Home > A statistical poster is a display containing two or more related graphics that summarize a set of data, that look at the data f

# A statistical poster is a display containing two or more related graphics that summarize a set of data, that look at the data f

The last Installment of the Water Footprint Project is to present a poster at the Water Footprint Poster Session on June 7th and 8th in BE 1110

Guidelines for making a Statistical Poster� (taken from the American Statistical Association’s Education website):

A statistical poster is a display containing two or more related graphics that summarize a set of data, that look at the data from different points of view, and that answer some specific questions about the data.

BASIC GUIDELINES

While constructing a poster, it is important to keep in mind that the central idea of the study should be the most prominent feature of the poster.

To bring the main idea into focus, questions such as the following should be asked.

"What is the purpose for displaying this information?"

"Which trends should be shown?"

Questions should be asked until the central idea of the study becomes clear. This then, becomes the focal point of the poster. The poster must reveal what the data have to say. It must allow the viewer to see the data, that is, to see the variation in the data, the structure of the data, the important patterns in the data (or lack thereof), the data points that do not fit the pattern, and the conclusions that can be drawn from the data. Further, each graphic on the poster should convey new information about the data--a pattern or structure, for example, that cannot be seen in the other graphics.

The poster title should be informative to reduce the need for additional explanatory text. For example, the title can indicate the questions addressed by the graphics or can even convey the major conclusion to be drawn from the data.

Each graphic's legend should be positioned so that there is no question which graphic and which legend go together. Further, each graphic and its legend should stand alone. If the graphics need to be viewed in a certain sequence, however, then the viewer's eyes must be guided in the right sequence.

Try to eliminate trivial and extraneous information, linework, or lettering. In particular, redundancy in titles and legends should be omitted. Only explanations that are needed to make the conclusions clear and obvious should be included. Data tables should not be shown on the poster; reading off numbers is not the point of the display. [Data tables can, however, help display the structure of the data. So not totally discouraged.]

Choose a few harmonious colors that are easily visible. The key to using colors effectively is restraint; the colors should not distract the viewer, but should enhance recognition of the structure of the data and of the conclusions.

Statistician John W. Tukey said "[m]uch of what we want to know about the world is naturally expressed as phenomena, as potentially interesting things that can be described in non-numerical words." We collect data to describe and answer questions about phenomena. We present data to communicate our ideas to others. The purpose of a statistical poster, then, is to visually tell a story from the data about some phenomena revealing the conclusions that can be drawn. Because there is no narrator to tell the story, nor an accompanying report to discuss it, the poster must be able to stand alone; it should not have to be explained.

Part IV: Statistical Poster�� (50 PTS)

Rubrics for this last installment:

•������������� Overall impact of the display for eye-catching appeal and visual attractiveness; for its ability to draw in the viewer to investigate the individual graphs.

•������������� Clarity of the message's demonstration of important relationships and patterns, obvious conclusions, and ability to stand alone, even without the explanatory paragraph.

•������������� Appropriateness of the graphics for the data

•�������� Creativity, neatness and originality

•�������� Great Team work

I have written down which graphs to use. If you find other interesting things, please include them in your poster. NOTE: Highlight the most interesting parts of the graph and think of a catchy subtitle. Each group will do one of the parts describe below:

1. Using various graphical display and keeping in mind the type of variables, describe the population by:
1. Course – bar chart
2. Gender� - bar chart
3. Race – pie chart
4. Compare these variables to the profile of a typical SCCC student (ask me about the statistics).
5. Income distribution –histogram (include important numerical summaries)
6. Distance from school – histogram (include numerical summaries). The top three zip codes of where SCCC students live are 98122, 98118, 98144. Check the distances of these places and compare.
7. types of transportation to school – pie chart
8. Go to the Global Water Footprint site and do a quick calculation of the Water Footprint for a typical person in your population (based on gender, race, income and dietary habit).
9. Find the Total Water Footprint average of a typical person by gender and compare to your numbers in the previous question.
1. Food Preference & Drinks Consumption:
1. Fat Preference – bar chart
2. Sweet Preference –bar chart
3. Coffee versus Tea distribution – side by side boxplots (include average number of cups per week)
4. Alcohol, bottled water and soft drink consumption distribution – side by side boxplots
5. Get the Water Footprint distribution for Fat-W and Sugar-W (bar chart or histogram, depending on whether it is categorical or not)
6. Get the Water Footprint distribution for Stimulant-W.
7. Total Water Footprint versus Coffee – scatter plot (include the water footprint of coffee versus tea from the Product Gallery of the Global Water Footprint). Use a residual plot.
8. Get the Water Footprint of coffee and tea from the Global site product gallery and convert to gallons/cup of coffee or tea.
1. Water Use at home:
1. Type of shower heads distribution – bar chart
2. Tap running distribution – bar chart
3. Shower lengths distribution – histogram (include mean and median in minutes/day)
4. Water use times distribution – histogram (include mean and median in number/day)
5. Total Water Footprint by shower heads – side by side box plots
6. Total Water Footprint by tap running – side by side boxplots
7. Do a confidence interval or hypothesis testing of the differences in the Total Water footprint by shower heads and tap running (Chapter 18). Convert to gallons at the end to get a better perspective.
1. Food Consumption:
1. Food types Distribution – histograms or side by side boxplots using a second variable like gender to show the difference (include amount food consumed per day to get a better perspective). Describe in layman’s terms what it means when it is skewed to the right, left or symmetric. Convert the average to number of ounces per day per meal to get a better perspective.
2. Use the Food Pyramid to show whether the daily food diet of our population is different. Use a table to show this.
3. Look at scatter plots of Meat versus other food types. Pick the one with the highest correlation. Make a scatter plot and use gender as the third variable.
4. Look at scatter plot of food types versus income, with income as explanatory. Pick the one with the highest correlation and use gender as the third variable.
5. Do a confidence interval or hypothesis test of meat consumption.
1. Water Footprint:
1. Total Water Footprint distribution – histogram (include numerical summaries and compare to U.S. 2483 cu m/cap/year and Global average Total Water Footprint of 1243 cu m/cap/year). Convert the cubic meters to gallons and compare to something that we can relate to (like amount of water in a regular swimming pool.
2. Total Water Footprint distribution by Food types – side by side boxplots
3. Total Water Footprint by Categories (Food, Domestic, Industrial) –side by side boxplots
4. Total Water Footprint versus Income – scatter plot and use gender as the third variable (include r and r-squared). Find the regression line and use the line to predict the total water footprint of someone with certain income.
5. Total Water Footprint versus Meat Water Footprint – scatter plot and use gender as the third variable (include r and r-squared). Find the regression line and predict the total water footprint for amount of meat consumed.
6. Go to the Global Water Footprint and Product Gallery, convert the water footprint to gallons per pound or to other units that we can relate to and present in a table. Select the following products: beef, chicken, pork, egg, cheese, coffee, hamburger, bread and potato. Compare these numbers to capacity of a swimming pool to get a better perspective.�
1. Statistical Inference:
1. Randomly sample 30 students from the population. Find the average Total Water Footprint and standard deviation.
2. Is the distribution more or less normal or not very skewed?
3. Find a 95% confidence interval of the true average Total Water Footprint.
4. Do a hypothesis testing. Use the US average of 2483 and Global average of 1243.
5. Find a 95% confidence interval or hypothesis testing for the difference in total water footprint by gender (use Chapter 18)
6. Explain the limitations and assumptions in this analysis.
1. Describe the various statistical graphs and methods used in the posters above.
1. In concise and clear sentences, describe the different graphical displays like bar

and pie charts, histogram, boxplots, scatter plots.

1. In concise and clear sentences, describe the different numerical displays. Highlight the importance of knowing the difference between mean and median. How does standard deviation come in?
2. In concise and clear sentences, describe the regression analysis, r- and r-squared.
3. In concise and clear sentences, describe confidence intervals and hypothesis test.
4. Explain the limitations of the study in terms of random sampling and effects of lurking variables that may confound the results.