Reputation
563
Top tag
Next privilege 1,000 Rep.
Create new tags
Badges
1 5 15
Newest
 Custodian
Impact
~27k people reached

  • 0 posts edited
  • 0 helpful flags
  • 134 votes cast
Jul
11
comment How to calculate CI for percentage difference?
the percentage increase was normally distributed so I figure it is safe to use the standard T-test. Good to know that this isn't a huge violation of statistics.
Jul
11
comment How to calculate CI for percentage difference?
Thanks very much Bruce, very helpful.
Jul
3
comment Two different samples from different time periods.
@RossMillikan, I'm not assuming normal distribution. I just calculated mean by adding up numbers and dividing by n. I calculated standard devation by finding average distance between squares of numbers. I haven't made any assumptions about the distribution though.
Jul
3
comment Two different samples from different time periods.
@Feyre, does credibility theory apply here?en.wikipedia.org/wiki/Credibility_theory
Jul
3
comment Two different samples from different time periods.
@Feyre, just a thought experiment I invented myself. I welcome the most technical answers.
Jul
3
comment Two different samples from different time periods.
For the sake of simplicity, I want to assume that all conditions are the same for the students, except the period of time is separated by 1 year. Now I agree the samples are statistically different, but the 1st sample had a much greater sample size, and thus might still have some weight on my future prediction, as the most recent sample could be an anomoly.
Jun
14
comment Probability of tossing 16 coins.
Because the results in (a) aren't significantly different from 0.5 (expected for a coin), it seems they have used 0.5 as the probability in calculating b. Remember the probability of tails isn't 0.4625, but rather this is your estimate of the probability. Most likely the probability is still just 0.5 (can confirm with confidence intervals, p values etc.)
Jun
14
comment What are some simple (or elegant) functions that satisfy these conditions?
@Crostul, that looks good - how can I adjust how "flat" it is?
Apr
21
comment Distribution Function Of a Random Variable X - Question
@SuperRhinocerus, what are you studying?
Apr
20
comment A store is offering a 20% discount on a certain item. The store’s sale of the item is subject to a 6% sales tax.
no problem glad to have helped :)
Apr
20
comment A store is offering a 20% discount on a certain item. The store’s sale of the item is subject to a 6% sales tax.
correct, the pure tax component itself is 0.06*0.8x, and thus the total amount including tax is 1.06*0.8x, whereas scenario 1 is 0.8*1.06x, which is equal.
Apr
18
comment Find the height of statue.
@ClaudeLeibovici, yes my assumption was that the height of the observer was insignificant compared to the height of the tower, however without knowing the angles X and Y the validity of this assumption is still in the dark.
Apr
18
comment Derivation with respect to a derivative
Velocity often doesn't depend on position. E.g. if velocity = 4km/hr, you don't need to know the position in space to work out the velocity. But in general it depends on the nature of x(t) whether it is dependent on position or not. E.g. acceleration due to gravity is dependent on position, and thus you would have to apply the chain rule when differentiating.
Apr
18
comment Deriving a formula for a confidence interval
I think you should have a plus sign in the numerator of your pooled variance normally. Consider looking at the Welch t test when variances are not assumed to be equal.
Apr
18
comment Deriving a formula for a confidence interval
What are you studying?
Apr
17
comment Easy proof of Black-Scholes option pricing formula
It's kind of intuitive don't you think?
Apr
17
comment Find distance between two poles.
How is tan(ACB) = AB/BC. The angle ACB is not even part of a right angle triangle given the way you have described the situation.
Apr
17
comment Is it valid to get a correlation between moving averages?
I think it is fine to use the moving average, as while each day data point will be used 10 times, each moving average data point only counts 1/10th of this, and effectively with a large data set the moving average should yield the same correlation as a day by day analysis. I say a large data set because the first 9 data points won't be counted a full 10 times, nor the last 9 data points, so provided you have much more than 18 moving average data points you should be ok.
Apr
17
comment How sample size affects confidence interval.
In this example, sigma is the population standard deviation, and thus is independent of sample size. So your answer is correct. Technically however your working should be 1.96sigma/sqrt(n) is the margin error, but the 1.96 cancels out anyway.
Apr
17
comment Simple interest problem
@Al.Ka, my belief is that the best way to teach is by direct instruction. If a student sees enough well worked examples, they will learn to emulate that over time.