Daily Deaths by State - CDC
Why Use This Data Source In Your Models?
Seasonal Impact
Instantly Download this Data Using Our Automated Feature Engineering Tool.
Automated Data Profiling
Suggested Treatment:
Grain Transformation:
Source:
CDC Case Task Force
Release:
COVID-19 Deaths
Units:
Deaths
Frequency:
Daily
Available Through:
10/18/2022
Suggested Treatment:
The data shows auto correlation and a non-normal distribution. The data should be differenced. While the Order Norm transformation, provides the best normality, the Yeo Johnson variable will also perform well.
Grain Transformation:
Data is unable to be distributed by time or geography. The roll up method used is Weighted Average.
Auto Correlation Analysis:
Data shows auto correlation indicating a need for differencing
The ACF indicates 1 order differencing is appropriate.
Following first order differencing, no further differencing is required based on the differenced ACF at lag one of -0.57
Trend Analysis:
The Kwiatkowski-Phillips-Schmidt-Shin (KPSS) test, KPSS Trend = 0.16 p-value = 0.03 indicates that the data is not stationary.
Distribution Analysis:
The Shapiro-Wilk test returned W = 0.62 with a p-value =0.00 indicating the data does not follow a normal distribution.
A skewness score of 4.31 indicates the data are substantially skewed.
Hartigan's dip test score of 0.02 with a p-value of 0.02 inidcates the data is multimodal
Statistics (Pearson P/ df, lower => more normal)
Auto Correlation Function
Auto Correlation Function After Differencing
Partial Auto Correlation Function
Seasonal and Trend Decompostion