|
Multi-linear
Regression
Each district had a distinct
combination of climate variables for SPR and API that produced the largest R2
value for that set of predictor variables.
Below are displayed the group of climate variables for each district
that, together in a multi-linear regression, explained the most variability
(highest R2 values) in API and SPR by climatic variables alone.
|
BEST REGRESSION FOR API BY
DISTRICT IN KARNATAKA,
INDIA
|
|
|
|
|
|
|
|
|
Temperature
|
|
|
|
|
|
Precipitation
|
|
|
R^2
|
p>F
|
|
Coastal
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Uttara Kannara
|
Jan
|
Feb
|
March
|
May
|
Oct
|
Lag Dec
|
Lag Nov
|
|
|
0.67
|
0.07
|
|
Dakshina Kannara
|
Lag Dec
|
|
|
|
|
|
July
|
Lag Nov
|
|
|
0.30
|
0.03
|
North
Interior
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Raichur
|
Jan
|
Feb
|
|
|
|
|
|
April
|
|
|
|
0.53
|
0.002
|
|
Gulbarga
|
Jan
|
Feb
|
Lag Nov
|
|
|
|
|
Nov
|
Lag Nov
|
|
|
0.50
|
0.009
|
|
Bidar
|
Jan
|
Lag Nov
|
|
|
|
|
|
June
|
|
|
|
0.51
|
0.002
|
|
Belgaum
|
Jan
|
April
|
May
|
Lag Nov
|
|
|
Lag Nov
|
|
|
0.66
|
0.001
|
|
Bijapur
|
Jan
|
April
|
May
|
|
|
|
|
|
|
|
|
0.36
|
0.02
|
|
|
Dharwad
|
April
|
May
|
July
|
Sept
|
Dec
|
Lag Nov
|
Lag Dec
|
April
|
Lag Nov
|
|
|
0.87
|
0.0001
|
|
|
South
Interior
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Bellary
|
Jan
|
April
|
May
|
July
|
Feb
|
Lag Nov
|
Lag Dec
|
Lag Nov
|
|
|
0.84
|
0.0001
|
|
Shimoga
|
April
|
May
|
Lag Nov
|
Lag Dec
|
|
|
April
|
Nov
|
Lag Nov
|
0.87
|
0.0001
|
|
Chitradurga
and Hassan |
April
|
May
|
July
|
Lag Dec
|
|
|
April
|
Lag Nov
|
|
|
0.70
|
0.0007
|
|
Kodagu
|
May
|
|
|
|
|
|
|
Oct
|
Nov
|
Lag Nov
|
0.63
|
0.003
|
Bangalore
|
July
|
|
|
|
|
|
|
April
|
Lag Nov
|
Feb
|
|
0.47
|
0.008
|
|
Mandya
|
|
|
|
|
|
|
|
Apri
|
Lag Nov
|
Feb
|
|
0.59
|
0.002
|
|
Chikmagalur
|
April
|
July
|
Lag Dec
|
|
|
|
|
April
|
July
|
Oct
|
Lag Nov
|
0.77
|
0.0004
|
|
Mysore
|
May
|
Lag Nov
|
Lag Dec
|
|
|
|
|
April
|
Nov
|
|
|
0.62
|
0.002
|
|
Tumkur
|
Lag Dec
|
|
|
|
|
|
May
|
Nov
|
Lag Nov
|
0.67
|
0.002
|
|
Kolar
|
Feb
|
|
|
|