Unit 3 Project by Jett Honaker

Question

jetthonaker — 2025-03-04 21:04:48 UTC

Is household water usage and the number of people in a household correlated?

Is this a casual or spurious relationship?

Are there any confounding or mediating variables which help tell the story?

Data Collection

jetthonaker — 2025-03-04 21:06:12 UTC

The data will be from a Google survey to all students in period 3 data science class

Water Usage in Household Period 3 Graph

jetthonaker — 2025-03-04 21:08:06 UTC

Data Collection

jetthonaker — 2025-03-04 21:10:55 UTC

All of this data is from a survey from my whole class

Equation for the Least Squares Regression Line

jetthonaker — 2025-03-04 21:12:29 UTC

The equation for the least squares regression line is y=62x+173. The slope is 62 because that is the average water usage per house, while the y-intercept is 173 because that is the amount that the water usage increases per person in each household

Section C

jetthonaker — 2025-03-14 05:36:57 UTC

Statements about water usage and number of people in a household:

the more members in the household the higher the water usage tends to be
the less people in the household often correlates with a lower average of water usage

The Relationship Type

this is a casual relationship
it's because there are more people in the household so this equals to a higher amount of water usage, since more people are going to need water at different times in the day

Variables that lead to this are :
showers needed
sinks turned on to wash hands
and toilets flushed

Final Claim

jetthonaker — 2025-03-14 05:40:27 UTC

I learned that everyone uses gallons of water monthly and daily, that the number of people in a person's household only increases how much water is used overall. I also learned that individuals alone use thousands of gallons of water monthly. This further exemplifies that the California government has a right to ask citizens to conserve water during drought season, because people waste so much daily. People with multiple bathrooms, sinks, gardens, and pools only increase the amount of water usage for that household.

Purpose

jetthonaker — 2025-03-14 05:41:14 UTC

To determine my households water usage, and my classes household water usage and see how it correlates

Overview

jetthonaker — 2025-03-14 05:42:34 UTC

In my family, I am the only child with 2 parents and a dog. We own a jacuzzi, have an average size house with a nice lawn in the front and backyard, we have bushes and trees surrounding our house aswell, we have two bathrooms each with a toilet and sink and shower

Section D

jetthonaker — 2025-03-14 05:45:28 UTC

y=62x+173

x=# of people

y= water usage

Roseville water usage in only one day

the population: 159,135

y = 62(159,135)+173

y = 9,866,543 gallons of water used in one day

Lateral Reading

jetthonaker — 2025-03-14 05:47:18 UTC

"The water industry estimates that an average person uses 3,000 gallons of water monthly, so a family of 4 would use 12,000 gallons for bathing, cooking, washing, recreation, and watering."

Household water usage:

this reafrims my ideas that people use a lot of gallons of water each month, and it only increases with the amount of people in a persons household

Can we use the city data to predict further water usage?

jetthonaker — 2025-03-14 05:50:36 UTC

Yes, if you compare the average households' water usage in a city, it should be pretty similar in places like school, work, or hospitals. People tend to stick to similar habits. However, the only big change would be the number of people in the buildings. More people use the bathroom and sinks in bigger buildings, but in individual homes, people use water more for things like gardens, pools, laundry, showers. So it evens out and makes for a similar and predictable average in these cities.

My houses water usage

jetthonaker — 2025-03-14 05:54:45 UTC

The amount of water usage in my house is pretty much in the middle compared to other households in this data set

It compares the least squares regression line by aligning with the data set

LSRL value according to my graph

jetthonaker — 2025-03-14 06:00:23 UTC

The LSRL value tells me that the line of best fit has a bit of a weaker relationship according to the data set. This is most likely due to certain outliers affecting my data