Sample size and measurements accuracy

-
Seems obvious that larger sample size will give more close results to what happens in realty. Cool, if it's easy to select large elements to represent the sample, then we should do. Usually a sample of size 30 to 40 elements is great to have.

We should increase the sample size whenever we:
  • Can easily handle/select sample items (randomly).
  • Perform the measurement with little effort/time consumption.
Notice these are highly dependent on the problem or population nature and situations. Another point to keep is to have accurate measurements for the sample as possible.

In conclusion, two important factors should be regarded:
  • Good sample size as large as possible. This guarantees more information diversity is included in our sample. Thus it's more close to describe the whole population facts.
  •  Using accurate measuring tools/equipment when measuring the required property of the sample because these measurements will judge next steps. This requirement becomes more critical in small sample sizes.


Comments

Post a Comment

Popular posts from this blog

The "Sample"

-
Image
Anytime you aim to perform a study on the entire population, you will surely find that this task will be: Much time and/or efforts consuming as populations are normally huge . Impossible if the population is infinite (such as products). Here comes the role of taking samples. Yes! we just take a sample from the whole population, perform the study on the chosen sample, apply the results back to our population. This is the core of  inferential statistics because what we do is to infer parameters/properties of the population using information from a small sample. Well, this does not mean we will obtain 100% exact accurate estimations or inferences. But to be as close as possible, sample elements should be taken randomly ! At least, being random in sample selection will mostly include the diversity of information/facts within our population.
Read more

Understanding the distribution of sample mean (x_bar)

-
Image
Cool, say now we have a huge population with characteristics ( Mu, Sigma^2 ). When doing a study by sampling, we take a random sample ( size n items ) and then perform the study on the sample and conclude results back for the population. From Central Limit Theorem, we know that the sample mean will always follow a normal distribution  apart from what the population distribution is, such that: x_bar ~ N (Mu, Sigma^2/n) or say: Expected (x_bar) = Mu Variance (x_bar) = Sigma^2/n Well, let's see a simple illustrating example: Suppose we have a population with mean Mu=100 . Now, we have taken a sample, and computed the sample mean, x_bar. We mostly will have x_bar near 100 but not exactly 100. OK, let take another 9 separate samples... suppose these results: First sample --> x_bar = 99.8 Second sample --> x_bar = 100.1 .. .. .. 10th sample --> x_bar = 100.3 What we see that the sample mean is usually...
Read more

Conclusions of Hypothesis Testing

-
Image
A general hypothesis is defined as following (eg a hypothesis on the population mean): H0: Mu = Mu0 H1: Mu !=  Mu0 OK, apart from we have a two or one sided hypothesis, after performing the checking and statistical tests: our conclusion should be one of the following: Rejecting the null hypothesis (H0). Failing to reject the null hypothesis (H0). The following statements for conclusions are not accurate : Accepting the null hypothesis (H0). Accepting the alternative hypothesis (H1). But why? When we fail to reject H0, it does not mean we accept H0 as a fact because we still could not prove it as a fact. But what happened is that we failed to prove it to be false. This goes like following: we have suspected new factors may affected the population mean, then we have taken all possible evidences and checking, but all checking failed to prove our suspects. As well, rejecting H0 does not mean accepting H1 as a fact....
Read more