Interpreting output of RDestimate (rdd R package)

Question

I am trying to interpret a fuzzy Regression Discontinuity Design.

The output is as follows:

RDestimate(formula = y ~ x + z, cutpoint = 500, bw = optimal_bandwidth)

Type:
fuzzy 

Estimates:
           Bandwidth  Observations  Estimate  Std. Error  z value  Pr(>|z|)   
LATE       5          3000           90       120         0.90    0.45     
Half-BW    2.5        3000          500       800         0.50    0.80    
Double-BW  10         3000           60       40          0.95    0.40     
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

F-statistics:
           F         Num. DoF  Denom. DoF  p        
LATE        2        5         3000        3.0-01
Half-BW     0.5      5         3000        8.5-01
Double-BW  25        5         3000        2.0e-11

I've modified the results of my numbers, but I would like to understand the meaning of the output of an RDestimate object.

Answer 1

LATE is the average treatment effect. The half and double BW refer to outputs with a variation in the bandwidth. If you don't know what that is, just report your LATE. None of your estimates are stat. significant though.