Question

In: Statistics and Probability

Using the data below, we would like to understand why some cities have a higher proportion...

Using the data below, we would like to understand why some cities have a higher proportion of creative-class workers than others. Under one theory, the proportion may be explained only by the city’s income, while in another theory, income along with population and cost-of-living are thought to explain the proportion..

  1. (a) Estimate a linear regression model for each theory and report your results.

  2. (b) Use an F test to choose one theory over another.

  3. (c) State the null hypothesis, the test statistic, and the specific distribution used (including the degrees of freedom) for your test in (b)

    Metro Area Population Income Cost-of-Living Index Creative Class (%)
    New Orleans-Metairie-Kenner, LA 1,024.68 46.459 99 29.6
    Rochester, NY 1,035.44 47.749 102 33.1
    Salt Lake City, UT 1,067.19 53.587 101 30.4
    Birmingham-Hoover, AL 1,089.88 44.534 93 30.6
    Buffalo-Niagara Falls, NY 1,137.52 42.831 127 29.7
    Oklahoma City, OK 1,173.63 42.036 92 31.6
    Hartford-West Hartford-East Hartford, CT 1,188.84 61.753 116 37.5
    Richmond, VA 1,196.41 53.416 106 31.1
    Louisville-Jefferson County, KY-IN 1,220.64 45.115 98 27.2
    Memphis, TN-MS-AR 1,268.33 42.092 97 26.7
    Jacksonville, FL 1,276.86 49.736 96 27.4
    Nashville-Davidson--Murfreesboro, TN 1,455.30 47.699 92 29.8
    Austin-Round Rock, TX 1,506.43 52.882 93 36.5
    Milwaukee-Waukesha-West Allis, WI 1,509.98 50.27 100 30.3
    Charlotte-Gastonia-Concord, NC-SC 1,582.63 50.367 92 30.9
    Providence-New Bedford-Fall River, RI-MA 1,612.99 51.797 126 30.1
    Virginia Beach-Norfolk-Newport News, VA-NC 1,647.40 52.976 105 29.3
    Indianapolis-Carmel, IN 1,669.37 50.841 98 29.4
    Columbus, OH 1,725.57 49.92 102 30.9
    Las Vegas-Paradise, NV 1,777.54 53.536 109 20.6
    San Jose-Sunnyvale-Santa Clara, CA 1,784.83 80.638 154 44.4
    San Antonio, TX 1,948.44 45.019 92 29.7
    Kansas City, MO-KS 1,966.79 52.359 94 32.1
    Orlando-Kissimmee, FL 1,984.86 48.934 107 27.3
    Sacramento--Arden-Arcade--Roseville, CA 2,067.12 56.953 122 34
    Cincinnati-Middletown, OH-KY-IN 2,105.01 50.306 93 30.3
    Cleveland-Elyria-Mentor, OH 2,114.16 45.925 101 30.4
    Portland-Vancouver-Beaverton, OR-WA 2,137.60 52.48 109 30.1
    Pittsburgh, PA 2,370.78 43.26 95 30.1
    Denver-Aurora, CO 2,408.62 54.994 102 34.5
    Baltimore-Towson, MD 2,658.41 61.01 121 33.9
    Tampa-St. Petersburg-Clearwater, FL 2,697.73 43.742 101 30.2
    St. Louis, MO-IL 2,793.99 49.765 100 30.1
    San Diego-Carlsbad-San Marcos, CA 2,941.45 59.591 131 32.8
    Minneapolis-St. Paul-Bloomington, MN-WI 3,175.04 62.223 99 35.2
    Seattle-Tacoma-Bellevue, WA 3,263.50 60.663 108 35
    Riverside-San Bernardino-Ontario, CA 4,026.14 53.243 121 24.2
    Phoenix-Mesa-Scottsdale, AZ 4,039.18 51.862 102 28.3
    San Francisco-Oakland-Fremont, CA 4,180.03 70.463 157 38.8
    Boston-Cambridge-Quincy, MA-NH 4,455.22 64.144 139 41.6
    Detroit-Warren-Livonia, MI 4,468.97 52.004 105 30.6
    Atlanta-Sandy Springs-Marietta, GA 5,134.87 55.552 98 33
    Washington-Arlington-Alexandria, DC-VA-MD-WV 5,288.67 78.978 133 43.7
    Miami-Fort Lauderdale-Miami Beach, FL 5,463.86 46.637 115 25.6
    Houston-Sugar Land-Baytown, TX 5,542.05 50.25 88 31.3
    Philadelphia-Camden-Wilmington, PA-NJ-DE-MD 5,826.74 55.593 116 34.9
    Dallas-Fort Worth-Arlington, TX 6,006.09 52.001 92 33
    Chicago-Naperville-Joliet, IL-IN-WI 9,506.86 57.008 106 32.3
    Los Angeles-Long Beach-Santa Ana, CA 12,950.13 55.516 131 32.9
    New York-Northern New Jersey-Long Island, NY-NJ-PA 18,818.54 59.281 148 35.6

Solutions

Expert Solution

Model 1

Proportion=f(Income)

a)Reg equation->Creative Class %=9.61129+0.4165Income

b) F stat=72.48856, Hence, the model is significant

c)H0:The coefficients of regression are equal to 0

Ha: Atleast one coefficient of regression is not equal to 0

test stat=72.48856, pvalue=0.000

Hence,reject H0 in favor of Ha and say the model is significant.

Model2

Proportion= f(Population, Income, Cost of Living)

Reg Eqn->y=10.12808+0.0000381Population+0.4326Income-0.38136Cost of living.

F test shows us that the model is significant.

Comparison:

The model 1 is found to be performing better because the Adj Rsq of model 1 is higher than the one in model 2

orchestra answered 2 years ago
Next > < Previous

Related Solutions

Why don’t we have “monocentric cities” anymore? What are some of the positive and negative aspects...
Why don’t we have “monocentric cities” anymore? What are some of the positive and negative aspects of this change?
Why is home rule limited to cities of 5,000 or more citizens? Why would we want...
Why is home rule limited to cities of 5,000 or more citizens? Why would we want more state control of smaller communities? What are the drawbacks of home rule?
We would like to understand by department whether there is a significant pay difference between men...
We would like to understand by department whether there is a significant pay difference between men and women in 2017 (average gross salary by gender per pay period).   The gender is coming from the employee_info as 'M' and 'F' AND the gross salary is coming from the payroll_register. What would be the query?
The table below shows performance data for 100 flights between cities A - G for some...
The table below shows performance data for 100 flights between cities A - G for some airline, including: date, flight #, origin, destination, # passengers flown (load), and tardiness (late, in hours). write a VBA code (N=10000) to simulate the following: 1. (I7): number of flights which were late for at least 0.75 hrs. 2. (I10) average load of flights originated from C with load exceeding 250. 3. (I13): smallest tardiness of flights from B to E between 9/1/18 and...
Why do we have different data models like Uniform, Geometric, Binomial, Poisson, and Normal? Can we...
Why do we have different data models like Uniform, Geometric, Binomial, Poisson, and Normal? Can we apply the data model equations to any data set?
We all understand why a company would sell stock in order to raise cash, but why...
We all understand why a company would sell stock in order to raise cash, but why would a company use cash to buy back its own stock? What is the advantage or reason for a company to deal in "Treasury Stock"? (Hint: watch the instructor video on Treasury stock before you answer.)   Explain (in two or three sentences) the difference "Why Treasury Stock?" - Please give more than a one sentence response.
Why would a dissonance theorist joke that no decisions feel like good ones, so we have...
Why would a dissonance theorist joke that no decisions feel like good ones, so we have to convince ourselves that they are?
Stereotypes, as we have come to understand, are assumptions that some individuals have about certain groups....
Stereotypes, as we have come to understand, are assumptions that some individuals have about certain groups. Stereotypes can span across race, gender, religion, ethnicity, sexual preference, and other areas. We have also come to understand that individuals within these different groups face stereotype threat, or the risk of people feeling they are conforming to the stereotypes that exist about their social group. In your initial discussion post for this unit consider the impact that stereotype threat can have on an...
Stereotypes, as we have come to understand, are assumptions that some individuals have about certain groups....
Stereotypes, as we have come to understand, are assumptions that some individuals have about certain groups. Stereotypes can span across race, gender, religion, ethnicity, sexual preference, and other areas. We have also come to understand that individuals within these different groups face stereotype threat, or the risk of people feeling they are conforming to the stereotypes that exist about their social group. In your initial discussion post for this unit consider the impact that stereotype threat can have on an...
Step 3: Assess the Evidence We have summarized the sample data with a sample proportion. We...
Step 3: Assess the Evidence We have summarized the sample data with a sample proportion. We now determine the strength of our evidence with a P-value. Remember, the P-value is the probability of observing a statistic that is at least as extreme as the one we gathered, assuming the null hypothesis is true. Since the criteria for approximate normality are satisfied, we can use the normal distribution to determine the P-value. A. Notice that the normal curve below is centered...
ADVERTISEMENT
Subjects
ADVERTISEMENT
Latest Questions
ADVERTISEMENT