notes-shao2003

Unnamed repository; edit this file 'description' to name the repository.
git clone git://pcardenasb.com/notes-shao2003.git
Log | Files | Refs

chapter_01.tex (35527B)


      1 \title Probability Theory
      2 
      3 \begin{paragraph}{1.4}{Why Conditional Expectations Are Needed}
      4 	In elementary probability, the conditional probability of an event \(B\) given an event \(A\) is defined as
      5 	\[
      6 		P(B\mid A)=\frac{P(A\cap B)}{P(A)},
      7 	\]
      8 	provided that \(P(A)>0\). In probability and statistics, however, we sometimes need a notion of conditional probability even for events \(A\) with \(P(A)=0\); for example, \(A=\{Y=c\}\), where \(c\in\mathbb{R}\) and \(Y\) is a random variable having a continuous c.d.f.
      9 \end{paragraph}
     10 
     11 \begin{paragraph}{1.4}{Scope of Conditional Probability}
     12 	General definitions of conditional probability, expectation, and distribution are introduced in this section, and they are shown to agree with those defined in elementary probability in special cases.
     13 \end{paragraph}
     14 
     15 \begin{definition}{1.6}{Conditional Expectation and Probability}
     16 	Let \(X\) be an integrable random variable on \((\Omega,\mathcal{F},P)\).
     17 
     18 	\begin{itemize}
     19 		\item Let \(\mathcal{A}\) be a sub-\(\sigma\)-field of \(\mathcal{F}\). The conditional expectation of \(X\) given \(\mathcal{A}\), denoted by \(E(X\mid\mathcal{A})\), is the a.s.-unique random variable satisfying:
     20 		      \begin{itemize}
     21 			      \item \(E(X\mid\mathcal{A})\) is measurable from \((\Omega,\mathcal{A})\) to \((\mathbb{R},\mathcal{B})\);
     22 			      \item \(\int_A E(X\mid\mathcal{A})\,dP=\int_A X\,dP\) for every \(A\in\mathcal{A}\).
     23 		      \end{itemize}
     24 		      The existence of \(E(X\mid\mathcal{A})\) follows from Theorem~1.4.
     25 
     26 		\item Let \(B\in\mathcal{F}\). The conditional probability of \(B\) given \(\mathcal{A}\) is \(P(B\mid\mathcal{A})=E(I_B\mid\mathcal{A})\).
     27 
     28 		\item Let \(Y\) be measurable from \((\Omega,\mathcal{F},P)\) to \((\Lambda,\mathcal{G})\). The conditional expectation of \(X\) given \(Y\) is
     29 		      \[
     30 			      E(X\mid Y)=E[X\mid\sigma(Y)].
     31 		      \]
     32 	\end{itemize}
     33 \end{definition}
     34 
     35 \begin{paragraph}{1.4.1}{Information in a Random Element}
     36 	Essentially, the \(\sigma\)-field \(\sigma(Y)\) contains ``the information in \(Y\).'' Hence, \(E(X\mid Y)\) is the expectation of \(X\) given the information provided by \(\sigma(Y)\).
     37 \end{paragraph}
     38 
     39 \begin{paragraph}{1.4.1}{Representing Conditional Expectations}
     40 	The following useful result shows that there is a Borel function \(h\), defined on the range of \(Y\), such that \(E(X\mid Y)=h\circ Y\).
     41 \end{paragraph}
     42 
     43 \begin{lemma}{1.2}{Measurable Functions of a Random Element}
     44 	Let \(Y\) be measurable from \((\Omega,\mathcal{F})\) to \((\Lambda,\mathcal{G})\), and let \(Z\) be a function from \((\Omega,\mathcal{F})\) to \((\mathbb{R}^k,\mathcal{B}^k)\). Then \(Z\) is measurable from \((\Omega,\sigma(Y))\) to \((\mathbb{R}^k,\mathcal{B}^k)\) if and only if there is a measurable function \(h\) from \((\Lambda,\mathcal{G})\) to \((\mathbb{R}^k,\mathcal{B}^k)\) such that \(Z=h\circ Y\).
     45 \end{lemma}
     46 
     47 \begin{paragraph}{1.4.1}{Conditioning on a Value}
     48 	The function \(h\) in \(E(X\mid Y)=h\circ Y\) is a Borel function on \((\Lambda,\mathcal{G})\). For \(y\in\Lambda\), define
     49 	\[
     50 		E(X\mid Y=y)=h(y).
     51 	\]
     52 	Thus \(h(y)\) is a function on \(\Lambda\), whereas \(h\circ Y=E(X\mid Y)\) is a function on \(\Omega\).
     53 \end{paragraph}
     54 
     55 \begin{paragraph}{1.4.1}{Conditional Expectation of a Vector}
     56 	For a random vector \(X\), \(E(X\mid\mathcal{A})\) is defined as the vector of conditional expectations of the components of \(X\).
     57 \end{paragraph}
     58 
     59 \begin{example}{1.21}{Conditioning on a Countable Partition}
     60 	Let \(X\) be an integrable random variable on \((\Omega,\mathcal{F},P)\). Let \(A_1,A_2,\ldots\) be disjoint events such that \(\bigcup_i A_i=\Omega\) and \(P(A_i)>0\) for every \(i\), and let \(a_1,a_2,\ldots\) be distinct real numbers. Define
     61 	\[
     62 		Y=\sum_{i=1}^{\infty}a_iI_{A_i}.
     63 	\]
     64 	Then
     65 	\[
     66 		E(X\mid Y)
     67 		=
     68 		\sum_{i=1}^{\infty}
     69 		\frac{\int_{A_i}X\,dP}{P(A_i)}I_{A_i}.
     70 		\tag{1.59}
     71 	\]
     72 
     73 	We verify the two conditions in Definition~1.6 with \(\mathcal{A}=\sigma(Y)\). Since \(\sigma(Y)=\sigma(\{A_1,A_2,\ldots\})\), the right-hand side of (1.59) is measurable on \((\Omega,\sigma(Y))\). For every \(B\in\mathcal{B}\),
     74 	\[
     75 		Y^{-1}(B)=\bigcup_{i:a_i\in B}A_i.
     76 	\]
     77 	Using properties of integrals,
     78 	\begin{align*}
     79 		\int_{Y^{-1}(B)}X\,dP
     80 		 & =\sum_{i:a_i\in B}\int_{A_i}X\,dP \\
     81 		 & =\sum_{i=1}^{\infty}
     82 		\frac{\int_{A_i}X\,dP}{P(A_i)}
     83 		P\bigl(A_i\cap Y^{-1}(B)\bigr)       \\
     84 		 & =\int_{Y^{-1}(B)}
     85 		\left[
     86 			\sum_{i=1}^{\infty}
     87 			\frac{\int_{A_i}X\,dP}{P(A_i)}I_{A_i}
     88 			\right]dP.
     89 	\end{align*}
     90 	This verifies the second condition and proves (1.59).
     91 
     92 	Let \(h\) be a Borel function on \(\mathbb{R}\) satisfying
     93 	\[
     94 		h(a_i)=\frac{\int_{A_i}X\,dP}{P(A_i)}.
     95 	\]
     96 	Then \(E(X\mid Y)=h\circ Y\) and \(E(X\mid Y=y)=h(y)\).
     97 
     98 	If \(A\in\mathcal{F}\) and \(X=I_A\), then
     99 	\[
    100 		P(A\mid Y)=E(X\mid Y)
    101 		=\sum_{i=1}^{\infty}\frac{P(A\cap A_i)}{P(A_i)}I_{A_i}.
    102 	\]
    103 	For \(\omega\in A_i\), this equals \(P(A\cap A_i)/P(A_i)=P(A\mid A_i)\). Hence Definition~1.6 agrees with the elementary definition of conditional probability.
    104 \end{example}
    105 
    106 \begin{proposition}{1.9}{Conditional Expectation from a Joint Density}
    107 	Let \(X\) be a random \(n\)-vector and \(Y\) a random \(m\)-vector. Suppose that \((X,Y)\) has a joint p.d.f. \(f(x,y)\) with respect to \(\nu\times\lambda\), where \(\nu\) and \(\lambda\) are \(\sigma\)-finite measures on \((\mathbb{R}^n,\mathcal{B}^n)\) and \((\mathbb{R}^m,\mathcal{B}^m)\), respectively. Let \(g(x,y)\) be a Borel function on \(\mathbb{R}^{n+m}\) for which \(E|g(X,Y)|<\infty\). Then
    108 	\[
    109 		E[g(X,Y)\mid Y]
    110 		=
    111 		\frac{\int g(x,Y)f(x,Y)\,d\nu(x)}
    112 		{\int f(x,Y)\,d\nu(x)}
    113 		\quad\text{a.s.}
    114 		\tag{1.60}
    115 	\]
    116 \end{proposition}
    117 
    118 \begin{proof}{1.9}{Proof via Fubini's Theorem}
    119 	Denote the right-hand side of (1.60) by \(h(Y)\). By Fubini's theorem, \(h\) is Borel, and Lemma~1.2 implies that \(h(Y)\) is Borel on \((\Omega,\sigma(Y))\). Also,
    120 	\[
    121 		f_Y(y)=\int f(x,y)\,d\nu(x)
    122 	\]
    123 	is the p.d.f. of \(Y\) with respect to \(\lambda\). For \(B\in\mathcal{B}^m\),
    124 	\begin{align*}
    125 		\int_{Y^{-1}(B)}h(Y)\,dP
    126 		 & =\int_B h(y)\,dP_Y(y)                                         \\
    127 		 & =\int_B
    128 		\frac{\int g(x,y)f(x,y)\,d\nu(x)}
    129 		{\int f(x,y)\,d\nu(x)}
    130 		f_Y(y)\,d\lambda(y)                                              \\
    131 		 & =\int_{\mathbb{R}^n\times B}g(x,y)f(x,y)\,d(\nu\times\lambda) \\
    132 		 & =\int_{\mathbb{R}^n\times B}g(x,y)\,dP_{(X,Y)}                \\
    133 		 & =\int_{Y^{-1}(B)}g(X,Y)\,dP.
    134 	\end{align*}
    135 	The first and last equalities follow from Theorem~1.2, the second and fourth from the definitions of \(h\) and p.d.f.'s, and the third from Fubini's theorem.
    136 \end{proof}
    137 
    138 \begin{definition}{1.4.1}{Conditional Density}
    139 	For a random vector \((X,Y)\) with joint p.d.f. \(f(x,y)\) with respect to \(\nu\times\lambda\), define the conditional p.d.f. of \(X\) given \(Y=y\) by
    140 	\[
    141 		f_{X\mid Y}(x\mid y)=\frac{f(x,y)}{f_Y(y)},
    142 		\tag{1.61}
    143 	\]
    144 	where
    145 	\[
    146 		f_Y(y)=\int f(x,y)\,d\nu(x)
    147 	\]
    148 	is the marginal p.d.f. of \(Y\) with respect to \(\lambda\). For every fixed \(y\) with \(f_Y(y)>0\), \(f_{X\mid Y}(x\mid y)\) is a p.d.f. with respect to \(\nu\).
    149 \end{definition}
    150 
    151 \begin{paragraph}{1.4.1}{Expectation under a Conditional Density}
    152 	Equation~(1.60) can be rewritten as
    153 	\[
    154 		E[g(X,Y)\mid Y]
    155 		=
    156 		\int g(x,Y)f_{X\mid Y}(x\mid Y)\,d\nu(x).
    157 	\]
    158 	Thus the conditional expectation of \(g(X,Y)\) given \(Y\) equals its expectation with respect to the conditional p.d.f. of \(X\) given \(Y\), agreeing with elementary probability.
    159 \end{paragraph}
    160 
    161 \begin{proposition}{1.10}{Properties of Conditional Expectations}
    162 	Let \(X,Y,X_1,X_2,\ldots\) be integrable random variables on \((\Omega,\mathcal{F},P)\), and let \(\mathcal{A}\) be a sub-\(\sigma\)-field of \(\mathcal{F}\).
    163 
    164 	\begin{itemize}
    165 		\item If \(X=c\) a.s., where \(c\in\mathbb{R}\), then \(E(X\mid\mathcal{A})=c\) a.s.
    166 		\item If \(X\le Y\) a.s., then \(E(X\mid\mathcal{A})\le E(Y\mid\mathcal{A})\) a.s.
    167 		\item For \(a,b\in\mathbb{R}\),
    168 		      \[
    169 			      E(aX+bY\mid\mathcal{A})
    170 			      =aE(X\mid\mathcal{A})+bE(Y\mid\mathcal{A})
    171 			      \quad\text{a.s.}
    172 		      \]
    173 		\item \(E[E(X\mid\mathcal{A})]=EX\).
    174 		\item If \(\mathcal{A}_0\subset\mathcal{A}\), then
    175 		      \begin{align*}
    176 			      E[E(X\mid\mathcal{A})\mid\mathcal{A}_0]
    177 			       & =E(X\mid\mathcal{A}_0)                   \\
    178 			       & =E[E(X\mid\mathcal{A}_0)\mid\mathcal{A}]
    179 			      \quad\text{a.s.}
    180 		      \end{align*}
    181 
    182 		\item If \(\sigma(Y)\subset\mathcal{A}\) and \(E|XY|<\infty\), then
    183 		      \[
    184 			      E(XY\mid\mathcal{A})=YE(X\mid\mathcal{A})
    185 			      \quad\text{a.s.}
    186 		      \]
    187 		\item If \(X\) and \(Y\) are independent and \(E|g(X,Y)|<\infty\) for a Borel function \(g\), then
    188 		      \[
    189 			      E[g(X,Y)\mid Y=y]=E[g(X,y)]
    190 			      \quad\text{a.s. }P_Y.
    191 		      \]
    192 		\item If \(EX^2<\infty\), then
    193 		      \[
    194 			      [E(X\mid\mathcal{A})]^2\le E(X^2\mid\mathcal{A})
    195 			      \quad\text{a.s.}
    196 		      \]
    197 		\item If \(X_n\ge0\), then the conditional Fatou lemma gives
    198 		      \[
    199 			      E\left(\liminf_n X_n\mid\mathcal{A}\right)
    200 			      \le\liminf_n E(X_n\mid\mathcal{A})
    201 			      \quad\text{a.s.}
    202 		      \]
    203 		\item If \(|X_n|\le Y\) and \(X_n\to X\) a.s., then the conditional dominated convergence theorem gives
    204 		      \[
    205 			      E(X_n\mid\mathcal{A})\to E(X\mid\mathcal{A})
    206 			      \quad\text{a.s.}
    207 		      \]
    208 
    209 	\end{itemize}
    210 \end{proposition}
    211 
    212 \begin{paragraph}{1.4.1}{Further Convergence Properties}
    213 	Part (vii) of Proposition~1.10 follows from the more general Theorem~1.7(i). Since \(E(X\mid\mathcal{A})\) is defined only for integrable \(X\), conditional monotone convergence---if \(0\le X_1\le X_2\le\cdots\) and \(X_n\to X\) a.s., then \(E(X_n\mid\mathcal{A})\to E(X\mid\mathcal{A})\) a.s.---is a special case of Proposition~1.10(x).
    214 \end{paragraph}
    215 
    216 \begin{paragraph}{1.4.1}{Conditional Inequalities}
    217 	Holder's inequality (1.40), Liapounov's inequality (1.42), Minkowski's inequality (1.43), and Jensen's inequality (1.47) also hold a.s. when \(E\) is replaced by \(E(\,\cdot\mid\mathcal{A})\).
    218 \end{paragraph}
    219 
    220 \begin{example}{1.22}{Conditional Expectation as Best Predictor}
    221 	Let \(X\) be a random variable on \((\Omega,\mathcal{F},P)\) with \(EX^2<\infty\), and let \(Y\) be measurable from \((\Omega,\mathcal{F},P)\) to \((\Lambda,\mathcal{G})\). We wish to predict \(X\) from an observed value of \(Y\). Let
    222 	\[
    223 		\mathcal{H}
    224 		=
    225 		\{g:\ g\text{ is Borel and }E[g(Y)^2]<\infty\}.
    226 	\]
    227 	A predictor \(g(Y)\) is assessed by its mean squared prediction error \(E[X-g(Y)]^2\). Then \(E(X\mid Y)\) is the best predictor:
    228 	\[
    229 		E[X-E(X\mid Y)]^2
    230 		=
    231 		\min_{g\in\mathcal{H}}E[X-g(Y)]^2.
    232 		\tag{1.62}
    233 	\]
    234 
    235 	Proposition~1.10(viii) implies \(E(X\mid Y)\in\mathcal{H}\). For every \(g\in\mathcal{H}\),
    236 	\begin{align*}
    237 		E & [X-g(Y)]^2 =                                                      \\
    238 		  & =E[X-E(X\mid Y)+E(X\mid Y)-g(Y)]^2                                \\
    239 		  & =E[X-E(X\mid Y)]^2+E[E(X\mid Y)-g(Y)]^2                           \\
    240 		  & \quad+2E\{[X-E(X\mid Y)][E(X\mid Y)-g(Y)]\}                       \\
    241 		  & =E[X-E(X\mid Y)]^2+E[E(X\mid Y)-g(Y)]^2                           \\
    242 		  & \quad+2E\!\left(E\{[X-E(X\mid Y)][E(X\mid Y)-g(Y)]\mid Y\}\right) \\
    243 		  & =E[X-E(X\mid Y)]^2+E[E(X\mid Y)-g(Y)]^2                           \\
    244 		  & \quad+2E\{[E(X\mid Y)-g(Y)]E[X-E(X\mid Y)\mid Y]\}                \\
    245 		  & =E[X-E(X\mid Y)]^2+E[E(X\mid Y)-g(Y)]^2                           \\
    246 		  & \ge E[X-E(X\mid Y)]^2.
    247 	\end{align*}
    248 	The third equality follows from Proposition~1.10(iv), the fourth from Proposition~1.10(vi), and the last equality before the inequality from Proposition~1.10(i), (iii), and (vi).
    249 \end{example}
    250 
    251 \begin{definition}{1.7}{Independence}
    252 	Let \((\Omega,\mathcal{F},P)\) be a probability space.
    253 
    254 	\begin{itemize}
    255 		\item Let \(\mathcal{C}\) be a collection of sets in \(\mathcal{F}\). Events in \(\mathcal{C}\) are independent if and only if, for every positive integer \(n\) and distinct \(A_1,\ldots,A_n\in\mathcal{C}\),
    256 		      \[
    257 			      P(A_1\cap\cdots\cap A_n)=P(A_1)\cdots P(A_n).
    258 		      \]
    259 		\item Collections \(\mathcal{C}_i\subset\mathcal{F}\), \(i\in I\), are independent if and only if the events in every collection \(\{A_i\in\mathcal{C}_i:i\in I\}\) are independent.
    260 		\item Random elements \(X_i\), \(i\in I\), are independent if and only if the \(\sigma\)-fields \(\sigma(X_i)\), \(i\in I\), are independent.
    261 	\end{itemize}
    262 \end{definition}
    263 
    264 \begin{paragraph}{1.4.2}{Checking Independence}
    265 	The following result is useful for checking the independence of \(\sigma\)-fields.
    266 \end{paragraph}
    267 
    268 \begin{lemma}{1.3}{Independence of Generated Sigma-fields}
    269 	Let \(\mathcal{C}_i\), \(i\in I\), be independent collections of events. Suppose that every \(\mathcal{C}_i\) is closed under intersections: if \(A,B\in\mathcal{C}_i\), then \(A\cap B\in\mathcal{C}_i\). Then the \(\sigma\)-fields \(\sigma(\mathcal{C}_i)\), \(i\in I\), are independent.
    270 \end{lemma}
    271 
    272 \begin{paragraph}{1.4.2}{Independence and Joint Distributions}
    273 	Lemma~1.3 immediately shows that random variables \(X_i\), \(i=1,\ldots,k\), are independent according to Definition~1.7 if and only if (1.7) holds, with \(F\) the joint c.d.f. of \((X_1,\ldots,X_k)\) and \(F_i\) the marginal c.d.f. of \(X_i\). Thus Definition~1.7(iii) agrees with the notion of independence in Section~1.3.1.
    274 \end{paragraph}
    275 
    276 \begin{paragraph}{1.4.2}{Functions Preserve Independence}
    277 	Definition~1.7 also shows that if \(X\) and \(Y\) are independent random vectors, then \(g(X)\) and \(h(Y)\) are independent for every pair of Borel functions \(g\) and \(h\). This gives a simple proof of Lemma~1.1.
    278 \end{paragraph}
    279 
    280 \begin{paragraph}{1.4.2}{Independence as No Information}
    281 	For events \(A\) and \(B\) with \(P(A)>0\), they are independent if and only if \(P(B\mid A)=P(B)\). Thus \(A\) provides no information about the probability that \(B\) occurs. The next proposition extends this fact.
    282 \end{paragraph}
    283 
    284 \begin{proposition}{1.11}{Conditioning with Independent Information}
    285 	Let \(X\) be a random variable with \(E|X|<\infty\), and let \(Y_i\) be random \(k_i\)-vectors, \(i=1,2\). If \((X,Y_1)\) and \(Y_2\) are independent, then
    286 	\[
    287 		E[X\mid(Y_1,Y_2)]=E(X\mid Y_1)
    288 		\quad\text{a.s.}
    289 	\]
    290 \end{proposition}
    291 
    292 \begin{proof}{1.11}{Proof on Generating Rectangles}
    293 	First, \(E(X\mid Y_1)\) is Borel on \((\Omega,\sigma(Y_1,Y_2))\), since \(\sigma(Y_1)\subset\sigma(Y_1,Y_2)\). It remains to show that, for every \(B\in\mathcal{B}^{k_1+k_2}\),
    294 	\[
    295 		\int_{(Y_1,Y_2)^{-1}(B)}X\,dP
    296 		=
    297 		\int_{(Y_1,Y_2)^{-1}(B)}E(X\mid Y_1)\,dP.
    298 		\tag{1.63}
    299 	\]
    300 	If \(B=B_1\times B_2\), with \(B_i\in\mathcal{B}^{k_i}\), then
    301 	\[
    302 		(Y_1,Y_2)^{-1}(B)=Y_1^{-1}(B_1)\cap Y_2^{-1}(B_2)
    303 	\]
    304 	and
    305 	\begin{align*}
    306 		 & \int_{Y_1^{-1}(B_1)\cap Y_2^{-1}(B_2)}E(X\mid Y_1)\,dP        \\
    307 		 & \quad=\int I_{Y_1^{-1}(B_1)}I_{Y_2^{-1}(B_2)}E(X\mid Y_1)\,dP \\
    308 		 & \quad=\left[\int I_{Y_1^{-1}(B_1)}E(X\mid Y_1)\,dP\right]
    309 		\left[\int I_{Y_2^{-1}(B_2)}\,dP\right]                          \\
    310 		 & \quad=\left[\int I_{Y_1^{-1}(B_1)}X\,dP\right]
    311 		\left[\int I_{Y_2^{-1}(B_2)}\,dP\right]                          \\
    312 		 & \quad=\int I_{Y_1^{-1}(B_1)}I_{Y_2^{-1}(B_2)}X\,dP            \\
    313 		 & \quad=\int_{Y_1^{-1}(B_1)\cap Y_2^{-1}(B_2)}X\,dP.
    314 	\end{align*}
    315 	The second and fourth equalities use (1.38) and the independence of \((X,Y_1)\) and \(Y_2\); the third uses the definition of \(E(X\mid Y_1)\).
    316 
    317 	Thus (1.63) holds for rectangles. The collection
    318 	\[
    319 		\mathcal{H}
    320 		=
    321 		\{B\subset\mathbb{R}^{k_1+k_2}:B\text{ satisfies (1.63)}\}
    322 	\]
    323 	is a \(\sigma\)-field. Since
    324 	\[
    325 		\mathcal{B}^{k_1}\times\mathcal{B}^{k_2}\subset\mathcal{H},
    326 	\]
    327 	we have
    328 	\[
    329 		\mathcal{B}^{k_1+k_2}
    330 		=
    331 		\sigma(\mathcal{B}^{k_1}\times\mathcal{B}^{k_2})
    332 		\subset\mathcal{H},
    333 	\]
    334 	which proves the result.
    335 \end{proof}
    336 
    337 \begin{paragraph}{1.4.2}{Conditional Probabilities under Independence}
    338 	Proposition~1.11 remains true with \(X\) replaced by \(h(X)\) for any Borel \(h\). Consequently, if \((X,Y_1)\) and \(Y_2\) are independent, then
    339 	\[
    340 		P(A\mid Y_1,Y_2)=P(A\mid Y_1)
    341 		\quad\text{a.s. for every }A\in\sigma(X).
    342 		\tag{1.64}
    343 	\]
    344 	If \(Y_1\) is constant and \(Y=Y_2\), this becomes \(P(A\mid Y)=P(A)\) a.s. for every \(A\in\sigma(X)\). Thus \(\sigma(Y)\) supplies no additional information about the stochastic behavior of \(X\), giving another equivalent and more intuitive definition of independence.
    345 \end{paragraph}
    346 
    347 \begin{paragraph}{1.4.2}{Conditional Independence}
    348 	For nonconstant \(Y_1\), \(X\) and \(Y_2\) are conditionally independent given \(Y_1\) if and only if (1.64) holds. Proposition~1.11 therefore says that if \(Y_2\) and \((X,Y_1)\) are independent, then \(X\) and \(Y_2\) are conditionally independent given \(Y_1\). The proposition may fail if \(Y_2\) is independent of \(X\) but not of \((X,Y_1)\); see Exercise~96.
    349 \end{paragraph}
    350 
    351 \begin{paragraph}{1.4.3}{Conditional Distributions without Densities}
    352 	The conditional p.d.f. was introduced in Section~1.4.1 for random variables having p.d.f.'s with respect to specified measures. We now consider conditional distributions when no p.d.f. need exist.
    353 \end{paragraph}
    354 
    355 \begin{paragraph}{1.4.3}{Need for a Regular Version}
    356 	For random vectors \(X\) and \(Y\) on a common probability space, it is natural to consider \(P[X^{-1}(B)\mid Y=y]\) as the conditional distribution of \(X\) given \(Y=y\). Since conditional probability is defined only almost surely, however, for a fixed \(y\) this expression need not be a probability measure. The next theorem gives a version that is a probability measure for every fixed \(y\). A proof is given in Billingsley (1986, pp.~460--461).
    357 \end{paragraph}
    358 
    359 \begin{theorem}{1.7}{Existence of Conditional Distributions}
    360 	\begin{itemize}
    361 		\item Let \(X\) be a random \(n\)-vector on \((\Omega,\mathcal{F},P)\), and let \(\mathcal{A}\) be a sub-\(\sigma\)-field of \(\mathcal{F}\). There is a function \(P(B,\omega)\) on \(\mathcal{B}^n\times\Omega\) such that:
    362 		      \begin{itemize}
    363 			      \item \(P(B,\omega)=P[X^{-1}(B)\mid\mathcal{A}]\) a.s. for every fixed \(B\in\mathcal{B}^n\);
    364 			      \item \(P(\,\cdot,\omega)\) is a probability measure on \((\mathbb{R}^n,\mathcal{B}^n)\) for every fixed \(\omega\in\Omega\).
    365 		      \end{itemize}
    366 
    367 		      If \(Y\) is measurable from \((\Omega,\mathcal{F},P)\) to \((\Lambda,\mathcal{G})\), there is a function \(P_{X\mid Y}(B\mid y)\) such that:
    368 		      \begin{itemize}
    369 			      \item \(P_{X\mid Y}(B\mid y)=P[X^{-1}(B)\mid Y=y]\) a.s. \(P_Y\) for every fixed \(B\in\mathcal{B}^n\);
    370 			      \item \(P_{X\mid Y}(\,\cdot\mid y)\) is a probability measure on \((\mathbb{R}^n,\mathcal{B}^n)\) for every fixed \(y\in\Lambda\).
    371 		      \end{itemize}
    372 
    373 		      Furthermore, if \(g\) is Borel and \(E|g(X,Y)|<\infty\), then
    374 		      \begin{align*}
    375 			      E[g(X,Y)&\mid Y=y] =                                 \\
    376 			       & =E[g(X,y)\mid Y=y]                                \\
    377 			       & =\int_{\mathbb{R}^n}g(x,y)\,dP_{X\mid Y}(x\mid y)
    378 			      \quad\text{a.s. }P_Y.
    379 		      \end{align*}
    380 
    381 		\item Let \((\Lambda,\mathcal{G},P_1)\) be a probability space. Suppose \(P_2\) is a function from \(\mathcal{B}^n\times\Lambda\) to \(\mathbb{R}\) such that \(P_2(\,\cdot,y)\) is a probability measure on \((\mathbb{R}^n,\mathcal{B}^n)\) for every \(y\), and \(P_2(B,\,\cdot)\) is Borel for every \(B\in\mathcal{B}^n\). Then there is a unique probability measure \(P\) on \((\mathbb{R}^n\times\Lambda,\sigma(\mathcal{B}^n\times\mathcal{G}))\) such that
    382 		      \[
    383 			      P(B\times C)=\int_C P_2(B,y)\,dP_1(y)
    384 			      \tag{1.65}
    385 		      \]
    386 		      for \(B\in\mathcal{B}^n\) and \(C\in\mathcal{G}\).
    387 
    388 		      \hangindent\parindent If \((\Lambda,\mathcal{G})=(\mathbb{R}^m,\mathcal{B}^m)\), and \(X(x,y)=x\) and \(Y(x,y)=y\) are the coordinate random vectors, then \(P_Y=P_1\), \(P_{X\mid Y}(\,\cdot\mid y)=P_2(\,\cdot,y)\), and (1.65) defines the joint distribution of \((X,Y)\). Its joint c.d.f. is
    389 
    390 		      \begin{align*}
    391 			      F(x,y) & = \int_{(-\infty,y]} P_{X\mid Y}\bigl((-\infty,x]\mid z\bigr)\,dP_Y(z) \ \ (1.66) \\
    392 			             & x\in\mathbb{R}^n,\ y\in\mathbb{R}^m.
    393 		      \end{align*}
    394 		      Here \((-\infty,a]=(-\infty,a_1]\times\cdots\times(-\infty,a_k]\) for \(a=(a_1,\ldots,a_k)\).
    395 	\end{itemize}
    396 \end{theorem}
    397 
    398 \begin{definition}{1.4.3}{Conditional Distribution}
    399 	For fixed \(y\),
    400 	\[
    401 		P_{X\mid Y=y}=P_{X\mid Y}(\,\cdot\mid y)
    402 	\]
    403 	is called the conditional distribution of \(X\) given \(Y=y\). Under Theorem~1.7(i), if \(Y\) is an \(m\)-vector and \((X,Y)\) has a p.d.f. with respect to \(\nu\times\lambda\), then \(f_{X\mid Y}(x\mid y)\) from (1.61) is the p.d.f. of \(P_{X\mid Y=y}\) with respect to \(\nu\).
    404 \end{definition}
    405 
    406 \begin{paragraph}{1.4.3}{The Two-stage Experiment Theorem}
    407 	Theorem~1.7(ii) says that a distribution on one space and conditional distributions on a second space determine a joint distribution on the product space. If \(Y\in\mathbb{R}^m\) is selected in stage one according to \(P_Y=P_1\), and \(X\) is then selected according to \(P_2(\,\cdot,y)\), the combined experiment produces a jointly distributed pair \((X,Y)\) whose distribution is given by (1.65), with \(P_{X\mid Y=y}=P_2(\,\cdot,y)\). This gives a way to generate dependent random variables.
    408 \end{paragraph}
    409 
    410 \begin{example}{1.23}{A Market Survey}
    411 	A mail survey asks \(N\) randomly selected customers whether a new product is better than the old one. A response is \(1\) if the new product is preferred and \(0\) otherwise; some customers do not respond. Let \(X\) be the number of ones among the returned questionnaires.
    412 
    413 	If every customer responds, then \(X\) has the binomial distribution \(\operatorname{Bi}(p,N)\), assuming independent responses, where \(p\in(0,1)\) is the overall preference rate. Let \(Y\) be the number who respond. Suppose customers respond independently with probability \(\pi\in(0,1)\). Then
    414 	\[
    415 		Y\sim\operatorname{Bi}(\pi,N).
    416 	\]
    417 	Given \(Y=y\), \(P_{X\mid Y=y}\) is \(\operatorname{Bi}(p,y)\) for \(y\ge1\), and is point mass at \(0\) for \(y=0\).
    418 
    419 	Using (1.66) and counting measure, the joint c.d.f. is
    420 	\begin{align*}
    421 		F(x,y)
    422 		 & =\sum_{k=0}^{y}
    423 		P_{X\mid Y=k}((-\infty,x])
    424 		\binom Nk\pi^k(1-\pi)^{N-k}                \\
    425 		 & =\sum_{k=0}^{y}\sum_{j=0}^{\min\{x,k\}}
    426 		\binom kjp^j(1-p)^{k-j}
    427 		\binom Nk\pi^k(1-\pi)^{N-k},
    428 	\end{align*}
    429 	for \(x=0,1,\ldots,y\) and \(y=0,1,\ldots,N\).
    430 
    431 	The marginal c.d.f. is \(F_X(x)=F(x,\infty)=F(x,N)\). Its p.d.f. with respect to counting measure is
    432 	\begin{align*}
    433 		f_X(x)
    434 		 & =\sum_{k=x}^{N}
    435 		\binom{k}{x}p^x(1-p)^{k-x}
    436 		\binom Nk\pi^k(1-\pi)^{N-k}            \\
    437 		 & =\binom Nx(\pi p)^x(1-\pi p)^{N-x},
    438 	\end{align*}
    439 	for \(x=0,1,\ldots,N\). Thus \(X\sim\operatorname{Bi}(\pi p,N)\).
    440 \end{example}
    441 
    442 \begin{paragraph}{1.4.1}{Conditional Expectations from Densities}
    443 	The next result generalizes Example~1.21 to conditional expectations of random variables having p.d.f.'s.
    444 \end{paragraph}
    445 
    446 \begin{paragraph}{1.4.4}{Dependent Sequences}
    447 	As applications of conditional expectations, we introduce two important types of dependent sequences: Markov chains and martingales.
    448 \end{paragraph}
    449 
    450 \begin{definition}{1.4.4}{Markov Chain}
    451 	A sequence of random vectors \(\{X_n:n=1,2,\ldots\}\) is a Markov chain, or Markov process, if and only if
    452 	\[
    453 		P(B\mid X_1,\ldots,X_n)=P(B\mid X_n)
    454 		\quad\text{a.s.},
    455 		\quad
    456 		B\in\sigma(X_{n+1}),\ n=2,3,\ldots.
    457 		\tag{1.67}
    458 	\]
    459 \end{definition}
    460 
    461 \begin{paragraph}{1.4.4}{The Markov Property}
    462 	Comparing (1.67) with (1.64), \(X_{n+1}\), representing tomorrow, is conditionally independent of \((X_1,\ldots,X_{n-1})\), representing the past, given \(X_n\), representing today. However, \((X_1,\ldots,X_{n-1})\) need not be independent of \((X_n,X_{n+1})\).
    463 \end{paragraph}
    464 
    465 \begin{paragraph}{1.4.4}{Independent Sequences Are Markov}
    466 	Every sequence of independent random vectors is a Markov chain: Proposition~1.11 shows that both sides of (1.67) equal \(P(B)\). The next example gives dependent Markov processes.
    467 \end{paragraph}
    468 
    469 \begin{example}{1.24}{First-order Autoregressive Processes}
    470 	Let \(\varepsilon_1,\varepsilon_2,\ldots\) be independent random variables, let \(X_1=\varepsilon_1\), and define
    471 	\[
    472 		X_{n+1}=\rho X_n+\varepsilon_{n+1},
    473 		\quad n=1,2,\ldots,
    474 	\]
    475 	where \(\rho\in\mathbb{R}\). This is a first-order autoregressive process. For \(B\in\mathcal{B}\),
    476 	\begin{align*}
    477 		P(X_{n+1}\in B\mid X_1,\ldots,X_n)
    478 		 & =P_{\varepsilon_{n+1}}(B-\rho X_n) \\
    479 		 & =P(X_{n+1}\in B\mid X_n)
    480 		\quad\text{a.s.},
    481 	\end{align*}
    482 	where \(B-y=\{x\in\mathbb{R}:x+y\in B\}\); hence \(\{X_n\}\) is a Markov chain.
    483 
    484 	For \(y\in\mathbb{R}\),
    485 	\[
    486 		P_{\varepsilon_{n+1}}(B-y)
    487 		=P(\varepsilon_{n+1}+y\in B)
    488 		=\int I_B(x+y)\,dP_{\varepsilon_{n+1}}(x).
    489 	\]
    490 	Fubini's theorem implies that this is Borel in \(y\). Therefore \(P_{\varepsilon_{n+1}}(B-\rho X_n)\) is Borel with respect to \(\sigma(X_n)\), and hence with respect to \(\sigma(X_1,\ldots,X_n)\).
    491 
    492 	Let \(B_j\in\mathcal{B}\), \(j=1,\ldots,n\), and
    493 	\[
    494 		A=\bigcap_{j=1}^n X_j^{-1}(B_j).
    495 	\]
    496 	Since \(X_{n+1}=\varepsilon_{n+1}+\rho X_n\) and \(\varepsilon_{n+1}\) is independent of \((X_1,\ldots,X_n)\), Theorem~1.2 and Fubini's theorem give
    497 	\begin{align*}
    498 		\int_A & P_{\varepsilon_{n+1}}(B-\rho X_n)\,dP=            \\
    499 		       & =\int_{x_j\in B_j,\ j=1,\ldots,n,t\in B-\rho x_n}
    500 		dP_{\varepsilon_{n+1}}(t)\,dP_X(x)                         \\
    501 		       & =\int_{x_j\in B_j,\ j=1,\ldots,n,x_{n+1}\in B}
    502 		dP_{(X,\varepsilon_{n+1})}(x,t)                            \\
    503 		       & =P\bigl(A\cap X_{n+1}^{-1}(B)\bigr),
    504 	\end{align*}
    505 	where \(X=(X_1,\ldots,X_n)\), \(x=(x_1,\ldots,x_n)\), and \(x_{n+1}=\rho x_n+t\). The final argument in the proof of Proposition~1.11 now gives
    506 	\[
    507 		P(X_{n+1}\in B\mid X_1,\ldots,X_n)
    508 		=P_{\varepsilon_{n+1}}(B-\rho X_n)
    509 		\quad\text{a.s.}
    510 	\]
    511 	The proof that the latter equals \(P(X_{n+1}\in B\mid X_n)\) a.s. is similar and simpler.
    512 \end{example}
    513 
    514 \begin{proposition}{1.12}{Characterizations of Markov Chains}
    515 	A sequence \(\{X_n\}\) is a Markov chain if and only if any one of the following conditions holds:
    516 
    517 	\begin{itemize}
    518 		\item For every \(n\ge2\) and every integrable \(h(X_{n+1})\), with \(h\) Borel,
    519 		      \[
    520 			      E[h(X_{n+1})\mid X_1,\ldots,X_n]
    521 			      =E[h(X_{n+1})\mid X_n]
    522 			      \quad\text{a.s.}
    523 		      \]
    524 		\item For every \(n\ge1\) and \(B\in\sigma(X_{n+1},X_{n+2},\ldots)\),
    525 		      \[
    526 			      P(B\mid X_1,\ldots,X_n)=P(B\mid X_n)
    527 			      \quad\text{a.s.}
    528 		      \]
    529 		\item For every \(n\ge2\), \(A\in\sigma(X_1,\ldots,X_n)\), and \(B\in\sigma(X_{n+1},X_{n+2},\ldots)\),
    530 		      \[
    531 			      P(A\cap B\mid X_n)
    532 			      =P(A\mid X_n)P(B\mid X_n)
    533 			      \quad\text{a.s.}
    534 		      \]
    535 	\end{itemize}
    536 \end{proposition}
    537 
    538 \begin{proof}{1.12}{Proof of the Characterizations}
    539 	First, condition (a) clearly implies (1.67). Conversely, (1.67) implies (a) for simple \(h\) by Proposition~1.10(iii). For nonnegative \(h\), choose nonnegative simple functions \(h_1\le h_2\le\cdots\le h\) with \(h_j\to h\), and apply Proposition~1.10(iii) and (x). The general case follows from \(h=h^+-h^-\).
    540 
    541 	Condition (b) clearly implies (1.67). Conversely,
    542 	\[
    543 		\sigma(X_{n+1},X_{n+2},\ldots)
    544 		=
    545 		\sigma\left(\bigcup_{j=1}^{\infty}\sigma(X_{n+1},\ldots,X_{n+j})\right).
    546 	\]
    547 	It therefore suffices to prove (b) for \(B\in\sigma(X_{n+1},\ldots,X_{n+j})\), by induction on \(j\). The case \(j=1\) is (1.67). The induction hypothesis also gives
    548 	\begin{align*}
    549 		E[h(X_{n+1},\ldots,X_{n+j})&\mid X_1,\ldots,X_n] =  \\
    550 		 & =E[h(X_{n+1},\ldots,X_{n+j})\mid X_n] \ \ (1.68)
    551 	\end{align*}
    552 	for every Borel \(h\).
    553 
    554 	For \(B_1\in\sigma(X_{n+j+1})\) and \(B_2\in\sigma(X_{n+1},\ldots,X_{n+j})\),
    555 	\begin{align*}
    556 		E & (I_{B_1}I_{B_2}\mid X_1,\ldots,X_n)=                            \\
    557 		  & =E[E(I_{B_1}I_{B_2}\mid X_1,\ldots,X_{n+j})\mid X_1,\ldots,X_n] \\
    558 		  & =E[I_{B_2}E(I_{B_1}\mid X_1,\ldots,X_{n+j})\mid X_1,\ldots,X_n] \\
    559 		  & =E[I_{B_2}E(I_{B_1}\mid X_{n+j})\mid X_1,\ldots,X_n]            \\
    560 		  & =E[I_{B_2}E(I_{B_1}\mid X_{n+j})\mid X_n]                       \\
    561 		  & =E[I_{B_2}E(I_{B_1}\mid X_n,\ldots,X_{n+j})\mid X_n]            \\
    562 		  & =E[E(I_{B_1}I_{B_2}\mid X_n,\ldots,X_{n+j})\mid X_n]            \\
    563 		  & =E(I_{B_1}I_{B_2}\mid X_n)
    564 		\quad\text{a.s.}
    565 	\end{align*}
    566 	Here the first and last equalities use Proposition~1.10(v), the second and sixth use Proposition~1.10(vi), the third and fifth use (1.67), and the fourth uses (1.68). This completes the induction.
    567 
    568 	If (b) holds, then for \(A\in\sigma(X_1,\ldots,X_n)\) and \(B\) in the future \(\sigma\)-field,
    569 	\begin{align*}
    570 		E(I_AI_B\mid X_n)
    571 		 & =E[E(I_AI_B\mid X_1,\ldots,X_n)\mid X_n] \\
    572 		 & =E[I_AE(I_B\mid X_1,\ldots,X_n)\mid X_n] \\
    573 		 & =E[I_AE(I_B\mid X_n)\mid X_n]            \\
    574 		 & =E(I_A\mid X_n)E(I_B\mid X_n),
    575 	\end{align*}
    576 	which is (c).
    577 
    578 	Conversely, assume (c). Let \(A_1\in\sigma(X_n)\), \(A_2\in\sigma(X_1,\ldots,X_{n-1})\), and \(B\in\sigma(X_{n+1},X_{n+2},\ldots)\). Then
    579 	\begin{align*}
    580 		\int_{A_1\cap A_2}E(I_B\mid X_n)\,dP
    581 		 & =\int_{A_1}I_{A_2}E(I_B\mid X_n)\,dP            \\
    582 		 & =\int_{A_1}E[I_{A_2}E(I_B\mid X_n)\mid X_n]\,dP \\
    583 		 & =\int_{A_1}E(I_{A_2}\mid X_n)E(I_B\mid X_n)\,dP \\
    584 		 & =\int_{A_1}E(I_{A_2}I_B\mid X_n)\,dP            \\
    585 		 & =P(A_1\cap A_2\cap B).
    586 	\end{align*}
    587 	Disjoint unions of events \(A_1\cap A_2\) generate \(\sigma(X_1,\ldots,X_n)\), so \(E(I_B\mid X_n)=E(I_B\mid X_1,\ldots,X_n)\) a.s., proving (b).
    588 \end{proof}
    589 
    590 \begin{paragraph}{1.4.4}{Past and Future Given the Present}
    591 	Condition (b) of Proposition~1.12 says that the past and future are conditionally independent given the present. This is a property of every Markov chain. More discussion and applications appear in Section~4.1.4.
    592 \end{paragraph}
    593 
    594 \begin{definition}{1.4.4}{Martingales}
    595 	Let \(\{X_n\}\) be integrable random variables on \((\Omega,\mathcal{F},P)\), and let
    596 	\[
    597 		\mathcal{F}_1\subset\mathcal{F}_2\subset\cdots\subset\mathcal{F}
    598 	\]
    599 	with \(\sigma(X_n)\subset\mathcal{F}_n\). The sequence \(\{X_n,\mathcal{F}_n:n=1,2,\ldots\}\) is a martingale if and only if
    600 	\[
    601 		E(X_{n+1}\mid\mathcal{F}_n)=X_n
    602 		\quad\text{a.s.},\quad n=1,2,\ldots.
    603 		\tag{1.69}
    604 	\]
    605 	It is a submartingale if equality is replaced by \(\ge\), and a supermartingale if equality is replaced by \(\le\). The sequence \(\{X_n\}\) itself is called a martingale, submartingale, or supermartingale when the filtration is \(\sigma(X_1,\ldots,X_n)\). Proposition~1.10(v) shows that if \(\{X_n,\mathcal{F}_n\}\) has one of these properties, then so does \(\{X_n\}\).
    606 \end{definition}
    607 
    608 \begin{paragraph}{1.4.4}{Basic Martingale Properties}
    609 	For a martingale \(\{X_n,\mathcal{F}_n\}\),
    610 	\[
    611 		E(X_{n+j}\mid\mathcal{F}_n)=X_n
    612 		\quad\text{and}\quad
    613 		EX_1=EX_j.
    614 	\]
    615 	For a submartingale the corresponding statements are
    616 	\[
    617 		E(X_{n+j}\mid\mathcal{F}_n)\ge X_n
    618 		\quad\text{and}\quad
    619 		EX_1\le EX_2\le\cdots.
    620 	\]
    621 	These hold for every \(j=1,2,\ldots\).
    622 \end{paragraph}
    623 
    624 \begin{paragraph}{1.4.4}{Constructing Martingales}
    625 	Given \(\mathcal{F}_1\subset\mathcal{F}_2\subset\cdots\subset\mathcal{F}\) and an integrable \(Y\), the sequence \(\{E(Y\mid\mathcal{F}_n)\}\) is a martingale. Another construction uses independent integrable random variables \(\{\varepsilon_n\}\) and
    626 	\[
    627 		X_n=\varepsilon_1+\cdots+\varepsilon_n.
    628 	\]
    629 	Since
    630 	\[
    631 		E(X_{n+1}\mid X_1,\ldots,X_n)
    632 		=X_n+E\varepsilon_{n+1}
    633 		\quad\text{a.s.},
    634 	\]
    635 	\(\{X_n\}\) is a martingale if \(E\varepsilon_n=0\), a submartingale if \(E\varepsilon_n\ge0\), and a supermartingale if \(E\varepsilon_n\le0\), for every \(n\). Example~1.24 with \(\rho=1\) also shows that \(\{X_n\}\) is a Markov chain.
    636 \end{paragraph}
    637 
    638 \begin{paragraph}{1.4.4}{Another Martingale Example}
    639 	The next example gives another construction of martingales.
    640 \end{paragraph}
    641 
    642 \begin{example}{1.25}{Likelihood Ratio Martingale}
    643 	Let \((\Omega,\mathcal{F},P)\) be a probability space, let \(Q\) be another probability measure on \(\mathcal{F}\), and let \(\mathcal{F}_1\subset\mathcal{F}_2\subset\cdots\subset\mathcal{F}\). Write \(P_n\) and \(Q_n\) for the restrictions of \(P\) and \(Q\) to \(\mathcal{F}_n\). If \(Q_n\ll P_n\) for every \(n\), then
    644 	\[
    645 		X_n=\frac{dQ_n}{dP_n}
    646 	\]
    647 	defines a martingale \(\{X_n,\mathcal{F}_n\}\).
    648 
    649 	Now suppose \(\mathcal{F}_n=\sigma(Y_1,\ldots,Y_n)\), and there is a \(\sigma\)-finite measure \(\nu_n\) on \(\mathcal{F}_n\) such that \(P_n\ll\nu_n\ll P_n\). Define
    650 	\[
    651 		p_n(Y_1,\ldots,Y_n)=\frac{dP_n}{d\nu_n},
    652 		\qquad
    653 		q_n(Y_1,\ldots,Y_n)=\frac{dQ_n}{d\nu_n}.
    654 	\]
    655 	By Proposition~1.7(iii),
    656 	\[
    657 		X_n
    658 		=
    659 		\frac{q_n(Y_1,\ldots,Y_n)}
    660 		{p_n(Y_1,\ldots,Y_n)},
    661 	\]
    662 	which is called a likelihood ratio in statistics.
    663 \end{example}
    664 
    665 \begin{paragraph}{1.4.4}{Functions of Martingales}
    666 	The following results give useful properties of martingales and submartingales.
    667 \end{paragraph}
    668 
    669 \begin{proposition}{1.13}{Convex Functions of Martingales}
    670 	Let \(\phi\) be convex on \(\mathbb{R}\).
    671 
    672 	\begin{itemize}
    673 		\item If \(\{X_n,\mathcal{F}_n\}\) is a martingale and \(\phi(X_n)\) is integrable for every \(n\), then \(\{\phi(X_n),\mathcal{F}_n\}\) is a submartingale.
    674 		\item If \(\{X_n,\mathcal{F}_n\}\) is a submartingale, \(\phi(X_n)\) is integrable for every \(n\), and \(\phi\) is nondecreasing, then \(\{\phi(X_n),\mathcal{F}_n\}\) is a submartingale.
    675 	\end{itemize}
    676 \end{proposition}
    677 
    678 \begin{proof}{1.13}{Proof by Conditional Jensen}
    679 	For the first part,
    680 	\[
    681 		\phi(X_n)
    682 		=\phi(E(X_{n+1}\mid\mathcal{F}_n))
    683 		\le E[\phi(X_{n+1})\mid\mathcal{F}_n]
    684 		\quad\text{a.s.}
    685 	\]
    686 	by Jensen's inequality for conditional expectations. For the second, monotonicity and the submartingale property give
    687 	\[
    688 		\phi(X_n)
    689 		\le\phi(E(X_{n+1}\mid\mathcal{F}_n))
    690 		\le E[\phi(X_{n+1})\mid\mathcal{F}_n]
    691 		\quad\text{a.s.}
    692 	\]
    693 \end{proof}
    694 
    695 \begin{paragraph}{1.4.4}{Examples of Convex Transformations}
    696 	Proposition~1.13 shows that if \(\{X_n,\mathcal{F}_n\}\) is a submartingale, then so is \(\{X_n^+,\mathcal{F}_n\}\). If it is a martingale, then \(\{|X_n|,\mathcal{F}_n\}\), \(\{|X_n|^p,\mathcal{F}_n\}\) for \(p>1\), and \(\{|X_n|(\log|X_n|)^+,\mathcal{F}_n\}\) are submartingales whenever the displayed random variables are integrable.
    697 \end{paragraph}
    698 
    699 \begin{proposition}{1.14}{Doob's Decomposition}
    700 	Let \(\{X_n,\mathcal{F}_n\}\) be a submartingale. Then
    701 	\[
    702 		X_n=Y_n+Z_n,\quad n=1,2,\ldots,
    703 	\]
    704 	where \(\{Y_n,\mathcal{F}_n\}\) is a martingale,
    705 	\[
    706 		0=Z_1\le Z_2\le\cdots,
    707 	\]
    708 	and \(EZ_n<\infty\) for every \(n\). If \(\sup_nE|X_n|<\infty\), then
    709 	\[
    710 		\sup_nE|Y_n|<\infty
    711 		\quad\text{and}\quad
    712 		\sup_nEZ_n<\infty.
    713 	\]
    714 \end{proposition}
    715 
    716 \begin{proof}{1.14}{Proof of Doob's Decomposition}
    717 	Define
    718 	\[
    719 		\eta_1=X_1,\qquad \zeta_1=0,
    720 	\]
    721 	and, for \(n\ge2\),
    722 	\begin{align*}
    723 		\eta_n  & =X_n-X_{n-1}-E(X_n-X_{n-1}\mid\mathcal{F}_{n-1}) \\
    724 		\zeta_n & =E(X_n-X_{n-1}\mid\mathcal{F}_{n-1}).
    725 	\end{align*}
    726 	Then
    727 	\[
    728 		Y_n=\sum_{i=1}^n\eta_i,
    729 		\qquad
    730 		Z_n=\sum_{i=1}^n\zeta_i
    731 	\]
    732 	satisfy \(X_n=Y_n+Z_n\) and the required conditions.
    733 
    734 	If \(\sup_nE|X_n|<\infty\), then \(EY_1=EY_n\) and \(Z_n\le|X_n|-Y_n\), so
    735 	\[
    736 		EZ_n\le E|X_n|-EY_1.
    737 	\]
    738 	Hence \(\sup_nEZ_n<\infty\). Since \(|Y_n|\le|X_n|+Z_n\), it also follows that \(\sup_nE|Y_n|<\infty\).
    739 \end{proof}
    740 
    741 \begin{paragraph}{1.4.4}{Doob's Convergence Theorem}
    742 	The following martingale convergence theorem, due to Doob, has many applications; see, for example, Example~1.27 in Section~1.5.1. A proof is given in Billingsley (1986, pp.~490--491).
    743 \end{paragraph}
    744 
    745 \begin{proposition}{1.15}{Martingale Convergence}
    746 	Let \(\{X_n,\mathcal{F}_n\}\) be a submartingale. If
    747 	\[
    748 		c=\sup_nE|X_n|<\infty,
    749 	\]
    750 	then \(X_n\to X\) a.s. for a random variable \(X\) satisfying \(E|X|\le c\).
    751 \end{proposition}