| Fashion designers: | | | | Stem and leaf |
| Introduction: | | | | 14 |
| This paper analysis the income levels of | | | | 42 |
| employees in the fashion designers industry, this | | | | 20 |
| industry according to the bureau of labour in the | | | | 22 |
| United States it is estimated that this industry | | | | 24 |
| employs over 20,000 individuals according to the | | | | 50 |
| year 2006 statistics. This industry mainly focuses | | | | 25 |
| on dress making, clothing, shoes of different | | | | 47 |
| styles and making. | | | | 68 |
| Data on the income levels of employees in the | | | | 27 |
| fashion industry was retrieved from the bureau | | | | 19 |
| of statistics in the US | | | | 07 |
| The data: | | | | 33 |
| Data was retrieved the data contains | | | | 64 |
| employment levels in these states, hourly wage | | | | 03 |
| rate and the mean annual income in terms of | | | | 03 |
| wage, the data below shows the data: | | | | 29 |
| Area name | | | | 49 |
| Employment | | | | 80 |
| Hourly mean wage | | | | 61 |
| Annual mean wage(2) | | | | 30 |
| Los Angeles-Long Beach-Glendale, CA Metropolitan | | | | 87 |
| Division | | | | 88 |
| 2500 | | | | 31 |
| 34.34 | | | | 12 |
| 71430 | | | | 0 |
| Los Angeles-Long Beach-Santa Ana, CA | | | | 32 |
| 2920 | | | | 01 |
| 33.66 | | | | 07 |
| 70010 | | | | 33 |
| Riverside-San Bernardino-Ontario, CA | | | | 66 |
| 30 | | | | 80 |
| 27.19 | | | | 34 |
| 56560 | | | | 34 |
| San Francisco-Oakland-Fremont, CA | | | | 36 |
| 240 | | | | 25 |
| 36.25 | | | | 37 |
| 75400 | | | | 70 |
| San Francisco-San Mateo-Redwood City, CA | | | | 28 |
| Metropolitan Division | | | | 71 |
| 150 | | | | 70 |
| 33.8 | | | | 22 |
| 70310 | | | | The above is the stem and leaf representation of |
| Santa Ana-Anaheim-Irvine, CA Metropolitan | | | | the data, it is clear that most of the observation |
| Division | | | | are in the wage rate 27, this data therefore is |
| 410 | | | | skewed to the left and does not assume a |
| 29.49 | | | | normal distribution. |
| 61350 | | | | Binomial probability distribution: |
| Washington-Arlington-Alexandria, DC-VA-MD-WV | | | | The binomial probability distribution is applied to |
| 30 | | | | find the probability that an outcome will occur in a |
| 27.07 | | | | given number of trials. The variable in this case |
| 56300 | | | | however must be a discrete dichotomous random |
| Boston-Cambridge-Quincy, MA-NH | | | | variable, in this distribution we consider n identical |
| 680 | | | | trials, each trial has two possible outcomes where |
| 29.8 | | | | we refer to a success and the other as a failure, |
| 61990 | | | | a success in our case will be denoted as P and a |
| Boston-Cambridge-Quincy, MA NECTA Division | | | | failure will be denoted as Q. finally the outcome of |
| 450 | | | | one trial does not affect the outcome of the |
| 29.61 | | | | other trial, |
| 61600 | | | | In our case we will construct the binomial |
| Brockton-Bridgewater-Easton, MA NECTA Division | | | | probability distribution using the statement that |
| 60 | | | | the employment level in the fashion and design |
| 27.33 | | | | industry is expected to grow by 5%, assuming |
| 56850 | | | | that our level of employment in our selected |
| Providence-Fall River-Warwick, RI-MA | | | | states is 12,000 then we expect that in 2016 the |
| 50 | | | | employment level will be 70,000. |
| 24.5 | | | | According to this statistics the employment level |
| 50970 | | | | is based on a 2006 report and therefore the time |
| Minneapolis-St. Paul-Bloomington, MN-WI | | | | period is 10 years, which also means 120 months, |
| 90 | | | | so employment level is expected to increase by 5 |
| 27.64 | | | | individual each month. This statistics were |
| 57490 | | | | retrieved . if now we assume that the probability |
| Allentown-Bethlehem-Easton, PA-NJ | | | | of this happening is 70% then our binomial |
| 30 | | | | probability distribution will be as follows: |
| 30.87 | | | | The binomial probability function is given by: |
| 64200 | | | | P (x) = n ∏ x ( 1-∏ ) n-x |
| Edison, NJ Metropolitan Division | | | | X |
| 50 | | | | Where in our case n = 5 which is the number of |
| 31.12 | | | | employment per month, x = 0,1,2,3,4,5) which are |
| 64720 | | | | the number of outcomes per month, ∏ = 0.7 |
| New York-White Plains-Wayne, NY-NJ Metropolitan | | | | which is the probability that the employment level |
| Division | | | | will increase by 5% from 2006 to 2016. |
| 6920 | | | | Our binomial distribution is as follows after |
| 37.7 | | | | calculations:x |
| 78410 | | | | P(x) |
| Nassau-Suffolk, NY Metropolitan Division | | | | 0 |
| 380 | | | | 0.00243 |
| 37.28 | | | | 1 |
| 77540 | | | | 0.02835 |
| New York-Northern New Jersey-Long Island, | | | | 2 |
| NY-NJ-PA | | | | 0.1323 |
| 7390 | | | | 3 |
| 37.71 | | | | 0.3087 |
| 78450 | | | | 4 |
| New York-White Plains-Wayne, NY-NJ Metropolitan | | | | 0.36015 |
| Division | | | | 5 |
| 6920 | | | | 0.16807 |
| 37.7 | | | | If we are to draw a chart regarding the binomial |
| 78410 | | | | probability distribution then our chart will be as |
| Portland-Vancouver-Beaverton, OR-WA | | | | follows: |
| 200 | | | | The binomial probability distribution helps us |
| 32.01 | | | | estimate the probability of an outcome, in this |
| 66590 | | | | case we can be in a position to estimate the |
| Allentown-Bethlehem-Easton, PA-NJ | | | | probability for example what is the probability that |
| 30 | | | | the persons who are likely to be employed will be |
| 30.87 | | | | greater than 2 individuals, more than 3 individuals |
| 64200 | | | | or even less than one individuals, for this reason |
| Philadelphia, PA Metropolitan Division | | | | therefore the probabilities can be calculated by |
| 120 | | | | adding the probabilities of each outcome to come |
| 25.47 | | | | up with the desired answer in question. |
| 52970 | | | | Hypothesis testing: |
| Philadelphia-Camden-Wilmington, PA-NJ-DE-MD | | | | We still consider our data from the fashion design |
| 270 | | | | industry to analyse the data, in hypothesis testing |
| 31 | | | | we will consider hypothesis test for the data and |
| 64480 | | | | stating the null and alternative hypothesis, in this |
| Reading, PA | | | | case therefore it is clear that we will have to use |
| 270 | | | | the T table, Z table or even the F table on the |
| 20.22 | | | | nature of the test and deepening on the |
| 42050 | | | | hypothesis in question |
| Dallas-Plano-Irving, TX Metropolitan Division | | | | Confidence interval: |
| 550 | | | | 90% confidence interval: |
| 37.22 | | | | When we are constructing the confidence interval |
| 77420 | | | | we consider the standard deviation, the mean and |
| Fort Worth-Arlington, TX Metropolitan Division | | | | the value from the T tables at 90% level of |
| 40 | | | | measure: we lookup 10% at two tail from the T |
| 14.42 | | | | table and the figure is 2.015048: |
| 29980 | | | | Our confidence interval will take the following |
| Portland-Vancouver-Beaverton, OR-WA | | | | form: |
| 200 | | | | P(x – st) ≤ (x + st) = 90% |
| 32.01 | | | | Where X is the mean, S is the standard deviation |
| 66590 | | | | and T is the value from the tables: |
| Seattle-Bellevue-Everett, WA Metropolitan Division | | | | P(32.54 –(3.07 X 2.015) ≤ X ≤ (32.54 + |
| 160 | | | | (3.07 X 2.015) = 90% |
| 27.03 | | | | P(26.35395) ≤ X ≤ (38.72605) = 90% |
| 56210 | | | | This confidence interval states that at 90% |
| Seattle-Tacoma-Bellevue, WA | | | | confidence interval the mean will range from 26.35 |
| 160 | | | | to 38.72 where they are the lower and upper |
| 27.03 | | | | bound respectively. This also means that we are |
| 56210 | | | | 90% confident that the mean ranges from 26.35 |
| Minneapolis-St. Paul-Bloomington, MN-WI | | | | to 38.72 |
| 90 | | | | 95% confidence interval: |
| 27.64 | | | | When we lookup 5% at two tail t test then the |
| 57490 | | | | value is 0.726687, therefore our confidence |
| Bridgeport-Stamford-Norwalk, CT | | | | interval will be as follows: |
| 110 | | | | P(32.54 –(3.07 X 0.726687) ≤ (32.54 + (3.07 |
| 25.68 | | | | X 0.726687) = 95% |
| 53410 | | | | P(30.30907091) ≤ X ≤ (34.77093) = 95% |
| Mean, standard deviation and median: | | | | This confidence interval states that at 95% |
| When we use ungrouped data to analyse the | | | | confidence interval the mean will range from 30.30 |
| mean and the median of the data our results are | | | | to 34.77 where they are the lower and upper |
| as follows:total | | | | bound respectively. This also means that we are |
| 31500 | | | | 95% confident that the mean ranges from 30.30 |
| 903.66 | | | | to 34.77. |
| 1879590mean | | | | From the measure of confidence interval it is |
| 1050 | | | | clear that when we consider a larger confidence |
| 30.122 | | | | interval then it is clear that the lower is the range |
| 62653standard deviation | | | | of the interval as compared to when we use a |
| 2147.812038 | | | | lower confidence interval. |
| 5.384997295 | | | | Linear regression: |
| 11203.3099 | | | | We will perform the regression model on the |
| MIN | | | | employment level and the hourly wage rate, we |
| 30 | | | | will assume that the higher the level of |
| 14.42 | | | | employment then the higher is the wage rate, |
| 29980 | | | | therefore we will assume that the wage rate |
| MAX | | | | dependent on the rate of employment, in this |
| 7390 | | | | case therefore our dependent variable will be |
| 37.71 | | | | wage rate and the independent variable will be |
| 78450 | | | | employment level: |
| RANGE | | | | After estimation our: |
| 7360 | | | | B = 0.0005673 |
| 23.29 | | | | α = 31.391809 |
| 48470 | | | | Therefore our estimated model will take the |
| The mean hourly wage is 30.12 dollars, the range | | | | following form below: |
| is 23.29 and our standard deviation is equal to | | | | Y = 31.39 + 0.0005673 X |
| 5.38, these are measures of central tendencies of | | | | We can define this model as follows, if we hold all |
| data, the mean gives us an estimate of the | | | | other factors constant and the level of |
| hourly wage rate in the fashion industry and the | | | | employment is zero then the level of wage rate |
| standard deviation give us the measure of | | | | will be 31.39. if we hold all other factors constant |
| deviations from the mean of the different wages | | | | and increase the level of employment by one unit |
| paid by different states. | | | | then the wage rate level per hour will increase by |
| Grouped data: | | | | 0.0005673 units. |
| When we group the data into 6 classes and | | | | For this reason therefore it is clear that our earlier |
| considering the class interval to be two then we | | | | stated objective has been achieved, this is in |
| will be in a position to obtain our frequency and | | | | reference to the objective that an increase in |
| therefore construct a histogram, after grouping | | | | employment will raise the wage rate level. |
| our data the results are as | | | | Correlation: |
| follows:classfrequencycummulative | | | | When we undertake the calculation of the |
| frequencypercentage | | | | Pearson correlation coefficient then our correlation |
| 10.50 TO 15.50 | | | | after calculation is equal to 0.8366, from the figure |
| 1 | | | | of the coefficient it is clear that we have positive |
| 1 | | | | correlation between the two data, we also have a |
| 3% | | | | moderately strong relation and this is obtained by |
| 15.51 TO 20.50 | | | | the fact that the correlation coefficient is close to |
| 2 | | | | 1, we therefore can conclude that there is a |
| 3 | | | | strong positive correlation between employment |
| 7% | | | | and wage rate per hour. |
| 20.51 TO 25.50 | | | | Summary: |
| 4 | | | | From our statistical analysis that we have |
| 7 | | | | performed on the fashion and design industry it is |
| 13% | | | | clear that the industry provides employment to a |
| 25.51 TO 30.50 | | | | large number of individuals in the United States, in |
| 8 | | | | our selected states which are 6 in number the |
| 15 | | | | industry employs over 12,000 individuals according |
| 27% | | | | to the 2006 statistics. |
| 30.51 TO 35.50 | | | | According to the bureau of labour in the United |
| 9 | | | | States the growth rate of this industry is |
| 24 | | | | expected to grow by 2016 where its |
| 30% | | | | employment rate will increase by 5%, when |
| 35.51 TO 40.50 | | | | calculating using the percentage given then it is |
| 6 | | | | clear that by 2016 the employment level of the |
| 30 | | | | industry in our selected state will increase from |
| 20% | | | | 19,000. |
| 30 | | | | When we perform a linear regression estimation |
| 100% | | | | of the data and consider that the wage rate is |
| Our histogram will be as follows: | | | | dependent on the employment level then it is |
| This histogram shows that there is a high | | | | clear that the employment level positively affect |
| possibility that the wage rate will be between | | | | the wage rate, this is to say that the higher the |
| 30.51 to 35.50, to be precise the probability that | | | | employment level then the higher is the wage |
| the wage rage will be at this level is 0.5 or 50% | | | | rate. Further we found a strong correlation |
| probability. | | | | coefficient between wage rate and employment. |
| Also our or give will be as follows: | | | | Finally we conclude by saying that there is a need |
| The orgive represents the cumulative frequency | | | | to use a larger sample size in order to get a |
| data and shows the trend of the cumulative | | | | clearer picture of the fashion and design industry, |
| frequency to the 100% level. | | | | a large data sample will allow us to overcome |
| The stem and leaf: | | | | biasness in statistical analysis, samples are |
| A stem and leaf diagram displays the trends in | | | | expected to be a representative of the entire |
| data and also gives us an overview of the nature | | | | population, for this reason therefore there is need |
| of the data, whether skewed or normal | | | | to select a larger sample size and compare the |
| distribution. Below is the stem and leaf diagram: | | | | results. |