pvllabs-blog

[pvllabs-blog]

Dataset Description

Sample: Housing prices in King County was studied. Features such as houseId, date House was Sold, bedrooms, bathrooms, square Footage of Living Area, square Footage of the lot, number of Floors, waterfront View, house has been Viewed, overall Condition, grade given to the House Apart from Basement, square Footage of the Basement, built Year, renovated Year, zip, latitude, longitude, square Footage of the Living Room Area in 2015, square Footage of the Lot in 2015 and Price of the house were captured. A total of  21,613 houses belonging to 70 zip codes.

Below are the minimum and maximum range values of the variables in the data set:

1. House Id: Unique Identifier of the House

2. Date house was sold

3: Price: min 75,000 and max 77,00,000

4. Bedrooms: min 0 and max 33

5. Bathrooms: min 0 and max 8

6. Square Footage of Living Area: min 290 and max 13,540

7. Square Footage of the Lot: min 520 and max 16,51,359

8. Number of Floors: min 1 and max 3.5

9. Waterfront View: min 0 and max 1

10. House has been Viewed: min 0 and max 4

11. Overall Condition: min 1 and max 5

12. Grade given to the House Based on King County Grading System: min 1 and max 13

13. Square Footage of the House apart from Basement: min 290 and 9,410

14. Square Footage of the Basement: min 0 and max 4,820

15. Built Year: min 1900 and max 2015

16. Renovated Year: min 0 and max 2015

17. Zip

18. Latitude

19. Longitude

20. Square Footage of the Living Room Area in 2015: min 399 and max 6,210

21. Square Footage of the Lot in 2015: min 651 and max 8,71,200

Procedures: For the purpose of this assignment, I downloaded this dataset from Kaggel website. This data was made available by King County Government. Information on how the data is collected  is not mentioned on the website.

Measures: The King County Housing Authority (KCHA) is a public housing agency serving King County, Washington, excluding the cities of Seattle and Renton. The agency oversees 132 properties, including more than 4,200 units of federally assisted subsidized housing and 6,000 units of workforce housing for qualified low- and moderate-income families and individuals. The agency also administers 10,000 Housing Choice (Section 8) vouchers (Source: https://en.wikipedia.org/wiki/King_County_Housing_Authority). Data is made available on data.kingcounty.gov and Kaggel (Kaggel https://www.kaggle.com/harlfoxem/housesalesprediction/downloads/housesalesprediction.zip/1)

[pvllabs-blog]

Assignment#1 Data Analysis

Step#1

Dataset: National Longitudinal Study of Adolescent Health (AddHealth)

Step#2

Specific topic of interest: What is the influence of Non-Resident Biological Father or Non-Resident Biological Mother on their ward's behavior. In particular: i)  Addiction to Tobacco, Alcohol, Drugs; ii) Indulgence in Fighting and Violence; iii) Motivations to Engage in Risky Behaviors;

Step#3

Prepare a codebook of your own - Done URL:https://www.dropbox.com/sh/zp532wffmvm78xi/AAAuupOyGj8AdL5whIg_QvMsa?dl=0

Step#4

Second topic: What is the influence of Friends, Neighborhood, Relationship with Neighbors and Siblings on a person's behavior. In particular: i)  Addiction to Tobacco, Alcohol, Drugs; ii) Indulgence in Fighting and Violence; iii) Motivations to Engage in Risky Behaviors;

Step#5:

Added these details to codebook.

Step#6:

Literature Review: It is an ongoing process and so far I found out that AddHealth data is not independent data and such types of data are to be processed before hand and the results should be inferred, or else results won't reflect the entire population. References (so far): [1] http://ucdata.berkeley.edu/pubs/addhealth_data_presentation_suli.pdf [2] http://www.cpc.unc.edu/projects/addhealth/documentation/guides/weight1.pdf

Step#7:

As my literature review is on going, I formulated my own hypothesis for timebeing. Hypothesis: Are students more likely to addict to Tobacco, Alcohol, Drugs, indulgence in Fighting and Violence, and,  Motivated to Engage in Risky Behaviors if either of their Biological Father or Mother is non-Resident? My opinion: I am not sure as of now and I want to explore this. Specific Variables: i)   Non-Resident Biological Father; ii)  Non-Resident Biological Mother; iii) Addiction to Tobacco, Alcohol, Drugs; iv)  Indulgence in Fighting and Violence; v)   Motivations to Engage in Risky Behaviors;

[pvllabs-blog]

Data set and Association for Assignment#1

National Longitudinal Study of Adolescent Health (Add Health) Code Book:

Non-Resident Biological Father;

Resident Father;

Relations with Parents;

Relations with Siblings;

Motivations to Engage in Risky Behaviors;

Parents' Attitude;

Relationship Information;

Personality and Family;

Tobacco, Alcohol, Drugs;

Fighting and Violence;

Friends;

Neighborhood;

Step1: National Longitudinal Study of Adolescent Health (Add Health) Code Book Step2: What is the influence of Family(Both Biological Father, Biological Mother and Siblings), Friends and Neighborhood on a child's behavior and how is he behaving with others...... example: Tobacco, Alcohol, Drugs, Motivation to Engage in Risky Behaviors etc. Step3: Prepare a code book of your own. Step4: Original topic is " Does the relation of a ward with his/her parents' affect his behavior in public, is the ward more likely to addict to Tobacco, Alcohol, Drugs if one of their biological parents is non-resident? Second topic: What is the influence of Friends and Neighborhood on a ward? Are they more likely to influence a person than his/her parents? Step5: Add questions/items/variables documenting this second topic to your personal code book. Step6: Perform Literature Review Step7: Based on your literature review, develop a hypothesis about what you believe the association might be between these topics. Be sure to integrate the specific variables you selected into the hypothesis.