Homework answers / question archive / In your response, provide your own interpretation of their distribution graph

In your response, provide your own interpretation of their distribution graph

Business

Share With

---

In your response, provide your own interpretation of their distribution graph. Note any differences between your classmate’s interpretation and your own. Though two replies are the basic expectation for class discussions, for deeper engagement and learning you are encouraged to provide responses to any comments or questions others have given to you. Continuing to engage with peers and the instructor will further the conversation and provide you with opportunities to demonstrate your content expertise, critical thinking, and real-world experiences with the discussion topics. THIS IS FOR QUESTION 1&2

 

Question 1(Andre)

The visualization of graphs helps represent the data to the viewer to understand the chart.  Once you create a chart and provide the data, each individual can ask questions about the outcome of your data. For example, looking at the United States Census data is a perfect visualization of what's going on in different demographics.  The data comes in many other formats, but asking for a percentage of adults who have received at least one dose of a COVID-19 vaccine.  The site shows a United States image to allow the viewer to see where the virus affects the country.  The chart shows where the data is possessed to reach out to companies to understand poverty and make the chart interactive to drill down on a particular state.  The part that ties everything together is making the data very visible, along with a user-friendly interface.  

    I believe the author of the technical analyst would be someone in the firm that handles the analytics of providing the data compelled.  I think the data gathered will help with getting everything together to present to an audience.  The data is credible when deciding to put things together; however, once the data is shown in a graph, it's up to the audience to make sure the information is correct. For example, https://www.census.gov/popclock/ offers a population clock for domestic and global populations.  On this page, you will also find a couple of annual population estimates.  The page shows different graphs to help understand each category selected to provide an output of the data.  The site also indicates which state is popular with the number of population citizens.  Each graph has different data such as gender, location, or demographic and which state has a significant increase in population.          I believe the data distribution can be compiled and presented in different formats to have the user understand it better.  The example we currently used with the Census is spot on since it shows multiple data streams, plus the data was compiled and presented in a visual graph that was interactive to drill down to each particular state. Of course, the data can be false in some circumstances, but verifying the data from a government site is less likely to happen since the data should be accurate.  

 

The forecast to the site shows each limitation, as well as growth.  The key to understanding the data is to make sure the data is precise and following up on the team that's compiling it. 

 

Question 2(Avantay)

I decided to explore the Census profile of married couples in the United States. I found this particular data intriguing as a same-sex couple and was interested in the findings. The notes at the bottom of the graphs advise that the data source is the 2019 American Community Survey from the United States Census Bureau. We also know that the data includes adults 15 years or older, who are either the householder, spouse, or unmarried partner of the householder. According to the notes, the U.S. Census Bureau reviewed the data and for unauthorized disclosure of confidential info and approved it. When reviewing the State Estimates of Same-Sex Married Couple Households in 2019, Montana, Wyoming, North Dakota, South Dakota, and West Virginia results were suppressed. I would love to believe that this data is credible because it is from the U.S. Census Bureau, however I’d really like to know the true number of couples that responded to this survey and whether that is an accurate reflection of the population.

The histogram reflects the age distribution of the married couples along the Y-axis, and the percentage of opposite-sex versus same-sex married couples along the X-axis. There is a significant drop in percentage of married couples before the age of 25, same-sex or opposite. There is a significant decrease in same-sex marriages only after the age of 65. The histogram is relatively skewed and bimodal.

Something I found interesting is that there is no cut-off for the final age group of 65+, every other group had about a 9-year distribution. However, the final group could be 65-74 or 65-100, which could potentially be decreasing the results for that age because the spread is so vast. I noticed that the percentages of same-sex and opposite-sex couples among the 35-64 age groups are relatively close. My interpretation of this data at face value is that for middle age Americans, there is not significant difference between marriage types. Overall, I feel that this data is missing important information that would make this data and display more accurate, such as defined cut-off age for last age group, and healthy representation of each state population of surveyors.

 

 

 

 

 

250 words.  In your response, identify the lurking variable in your classmate’s study, and explain how the lurking variable may cause a false correlation. THIS IS FOR QUESTION 3&4

 

 

Question 3(Catherine)

When conducting a study it is important that whoever is leading the study considers all of their variables. A lurking variable is unknown and not controlled for. The people who lead these studies might come to incorrect conclusions about what their data means if they do not take these lurking variables into account. Once these variables have been identified, they should be included to get the most accurate analysis possible. Another way to think about lurking variables is to remember that correlation does not always equal causation. Just because one thing happens at the same time as something else does not mean the first thing caused the second thing.

Keeping this in mind, it is easy to come up with the examples of a lurking variable. A simple example would be a study relating the height of the driver to the frequency of car crashes. Someone conducting this study could easily find that taller drivers crash their cars more frequently and reach the conclusion that being tall means you are more likely to crash your car. However, they will have failed to consider age and driving history.

The variables a person needs to consider might not be so obvious. For example, say someone is conducting a survey on the safety of a specific intersection. They notice that the number of collisions that occur around this intersection go down drastically in the summer months. This might lead them to conclude that people are safer drivers in the summer.

So what are the variables they might have missed? Maybe they did not know of or forgot to include the fact that the intersection is right next to a high school. If they had included that in their study, they might remember to include the age range of drivers, the times when the collisions occurred, and make a note of why there might be fewer drivers during the summer.

 

Question 4(Andrew)

 lurking variable is defined as “A variable other than x and y that simultaneously affects both variables, accounting for the correlation between the two” (Sharpe et al., 2019). These variables often account for other unconsidered factors that directly affect the measured outcome but were not measured within the data set. These kinds of studies and a data set often seek to determine correlation, or the connection between two variables where if one variable increases, so should the other. Additionally, they seek to determine causation, where the input variable is directly responsible for changing the outcome of the other.

An example study of where this could be determined would the correlation between Intelligence quotient, (IQ) and grade point average (GPA). While there is strong evidence to suggest correlation that students with higher IQ’s attain higher GPA’s, measuring just these two variables leaves out other key variables such as time spent studying, if they have been tutored, and hours of work put into their assignments. While it may be easy to assume that high IQ is causation for high grade point average, research suggests that type of intelligence is a strong predictor for achievement. For example, students that have higher levels of verbal (crystallized) intelligence, tend to score much better on achievement tests then individuals who score high in nonverbal (fluid) intelligence metrics (Horn & Cattell, 1966). The key difference is both kinds of intelligence must be measured in order to accurately predict future performance, rather than just assuming high IQ will result in high GPA.