statistics project

Project 1: Phase 2 Descriptive Statistics and Preliminary Analysis

Dependent Variable:

Median Household Income

· Description:

· Median Household Income is generally the combination of two income earners in a single household for people above the age of 15 for a period of 12 months.

· Units:

· Median Household Income is measured in U.S. dollars. In this data set, the income is measured in U.S. 2013 dollars.

· Central Tendency:

· The mean, median, and mode would all be good measures of center for this data set since it is relatively normal (between +/- 1.0). However, since there isn’t a reoccurring value within this variable’s data, then there isn’t a value for mode. Thus, the median and mean are measures of center.

· Mean= 53284.28

· Median= 51757.5

· Mode= N/A

· Variability:

· There is a relatively large variability among the values between the 50 states. The value for the range shows relative dispersion of the data and since it is relatively high (about the same as some of the actual data points) we can say that the data has high variability. In addition, the standard deviation is very high, which indicates that the data points are spread out over a large range of values relative to the mean.

· Range: 34507

· Standard Deviation: 8690.23413

· Normal Distribution?

· Yes, the median household income is 0.649999636, which is normally distributed about the mean. The skewness is between +/- 1.0, which is the skewness range that we use to determine if the data is normally distributed.

· Outliers?

· There aren’t any apparent outliers for this variable.

Independent Variables:

Population

· Description:

· Population is the summation of all the people in the United States.

· Units:

· The population is recorded as the number of people in a certain area.

· Central Tendency:

· Population is positively skewed. Therefore, the mode is the best measure of center, but since there isn’t a mode for this data, the next best measure of center would be the median at about 4.5 million people.

· Mean= 630947.8

· Median= 4510382.5

· Variability:

· There is a relatively large variability among the values between the 50 states. The value for the range shows relative dispersion of the data and since it is relatively high, about 3.8 million people we can say that the data has high variability. In addition, the standard deviation is very high, which indicates that the data points are spread out over a large range of values relative to the mean.

· Range: 37749863

· Standard Deviation: 7061295.252

· Normal Distribution?

· No, the value for skewness is about 2.7 which is above the skewness range that we use to determine if the data is normally distributed (+/-1.0).

· Outliers?

· In the scatter plot used to depict the correlation between population and median household income, there is one obvious outlier, California, which has the highest population than all other states. Since is it one of my observations, and the correlation between population and median household income aren’t strong, I am not worried about the outlier, since I may not use this variable.

· Correlation with Dependent Variable:

· The correlation with the dependent variable is minimal; 0.073993082. In addition, r^2 is only 0.04, which means that only about 4% of the variation in median household income can be explained by population.

· Correlation with other Independent Variables:

· No correlations above .7 were found which shows no concerns for multicollinearity

predictions.

Population (2013 Estimate)

Mean6309647.8

Standard Error998617.9513

Median4510382.5

Mode#N/A

Standard Deviation7061295.252

Sample Variance4.98619E+13

Kurtosis8.823667604

Skewness2.669677796

Range37749863

Minimum582658

Maximum38332521

Sum315482390

Count50