Question and Answers Forum

All Questions      Topic List

Probability and Statistics Questions

Previous in All Question      Next in All Question      

Previous in Probability and Statistics      Next in Probability and Statistics      

Question Number 683 by 112358 last updated on 24/Feb/15

Determine the following sum in  terms of n.                             S_n =Σ_(i=1) ^n i^2 q^(i−1)   where 0 < q < 1.  For the distribution of the discrete  random variable X given as                            X∽Geo(p)  prove that                            Var(X)=(q/p^2 )  where q=1−p, if   Var(X)=Σ{x^2 P(X=x)}−E^2 (X)  for a given discrete random   variable X.

$${Determine}\:{the}\:{following}\:{sum}\:{in} \\ $$ $${terms}\:{of}\:{n}. \\ $$ $$\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:{S}_{{n}} =\underset{{i}=\mathrm{1}} {\overset{{n}} {\sum}}{i}^{\mathrm{2}} {q}^{{i}−\mathrm{1}} \\ $$ $${where}\:\mathrm{0}\:<\:{q}\:<\:\mathrm{1}. \\ $$ $${For}\:{the}\:{distribution}\:{of}\:{the}\:{discrete} \\ $$ $${random}\:{variable}\:{X}\:{given}\:{as} \\ $$ $$\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:{X}\backsim{Geo}\left({p}\right) \\ $$ $${prove}\:{that}\: \\ $$ $$\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:{Var}\left({X}\right)=\frac{{q}}{{p}^{\mathrm{2}} } \\ $$ $${where}\:{q}=\mathrm{1}−{p},\:{if}\: \\ $$ $${Var}\left({X}\right)=\Sigma\left\{{x}^{\mathrm{2}} {P}\left({X}={x}\right)\right\}−{E}^{\mathrm{2}} \left({X}\right) \\ $$ $${for}\:{a}\:{given}\:{discrete}\:{random}\: \\ $$ $${variable}\:{X}. \\ $$

Commented byprakash jain last updated on 24/Feb/15

S_n =1^2 +2^2 q+3^2 q^2 +4^2 q^3 +... +n^2 q^(n−1)         ....(i)  qS_n =     1^2 q   +2^2 q^2 +3^2 q^2 +...+(n−1)^2 q^(n−1) +n^2 q^n     ...(ii)  Subtracting (ii) from (i)  (1−q)S_n =1+3q+5q^2 +.....+(2n−1)q^(n−1) −n^2 q^n     ...(iii)  q(1−q)S_n =         q+3q^2 +.....+(2n−3)q^(n−1) +(2n−1)q^n −n^2 q^(n+1) ...(iv)  Subtracting (iv) from (iii)  (1−q)^2 S_n =1+2q+2q^2 +..+2q^(n−1) −(n^2 −2n+1)q^n +n^2 q^(n+1)   (1−q)^2 S_n =1+2  ((q−q^n )/(1−q))−(n−1)^2 q^n +n^2 q^(n+1)   S_n =(1/((1−q)^2 ))[1+2((q−q^n )/(1−q))−(n−1)^2 q^n +n^2 q^(n+1) ]  I don′t think you can calculate S_n  only in terms  of n (you will also need q)

$${S}_{\mathrm{n}} =\mathrm{1}^{\mathrm{2}} +\mathrm{2}^{\mathrm{2}} {q}+\mathrm{3}^{\mathrm{2}} {q}^{\mathrm{2}} +\mathrm{4}^{\mathrm{2}} {q}^{\mathrm{3}} +...\:+{n}^{\mathrm{2}} {q}^{{n}−\mathrm{1}} \:\:\:\:\:\:\:\:....\left(\mathrm{i}\right) \\ $$ $${qS}_{\mathrm{n}} =\:\:\:\:\:\mathrm{1}^{\mathrm{2}} {q}\:\:\:+\mathrm{2}^{\mathrm{2}} {q}^{\mathrm{2}} +\mathrm{3}^{\mathrm{2}} {q}^{\mathrm{2}} +...+\left({n}−\mathrm{1}\right)^{\mathrm{2}} {q}^{{n}−\mathrm{1}} +{n}^{\mathrm{2}} {q}^{{n}} \:\:\:\:...\left(\mathrm{ii}\right) \\ $$ $$\mathrm{Subtracting}\:\left(\mathrm{ii}\right)\:\mathrm{from}\:\left(\mathrm{i}\right) \\ $$ $$\left(\mathrm{1}−{q}\right){S}_{{n}} =\mathrm{1}+\mathrm{3}{q}+\mathrm{5}{q}^{\mathrm{2}} +.....+\left(\mathrm{2}{n}−\mathrm{1}\right){q}^{{n}−\mathrm{1}} −{n}^{\mathrm{2}} {q}^{{n}} \:\:\:\:...\left(\mathrm{iii}\right) \\ $$ $${q}\left(\mathrm{1}−{q}\right){S}_{{n}} =\:\:\:\:\:\:\:\:\:{q}+\mathrm{3}{q}^{\mathrm{2}} +.....+\left(\mathrm{2}{n}−\mathrm{3}\right){q}^{{n}−\mathrm{1}} +\left(\mathrm{2}{n}−\mathrm{1}\right){q}^{{n}} −{n}^{\mathrm{2}} {q}^{{n}+\mathrm{1}} ...\left(\mathrm{iv}\right) \\ $$ $$\mathrm{Subtracting}\:\left(\mathrm{iv}\right)\:\mathrm{from}\:\left(\mathrm{iii}\right) \\ $$ $$\left(\mathrm{1}−{q}\right)^{\mathrm{2}} {S}_{{n}} =\mathrm{1}+\mathrm{2}{q}+\mathrm{2}{q}^{\mathrm{2}} +..+\mathrm{2}{q}^{{n}−\mathrm{1}} −\left({n}^{\mathrm{2}} −\mathrm{2}{n}+\mathrm{1}\right){q}^{{n}} +{n}^{\mathrm{2}} {q}^{{n}+\mathrm{1}} \\ $$ $$\left(\mathrm{1}−{q}\right)^{\mathrm{2}} {S}_{{n}} =\mathrm{1}+\mathrm{2}\:\:\frac{{q}−{q}^{{n}} }{\mathrm{1}−{q}}−\left({n}−\mathrm{1}\right)^{\mathrm{2}} {q}^{{n}} +{n}^{\mathrm{2}} {q}^{{n}+\mathrm{1}} \\ $$ $${S}_{{n}} =\frac{\mathrm{1}}{\left(\mathrm{1}−{q}\right)^{\mathrm{2}} }\left[\mathrm{1}+\mathrm{2}\frac{{q}−{q}^{{n}} }{\mathrm{1}−{q}}−\left({n}−\mathrm{1}\right)^{\mathrm{2}} {q}^{{n}} +{n}^{\mathrm{2}} {q}^{{n}+\mathrm{1}} \right] \\ $$ $$\mathrm{I}\:\mathrm{don}'\mathrm{t}\:\mathrm{think}\:\mathrm{you}\:\mathrm{can}\:\mathrm{calculate}\:{S}_{{n}} \:\mathrm{only}\:\mathrm{in}\:\mathrm{terms} \\ $$ $$\mathrm{of}\:{n}\:\left(\mathrm{you}\:\mathrm{will}\:\mathrm{also}\:\mathrm{need}\:{q}\right) \\ $$

Commented by112358 last updated on 24/Feb/15

Would it be safe to assume that q  is a constant such that q∈(0,1)?

$${Would}\:{it}\:{be}\:{safe}\:{to}\:{assume}\:{that}\:{q} \\ $$ $${is}\:{a}\:{constant}\:{such}\:{that}\:{q}\in\left(\mathrm{0},\mathrm{1}\right)? \\ $$

Commented byprakash jain last updated on 24/Feb/15

For a give distribution as mention in problem  q=1−p  so q is independent of i and n. So it is a  constant for the summation.

$$\mathrm{For}\:\mathrm{a}\:\mathrm{give}\:\mathrm{distribution}\:\mathrm{as}\:\mathrm{mention}\:\mathrm{in}\:\mathrm{problem} \\ $$ $${q}=\mathrm{1}−{p}\:\:\mathrm{so}\:{q}\:\mathrm{is}\:\mathrm{independent}\:\mathrm{of}\:{i}\:\mathrm{and}\:{n}.\:\mathrm{So}\:\mathrm{it}\:\mathrm{is}\:\mathrm{a} \\ $$ $$\mathrm{constant}\:\mathrm{for}\:\mathrm{the}\:\mathrm{summation}. \\ $$

Answered by prakash jain last updated on 24/Feb/15

Expected Value  E(x)=Σ_(i=1) ^∞ i.(1−p)^(i−1) p  E=                 p+2(1−p)p+3(1−p)^2 p+...  (1−p)E=     +(1−p)p+2(1−p)^2 p+...  pE =p+(1−p)p+(1−p)^2 p+..  pE=(p/(1−(1−p)))=1⇒E(x)=(1/p)  Variance  Var(x)=Σ_(i=1) ^∞ i^2 (1−p)^(i−1) p−[E(x)]^2         (i)  S=Σ_(i=1) ^∞ i^2 (1−p)^(i−1) p  S=p+2^2 (1−p)p+3^2 (1−p)^2 p+..  (1−p)S=(1−p)p+2^2 (1−p)^2 p+...  Subtracting  pS=p+3(1−p)p+5(1−p)^2 p+...  S=1+3(1−p)+5(1−p)^2 +...  (1−p)S=(1−p)+3(1−p)^2 +5(1−p)^3 +..  Subtracting  pS=1+2(1−p)+2(1−p)^2 +...  pS=1+((2(1−p))/(1−(1−p)))=1+((2−2p)/p)=(2/p)−1  S=(2/p^2 ) −(1/p)  Substituting S in (i)  Var(x)=(2/p^2 ) −(1/p)−[E(x)]^2 =(2/p^2 ) −(1/p) −(1/p^2 )  =(1/p^2 )−(1/p)=((1−p)/p^2 )=(q/p^2 )

$$\mathrm{Expected}\:\mathrm{Value} \\ $$ $${E}\left({x}\right)=\underset{{i}=\mathrm{1}} {\overset{\infty} {\sum}}{i}.\left(\mathrm{1}−{p}\right)^{{i}−\mathrm{1}} {p} \\ $$ $${E}=\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:\:{p}+\mathrm{2}\left(\mathrm{1}−{p}\right){p}+\mathrm{3}\left(\mathrm{1}−{p}\right)^{\mathrm{2}} {p}+... \\ $$ $$\left(\mathrm{1}−{p}\right){E}=\:\:\:\:\:+\left(\mathrm{1}−{p}\right){p}+\mathrm{2}\left(\mathrm{1}−{p}\right)^{\mathrm{2}} {p}+... \\ $$ $${pE}\:={p}+\left(\mathrm{1}−{p}\right){p}+\left(\mathrm{1}−{p}\right)^{\mathrm{2}} {p}+.. \\ $$ $${pE}=\frac{{p}}{\mathrm{1}−\left(\mathrm{1}−{p}\right)}=\mathrm{1}\Rightarrow{E}\left({x}\right)=\frac{\mathrm{1}}{{p}} \\ $$ $$\mathrm{Variance} \\ $$ $$\mathrm{Var}\left({x}\right)=\underset{{i}=\mathrm{1}} {\overset{\infty} {\sum}}{i}^{\mathrm{2}} \left(\mathrm{1}−{p}\right)^{{i}−\mathrm{1}} {p}−\left[{E}\left({x}\right)\right]^{\mathrm{2}} \:\:\:\:\:\:\:\:\left(\mathrm{i}\right) \\ $$ $${S}=\underset{{i}=\mathrm{1}} {\overset{\infty} {\sum}}{i}^{\mathrm{2}} \left(\mathrm{1}−{p}\right)^{{i}−\mathrm{1}} {p} \\ $$ $${S}={p}+\mathrm{2}^{\mathrm{2}} \left(\mathrm{1}−{p}\right){p}+\mathrm{3}^{\mathrm{2}} \left(\mathrm{1}−{p}\right)^{\mathrm{2}} {p}+.. \\ $$ $$\left(\mathrm{1}−{p}\right){S}=\left(\mathrm{1}−{p}\right){p}+\mathrm{2}^{\mathrm{2}} \left(\mathrm{1}−{p}\right)^{\mathrm{2}} {p}+... \\ $$ $${S}\mathrm{ubtracting} \\ $$ $${pS}={p}+\mathrm{3}\left(\mathrm{1}−{p}\right){p}+\mathrm{5}\left(\mathrm{1}−{p}\right)^{\mathrm{2}} {p}+... \\ $$ $${S}=\mathrm{1}+\mathrm{3}\left(\mathrm{1}−{p}\right)+\mathrm{5}\left(\mathrm{1}−{p}\right)^{\mathrm{2}} +... \\ $$ $$\left(\mathrm{1}−{p}\right){S}=\left(\mathrm{1}−{p}\right)+\mathrm{3}\left(\mathrm{1}−{p}\right)^{\mathrm{2}} +\mathrm{5}\left(\mathrm{1}−{p}\right)^{\mathrm{3}} +.. \\ $$ $${S}\mathrm{ubtracting} \\ $$ $${pS}=\mathrm{1}+\mathrm{2}\left(\mathrm{1}−{p}\right)+\mathrm{2}\left(\mathrm{1}−{p}\right)^{\mathrm{2}} +... \\ $$ $${pS}=\mathrm{1}+\frac{\mathrm{2}\left(\mathrm{1}−{p}\right)}{\mathrm{1}−\left(\mathrm{1}−{p}\right)}=\mathrm{1}+\frac{\mathrm{2}−\mathrm{2}{p}}{{p}}=\frac{\mathrm{2}}{{p}}−\mathrm{1} \\ $$ $${S}=\frac{\mathrm{2}}{{p}^{\mathrm{2}} }\:−\frac{\mathrm{1}}{{p}} \\ $$ $$\mathrm{Substituting}\:{S}\:\mathrm{in}\:\left(\mathrm{i}\right) \\ $$ $$\mathrm{Var}\left({x}\right)=\frac{\mathrm{2}}{{p}^{\mathrm{2}} }\:−\frac{\mathrm{1}}{{p}}−\left[{E}\left({x}\right)\right]^{\mathrm{2}} =\frac{\mathrm{2}}{{p}^{\mathrm{2}} }\:−\frac{\mathrm{1}}{{p}}\:−\frac{\mathrm{1}}{{p}^{\mathrm{2}} } \\ $$ $$=\frac{\mathrm{1}}{{p}^{\mathrm{2}} }−\frac{\mathrm{1}}{{p}}=\frac{\mathrm{1}−{p}}{{p}^{\mathrm{2}} }=\frac{{q}}{{p}^{\mathrm{2}} } \\ $$

Terms of Service

Privacy Policy

Contact: info@tinkutara.com