Experimental unit=the object which a variable is measured.

Population=set of all measurements of interest Sample=subset of measurements selected from the population. Univariate data=result when a single variable is measured on a single experiment unit Bivariate data result when 2 variables are measured on a single experimental unit Multivariate=more than 2. Qualitative variables measure a quality or characteristic on each experimental unit. Quantitative measure a # quantity or amount on each experimental unit. Discrete=variable can assume only a finite or countable number of values; likewise, continuous variable is the opposite. Frequency = number of measurements in each category Relative frequency= proportion of measurements in each category Unimodal-one peak, bimodal-distribution has 2 peaks Parameters-numerical descriptive measures associated with a population of measurements Statistics are those computed from sample measurements. Random variable= if the value that it assumes, corresponding to the outcome of an experiment is a chance or random event (randomly selected ppl, etc.) Requirements for a discrete probability distrib. = 0 <= p (x) <= 1, and SigmaP (x) = 1 Binomial experiment= n identical trials, success and failure, (2) trials are independent, we are interested in x, the # of successes observed during the n trials, x = 0 1 2.n, (1-p=q) Simple random sampling is a commonly used plan = every sample of size n has = chance. Stratified random sample = pop consist of 2 or more sub pops called strata, a sampling plan that ensures that each sub pop is represented in the sample. Cluster sample= simple random sample of clusters from the available clusters in the pop. 1 in k systematic random sample involves the random selection of one of the first k elements in an ordered population then the systematic collection of every kth element thereafter. Calculating probabilities for the sample mean= 1) find u and calculate SE (x-) = stnd/sqrt (n) 2) Write down the event of interest in terms of x and locate the appropriate area on the normal curve. 3) Convert the necessary values= z = xhat – u/ stnd/sqrt (n). Then use appendix #s. Calculating probabilities for sample proportion phat= 1) find n and p. 2) check whether the normal approximation to the binomial distribution is appropriate (np>5 and nq>5) 3) write down the event of interest in terms of phat, and locate the area on the normal curve. 4) Z = phat – p / sqrt (pq/n). 5) Use table with appendix.

Rage-largest to smallest given measurements. Deviation= Quartiles (IQR) = Q3 – Q1. Position q1 = .25(n+1) , q3=.75(n+1) = arrange data from smallest to largest. Number of ways we can arrange n distinct objects taking them r at a time = Pn/r = n! / (N – r)! Counting rule for combinations = the # of distinct combinations of n objects that can be formed, taking them r at a time, = Cn/r = n! / R! (N-r)! Probabilities: (A and B) independent variables= heads on a coin 2x in a row? (Example) = P|A ^ B| = P [A] P [B]. ½ x ½ = ¼ Probabilities: dependent= draw 2 cards, both aces? (Example) = P [A ^B] = P [A] P [B | A] 4/52 = one ace, 3/51 = second card ace, x those = 1/221. . Probabilities: (A or B) mutually exclusive variables (one event occurs-other cannot) = P [A V B] = P [A] + P [B], not mutually exclusive variables = p [A V B] = p [A] + p [B] – p [A ^ B] Binomial distribution (r success in N trials) P [x = k] = N! / K! (N – k)! X p^k x q^(n-k). Mean = u = np, variance = s^2 = npq, s = sqrt (npq) Cumulative binomial probabilities = example= 3 successes= p (x <= 3) = p (0) + p (1) + p (2) + p (3) = p (x<= 2) = p (0) + p (1) + p (2) so p (x=3) = P (x<= 3) – p (x<= 2). To find 3 or more, 1 – p (x <3) = 1 – p (x<= 2). Poisson random variable = u = average # of times that an event occurs in period of time. K occurrences = p (x = k) u^k e^-u / k!

0160 b) np = 500 x . soda bottler in the example claims that only 5% of the soda cans are underfilled.83 = (use same formula above) = -1.85 = 425 which is greater than 5.05.70 (proportion of individuals with Rh positive blood is 85%. Z+ = x>mean.5455. so no sample produces a mean equal to the mean in part b.0301 = .. What is the probability that 3 are hit? = P(x=3) = C(n/3) p^3q^n-3 = 10(.5 / 6 = 3 (. standard deviation = s = sqrt s^2 = 1.9699 . Statistical process control x2hat = 3 x s/sqrt (n). c) phat > .88 (used calculator) using the table in the back of the book. Highway patrol stops every 10th vehicle given city artery between 9am and 3pm etc= 1 in 10 systematic sample.18 e) population mean = (6+1+3+2) /4 = 3. I get 1 . z=0 Rule of thumb=np>5 and nq>5 = normal approximation to the binomial probabilities will be adequate.Hyper geometric probability distribution (m&m problem) = pop.2s contains approx.5 + 2 + 1.1) (6.60 finite pop consists of four elements. we get . Equations: normal distribution = f(x) = 1/deviation x sqrt(2pie) Make a box plot = lower fence |-------Q1box | median | box-Q3-----| outer fence Normal distr.. np = 10. Tchebscheffs theorem can be used for x & s or u & sntd given that k is greater than or equal to 1 and set of measurements: .s contains approx. Soda machine fills cans of soda with 12 flouid ounces.88 = phat = . 3 of which are spoiled.88 (same formula) = 1. 95% of the measurements The interval m+. Is the distrib. Standard normal random variable = z = x – u/std.5 + 2.3) (6. If =. Compute the sample mean for each sample. Marksman hits a target 80% of the time. q = . M = 3. What is the prob that the sample lies between 83% and 88%? 99% of the time the sample proportion would lie between what 2 limits? n = 500 and p = .2) d) mean = 3. nq = 190. 4 bottles is randomly selected.58 = 0. List possible samples of size n=2.4. p P(S) = 0.2) (1. f(x) = 1/s(sqrt(2pie)) x e^. Of phat approximately normal.83 < phat < 0. 1. if x < mean=z is -.s=underfilled can.2/sqrt(6) = . Probability = N = 12. 7.15 a) SE(proportion) = sqrt (p x q)/n = .85 +.8643 e) z_0 = p_0 – p / sqrt(p x q / n ) = +.7% of the measurements.85. Whats the prob. That the sample proportion phat exceeds 82. phat = sigma (phati) / k.1 oz and a stnd of .8^3) (.the histogram) s2= xi2-xi 2n n-1 = 7/5 = 1. Example: case of wine has 12 bottles. 68% of the measurements The interval m+.2048.. (N-M) = 9. 6 1 3 2. mound shaped: interval m +. the sample proportion.81 . variance = . N = 500. Sample problems 7. Hitting 3 or more = P(x>3) = C(5/4) p^4 q^5-4 + C(5/5)p^5q^5-5 = answer. Therefore it is appropriate to use the normal distribution because np > 5 as well as q > 5.2) (3.1/ .2^2) = .88 using the back of the book.15 = 75 which is greater than 5 as well. Find the sampling distribution of xhat.82 = z = phat – p / sqrt(p x q)/n = -1. and phat = . what is the probability that more than 10 % of the cans are underfilled? = n=200. Solve for p (0).0160) = (0.5 + 4. he fires 5 shots. 0. Randomly sampled 200 cans. 99.3) (1.2oz. create upper and lower control limits = phat = 3 sqrt (phat (1-phat)/n) Examples of samples= random sample of n=50 city blocks are selected and a census is done for each single family dwelling= cluster sample. 2. Suppose the fills are arctually distributed with a mean of 12.1056 = . What are the mean and snd of phat.3s contains approx.5(x-u/s)^2 Empirical rule: for a distribution that is approx. 3 = mean = 1. Contains M successes and N-M failures the probability of k successes in a random sample of size n is: Px=k) = C (m over k) C (N-M over n-k) / C (N over n). q = . = mean = n(M/N) variance= n(M/N)(N-M/N)(N-n/N-1) .9699 = the probability that the sample proportion exceeds 82% d) 0. and nq = 500 x .2.(2. wat is the probability that the average for a 6 pack is less than 12 oz? = p(xhat <12) = p(xhat – u)/stnd/sqrt(n) < 12 – 12.25.95. How many diff samples of size n =2 can be selected from this pop if you sample without replacement. Do any values = mean? a) 4!/(2!)(2!) = 6 b) (6. n = 4. 1112. One hundred household in each of 4 cities wards are surveyed concering blah = stratified.58 x 0.

There are 13 spades. based on the rule of addition: P(S ∪ A) = P(S) + P(A) P(S ∩ A) … P(S ∪ A) = 13/52 + 4/52 . 10 bucks if its an ace or a spade card. and upper fence: q3 + 1. 8/9 of the measurement are within3 stnd dev of the mean. Draw a card from deck. We know the following: There are 52 cards in the deck. Position of q1 = . if k = 3. There is 1 ace that is also a spade.If k = 2 at least 1 -1/2^2 = ¾ of the measurements are within 2 stnd of the mean.5(IQR). IQR =q3 – q1. and let A = the event that the card is an ace.25(n+1) . so P(S ∩ A) = 1/52. Let S = the event that the card is a spade. so P(A) = 4/52.75(n+1). q3 = . Therefore.5(IQR). There are 4 aces. lower fence: q1 – 1.1/52 = 16/52 = 4/13 . Probability?The correct answer is C. so P(S) = 13/52.