SAMPLING AND SAMPLING

DISTRIBUTION
LECTURE-VII
 INTERVAL ESTIMATION OF POPULATION PROPORTION
•Interval
  estimation for a population proportion p is =
•For infinite population (np≥5 and n(1-p)≥5), sampling distribution of is =.
•M.
With this margin of error interval estimation of p =
 LET US DO SOME NUMERICALS
1. A USA today/CNN/Gallup survey of 369 working parents found 200 who said
they spend too little time with their children because of work commitments.
1. What is the point estimate of the proportion of the population of working
parents who feel they spend too little time with their children because of
work commitments?
2. At 95% confidence, what is the margin of error?
3. What is the 95% confidence interval estimate of the population proportion of
working parents who feel they spend too little time with their children
because of work commitments?
 STRATIFIED RANDOM SAMPLING
• When
  the population is heterogeneous with respect to the characteristics under study,
then to reduce variability of the population, stratified sampling is done in such a way
that stratifying the given population into number of sub groups make each group
homogeneous as possible and each strata are disjointed.
• After stratification of heterogeneous population to numbers of homogeneous
populations, simple random sample is taken from each strata. If elements within strata
are alike, the strata will have low variance and hence small sample size can give good
estimate of the strata characteristics.
• Formula for combining the result of the individual stratum sample is

L= Count of strata N = Sum of all stratum sizes Nh= size of stratum h

nh = number of observation in stratum h Sh =Sample standard dev of stratum h
() is finite population correction
 POPULATION MEAN σ UNKNOWN
• When developing an interval estimate of a population mean we may not have a
good estimate of the population standard deviation. In these cases, we must use
the same sample to estimate both 𝜇 and σ. This situation represents the σ
unknown case. When s is used to estimate σ, the margin of error and the
interval estimate for the population mean are based on a probability
distribution known as t disdtribution.
• The t-distribution is used when data are approximately normally distributed,
which means the data follow a bell shape but the population variance is unknown.
The variance in a t-distribution is estimated based on the degrees of freedom of
the data set (total number of observations minus 1). It is a more conservative form
of the standard normal distribution
This means that it gives a lower
probability to the center and a higher
probability to the tails than the standard
normal distribution.
 T DISTRIBUTION AND STANDARD NORMAL
DISTRIBUTION
• As the degrees of freedom (total number of observations minus 1) increases, the t-
distribution will get closer and closer to matching the standard normal distribution
• Above 30 degrees of freedom, the t-distribution roughly matches the z-distribution.
Therefore, the z-distribution can be used in place of the t-distribution with large
sample sizes.
A t-score is the number of standard deviations from the mean
in a t-distribution. t-score can be look in a t-table.

In statistics, t-scores are primarily used to find two things:

1. The upper and lower bounds of a confidence interval when

the data are approximately normally distributed.
2. The p-value of the test statistic for t-tests and regression
tests.

  subscript is placed on t to indicate the area in the upper trail of

A
t distribution and generally expressed as . This represent a t
value with an area of 𝛼/2 in the upper trail.
 MARGIN OF ERROR AND INTERVAL ESTIMATION
•  For σ unknown case the sample standard deviation s is used to
estimate σ and is replaced by and interval estimate is
where
 LET US DO SOME NUMERICALS
2. The average annual premium for automobile insurance in the United States is $1503
(Insure.com website, March 6, 2014). The following annual premiums ($) are
representative of the website’s
1905
finding
3112
for the state of Michigan .
2312
2725 2545 2981
2677 2525 2627
2600 2370 2857
2962 2545 2675
2184 2529 2115
2332 2442

• Assume the population is approximately normal.

• Provide a point estimate of the mean annual automobile insurance premium in Michigan.
• Develop a 95% confidence interval for the mean annual automobile insurance premium in
Michigan.
• Does the 95% confidence interval for the annual automobile insurance premium in
Michigan include the national average for the United States? What is your interpretation of
the relationship between auto insurance premiums in Michigan and the national average?
DEVELOPING HYPOTHESIS
LECTURE-VIII
 TESTING OF HYPOTHESIS
• Characteristics
  of population is decided based on sample study. But such decision
may not be totally correct. Therefore a statistical technique is developed to arrive
at decision known as testing of hypothesis.
• Statistically hypothesis is an assumption or statement about a population on the
basis of evidence from a random sampling. If the hypothesis completely specify
the population, then it is known as simple hypothesis, otherwise known as
composite hypothesis
• Simple hypothesis H:𝜇 = () and

• Test of statistical hypothesis is two action decision – acceptance/ Rejection

 TESTING OF HYPOTHESIS
• Test
  of significance: It is the
• The difference between a statistics and the corresponding population parameter
• The difference between two independent statistics.
• Every test of significance starts with a null hypothesis It is the hypothesis which is
tested for possible rejection under the assumption that it is true.
• Null hypothesis is expressed as an equality : where ), proportion (p) etc. Null
hypothesis is chosen in such a way that the difference between a statistics and
the parameter is not significant.
• For example, to test if a drug is better than existing one, a neutral attitude is
taken to set up the null hypothesis that is not better/ equal to the existing.
 ALTERNATIVE OF HYPOTHESIS
•• The
  hypothesis which is complementary to the null hypothesis is known as
alternative hypothesis. It is expressed asH1 and in respect to null hypothesis H0,
because the acceptance or rejection is tested against a rival hypothesis.
• If : then alternative hypothesis can be

1. :
2. :
• Alternative hypothesis (1) is known as two-tailed alternative and (2) and (3) are
known as upper trailed/ right trailed and lower trailed/left-trailed respectively.
Accordingly the corresponding test of significance are called two-trailed etc.
• Null hypothesis as an assumption to be challanged
 LET US DO SOME NUMERICALS
The manager of an automobile dealership is considering a new bonus plan
designed to increase sales volume. currently, the mean sales volume is 14
automobiles per month. The manager wants to conduct a research study to see
whether the new bonus plan increases sales volume. to collect data on the plan,
a sample of sales personnel will be allowed to sell under the new bonus plan
for a one-month period.
1. develop the null and alternative hypotheses most appropriate for this
situation.
2. comment on the conclusion when h0 cannot be rejected.
3. comment on the conclusion when h0 can be rejected.
THANK YOU