for loop compute historical volatility select lines per year

Question

i am a beginner on R and i am currently trying to compute the historical volatility per year. My dataset looks like this :

date           prices

01/01/2000     100

03/01/2000     98

05/10/2000     103

08/03/2001     102

08/04/2001     110

i would like to create a for loop in order to compute quickly the historical volatility i have been computing "manually" as follows :

data_hv <- read.csv("file")
data_hv_2000 <- data_hv[(1:259),]
data_hv_2001 <- data_hv[(260:518),]
data_hv_2002 <- data_hv[(519:778),]
data_hv_2003 <- data_hv[(779:1038),]

and then, computing the historical volatility once i have grouped per year the data in subsets of data :

price = data_hv_2000$price
ret <- log(lag(price)) - log(price)
print(ret)
vol <- sd(ret, na.rm = TRUE) * sqrt(259) * 100
vol

price_2001 = data_hv_2001$price
ret <- log(lag(price_2001)) - log(price_2001)
vol_2001 <- sd(ret, na.rm = TRUE) * sqrt(260) * 100
vol_2001

260 and 259 being the number of rows of each subset.

i have tried to start doing a for loop :

data_hv %>%
  for (i in 2000:2022) {
    filter(contains(i)) %>%
    price_i = data_hv_i$Wheat
    ret <- log(lag(price_i)) - log(price_i)
    vol_i <- sd(ret, na.rm = TRUE) * sqrt(nrows(data_hv_i)) * 100
    vol_i 
}

but it doesn't work and im a bit lost. I would finally like to store these values in a list (one value - the historical volatility - per year). Could anyone help me ?

Answer 1

There are a couple things you want to remember when running for loops and one of them is to create a empty object of desired type before running the loop. Also, you are piping into a for-loop and into an object, which is probably causing an error.

data_hv %>%
  for (i in 2000:2022) {
    filter(contains(i)) %>%
    price_i = data_hv_i$Wheat
    ret <- log(lag(price_i)) - log(price_i)
    vol_i <- sd(ret, na.rm = TRUE) * sqrt(nrows(data_hv_i)) * 100
    vol_i 
}

Try this:

# when doing a for-loop save to an empty object first
vol_final <- list()

# then iterate over what you want

  for (i in 2000:2022) {
      
      # do work
      data_hv_i <- data_hv %>% filter(year == i)
      
      price_i = data_hv_i$prices
      ret <- log(lag(price_i)) - log(price_i)
      vol_i <- sd(ret, na.rm = TRUE) * sqrt(nrow(data_hv_i)) * 100
      
      #finally save to a list by appending a list to a list, e.g. vol_i -> vol_final
      vol_final  <- append(vol_final, list(data.frame(year = i, vol_i)))
  }

vol_final
#

Final Solution

library(clock)
#> Warning: package 'clock' was built under R version 4.1.3
library(tidyverse)
library(lubridate)
#> 
#> Attaching package: 'lubridate'
#> The following object is masked from 'package:clock':
#> 
#>     as_date
#> The following objects are masked from 'package:base':
#> 
#>     date, intersect, setdiff, union

data_hv <- tibble(date = rep(date_build(2000:2022), 263),
                  prices = rnorm(6049, 100, 2),
                  year = year(date))

# when doing a for-loop save to an empty object first
vol_final <- list()

# then iterate over what you want

  for (i in 2000:2022) {
      
      # do work
      data_hv_i <- data_hv %>% filter(year == i)
      
      price_i = data_hv_i$prices
      ret <- log(lag(price_i)) - log(price_i)
      vol_i <- sd(ret, na.rm = TRUE) * sqrt(nrow(data_hv_i)) * 100
      
      #finally save to a list by appending a list to a list, e.g. vol_i -> vol_final
      vol_final  <- append(vol_final, list(data.frame(year = i, vol_i)))
  }

vol_final
#> [[1]]
#>   year    vol_i
#> 1 2000 44.07769
#> 
#> [[2]]
#>   year    vol_i
#> 1 2001 43.39855
#> 
#> [[3]]
#>   year    vol_i
#> 1 2002 41.52856
#> 
#> [[4]]
#>   year   vol_i
#> 1 2003 43.0145
#> 
#> [[5]]
#>   year    vol_i
#> 1 2004 46.15526
#> 
#> [[6]]
#>   year    vol_i
#> 1 2005 49.52201
#> 
#> [[7]]
#>   year    vol_i
#> 1 2006 49.14017
#> 
#> [[8]]
#>   year    vol_i
#> 1 2007 46.17739
#> 
#> [[9]]
#>   year    vol_i
#> 1 2008 46.81863
#> 
#> [[10]]
#>   year    vol_i
#> 1 2009 43.77617
#> 
#> [[11]]
#>   year    vol_i
#> 1 2010 47.30922
#> 
#> [[12]]
#>   year    vol_i
#> 1 2011 47.00433
#> 
#> [[13]]
#>   year    vol_i
#> 1 2012 45.93459
#> 
#> [[14]]
#>   year    vol_i
#> 1 2013 40.46577
#> 
#> [[15]]
#>   year    vol_i
#> 1 2014 48.49482
#> 
#> [[16]]
#>   year    vol_i
#> 1 2015 44.76563
#> 
#> [[17]]
#>   year    vol_i
#> 1 2016 45.18651
#> 
#> [[18]]
#>   year    vol_i
#> 1 2017 49.04513
#> 
#> [[19]]
#>   year   vol_i
#> 1 2018 45.6688
#> 
#> [[20]]
#>   year    vol_i
#> 1 2019 43.08453
#> 
#> [[21]]
#>   year    vol_i
#> 1 2020 46.07952
#> 
#> [[22]]
#>   year    vol_i
#> 1 2021 47.65877
#> 
#> [[23]]
#>   year    vol_i
#> 1 2022 45.06297

^{Created on 2022-06-20 by the reprex package (v2.0.1)}