ANALYZING CHANGE IN MEAN MARKET VALUE THADS DATASET

 

1. Objective

The primary objective of this assessment is to analyze the change in the Mean Fair Market Rent (FMR) across five distinct THADS years (2005, 2007, 2009, 2011, 2013). By conducting pairwise comparisons of FMR values between these years, we aim to understand the potential impact of the 2008 Subprime Mortgage Crisis on rental markets.

2. Methodology

Data Source: The analysis utilizes THADS (The American Housing Survey) datasets for the years 2005, 2007, 2009, 2011, and 2013.

Data Preparation:

  • Individual year datasets were loaded and concatenated into a single DataFrame.
  • A 'Year' column was added to each dataset to identify the origin year of the data.
  • The 'FMR' (Fair Market Rent) column was converted to a numeric type, with non-convertible values coerced to NaN.
  • An 'Occupancy_Status' column was derived from the 'STATUS' variable, categorizing units as 'Occupied' or 'Vacant'.
  • Crucially, data points with FMR values less than $1 were filtered out to ensure realistic and meaningful FMR calculations, as negative or zero FMR values are not logically sound.

Analytical Approach:

  • Descriptive Statistics: Summary statistics (count, mean, median, min, max, standard deviation) for FMR and value counts for 'Occupancy_Status' were calculated for each year to understand the central tendency and spread of the data.
  • Pairwise T-tests: To statistically compare the mean FMR between different years, a series of pairwise two-sample independent t-tests were performed. Welch's t-test (equal_var=False) was chosen to accommodate the potential for unequal variances between the FMR distributions of different years. A significance level of 0.05 was used for hypothesis testing.

3. Key Findings

3.1. Descriptive Statistics of FMR and Occupancy Status (Post-Filtering):

YearFMR_countFMR_meanFMR_medianFMR_minFMR_maxFMR_stdOccupiedVacant
200546805922.5678863.0000345.00003464.0000328.7770433603493
200742729971.5420902.0000361.00003400.0000332.1499391073622
2009490901073.04921002.0000427.00003501.0000355.6454450574033
20111455311179.65231051.0000419.00003586.0000448.093613491810613
2013645351164.39521100.0000394.00003511.0000394.1192600974438
  • FMR Trend: The mean FMR generally increased from $922.57 in 2005 to a peak of $1179.65 in 2011, then slightly decreased to $1164.40 in 2013. The median FMR follows a similar pattern.
  • FMR Spread: The standard deviation of FMR increased significantly from 2005 to 2011, indicating greater variability, before decreasing slightly in 2013. This suggests increased volatility in FMR values, possibly related to economic shifts.
  • Occupancy Status: The total number of units and the counts of both 'Occupied' and 'Vacant' units show considerable fluctuations across the years, notably a large increase in data points for 2011.
3.2.1. Boxplot Showing the Change in Mean and Median across Years from 2005 to 2013



3.2. Pairwise T-Test Results for Mean FMR:

All pairwise comparisons of mean FMR between the years yielded P-values of 0.0000, which are well below the 0.05 significance level. This indicates that there are statistically significant differences in the mean FMR between every single pair of years analyzed.

  • Consistent FMR Increase (2005-2011): For most comparisons from 2005 onwards, the T-statistics were negative (e.g., Year 2005 vs. Year 2011: T-statistic = -134.1407). This signifies that the mean FMR in later years was statistically significantly higher than in earlier years, reflecting a period of increasing FMR from 2005 up to 2011.

  • FMR Decline Post-2011 (2011 vs. 2013): A critical finding is the comparison between 2011 and 2013 (T-statistic = 7.8406). The positive T-statistic indicates that the mean FMR in 2011 was statistically significantly higher than in 2013. This marks a reversal of the previous upward trend, suggesting a decline in FMR after 2011.

4. Conclusion: Impact of the 2008 Subprime Mortgage Crisis

The analysis strongly suggests that the 2008 Subprime Mortgage Crisis had a discernible impact on Fair Market Rent trends. While FMR generally trended upwards in the years immediately following the crisis (2009 and 2011, relative to pre-crisis years), which could be attributed to increased demand for rentals as homeownership became less accessible or desirable, a significant shift occurred between 2011 and 2013. The statistically significant decrease in mean FMR from 2011 to 2013 indicates that the housing market, including the rental sector, continued to adjust and perhaps stabilize or even decline in certain areas in the aftermath of the crisis and subsequent economic downturns.

5. Next Steps

To further enhance this analysis and provide deeper insights, the following next steps are recommended:

  • Regional Analysis: Investigate FMR trends at a more granular geographic level (e.g., by metropolitan area or state) to identify regional variations in the crisis's impact.
  • Other Housing Market Indicators: Integrate additional variables such as unemployment rates, median household income, housing supply, and foreclosure rates to build a more comprehensive model of FMR determinants.
  • Regression Analysis: Employ regression techniques to quantify the relationship between FMR and various economic and housing market indicators, and to model the FMR changes over time.
  • Outlier Detection: Further investigate the FMR distribution for each year, specifically addressing any potential outliers that might skew the mean and standard deviation, even after filtering negative values.

Interpretation of Pairwise T-Test Results:

The output above shows the results of a two-sample t-test for each pair of years, comparing the mean Fair Market Rent (FMR). The equal_var=False argument means we are performing Welch's t-test, which is robust to unequal variances between the groups.

How to interpret the results:

  • T-statistic: This value measures the difference between the sample means relative to the variation within the samples. A larger absolute t-statistic indicates a greater difference between the means.
  • P-value: This is the probability of observing a t-statistic as extreme as, or more extreme than, the one calculated, assuming that the null hypothesis (i.e., there is no significant difference between the means of the two years) is true.

Decision Rule:

  • If the p-value is less than your chosen significance level (commonly 0.05), you reject the null hypothesis. This suggests that there is a statistically significant difference in the mean FMR between the two years being compared.
  • If the p-value is greater than or equal to your chosen significance level, you fail to reject the null hypothesis. This suggests that there is no statistically significant difference in the mean FMR between the two years at that significance level.

By examining the p-values for each pair, we can identify which year-to-year changes in FMR are statistically significant.

Comments

Popular posts from this blog

Teach your Child Coding

Google Data Analytics Project 2: Bike Share Case Study Project