Felipe bought a new suit that he thinks will get him more compliments in the office than his old suit.
He randomized $50$ workdays between a treatment group and a control group. On each day from the treatment group he wore his new suit, and on each day from the control group he wore his old suit.
The results of the experiment showed that the median number of compliments he got for wearing the new suit is $1.5$ greater than the median number of compliments he got for wearing the old suit. To test whether the results could be explained by random chance, Felipe created the table below, which summarizes the results of $1000$ re-randomizations of the data (with differences between medians rounded to the nearest $0.5$ compliments).
**According to the simulations, what is the probability of the treatment group's median being higher than the control group's median by $1.5$ compliments or more?**
$\qquad$[[☃ input-number 1]]
Assume that if the probability you found is *lower* than $5\%$, then the result should be considered as significant.
**What should we conclude regarding the experiment's result?**
[[☃ radio 1]]
New suit (Treatment) median $-$ Old suit (Control) median | Frequency
:-: | :-:
$-2$ | $2$
$-1.5$ | $14$
$-1$ | $40$
$-0.5$ | $142$
$0$ | $597$
$0.5$ | $154$
$1$ | $35$
$1.5$ | $15$
$2$ | $1$