# Explainability of groups mix affect on overall mean

I am stuck on understanding the best way to approach this problem from a purely statistical/mathematical way.

Say that I have this data in the table below. It shows the comparison of prices for one hotel between two years with a breakdown of the board type and room type.

Hotel Board Room 2023 Price 2024 Price
1 HB A 1000 1100
1 HB B 1600 1850
1 FB A 1500 1750
1 FB B 1900
1 FB C 2250 2250
1 ALL A 2000
1 ALL B 2600 2750

Within this data, as a human I can easily tell that most of the prices go up year on year and from the averages below I can also understand this too

2023 average - 1808

2024 average - 1950

However when eyeballing the data I can also see there are some mix differences that will be affecting the overall mean, for example

Board type of "ALL" averages:

2023 average - 2600

2024 average - 2375

Here we can see that because of a lack of data in 2023 for the room type "A" for the board type "ALL" there looks to be a step back in price. This then may actually be artificially increasing the overall mean for this hotel and thus showing a smaller increase in price year on year.

What I want to try and understand - is there a technique out there that will be able to show and explain the drivers affecting the yearly overall means across all groups?