Statistics Assignment NFL Fall 2015 (Word file with working in excel)

Project Description

Goal: The goal of this project is to illustrate how statistics can be used in the "real world". You will be completing some calculations and then answering some questions about football statistics for the 2012 regular season and filling out the answer sheet. If you despise sports, I am sorry, but this seems to be the most selected topic of interest in prior classes. You may work with a partner if desired but each of you should upload your finished project with both your names contained within. The following are the instructions for this project which is worth 150 points.

Descriptive Statistics Portion:

Provide a brief description (one paragraph) of the game of football. Provide a definition of offensive passing yards, definition of offensive rushing yards, and definition/description of points per game. Tell me if you watch the game and who is your favorite team. If you don't watch and don't have a favorite team, so state. That's not a problem – I generally don't watch football but do have a favorite team (Go Vikings – if nothing else their new stadium is going to look good).

Review the data given on the spreadsheet. The offensive data is from ESPN NFL stats and is from the 2012 regular season with some modifications.

Complete most all your calculations within the downloaded Excel spreadsheet.

Determine the level of measurement used for the points per game. Choose from nominal, ordinal, interval, or ratio.

Calculate the mean of the passing yards, the mean of the rushing yards, and the mean of the points per game for the 32 teams listed. Show units.

Calculate the median of the passing yards, the median of the rushing yards, and the median of the points per game for the 32 teams listed. Show units.

Calculate the standard deviation of the passing yards, the standard deviation of the rushing yards, and the standard deviation of the points per game for the 32 teams listed. Show units. This is a population requiring the use of stdev.p in Excel. The stdev function in Excel is for samples.

Give the range of the passing yards, the range of the rushing yards and the range of the points per game. Show units.

Develop a frequency distribution (table) for rushing yards. Use intervals of 100 yards. For example, your first table value will be 1200 yards up to 1300 yards.

Draw a bar chart of the passing and the rushing yards. The x axis should have the team names and the y axis the yard. Both rushing and passing yards should be on the same bar chart.

Develop a histogram for rushing yards. You may do this in Excel or hand draw, whichever is easier for you – hand drawing may be the easiest – just make sure it is legible. Remember a histogram is not a bar chart. The columns in a histogram touch. Place yardage intervals on the x axis and frequency within those intervals on the y axis. Review the text book to refresh in your mind what a histogram looks like.

Describe the shape of the distribution – does it look normally distributed, right skewed or left skewed or none of the above – calculate the skew using the Pearson's skew coefficient.

Inferential Statistics Portion:

Show a correlation between the rushing yards and passing yards. The research question you will be asking is this: As rushing yards increase, do passing yards increase or decrease? Show a scatterplot of rushing yards versus passing yards using Excel or hand drawing. If you use Excel, you need to understand how to enter an array to get the scatterplot to turn out correctly. Show the correlation coefficient "r". Review how a scatterplot looks and how it is created before starting this portion. Make sure to place the independent variable on the x axis and the dependent variable on the y axis. Do passing yards increase or decrease as rushing yards increase?

Calculate the 95% confidence limit for the passing yards. Show both the upper and lower confidence limits. A confidence limit indicates that you are 95% confident the mean lies between the upper and lower confidence limits.

Test the following hypothesis with an alpha value of 0.10: Is the mean of rushing yards statistically different than the mean of the passing yards? Show your full calculations for z and other items as required on the answer sheet.

Put all of this together in the answer sheet containing your name and your project partner's name (if you have one). Throw in a graphic or two for entertainment and make a summary statement about the usefulness of all the information you just compiled or how this knowledge could be used in the future. You must copy and paste or sketch relevant figures into the document to make a comprehensive report or I will return to you for re-accomplishment.



Answer Sheet
Name________________________________ Partner_________________
Answer all blank areas and sketch or insert tables or charts. Use Excel for the Descriptive Statistics portion. Hand calculate the inferential statistics portion.
Football Description (10 Points)
(Offensive Passing Yards, Offensive Rushing Yards, Point per Game, Favorite Team)

Level of Measurement for points per game ___________________(5 points)

Mean Passing Yards _____________yards (5 points for all three)
Mean Rushing Yards _____________yards
Mean Points per Game _____________points

Median Passing Yards ____________________yards (5 points for all three)
Median Rushing Yards _____________________yards
Median Points per Game _____________________points

StDev.p Passing Yards ______________yards (5 points for all three)
StDev.p Rushing Yards ______________yards
StDev.p Points per Game ______________points


Range of Passing Yards ________________yards (5 points for all three)
Range of Rushing Yards ________________yards
Range Points per Game ________________points



Frequency Table (complete the table I started for you) (5 points)
1200 up to 1300 yards _____________
1300 up to 1400 yards ______________
Etc.
Sketch one bar chart of the rushing and passing yardage (10 points)

Sketch a histogram of rushing yards using the 100 yards categories above (10 points)




Does the distribution appear to be right or left skewed or perfectly normal – show your Pearson's skew calculation _________ (10 points)

Draw or enter your scatter plot. If you use Excel, you must enter the data as an x,y array. (10 points)



Calculate the correlation coefficient (r) ___________________________ (10 points)

Do passing yards increase or decrease as rushing yards increase? (5 points)


Calculate the 95% confidence limit for the passing yards. Show both the upper and lower confidence limits. Shower your calculation on this answer sheet (10 points)

(LCL, UCL) = ( , )

Hint – for the hypothesis portion you should be using information from Chapter 11 and not using Excel. If you use Excel for this portion you will not get credit. Calculations must be shown.

State the null and alternate hypothesis (5 points)

State the level of significance ________________(5 points)

Determine the critical z test statistic values (5 points)

Draw the picture of the normal distribution curve with the areas of rejection and acceptance of the null hypothesis marked. Put the critical z values on the picture (10 points)





Show calculations of the sample statistic z value (5 points)

Are the means statistically different? _______________ (5 points)

Commentary on the project and the relationship of what you have done here to you future career. (10 points)