You will choose a dataset to study, and each component of the project will relate to topics we have studied in this class. Based on their analysis, will submit a typedreport(3-5 pages)using complete sentences, tables, charts, and graphs.

These are the steps that should be followed to complete the project:1.Decide on a research topic.There are truly an unlimited number of topics you may choose. Some examples could be baseball, weather, stock market, elections, healthcare, hunting, cars, video games, etc.

2.Obtain a data set.You have several options forchoosingthe dataset youll be working with. You will need a data set with at least two quantitative and two categorical variables. oYou may find a data set on the internet.If you choose to do this,consider the source of your data and use data that you have reason to believe is reliable and unbiased.oYou can collect your own data. If you go this route, I suggest that you discuss your plan with me BEFORE you start collecting data to make sure that it will workwell.

3.Complete the project requirements for each section of the textbook covered.

Chapter 1oSpecify which data set you are using.oIdentify the population of interest. oIdentify the variables being studied and classify them as categorical or quantitative.oIdentify the sampling method. Ifyou didnt design the study, but rather, relyon a given data set, discuss how youthinkthe data was collected and whether that was effective and appropriate.If you choose tocollect your own data, you willknowwhy the study was designed in a certain way.oDetermine if the data was collected as part of an observational study (retrospective/cross-sectional/prospective) or experiment.oDiscussany possible biases that could haveaffected the sample data.oDiscuss any confounding variables which couldhaveaffectedthe data.

Chapter 2

oConstruct a frequency table for categorical data and a corresponding bar chart.

oConstruct afrequency table for quantitative data and a corresponding histogram.Chapter 3

oState the 5-number summary andconstruct aboxplot. Explain what this tells you about the data.

oCalculate the mean and standard deviation.oIdentify any outliers.

oUse yourhistogram from Chapter 2 toanalyze the distribution of the data. Is it left-skewed, right-skewed, symmetric? Does it appear to be normally distributed?

oExplainwhythe data appears to be distributed in the way that it is. Think about why data setsare skewed or not skewedwhat does this say about the data?

Chapter 4

oConstruct a contingency table and use the tableto calculate probabilities using the Addition Rule and Multiplication Rule.

Chapter 6

oPretend that your data is normally distributed(or maybe it actually is) so thatyou can use the Standard Normal Table.Calculate z-scores and probabilities.Show your computationsand labeled and shaded normal distributions. Id like to see a greater than, a less than, and a between probability.

oUsethe Central Limit Theorem to calculate the probability of a particular sample (of size ___)occurring from your data.

Chapter 7

oChooseaconfidence leveland construct the corresponding confidence interval.Please create one for proportions and one formeans, showing all calculations.

oExplain how to interpret the confidence intervalsusing thecorrect languageand context. (Rememberthatconfidence intervals are not expressed as probabilities.)

Chapter 8

oConstruct ahypothesis test to correspond with the one of the confidence intervals created for Chapter 7.

oState an appropriate null and alternative hypothesis.oState whether thetest is a one-tailedor two-tailed test.How do you know?

oChoose an appropriatesignificance levelalpha for the test and explain why you chose it.

oCalculate thetest statistic and P-value, using StatCrunch for the P-value if needed.

oState the conclusionsof the test.

oCompare the confidence interval and hypothesis test and determine if they agree or not.

Chapter 9

oConduct a 95% confidence interval AND a hypothesis test using twoindependent samplemeans from your data. You might test for a difference in ages of male/female superheroes, or number of chocolate chips in different brands of cookies. The two samples should be independent, so explain why we would believe the two samples are truly independent.

Chapter 10

oFirst, determine whether a linear correlation may exist between two quantitative variables.You can do this by usingStatCrunchto construct a scatterplot. Show the scatterplot.

oIf you see a linear relation on your scatterplot, calculater and find the critical value to determine whether a linear correlation exists. State the regression equationand use the equation to make a prediction.oIf a linear correlation does not exist, explain why it doesnt usingrand the critical value, and explain what the best predictor would be for your data.

4.Combine all parts of project.

oPlease useWord to type all that is possible. Please do not try to type out the calculations, unless you know how to insert math formulas into Word. oIn Word, include screenshots of graphs/tables/charts as needed from StatCrunch or Excel.

oYou can also take pictures of hand written calculations or figures (such as labeled and shaded normal distributions) and paste them into the Word document.