A solution to de-seasonalizing data? Admission rate to emergency room I am trying to fit a model for the admission rate to our emergency department by using time series in STATA, which is fairly new to me and I would like to take your input about deseasonalizing. data:datafile
The data consists of 2 years of univariate data with weekly seasonality, where Saturdays and Sundays show more admission as seen in the image below.

To overcome this 7 day seasonality, first I differenced by 7 and built the model with d=7. But the residuals failed to show white noise with portmanteau test. SARIMA model with 7 days differencing resulted in the same
behavior but I modeled with regression analysis with seasonal dummy variables: d1-d7 for 7 days of week (thanks to Prof Hansen and his lecture):
regress totalhasta d1 d2 d3 d4 d5 d6 d7 L(1/7).VAR_NAME, noconstant

The residuals show white noise and model shows better fit with lower AIC and BIC tests compared to other 2 models.
So is it a good practice to use dummy variables instead of differencing with the seasonality length, SARIMA models to overcome seasonality?
 A: As nobody more experienced with time series is answering, I will give a try. First, you should tell us clearer what is your goal---prediction or description/estimation of seasonalities. If goal is prediction, I think seasonalities should be part of the model, you should not deseasonalize first. As you have daily data, tou could find much information here.  But, in all cases I would start with visualization to understand the data better.
dta <- readstata13::read.dta13("veriseti min 13 03 2020.dta")

library(lubridate)
library(tidyverse)
library(tsibble)
library(feasts)

dta <- as_tsibble(dta)


produced by gg_season(dta, period=7).  A subseries plot can be helpful: 

produced by dta %>% gg_subseries(period=7). This plot makes it clear that the series is not stationary, it is a dip around the mid of the time period. A Seasonal decomposition made by dta %>% model(STL(pt  ~ season(period=7))) %>% components() %>% autoplot():

It is interesting that the spread of the seasonal component seems to be diminishing somewhat.
