I know that the size of a sample is inversely proportional to the width of a confidence interval, and that outliers tend to increase the width of the interval as well. So that must mean that increasing the sample size reduces the effect of outliers on a confidence interval, and decreasing the sample size amplifies the effect, correct? How can I show this using formulae instead of words for, say a confidence interval for a one-sample z-test?

Elisabeth Wiley 2022-08-13 Answered
The effect of changing sample sizes on outliers
I know that the size of a sample is inversely proportional to the width of a confidence interval, and that outliers tend to increase the width of the interval as well. So that must mean that increasing the sample size reduces the effect of outliers on a confidence interval, and decreasing the sample size amplifies the effect, correct?
How can I show this using formulae instead of words for, say a confidence interval for a one-sample z-test?
Also as a side note, does changing the sample size change how outliers affect the p-value of a hypothesis test? I'm inclined to say yes, but I'm not sure how to justify that conclusion.
You can still ask an expert for help

Expert Community at Your Service

  • Live experts 24/7
  • Questions are typically answered in as fast as 30 minutes
  • Personalized clear answers
Learn more

Solve your problem for the price of one coffee

  • Available 24/7
  • Math expert for every subject
  • Pay only if we can solve it
Ask Question

Answers (1)

kunstboom8w
Answered 2022-08-14 Author has 8 answers
Step 1
(1) The width of a z CI for normal μ when σ is known is inversely proportional to n ,, not n. Because σ is known, the sample SD S plays no role in the width of the CI. [If you are talking about unknown σ and t CI's, then the width depends on n, the appropriate quantile of t for df n 1, and the size of the sample SD (a random variable).]
Step 2
(2) If data are normal, there may be outliers. Normal tails go out to ± even though the probability of extreme values beyond μ ± 3 σ are rare. After a certain point, as the sample size increases, so does the likelihood of getting an outlier. (Boxplots are not really intended for use with samples with very small n, and so I'm talking about n 15 or so. The definition of 'quartile' is a bit sketchy in a sample of size 5, or 11.)
Step 3
(3) I do not know of any 'formula' that directly links (1) and (2), mostly because I know of no formula for the numbers of outliers. I have seen simulation studies that show the results, but outliers depend on the quartiles and their distributions with increasing n are a bit messy.
Step 4
(4) Here are simulations that estimate the average numbers of outliers per sample in normal samples of various sizes n = 20, n = 50 ,, and n = 100. By averaging outliers in many samples of each size, one can approximate the expected number of outliers. Results for expected numbers of outliers per sample are about 0.33, 0.58, and 0.92, respectively.
Step 5
While many extreme outliers may be a signal that a sample is not from a normal distribution, we see from these simulations that there is nothing 'abnormal' about getting some outliers in a normal sample. About a quarter of samples of size 20 have them and a normal sample of size 100 is more likely to have some outliers than not. The values from t tables that are used to make t CIs (when σ is estimated by S) allow for the effect of such inherently normal outliers.
Not exactly what you’re looking for?
Ask My Question

Expert Community at Your Service

  • Live experts 24/7
  • Questions are typically answered in as fast as 30 minutes
  • Personalized clear answers
Learn more

You might be interested in

asked 2022-07-19
Is a horizontal line an increasing or decreasing function?
This is the definition of an increasing and decreasing function.
"A function f(x) increases on an interval I if f ( b ) f ( a ) b > a, where a , b I. If f ( b ) > f ( a ) b > a, the function is said to be strictly increasing.
Conversely, A function f(x) decreases on an interval I if f ( b ) f ( a ) b > a, where a , b I. If f ( b ) < f ( a ) b > a, the function is said to be strictly decreasing.
Then how would a horizontal line be described? If f ( x 2 ) = f ( x 1 ) x 2 > x 1 does that mean that a horizontal line meets the definition of an increasing function and a decreasing function?
asked 2022-08-12
Question about strictly increasing and continuous functions on an interval
If F , φ : [ a , b ] R with F continuous, φ strictly increasing and ( F + φ ) ( a ) > ( F + φ ) ( b ) is F + φ decreasing on some interval in (a,b)?
This is clearly true if φ has finitely many points of discontinuity in the interval but I am unsure if this statement is true if there are infinitely many points of discontinuity.
asked 2022-08-19
A polynomial P(x) of degree 5 with lead coefficient one,increases in the ( , 1 ) and ( 3 , ) and decreases in the interval (1,3)
A polynomial function P(x) of degree 5 with leading coefficient one,increases in the interval ( , 1 ) and ( 3 , ) and decreases in the interval (1,3). Given that P ( 0 ) = 4 and P ( 2 ) = 0, find the value of P'(6).
I noticed that 1,2,3 are the roots of the polynomial P′(x).P′(x) is a fourth degree polynomial. So
Let P ( x ) = ( x 1 ) ( x 2 ) ( x 3 ) ( a x + b ).
Now I expanded P′(x) and integrated it to get P(x) and use the given condition P ( 0 ) = 4, but I am not able to calculate a, b.
asked 2022-09-20
Let f ( x ) = ln ( x ) x . Find the critical values of f(x)
How would you find the critical value of this equation? So far... I have gotten that you find the derivative of f(x) which is f ( x ) = 1 x 3 / 2 ln ( x ) 2 x 3 / 2 ..
To find the critical values set f ( x ) = 0? But how would you factor out the derivative to find the critical values?
Also, after that how would you find the intervals of increase and decrease and relative extreme values of f(x).
And lastly the intervals of concavity and inflection points.
asked 2022-07-25
Find the percent of increase.
Original price:$4
New price:$4.50
asked 2022-08-11
Find the Intervals of Increase or Decrease, the concavity, and point of inflection for: f ( x ) = ( 1 x ) e x .
f ( x ) = ( 1 x ) e x = 1 x e x
Quotient Rule:
f ( x ) = e x [ 1 x ] ( 1 x ) [ e x ] = e x ( 2 + x )
What do I do now? Take the derivative again?
asked 2022-08-12
Sketch f ( x ) = sin x + 1 x finding local maxima and minima, intervals of increase and decrease. I'm trying to use differentiation to draw this picture and find critical points.
So, I get f ( x ) = cos x 1 x 2 . However, I'll have to deal with inequality f ( x ) > 0, and f ( x ) = 0, I feel I lack an ability to solve an equation like this. So is there any better way to find local maximun and minumum for this function?