From d8a00dbd10f6c269fb0a4bacacb46099af2ab053 Mon Sep 17 00:00:00 2001 From: rnhmjoj Date: Mon, 6 Jul 2020 15:14:39 +0200 Subject: [PATCH] notes: fix statistic typos --- notes/sections/1.md | 6 +++--- notes/sections/7.md | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/notes/sections/1.md b/notes/sections/1.md index 3110004..392ae2f 100644 --- a/notes/sections/1.md +++ b/notes/sections/1.md @@ -125,8 +125,8 @@ $$ On each iteration the function is interpolated by a parabola passing though the points $x_\text{min}$, $x_e$, $x_\text{max}$ and the minimum is computed as the vertex of the parabola. If this point is found to be inside the interval, it is -taken as a guess for the true minimum; otherwise the method falls back to a g -olden section (using the ratio $(3 - \sqrt{5})/2 \approx 0.3819660$ proven to be +taken as a guess for the true minimum; otherwise the method falls back to a +golden section (using the ratio $(3 - \sqrt{5})/2 \approx 0.3819660$ proven to be optimal) of the interval. The value of the function at this new point $x'$ is calculated. In any case, if the new point is a better estimate of the minimum, namely if $f(x') < f(x_e)$, then the current estimate of the minimum is updated. @@ -173,7 +173,7 @@ although the result is quite imprecise. #### Median -The median is a central tendency statistics that, unlike the mean, is not +The median is a central tendency statistic that, unlike the mean, is not very sensitive to extreme values, albeit less indicative. For this reason is well suited as test statistic in a pathological case such as the Landau distribution. diff --git a/notes/sections/7.md b/notes/sections/7.md index 3943d29..ad406dc 100644 --- a/notes/sections/7.md +++ b/notes/sections/7.md @@ -389,7 +389,7 @@ Aerial and lateral views of the samples. Projection line in blue and cut in red. Using the same parameters of the training set, a number $N_t$ of test samples was generated and the points were classified applying both methods. To avoid storing large datasets in memory, at each iteration, false positives and -negatives were recorded using a running statistics method implemented in the +negatives were recorded using a running statistic method implemented in the `gsl_rstat` library. For each sample, the numbers $N_{fn}$ and $N_{fp}$ of false negative and false positive were obtained in this way: for every signal point $x_s$, the threshold function $f(x_s)$ was computed, then: