Exam 2 - Probabilities and sampling distribution Flashcards
Probability of an outcome is the
Proportion of times that an outcome occurs in many, many repetitions(plays) of the random phenomenon.
Random phenomenon
A phenomenon where the outcome of one play is unpredictable, but the outcomes from many plays form a distribution
In single random phenomenon the outcome is
Uncertain
Will the next flight to NY leave on time?
In many, many repetitions the proportion of specific outcomes is
Predictable
What proportion of flights to NY leave on time?
Randomness does NOT mean
Haphazard (disorganization)
SRS imposes …. chance of selection for each individual in the population
Equal
Sample space in probability is
The list of all possible outcomes of a random phenomen
Event in probability is a
Single outcome or a subset of outcomes from the sample space
Probability model is a
Mathematical description of a random phenomenon consisting of a sample space and a way of assigning probabilities to events.
Probability explains only what happens in the …. run
Long
If all probabilities are EQUALLY LIKELY, we need to count:
1.
2.
And that would be our probability
Count of outcomes in event of interest /
Over
Count of outcomes in sample space
Probability rule 1
Probability must be a number
Between 0 and 1
Probability rule 2:
The sum of probabilities from all
Possible outcomes must equal 1
Probability rule 3
If two events cannot occur simultaneously, …
The probability either one or the other occurs equals the sum of their probabilities
Probability rule 4:
The probability that an event does not occur equals
1 minus the probability that the event does occur
Disjoint Events
Two events that have no outcomes in common and, thus cannot both occur simultaneously.
“Playing the game” or simulation means
Looking at the phenomena many many times
Census
An examination of entire population
Census is time consuming, very expensive and often impractical. What is the alternative?
- Select SRS from population and compute x-bar(mean)
2. Make inference -
Parameter
Values that represent whole population. In statistical practice, the value is not known because we cannot examine the entire population.
Mean (mu), sigma and Proportion P
Parameter - mean
Mu - mean number of cigarets smoked per day by ALL teenagers
Parameter of population P
Proportion of ALL teenagers who used tobacco in the last 30 days
Statistic (think real world)
Values that come from a SAMPLE, statistics estimate parameters.
X-bar -sample mean
P-hat - sample proportion
Sample mean
X-bar
Mean number of cigarettes smoked per day in a SAMPLE of teenagers
Sample proportion
P- hat proportion of a SAMPLE of teenagers who used tobacco in the last 30 days
In inference we use …. to estimate ..,
Statistics to estimate parameter
Statistics
Mean -
Proportion -
Standard deviation -
X- bar
P- hat
S
Parameter
Mean
Proportion
Standard deviation
Mu
P
Sigma
What is statistical estimation?
Using sample statistics to estimate population parameter value
Parameter is the result summarized from the
Entire population
Statistic is any number result summarized from the
Sample
If the response variable is quantitative we analyze …
Mean x-bar
If the response variable is categorical we analyze …
Proportion p
Law of Large Numbers
IF …..
Then …
Draw observations at random from any population with finite mean mu. As the number of observations drawn increases, the mean x- bar of the observed values gets closer and closer to the mean mu of the population
The larger the sample size, the …. the sample mean is to the population mean
Closer
Sample statistic facts:
- Value of statistic…
- Value of statistic almost…
- Statistic approaches…
- Varies from sample to sample
- Always differs from parameter values
- Parameter value as sample size increases (the law of large numbers)
How do we investigate the behavior of statistic?
By examining the sampling distribution of statistic
Theoretical sampling distribution of x- bar is
The distribution of ALL x- bar values from ALL POSSIBLE SAMPLES of the same size from the same population
Theoretical sampling distribution of x- bar
- Take
- Compute
- Approximate
- Take many, many SRSs
- Compute x- bar for each
- Approximate the theoretical sampling distribution of x- bar
Approximate sampling distribution of x- bar is
The distribution of x- bar values obtained from repeatedly taking SRSs. Of the same size from the same population.
Approximate sampling distribution of x-bar can be modeled with …. curve
Normal
How to determine how accurate is the sample mean as an estimator of mu?
- Take…
- Construct…
- Note …
- Take many,many SRSs, compute x- bar for each sample
- Construct histogram of x-bars to display the approximate sampling distribution of x- bar
- Note center, spread and shape
Mean of all sampling distributions of x- bar =
Mean of population
As n increases, spread of sampling distribution of x- bar
decreases
As n increases, shape of sampling distribution of x- bar becomes
More normal
In sampling distributions
Center … to population center regardless of sample size
Equal or X- bar=mu
In sampling distributions as spread decreases n …
Increases
In sampling distributions the shape becomes ….. ……. as n increases
More normal
How well does x-bar estimate mu?
Quite well for large SRSs
Does x- bar vary about mu?
Yes
Probability is measured on 0 to 1 scale , where 0 is …. And 1 is….
0 impossible , never occur 0.01 unlikely but occur once in a while in a long run 0.45 slightly less often than not 0.50 half of the time 0.55 slightly greater than one- half 0.99 greater than one half but less 1 1 - certain, will occurs every time
Population distribution
The distribution of values of a variable among all individuals in the population
Sampling distribution
The distribution of values taken by a statistic in all possible samples of the same size from the same population