rdm and pdf needed or doc

rdm and pdf needed or doc


Instruction: This is the last exam in BMB 620. Complete the following questions in RMarkdown and submitted the generated PDF on Classes by the deadline. Make sure to show both the input and output. 1. Use the gas time series data from the forecast package to answer the following questions. The gas data include the Australian monthly gas production from 1956 to 1995. a. Extract the starting month, ending month, and frequency of the time series. b. Visualize the time series and interpret its components. c. Smoothen the time series with different smoothing factor k. d. Decompose the time series and interpret the decomposition. 2. Use the taylor time series data from the forecast package to answer the following questions. The taylor data contain half-hourly electricity demand in England and Wales from Monday 5 June 2000 to Sunday 27 August 2000. a. Visualize the time series and interpret its components. b. Use single exponential forecasting to fit the time series. Interpret the results. c. Make forecast using the model in b. d. Use Holt exponential smoothing to fit the time series. Interpret the results. 3. Use the woolyrnq time series data from the forecast package to answer the following questions. The woolyrnq data contain quarterly production of woollen yarn in Australia: tonnes. Mar 1965 – Sep 1994. a. Visualize the time series. b. Estimate the number of differences required to make the time series stationary c. Use Acf() and Pacf() to identify and fit an ARIMA model. Interpret the result. d. Make forecast using the model in c. e. Create an automated ARIMA forecasting model and make forecast. 4. Use the birth data from the flexclust package to answer the following questions. The birth data contain birth and death rates of 70 countries. a. Perform a hierarchical clustering of the birth data. Your solutions should contain the full procedure of hierarchical cluster analysis. Interpret your results. b. Use K-means clustering on the birth data. Your solutions should contain the full procedure of K-means clustering. Interpret your results. c. Compare the results between a and b. 5. Use the bcancer data from the VIM package to answer the following questions. The bcancer data contain the original Wisconsin breast cancer data with 699 observations on 11 variables. a. Identify the missing values using ma.pattern() function from the mice package. Interpret the result. b. Conduct a complete-case analysis to retain the non-missing values. c. Conduct a simple imputation on the data.