of determining how much opportunity individuals really have in a society, social scientists use social mobility as an approximate measure. Social mobility is the pattern of intergenerational inheritance in a society and a measure of the extent to which parents and their children have similar or different social and economic positions in adulthood. A high-mobility society, where there is relatively little connection between parents’ and children’s place in life, approximates the ideal of equality of opportunity. In highly mobile societies, where a child ends up in life is determined largely through her or his own achievements. By contrast, when there is a relatively close connection between parents and their children's positions when children reach adulthood, social mobility is low. In low-mobility societies, the advantages or disadvantages of birth fully determine one’s social position.

### Subject: Statistics

What is the role of descriptive statistics in the analysis of a data set. Please describe the three basic categories of descriptive statistics (distribution, central tendency, and dispersion) in detail. Finally, what is important to keep in mind about sample size?

In any statistical analysis, especially with human data, it is necessary to first cover the descriptive statistics of the data. The descriptive statistics are varying measures that allow a research to describe what the data looks like to determine in what ways they can proceed with analyzing it. This first step of inspecting the data is necessary to ensure the validity of the data and subsequent analysis. There are three main categories of descriptive statistics that each contain different measures. Those categories are distribution, central tendency, and dispersion. DISTRIBUTION The distribution refers to our ability to describe the frequency and range of observed values in a dataset. Two common ways to assess the distribution of our data is look at the frequency of each value as well as the range of values in our dataset. Another common way to assess the distribution is through observing the range. Distribution in this way can be observed through the theoretical range, which describes the potential range of the data. The actual range describes the observed difference between the highest and lowest value in a dataset. Describing the range is useful because it shows the breadth of your data and allows you to assess how the actual data measures up to what you conceived as theoretically possible. Discrepancies in these scores can be intellectually productive in refining theory and constructed measures. However, the range is also problematic. Range only addresses a few data points in your dataset, neglecting everything else. Those data points are at the extremes of your data set and can be misleading if there are outliers, meaning they are not representative of how the rest of your data is distributed. To partially assess for this, researchers can utilize interquartile range, which divides your dataset into four equal parts. The interquartile range is the difference between the average of the upper half of the data and the average of the lower half of the data. This provides a range that describes the “middle” fifty percent of your data set. CENTRAL TENDENCY The central tendency are calculations made to assess the “center” of the distribution. Depending on how skewed the dataset is in one direction or the other, a researcher may not be describing the “center” of the distribution but rather the typical value to be expected in the dataset. Two measures of central tendency are median and mean. The median is the exact middle value in our dataset when we line up the scores in numerical order. Half of the scores in our dataset lie above and below the value of the median. The mean is the “average” value in your data set. To calculate the mean, you add up all the scores in your dataset and divide by the total number of scores. The resulting number is your mean. The mean is often used to calculate central tendency, but it has a few drawbacks. Since the mean incorporates each unique value in the dataset, it is more reflective of the dataset as a whole but that also means it is sensitive to outliers that may pull the mean in one direction or another thus distorting the true distribution of the data. The median is not as impacted by outliers because it is only concerned with the placement of the data, and less-so the actual value. The consequence of this is that the median is less sensitive to the unique value of each datapoint thus less representative of the actual average. As such, mean is often preferred for normal distributions, which is the gold standard for much statistical analysis. The median is often reserved for skewed distributions with major outliers. DISPERSION Dispersions assess the ways in which the values in a dataset are spread around the mean. The range is often considered a measure a dispersion, but we discussed it above under the category of distribution because we were less concerned about central tendency at that point in our description of the data. The most common way to discuss dispersion is through standard deviation. The standard deviation (SD) allows us to quantify how dispersed our data is. It describes how far away from the mean a particular data point is. The lower a SD value, the close a data point is to the mean. The SD is important because it allows us to assess how significant the variation in our data is. It helps us give meaning to the individual datapoints in our dataset. A difference of 10 between the mean and a datapoint means one thing if the SD is 1 and something completely different if the SD is 20. The important thing about SD is that is assumes a normal distribution. If you have a significantly skewed dataset, the SD is not going to be of much use. SAMPLE SIZE It is also important to note the role of sample size in the study of human populations. The sample size is crucial to survey research because it influences how precise our estimates are (the margin of error in our results) and the strength we can put into our conclusions (how much explanatory weight we can put into our statistically significant results). Just knowing the size of our sample does not tell us a whole lot because it lacks the necessary details of how the sample was drawn and what it refers to (e.g. a particular section of Chicago or Chicago as a whole). If we are to conclude that we can move forward with statistical analyses, these questions would have to be answered for our results to have any meaning.

## Contact tutor

needs and Bob will reply soon.