Statistics

EXAMPLE (Part 1): Here is my data exactly how it appeared in the original spreadsheet I downloaded. Each row represents one survey respondent (person), and each column represents one question. You must save a copy of your data EXACTLY LIKE THIS so that you can tie together your responses for analysis. In other words, you must know how EACH respondent answered for all six questions, by looking at each ROW, so that you can draw conclusions and discuss your results (this will be done in Weeks 9 and 10).

Refer to the corresponding assignment scoring guide for how your assignment will be scored.

EXAMPLE (part 2): Here I have sorted my data from smallest to largest in each column. I have done this so that I can easily find the mode/s. Reminder: a data set can have one mode, no mode, or multiple modes. To sort your data, follow these steps: 1. Highlight the entire column (make sure to not miss any values). 2. Right click and select "sort" and then "sort smallest to largest." 3. Next, a pop up window will appear. Select "continue with the current selection" and click "sort." 4. Do this for each of your six columns to sort your results. 5. You do NOT need to provide me with a copy of your unsorted data - this is for your use only. For the assignment that you will submit to me, please just include your SORTED data.

EXAMPLE (part 3): Remember—scroll ALL the way DOWN this document, AND all the way to the RIGHT. Now, with my sorted data, I can proceed to analysis using descriptive statistics. You can follow this example to help you complete the assignment. On the next tab you will find the REQUIRED template. The following elements must be present in your submission: 1. Proportion values for each of your four binary questions. 2. Mean, median, mode, standard deviation, range, minimum, maximum for your two continuous questions. 3. A bar graph or pie chart for each of your binary questions (4 total graphs). 4. A histogram for each of your continuous questions (2 total graphs). 5. Interesting findings presented in the form of a table AND a graph. To calculate the mean, median, standard deviation, range, min, and max, you should use Excel formulas.To use Excel formulas, click on the fx button at the top (it is near the top where you type. Then, select the "Statistical" Category for formulas. When you select each formula, you will be prompted to highlight the range values - simply highlight one question (column) at a time, and be sure to include all the values and not accidentally miss one. Below, I have listed the names/abbreviations of all the formulas in Excel. Hint: you can click on each of the cells to the left to see the formula that I used when calculating the values - you should use that formula too. Extra hint: YouTube has thousands of Excel tutorials - feel free to search for extra help if something doesn't quite "click" :-) Mean = MEAN         Median = MEDIAN       Mode = MODE         Standard Deviation = STDEV   Min = MIN         Max = MAX Range: =MAX-MIN         Note you will need to manually find the mode. The mode is the value that occurs most frequently in the data set. Remember that there can be one mode, multiple modes, or no mode.

Proportions: "p" represents the proportion of "0" responses that you received. "q" reprsents the proportion of "1" responses that you received. To find "p", divide the number of "0" responses by the number of total responses. Round as necessary. To find "q", divide the number of "1" responses by the number of total respones. Round as necessary.

Are you male or female?

Do you hold at least a Bachelor's degree?

Do you believe that GMOs are dangerous?

Could you provide a summary of how GMOs are created and what risks have been found?

How to create Pie Charts Click on the white area of this pie chart I have created to the right. You will see the data that I highlighted and used to make the pie chart. You must input this data for each of your binary questions and highlight it with your mouse. Then, at the top of the screen, select "Insert" and then "Pie." If you need extra help formatting your charts there are many excellent and helpful tutorial videos on YouTube.

How to create Histograms Class, creating the histograms will likely be the most challening part of the Unit 7 project, but the following tutorial will make it a lot easier! :-) First, what is a histogram? A histogram is a graphical representaton of frequency distribution. It shows a simple and clear picture of how many times values that fall within a certain range occur. Let's say that one of your continuous questions is: how old are you? An effective graphical representation is to show how many people fall within a certain age bracket. For this, we use the histogram. Let's focus on my 5th question (which is the first continous question), which was, "how old are you?" My min value is 18 and my max value is 83. My range is 65. Steps: 1. My first step is to divide the range into even "classes" (bins). In this case I choose to divide my range into 5 classes of width 13. If you do not have a number that is wholly divisible, round up to the next whole number. 2. Now, I will create a frequency distribution table. This table will show how many values fall within the classes that I identified above. Follow the black arrow to see the frequency distribution table. In the left column you will need to enter your class min and max values exactly as shown with the dash in between them. In the right column, count the number of values from your data set that fall within each range, and enter that number. 3. Next, you must highlight both of the columns. To see what data has been highlighted, just click on one of the histograms that I have created to the right and you will see the highlight appear around the data. 4. Once you have done this, click the "Insert" button at the top: 5. Next click on "Column" and then select the first 2D option: 6. Now, a bar graph will appear. But remember that the bars must have NO GAPS between each other in order for it to be a histogram. The way to do this is: 7. Right-click one of the bars and select "format data series." 8. Next, slide the cursor to the "no gap" side. 9. Finally, you can add a title to your Histogram, as well as titles for the horizontal and vertical axes. In Excel 2007, you can do this by clicking on the histogram itself and then selecting the layout tab from the ribbon. You will see many options that you can experiment with to format your graph. 10. Reminder about histograms. Remember - the important thing to think about when creating your histogram is that it is a CLEAR and EFFECTIVE visual. So, let's say that you have only 5 possible values for one of your continuous questions. In this case, it is OK for each BAR to represent only ONE value because there are only 5 values and the graph will not be cluttered. However, let's say that you have a range of 200 possible values as the answer. In this case, each BAR must represent a RANGE of values, otherwise the graph will be too cluttered if you have 200 bars. Example of inappropriate histogram: Why is this histogram inappropriate and ineffective? As you can see, the range of values is quite large, from 23 to 99, so it is not a a good idea to have one bar per each value. The graph is busy, cluttered, and not easy to decipher. In this instance, it would have been much better for each bar to represent a RANGE of values.

Age Range

Frequency

Age Histogram

Income Range

Frequency

Income Histogram

BS/BA or higher

No BS/BA

Do you believe that GMOs are dangerous?

Do you believe that GMOs are dangerous?

Interesting Findings Explained: I was interested to know if having a college degree would be related to people's beliefs about the dangers of GMOs. As my "interesting findings" table and graphs above show, 46% of the people who hold a Bachelor's degree or higher believe that GMOs are dangerous, whereas 41% of the people who do not hold a Bachelor's degree believe that GMOs are dangerous. This is not a profound difference, but it is still noticeable and worth mentioning. It is my belief that lack of information on the subject of GMOs leads people to falsely believe that GMOs are not dangerous. I speculate that the difference in beliefs in the two groups outlined above might be accounted for by the consideration that people who obtain a BS/BA or higher might be more naturally curious and seek out information on various topics. Additionally, college is a social and intellecutal community that provides for a greater exposure to ideas and information, which might not be as true in a non-college environment. However, these are just my speculations and a lot of further research would need to be carried out on the topic to provide any conclusive results.

Note that the min/max/range values here represent the actual SAMPLE data that I received, and may not necessarily match to my min/max values from Unit 3

Here I just manually counted how many values fall within the "bins" (classes" I identified.

IMPORTANT NOTE: Please create new/ original graphs for the interesting findings section, rather than just pasting graphs that were already created in part 1 above.

How did I make this table? I just manually counted how many people fall in each of the categories I created and manually entered these values in Excel. There is no "function" in Excel to automatically create this table.

You must place your SORTED (smallest to largest) data here. You can delete this text box and the arrow and then use as many rows as necessary to place all of your data towards the left.

This Template is required. You must place all of your work as outlined below. Note: You are welcome to shift cells and rows up or down and left or right to accomodate any need for extra space. However, the basic format of your submission must adhere to this template.

Bonus hints to make your life easier :) 1. Did you accidentally make a mistake? Delete something you didn't mean to? Hit Control + z and it will undo the last action. You can repeat this several times to delete multiple actions. 2. Remember that you can easily resize graphs by clicking inside the graph and dragging the corners. 3. To write inside Excel, click on "Insert" then "shapes" and then click the square icon with the letter "A" in it, which will insert a text box like this one. You can expand the size by clicking inside the text box and then dragging the corners.

Helpful hint: Suppose your project is looking very good, but you forgot to include a portion and need to clear some space and insert some information. Simply highlight an entire row of cells, right click, then “insert” and “shift cells down” (or to any other direction). You can press “control + y” to repeat the action (shift the cells again to clear more space) or “control + z” to undo the action.