Aim of the Project
My intention is to create a model in order to forecast the adjusted close price of Paddy Power PLC shares. I will examine some of the different Statistical Modelling techniques and evaluate the merits of each in turn.
I will use the Generalised Autoregressive Conditional Heteroskedasticity (GARCH) model if it is found that the variance of the time series is non-constant. My final forecasting model will primarily use the Autoregressive Integrated Moving Average (ARIMA) model to predict future closing prices of the share, with a GARCH model of the variance incorporated.
I will use the R Software to implement these methods. R is a large open source statistical software which is favoured by many professional statisticians and academics.
Data Set
I have obtained the Adjusted Daily Close Prices of Paddy Power PLC as quoted on the Irish Stock Exchange for the past 3 years, from October 15th 2008 to October 13th 2011. I believe that a sample of this size is large enough to test for statistical trends, such as seasonality. I have plotted my data set using the R software package. Figure 1 is what was generated. A sample of the data can be found in the References along with a link to an internet page containing the data.
Figure 1 Statistical Modelling Methods
Multiple Linear Regression
Regression analysis involves finding a relationship between a response variable and a number of explanatory variables. For a sample number t, with p explanatory
4. For the questions 1-3 we found out a couple different cost functions that could be useful for Delta when predicting salaries for 2003 and 2004. The multiple regressions may be most reliable considering it uses multiple variables, but the single R square is better than multiple regressions.
In order to study how stock prices react to these events, approximate three years of continuous daily stock price are chose, beginning at 17th March 2008 and ending more than three months after the final event at 22nd April 2011. In addition, SHANGHAI Stock Exchange Index (SSE) is adopted as a proxy of the market portfolio.
Regression analysis will be performed on all variables to determine if relationships exist between variables.
1. Introduction (brief discussion about your research question and how your dependent variable has been used in the past).
This support that Multiple Linear Regression model is better than the Simple Linear Regression, because it show the relationship with the variables more accurately and you can know which one to discard, and which one to
The purpose of the assignment is to review basic hypothesis testing and regression techniques. There is an appendix in your textbook, Appendix C: Using Excel to Conduct Analysis, which may help you with running regressions in Microsoft Excel. You may also wish to use a basic statistics text for guidance if needed. I have also provided you with a table with the t distribution.
Over the past months I’ve looked at the closing price every Friday of three different stocks. Those stocks were the Dow Jones Industrial Average (INDEX:DJIA), Fitbit Inc. (NYSE:FIT) and GoPro Inc. (NASDAQ:PRO). Each stock has fluctuated differently over the past two months and each has their own reason as to why the company went up or down.
In this project we first checked consistency and seasonality of S&P500 index stock performance by splitting its recent twenty years historical data into ten two year data and built ARIMA and GARCH models for each sub-period. We found that the models are considerably consistent before 2007-2008 sub-period, and there exists some minor seasonality in several subperiods, but no particular pattern can be identified for the whole period. We then tried to predict future return, volatility and VaR using the model we built for the last sub-period based on rolling forecast procedure. Though the fitted values of 10th sub-period model are
Students will use statistical modeling to determine if a correlation exists between two quantitative variables.
This regression equation can be graphed as follows assuming β0 as the intercept and β1 as the slope:
Numerous researches have provided the evidence of seasonal anomalies in Stock market, but different types of anomalies were found during the study. Patterns of anomalies varied from one study to another. According to Fama (1965), existing of seasonality in security market has made it difficult for the study of market efficiency and tests involving return models. Rozeff and Kinney (1976) found that seasonality existed in monthly rates of return on New York Stock Exchange (NYSE) during the time period of 1904-1974.
Once the parameters have been estimated, the strength of the relationship between the dependent variable and the independent variables can be measured in two ways. The first uses a measure called the coefficient of determination, denoted as R2, to measure how well the overall equation explains changes in the dependent variable. The second measure uses the t-statistic to test the strength of the relationship between an independent variable and the dependent variable. Testing Overall Explanatory Power : Define the squared deviation of any Yi from the mean of Y [i.e., (Yi– Y )2] as the variation in Y. The total variation is found by summing these deviations for all values of the dependent variable as total variation = S (Yi– Y )2 Total variation can be separated into two components: explained variation and unexplained variation. These concepts are explained below, for each Xi value,
Based on the data analysis, the result of study will be divided into two parts, including descriptive statistic and regression analysis.
Determine whether the correlation is significant Calculate and interpret the simple linear regression equation for a set of data Understand the assumptions behind regression analysis Determine whether a regression model is significant
Table [tab:test1_rmde], [tab:test1_rmie], [tab:test1_nnjd] and [tab:test1_time] respectively show the mean and standard deviation of the 6 compared methods on 5 datasets using the RMDE, RMIE, NNJD, and the running time metrics.