Smmd Assignment

Submitted by: Submitted by

Views: 160

Words: 754

Pages: 4

Category: Business and Industry

Date Submitted: 06/08/2013 05:19 AM

Report This Essay

ASSIGNMENT SUBMISSION FORM

Treat this as the first page of your assignment

Course Name:

Statistical Methods for Managerial Decisions

Assignment Title:

Assignment 1

Submitted by: Sandeep Patwa

PGID: 61410005

Section A

Group A11

1. The prices in the given area have a mean of 163862 and a standard deviation of 67651. The median is 151917. This implies the data is not exactly normal distribution but marginally normal given the graphical normal plot. This along with the box plot also tells us that the density of the data below the mean is high and that its right skewed thereby getting the mean higher than the median. The mode is 139079 which substantiate the data being denser on the left of median. The box plot gives me the position of the outliers being on the right and the histogram count gives me the frequency & range of these outliers, also cementing the fact that the data is right skewed. The co-efficient of skewness= 0.876 being positive and less than 1 confirms the right skew & the fact that data is almost normally distributed. The distinct mean, median & mode also confirm the fact that the data is not exactly normal. The box plot summary also tells us that the right side data is spread over 2.5 times IQR hence presence of certain high value prices on the upper side is stretching the data and also why the mean is higher than the median. y

2. The normal model does not provide a fairly good estimate of the home prices. This is because it discounts the outliers in representation though these points are of significant value to read the data set. Also it deviates from the median by a large amount, which potential impairs the comprehensive reading of data. As seen from the normal quartile the data points are above the expected normal range in the centre. Also the data is right skewed with a long tail which potentially explains the reason for data not being nearly normal. It can also be inferred that the lower half of the data set is below...