Unit 3: Project 3 by Mayeli Martinez Guerrero

Questioning

ffa22c856e0846299b29b90a1d689d7a_110472_8 — 2024-03-07 20:45:07 UTC

My name is Mayeli and I am currently discussing water use in my own home, district and the city and comparing it to other places. For my own home I went onto a website which calculated the gallons I use per day at any circumstance, then I would use those calculations to measure how much my whole household uses.

Modeling

ffa22c856e0846299b29b90a1d689d7a_110472_8 — 2024-03-07 20:45:26 UTC

Based on the scatter plot one can see that it is skewed right, LSRL is increasingly showing that the more people the more water used (relationship) based on where the dots are placed I believe it isn't the best representation as there is mixed and uncontrolled relationships between (people/water). ŷ = 225.0349 + 53.5741x In the context of this data the slope represents the usual connection within the data, how one data point relates to another , and Y intercept represents the least possible people and the water usage!

In other words for each person 53.5741 gallons are predicted to be used, and the y represent the minimum of people to water.

Analyzing

ffa22c856e0846299b29b90a1d689d7a_110472_8 — 2024-03-07 20:46:21 UTC

I could state the the amount of people affects the usage of water, while there might be more factors to this situation, the major idea behind water being used is caused by the household size. For one LSRL is increasing letting us know the more x the more y, a correlation that seems to repeat.

Communicating

ffa22c856e0846299b29b90a1d689d7a_110472_8 — 2024-03-07 20:46:49 UTC

While this data set included a variety of numbers and households, one cant apply this information to a wider population or community. Each zone has its unique qualities and this could be less people in a zip code because usual older couples live here. Or even places that usually have many family members in one home due to financial income. My point being that there is many situations where the data set isn't similar. With an LRSL like the one I found, it just goes to show there's a pattern and slightly correlation yet its not able to predict its own data nor another population.

Modeling 2

ffa22c856e0846299b29b90a1d689d7a_110472_8 — 2024-03-07 21:36:37 UTC

Now judging by the least square regression line, my point is accurately along that line, meaning that according to the data acquired and calculation my point is the average amount the RJUHSD district.

To find the residual= actual-estimate

500.45-500=.45 this suggests that the lower the number the more accurate the standing in the data.

Questioning 2

ffa22c856e0846299b29b90a1d689d7a_110472_8 — 2024-03-07 21:37:30 UTC

Following that I was able to compare with other households, then other districts after that other cities! After analyzing I believe that the amount of people in a household has a large impact in the water used!

Modeling 3

ffa22c856e0846299b29b90a1d689d7a_110472_8 — 2024-03-07 21:42:04 UTC

However the r and r^2 suggest a different topic!

The r is 0.212

The r^2 is 0.045

Based on the social science category chart for strength of correlation, this strength seems to be meaningless or rather have no correlation. Overall the LRSL is not a good representation nor predictor of this data.

Analyzing

ffa22c856e0846299b29b90a1d689d7a_110472_8 — 2024-03-16 04:43:30 UTC

Personally for my finding of my household a confounding variable is the water used up by machines.

It doesn't matter the amount of people the machines run on heavy loads of water. An example of this is the dishwasher and washer, my mom tries to occupy as much space to not waste water therefore stating that it doesn't matter the number of people.

ffa22c856e0846299b29b90a1d689d7a_110472_8 — 2024-03-16 04:57:38 UTC

More specifically , when comparing water use of district and then city its two different places that obviously has different routines and use of water therefore one can not predict the other. However, it gets more accurate when comparing it to similar places like another school! as its expected to use similar amounts of water. One has to question, does this school own a pool? does it automatically water their gardening, how many bathrooms does it own.

It all depends, it all is unique...

ffa22c856e0846299b29b90a1d689d7a_110472_8 — 2024-03-16 05:21:05 UTC

Based on the equation, ŷ = 225.0349 + 53.5741x lets predict the water usage in my city.

ŷ = 225.0349 + 53.5741(48,468)= 2596854.5137

Our city is predicted to use 2,596,854.5137 gallons of water.

(really 38 billion is use per day)

For our state ŷ = 225.0349 + 53.5741(39,000,000)= 2089390125.03

Our state is predicted to use 2,089,390,125.03 gallons of water.

For another state like Texas 225.0349 + 53.5741(28mil)=1,500,075,025.03 which makes sense compared to California as both this states have a high density of residence.

Communication 4

ffa22c856e0846299b29b90a1d689d7a_110472_8 — 2024-03-16 05:21:51 UTC

Overall with a quick glimpse one can conclude that the information is reasonable, however this is an average estimate that dint include confounding variables or anything of this sort. Concluding that we can make prediction based on the information gathered yet they are not accurate predictions.

Factors that affects water use: agriculture. California produces more agriculture than Texas due to its healthy soil which means it need more water. Although this might not be used by humans, human choose to use their water on these plants!

Other factors: amounts of pools in homes, bathrooms average on properties and so many more...