analistica/slides/sections/7.md

82 lines
1.3 KiB
Markdown
Raw Normal View History

2020-06-10 16:23:33 +02:00
# MC simulations
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
## In summary
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
-----------------------------------------------------
Landau Moyal
----------------- ----------------- -----------------
median $m_L\ex$ $m_M\ex (μ, σ)$
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
mode $\mu_L\ex$ $\mu_M\ex (μ)$
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
FWHM $w_L\ex$ $w_M\ex (σ)$
-----------------------------------------------------
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
## Moyal parameters
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
A $M(x)$ similar to $L(x)$ can be found by imposing:
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
\vspace{15pt}
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
- equal mode
$$
\mu_M\ex = \mu_L\ex \approx 0.22278298...
$$
2020-06-08 23:44:51 +02:00
. . .
2020-06-10 16:23:33 +02:00
- equal width
$$
w_M\ex = w_L\ex = \sigma \cdot a
$$
2020-06-08 23:44:51 +02:00
$$
2020-06-10 16:23:33 +02:00
\implies \sigma_M \approx 1.1191486...
2020-06-08 23:44:51 +02:00
$$
2020-06-10 16:23:33 +02:00
## Moyal parameters
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
:::: {.columns}
::: {.column width=50%}
![](images/both-pdf-bef.pdf)
:::
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
::: {.column width=50%}
![](images/both-pdf-aft.pdf)
:::
::::
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
## Moyal parameters
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
This leads to more different medians:
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
\begin{align*}
m_M = 0.787... \thus &m_M = 0.658... \\
&m_L = 1.355...
\end{align*}
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
## Compatibility test
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
Comparing results:
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
$$
p = 1 - \text{erf} \left( \frac{t}{\sqrt{2}} \right)\ \with
t = \frac{|x\ex - x\ob|}{\sqrt{\sigma\ex^2 + \sigma\ob^2}}
$$
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
- $x\ex$ and $x\ob$ are the expected and observed values
- $\sigma\ex$ and $\sigma\ob$ are their absolute errors
2020-06-08 23:44:51 +02:00
. . .
2020-06-10 16:23:33 +02:00
At 95% confidence level, the values are compatible if:
2020-06-08 23:44:51 +02:00
2020-06-10 16:23:33 +02:00
$$
p > 0.05
$$