subset_index.R

``` r
suppressPackageStartupMessages({
  library(dplyr)
})

# create synthetic data
set.seed(42)
year_basket <- sample(2000:2020,100, replace = TRUE)
set.seed(137)
fee_basket <- sample(6000:9000,100)
synthetic <- tibble(Year = year_basket, Fee = fee_basket)

# group by Year and summarize stats

synthetic %>% 
  arrange(Year) %>%
  group_by(Year) %>% summarize(
    Count = n(), 
    Mean = mean(Fee), 
    SD = sd(Fee), 
    Median = median(Fee), 
    IQR = IQR(Fee)) -> output

get_output <- function(x,y,z) x[which(x$Year < y & x$IQR < z),]

get_output(output,2017,500) 
#> # A tibble: 7 x 6
#>    Year Count  Mean    SD Median   IQR
#>   <int> <int> <dbl> <dbl>  <dbl> <dbl>
#> 1  2001     5 7641. 855.   8112  486  
#> 2  2002     5 7601. 997.   7714   75  
#> 3  2005     4 7480. 308.   7548. 321. 
#> 4  2006     3 6692. 455.   6735  453  
#> 5  2009     5 7190. 451.   6930  322  
#> 6  2011     2 6674.  29.0  6674.  20.5
#> 7  2015     3 7212  150.   7276  139
```