[172] | 1 | \hypertarget{classmgamma}{ |
---|
[30] | 2 | \section{mgamma Class Reference} |
---|
| 3 | \label{classmgamma}\index{mgamma@{mgamma}} |
---|
[172] | 4 | } |
---|
[30] | 5 | Gamma random walk. |
---|
| 6 | |
---|
| 7 | |
---|
| 8 | {\tt \#include $<$libEF.h$>$} |
---|
| 9 | |
---|
[33] | 10 | Inheritance diagram for mgamma:\nopagebreak |
---|
| 11 | \begin{figure}[H] |
---|
| 12 | \begin{center} |
---|
| 13 | \leavevmode |
---|
[91] | 14 | \includegraphics[width=58pt]{classmgamma__inherit__graph} |
---|
[33] | 15 | \end{center} |
---|
| 16 | \end{figure} |
---|
[30] | 17 | Collaboration diagram for mgamma:\nopagebreak |
---|
| 18 | \begin{figure}[H] |
---|
| 19 | \begin{center} |
---|
| 20 | \leavevmode |
---|
[91] | 21 | \includegraphics[width=76pt]{classmgamma__coll__graph} |
---|
[30] | 22 | \end{center} |
---|
| 23 | \end{figure} |
---|
| 24 | \subsection*{Public Member Functions} |
---|
| 25 | \begin{CompactItemize} |
---|
| 26 | \item |
---|
[172] | 27 | \hypertarget{classmgamma_af43e61b86900c0398d5c0ffc83b94e6}{ |
---|
| 28 | \hyperlink{classmgamma_af43e61b86900c0398d5c0ffc83b94e6}{mgamma} (const \hyperlink{classRV}{RV} \&\hyperlink{classmpdf_f6687c07ff07d47812dd565368ca59eb}{rv}, const \hyperlink{classRV}{RV} \&\hyperlink{classmpdf_acb7dda792b3cd5576f39fa3129abbab}{rvc})} |
---|
| 29 | \label{classmgamma_af43e61b86900c0398d5c0ffc83b94e6} |
---|
[30] | 30 | |
---|
| 31 | \begin{CompactList}\small\item\em Constructor. \item\end{CompactList}\item |
---|
[172] | 32 | \hypertarget{classmgamma_a9d646cf758a70126dde7c48790b6e94}{ |
---|
| 33 | void \hyperlink{classmgamma_a9d646cf758a70126dde7c48790b6e94}{set\_\-parameters} (double \hyperlink{classmgamma_43f733cce0245a52363d566099add687}{k})} |
---|
| 34 | \label{classmgamma_a9d646cf758a70126dde7c48790b6e94} |
---|
[30] | 35 | |
---|
[33] | 36 | \begin{CompactList}\small\item\em Set value of {\tt k}. \item\end{CompactList}\item |
---|
[172] | 37 | \hypertarget{classmgamma_a61094c9f7a2d64ea77b130cbc031f97}{ |
---|
| 38 | void \hyperlink{classmgamma_a61094c9f7a2d64ea77b130cbc031f97}{condition} (const vec \&val)} |
---|
| 39 | \label{classmgamma_a61094c9f7a2d64ea77b130cbc031f97} |
---|
[30] | 40 | |
---|
[172] | 41 | \begin{CompactList}\small\item\em Update {\tt ep} so that it represents this \hyperlink{classmpdf}{mpdf} conditioned on {\tt rvc} = cond. \item\end{CompactList}\item |
---|
| 42 | virtual vec \hyperlink{classmpdf_3f172b79ec4a5ebc87898a5381141f1b}{samplecond} (const vec \&cond, double \&ll) |
---|
[234] | 43 | \begin{CompactList}\small\item\em Returns a sample from the density conditioned on {\tt cond}, $x \sim epdf(rv|cond)$. \item\end{CompactList}\item |
---|
[219] | 44 | virtual mat \hyperlink{classmpdf_b1dae6171ee39a6a05976c7b1007a3c5}{samplecond\_\-m} (const vec \&cond, vec \&ll, int N) |
---|
[162] | 45 | \begin{CompactList}\small\item\em Returns. \item\end{CompactList}\item |
---|
[219] | 46 | \hypertarget{classmpdf_2ef8a6374029d990a678782f6decebbe}{ |
---|
| 47 | virtual double \hyperlink{classmpdf_2ef8a6374029d990a678782f6decebbe}{evallogcond} (const vec \&dt, const vec \&cond)} |
---|
| 48 | \label{classmpdf_2ef8a6374029d990a678782f6decebbe} |
---|
[30] | 49 | |
---|
[172] | 50 | \begin{CompactList}\small\item\em Shortcut for conditioning and evaluation of the internal \hyperlink{classepdf}{epdf}. In some cases, this operation can be implemented efficiently. \item\end{CompactList}\item |
---|
[219] | 51 | \hypertarget{classmpdf_95fcff214848f66f1b489459370573fa}{ |
---|
| 52 | virtual vec \hyperlink{classmpdf_95fcff214848f66f1b489459370573fa}{evallogcond\_\-m} (const mat \&Dt, const vec \&cond)} |
---|
| 53 | \label{classmpdf_95fcff214848f66f1b489459370573fa} |
---|
[30] | 54 | |
---|
[219] | 55 | \begin{CompactList}\small\item\em Matrix version of evallogcond. \item\end{CompactList}\item |
---|
[210] | 56 | \hypertarget{classmpdf_15ef062183b1ccdf794732d5fa0b77cd}{ |
---|
| 57 | \hyperlink{classRV}{RV} \hyperlink{classmpdf_15ef062183b1ccdf794732d5fa0b77cd}{\_\-rvc} () const } |
---|
| 58 | \label{classmpdf_15ef062183b1ccdf794732d5fa0b77cd} |
---|
| 59 | |
---|
[33] | 60 | \begin{CompactList}\small\item\em access function \item\end{CompactList}\item |
---|
[210] | 61 | \hypertarget{classmpdf_71256ffb5fbd08f41d650e606a5bd585}{ |
---|
| 62 | \hyperlink{classRV}{RV} \hyperlink{classmpdf_71256ffb5fbd08f41d650e606a5bd585}{\_\-rv} () const } |
---|
| 63 | \label{classmpdf_71256ffb5fbd08f41d650e606a5bd585} |
---|
[162] | 64 | |
---|
| 65 | \begin{CompactList}\small\item\em access function \item\end{CompactList}\item |
---|
[172] | 66 | \hypertarget{classmpdf_e17780ee5b2cfe05922a6c56af1462f8}{ |
---|
| 67 | \hyperlink{classepdf}{epdf} \& \hyperlink{classmpdf_e17780ee5b2cfe05922a6c56af1462f8}{\_\-epdf} ()} |
---|
| 68 | \label{classmpdf_e17780ee5b2cfe05922a6c56af1462f8} |
---|
[33] | 69 | |
---|
[234] | 70 | \begin{CompactList}\small\item\em access function \item\end{CompactList}\item |
---|
| 71 | \hypertarget{classmpdf_75ded3b0f657cd7da6590691a810963c}{ |
---|
| 72 | \hyperlink{classepdf}{epdf} $\ast$ \hyperlink{classmpdf_75ded3b0f657cd7da6590691a810963c}{\_\-e} ()} |
---|
| 73 | \label{classmpdf_75ded3b0f657cd7da6590691a810963c} |
---|
| 74 | |
---|
[33] | 75 | \begin{CompactList}\small\item\em access function \item\end{CompactList}\end{CompactItemize} |
---|
| 76 | \subsection*{Protected Attributes} |
---|
| 77 | \begin{CompactItemize} |
---|
| 78 | \item |
---|
[172] | 79 | \hypertarget{classmgamma_612dbf35c770a780027619aaac2c443e}{ |
---|
| 80 | \hyperlink{classegamma}{egamma} \hyperlink{classmgamma_612dbf35c770a780027619aaac2c443e}{epdf}} |
---|
| 81 | \label{classmgamma_612dbf35c770a780027619aaac2c443e} |
---|
[79] | 82 | |
---|
[172] | 83 | \begin{CompactList}\small\item\em Internal \hyperlink{classepdf}{epdf} that arise by conditioning on {\tt rvc}. \item\end{CompactList}\item |
---|
| 84 | \hypertarget{classmgamma_43f733cce0245a52363d566099add687}{ |
---|
| 85 | double \hyperlink{classmgamma_43f733cce0245a52363d566099add687}{k}} |
---|
| 86 | \label{classmgamma_43f733cce0245a52363d566099add687} |
---|
[79] | 87 | |
---|
[91] | 88 | \begin{CompactList}\small\item\em Constant $k$. \item\end{CompactList}\item |
---|
[172] | 89 | \hypertarget{classmgamma_5e90652837448bcc29707e7412f99691}{ |
---|
| 90 | vec $\ast$ \hyperlink{classmgamma_5e90652837448bcc29707e7412f99691}{\_\-beta}} |
---|
| 91 | \label{classmgamma_5e90652837448bcc29707e7412f99691} |
---|
[79] | 92 | |
---|
| 93 | \begin{CompactList}\small\item\em cache of epdf.beta \item\end{CompactList}\item |
---|
[172] | 94 | \hypertarget{classmpdf_f6687c07ff07d47812dd565368ca59eb}{ |
---|
| 95 | \hyperlink{classRV}{RV} \hyperlink{classmpdf_f6687c07ff07d47812dd565368ca59eb}{rv}} |
---|
| 96 | \label{classmpdf_f6687c07ff07d47812dd565368ca59eb} |
---|
[33] | 97 | |
---|
| 98 | \begin{CompactList}\small\item\em modeled random variable \item\end{CompactList}\item |
---|
[172] | 99 | \hypertarget{classmpdf_acb7dda792b3cd5576f39fa3129abbab}{ |
---|
| 100 | \hyperlink{classRV}{RV} \hyperlink{classmpdf_acb7dda792b3cd5576f39fa3129abbab}{rvc}} |
---|
| 101 | \label{classmpdf_acb7dda792b3cd5576f39fa3129abbab} |
---|
[33] | 102 | |
---|
| 103 | \begin{CompactList}\small\item\em random variable in condition \item\end{CompactList}\item |
---|
[172] | 104 | \hypertarget{classmpdf_7aa894208a32f3487827df6d5054424c}{ |
---|
| 105 | \hyperlink{classepdf}{epdf} $\ast$ \hyperlink{classmpdf_7aa894208a32f3487827df6d5054424c}{ep}} |
---|
| 106 | \label{classmpdf_7aa894208a32f3487827df6d5054424c} |
---|
[33] | 107 | |
---|
[172] | 108 | \begin{CompactList}\small\item\em pointer to internal \hyperlink{classepdf}{epdf} \item\end{CompactList}\end{CompactItemize} |
---|
[33] | 109 | |
---|
| 110 | |
---|
[30] | 111 | \subsection{Detailed Description} |
---|
| 112 | Gamma random walk. |
---|
| 113 | |
---|
[91] | 114 | Mean value, $\mu$, of this density is given by {\tt rvc} . Standard deviation of the random walk is proportional to one $k$-th the mean. This is achieved by setting $\alpha=k$ and $\beta=k/\mu$. |
---|
[30] | 115 | |
---|
[33] | 116 | The standard deviation of the walk is then: $\mu/\sqrt(k)$. |
---|
[30] | 117 | |
---|
[162] | 118 | \subsection{Member Function Documentation} |
---|
[172] | 119 | \hypertarget{classmpdf_3f172b79ec4a5ebc87898a5381141f1b}{ |
---|
[162] | 120 | \index{mgamma@{mgamma}!samplecond@{samplecond}} |
---|
| 121 | \index{samplecond@{samplecond}!mgamma@{mgamma}} |
---|
[172] | 122 | \subsubsection[samplecond]{\setlength{\rightskip}{0pt plus 5cm}virtual vec mpdf::samplecond (const vec \& {\em cond}, \/ double \& {\em ll})\hspace{0.3cm}{\tt \mbox{[}inline, virtual, inherited\mbox{]}}}} |
---|
| 123 | \label{classmpdf_3f172b79ec4a5ebc87898a5381141f1b} |
---|
[162] | 124 | |
---|
| 125 | |
---|
[234] | 126 | Returns a sample from the density conditioned on {\tt cond}, $x \sim epdf(rv|cond)$. |
---|
[162] | 127 | |
---|
[234] | 128 | \begin{Desc} |
---|
[162] | 129 | \item[Parameters:] |
---|
| 130 | \begin{description} |
---|
| 131 | \item[{\em cond}]is numeric value of {\tt rv} \item[{\em ll}]is a return value of log-likelihood of the sample. \end{description} |
---|
| 132 | \end{Desc} |
---|
| 133 | |
---|
| 134 | |
---|
[210] | 135 | Reimplemented in \hyperlink{classmprod_a48887eb8738a9e5550bfc38eb8e9d68}{mprod}. |
---|
[172] | 136 | |
---|
[219] | 137 | References mpdf::condition(), mpdf::ep, epdf::evallog(), and epdf::sample(). |
---|
[162] | 138 | |
---|
[219] | 139 | Referenced by MPF$<$ BM\_\-T $>$::bayes(), and PF::bayes().\hypertarget{classmpdf_b1dae6171ee39a6a05976c7b1007a3c5}{ |
---|
| 140 | \index{mgamma@{mgamma}!samplecond\_\-m@{samplecond\_\-m}} |
---|
| 141 | \index{samplecond\_\-m@{samplecond\_\-m}!mgamma@{mgamma}} |
---|
| 142 | \subsubsection[samplecond\_\-m]{\setlength{\rightskip}{0pt plus 5cm}virtual mat mpdf::samplecond\_\-m (const vec \& {\em cond}, \/ vec \& {\em ll}, \/ int {\em N})\hspace{0.3cm}{\tt \mbox{[}inline, virtual, inherited\mbox{]}}}} |
---|
| 143 | \label{classmpdf_b1dae6171ee39a6a05976c7b1007a3c5} |
---|
[162] | 144 | |
---|
| 145 | |
---|
| 146 | Returns. |
---|
| 147 | |
---|
| 148 | \begin{Desc} |
---|
| 149 | \item[Parameters:] |
---|
| 150 | \begin{description} |
---|
| 151 | \item[{\em N}]samples from the density conditioned on {\tt cond}, $x \sim epdf(rv|cond)$. \item[{\em cond}]is numeric value of {\tt rv} \item[{\em ll}]is a return value of log-likelihood of the sample. \end{description} |
---|
| 152 | \end{Desc} |
---|
| 153 | |
---|
| 154 | |
---|
[219] | 155 | References mpdf::condition(), RV::count(), mpdf::ep, epdf::evallog(), mpdf::rv, and epdf::sample(). |
---|
[172] | 156 | |
---|
[30] | 157 | The documentation for this class was generated from the following files:\begin{CompactItemize} |
---|
| 158 | \item |
---|
[172] | 159 | work/git/mixpp/bdm/stat/\hyperlink{libEF_8h}{libEF.h}\item |
---|
[145] | 160 | work/git/mixpp/bdm/stat/libEF.cpp\end{CompactItemize} |
---|