![ANOVA could also assist people to apply for various jobs and
also bring investors into the region to bring up these areas to
perform better for the community. Now that this shows that the
income levels are close to the same, so suppliers and businesses
should have almost identical pricing strategies to encourage
people to come in and buy their products.
Non-mortgage debt showed during the ANOVA testing to be
much different among the different regions. A recommendation
would be for financial institutions to have some limits on
lending practices when providing loans in the regions having a
high annual mean for non-household debt. Households who have
these larger debts should be encouraged with some incentives to
better their circumstances in the areas that they live.
References
Black, K. (2017). Business Statistics: For Contemporary
Decision Making (9th ed.).
Danvers, MA: Wiley
Descriptive Statistics. (2008). Social Research Methods.
Retrieved from
http://www.socialresearchmethods.net/kb/statdesc.php
University of Phoenix. (2018). Signature Assignment: Consumer
Food Forecasts [Multimedia]. Retrieved from University of
Phoenix, QNT/561 - Applied Business Research & Statistics
website](https://image.slidesharecdn.com/12signatureassignmentconsumerf-221201184846-80c08805/85/12Signature-Assignment-Consumer-F-docx-11-320.jpg)
12Signature Assignment Consumer F.docx
- 1. 1 2 Signature Assignment: Consumer Food StudentQNT 561 Signature Assignment: Consumer Food Every day in the United States, consumers continue to make important decisions on how to spend their money, especially towards food for their family. These decisions vary from different areas and regions throughout the country. Would consumers in the Northeast region make different choices on ho they spend for food versus other parts, such as the Midwest, South, and West regions? A survey of 200 statements from the four various areas of the country was supplied and will be used to test and verbalize a hypothesis using the given data set forth with this paper. Each data set used from the four different regions are their annual food spending, non-mortgage spending, and annual household income. There are five different samples from the data set, and they entail either quantitative and qualitative information. There are four parts to this paper, and they are preliminary analysis, descriptive statistics, inferential statistics, and a final recommendation and conclusion. Part One – Preliminary Analysis The reason for the case study we are conducting here is to determine in as plain language as possible the results of the consumer food spending habit of the four regions throughout the
- 2. country. Here we will have an emphasis on the Midwest portion of the country, which is on the excel sheet and shown as region two data. The objective for this case study analysis will be the five different variables that comprise the 200 sample dataset given to us. The main areas around this case study are targeted around three aims. First is to see if the average for annual food spending for the Midwest region in the United States is more than $8,000, by using the 1% significance level, the second aim is to see if any the differences in household spending levels between the metro and non-metro areas using the annual food spending parameters. The third one is to conduct a different one-way ANOVA for each three dependent variables All the data are shown by household income, food spending and non- mortgage debt held by households, are in different independent regions by identifying the northeast as code 1, Midwest is code 2, south is 3, and the west is code 4 as shown below. These are quantitative datasets we will be using for this and all the other regions as well as they are for actual spending levels. The level of measurement would be a ratio variable to determine if the question in hand would be shown as a monetary variable. Regions Location 1 (Northeast) 1 (Metro) 2 (Midwest) 2 (Non-Metro) 3 (South) 4 (North) Part Two – Assessment of Descriptive Statistics There are various ways to get the data you need to help determine an outcome you are looking for. Descriptive statistics is one of those and is an essential tool employ because it describes various descriptions in coefficients and summarizing
- 3. all the data set forth for this analysis. It is used to streamline large amounts of data and brought in a way that would make sense to someone (Descriptive Statistics, 2008). The data described here will show outliers if present within in the data sets shown here. All these samples were taken from the 200 sample population that was given. The annual household income was at $55,552.39. The megastat analysis of descriptive statistics was used, and all the locations and the regions were also used. Shown below are the various data set for each of the 200 household samples taken. The mean, median, range, minimum, maximum, standard deviation, sum, count confidence level, and the coefficient variance. Also shown here is the five number summary which shows in a graph how each region defers in spending levels from one another.
- 4. For the annual food spending, the mean was $8,966.07, and that was using the same sample of the 200 samples that were given.
- 6. The non-mortgage household debt spending mean is at $15,604.16, using the same sample of 200. Part 3 – Assessment of Inferential Statistics This part of the analysis, there will be three test conducted using inferential stats will show where there are predictions from the data that was given for this case study. This is a form of hypothesis testing which uses random variables by observing the processes and used to infer data. To better understand how this works, the author would first use a hypothesis test to see if the average annual food spending in the Midwest area is greater than $8,000. The following test will show differences in the metro and non-metro areas of annual food spending. Using this data can help over a period of time which can develop a trend over that period on the spending habits of the consumers in the region to assist the managerial choices for possible future prices on consumer foods. The third hypothesis test shows to associate the quantitative influences in the annual household income, annual food spending and the non-mortgage household debt and their effects on the various regions immersed in this study. Annual Food Spending Midwest- Test 1 This first test we used data from the Midwest region to establish whether the general household annual spending in this region is greater than $8,000. This test was conducted using the single sample z test. This is used to determine whether the average in the Midwest region is equal to $8,000 or maybe the alternate hypothesis not greater than $8,000. This ended up testing as H0; µ= 8000, H1 > 8000, results show H1: 8660 > 8000 so this null hypothesis was accepted due to the x-bar being greater than the
- 7. mean of 8000 as shown below. (Question 1 of Part 3) Metro vs. Non-Metro Households – Test 2 Here we like to see what if any differences there are between the metro and non-metro areas of the data set that was given. So the author had to sort through the two areas first to separate the areas, then form a hypothesis on them. The hypothesis reads as; H0 ; µ metro = µ non-metro, H1; µ metro ≠ µ non-metro. The author also used the sample z test to figure the null hypothesis on this, and the results are shown below. You can see below that this was rejected as well as the was a significant difference between the households in the different areas. (Question 2 of Part 3)
- 9. Comparison of three variables using ANOVA This part is now separating the three variables, annual income, annual spending, and non-mortgage debt to determine whether there is suggestively influenced by the four areas of the country where the three variables split into. A one-way, Analysis of Variance (ANOVA) was completed on each to see the null hypothesis where the area means are equal, in contrary to the alternate hypothesis where they are not equal. This can be written to be as: H0; µ Northeast = µ Midwest = µ West = µSouth, H1; µNortheast ≠ µ Midwest ≠ µ West ≠ µ South. These calculations show the difference between all four areas for the annual food spending, but the northeast and west areas have nearly the same food spending numbers that average about $545,084. Whereas, the south and Midwest are also similar with an average of $351,522 annually food spending. The household incomes varied widely and shown to averaging out between $50,508 to as high as $58,141, but the ANOVA showed the mean for all four at $55, 117. There are other numerous data shown below. Anova: Single Factor Region 1 Northeast
- 10. Part 4 – Conclusion and Recommendations The data we used in the Midwest area for the annual household food spending suggested that the mean data was not extensively different from the original mean of $8,000. Nonetheless, the computations we came up with did come up a bit more than the mean of $8,000. The observation showed us that the probability could have been a factor in that along with other factors such as; opening and shutting down of restaurants, household income levels in the area, produce availability, and possibly the time of year or season, etc. living in the Midwest area seems to be a bit more pricier than living outside the area. Along with this results, it is this author recommendation to have some type of control on prices of commodities, and this is to provide protection to the area consumers from being manipulated into paying higher prices for items that can otherwise be purchased cheaper in other locals. The annual food spending mean in the metro area is at $9,436 as compared to the non-metro area of $8,261. The null hypothesis was rejected for this area as the p-value is at .0065 and is less than the µ - .01 that was given to us. This shows that there was not much of a variance in the metro and non-metro areas for annual spending, but since these are close values, another evaluation will be conducted in about six months. To get a better understanding, it would have been easier with a better breakdown of the background of consumers, maybe by racial or religious types since different people would purchase different types of food and they are usually concentrated in specific locations in various areas. The ANOVA performed in each of the locations, identified that the mean spending was not as different as we thought among the four regions. That test shows that the cost of living could be close to the same as well. The information gathered using the
- 11. ANOVA could also assist people to apply for various jobs and also bring investors into the region to bring up these areas to perform better for the community. Now that this shows that the income levels are close to the same, so suppliers and businesses should have almost identical pricing strategies to encourage people to come in and buy their products. Non-mortgage debt showed during the ANOVA testing to be much different among the different regions. A recommendation would be for financial institutions to have some limits on lending practices when providing loans in the regions having a high annual mean for non-household debt. Households who have these larger debts should be encouraged with some incentives to better their circumstances in the areas that they live. References Black, K. (2017). Business Statistics: For Contemporary Decision Making (9th ed.). Danvers, MA: Wiley Descriptive Statistics. (2008). Social Research Methods. Retrieved from http://www.socialresearchmethods.net/kb/statdesc.php University of Phoenix. (2018). Signature Assignment: Consumer Food Forecasts [Multimedia]. Retrieved from University of Phoenix, QNT/561 - Applied Business Research & Statistics website