Titanic Analysis
Budget: $30 – $250 USD
Task Guidelines
For this task, I want you to use Python.
My question for titanic was whether the passengers survived by luck or any pattern such as gender, family size, fare, etc. Therefore, I did some descriptive analytics and created charts .
There are three airports in the NYC area. Is there any airport, such as JFK, delays most or least? How many minutes or hour delay? Of course, you are free to add more questions. Let me know if you need any assistance.
Here are the elements that must go into your project reporting:
Introduction – what is the goal of the project? Write a few lines about the motivation for this analysis.
Data
Source, variables - where did you get the data from? What are the dependent and independent variables? What units are they measured in?
Sample Size - how many observations in your sample?
Data Preparation, if any was needed - were there errors in the data you fixed? Any missing values? Did you create new variables from the set that you got (for instance, by taking the ratio of two variables to create a new one?) Were there any outliers that you eliminated or otherwise handled in some way?
Methodology
Preliminary Analysis – compute Means and Standard Deviations of each variable in the dataset so you get a sense of what the data look like. For numeric variables, draw histograms to see the distribution of the data. Interpret what you see.
Show scatterplots of each variable against the dependent (if independent is categorical, then do a pivot table instead, to show how the average and standard deviation of the dependent across the categories of the independent variable).
Perform Regression Analysis to predict or classify. Start with all the independent variables in the model. Remove variables that are not significant (high p-values). If several variables are not significant, do not remove all the insignificant ones at once. Remove those with the highest p-values first, and try regression again. Examine the output again, and repeat until you only have variables that have a p-value less than 0.05.
Results
Write out the regression model and interpret it. Show an example of how you would use the model to predict the dependent for a set of values of the independent variables.
Evaluate the model using R-square (and/or Standard Error).
Implementation/Conclusion
Discuss how the model results may be implemented in decision making.
For this task, I want you to use Python.
My question for titanic was whether the passengers survived by luck or any pattern such as gender, family size, fare, etc. Therefore, I did some descriptive analytics and created charts .
There are three airports in the NYC area. Is there any airport, such as JFK, delays most or least? How many minutes or hour delay? Of course, you are free to add more questions. Let me know if you need any assistance.
Here are the elements that must go into your project reporting:
Introduction – what is the goal of the project? Write a few lines about the motivation for this analysis.
Data
Source, variables - where did you get the data from? What are the dependent and independent variables? What units are they measured in?
Sample Size - how many observations in your sample?
Data Preparation, if any was needed - were there errors in the data you fixed? Any missing values? Did you create new variables from the set that you got (for instance, by taking the ratio of two variables to create a new one?) Were there any outliers that you eliminated or otherwise handled in some way?
Methodology
Preliminary Analysis – compute Means and Standard Deviations of each variable in the dataset so you get a sense of what the data look like. For numeric variables, draw histograms to see the distribution of the data. Interpret what you see.
Show scatterplots of each variable against the dependent (if independent is categorical, then do a pivot table instead, to show how the average and standard deviation of the dependent across the categories of the independent variable).
Perform Regression Analysis to predict or classify. Start with all the independent variables in the model. Remove variables that are not significant (high p-values). If several variables are not significant, do not remove all the insignificant ones at once. Remove those with the highest p-values first, and try regression again. Examine the output again, and repeat until you only have variables that have a p-value less than 0.05.
Results
Write out the regression model and interpret it. Show an example of how you would use the model to predict the dependent for a set of values of the independent variables.
Evaluate the model using R-square (and/or Standard Error).
Implementation/Conclusion
Discuss how the model results may be implemented in decision making.