Statistics Flashcards
(28 cards)
What is Student’s T- test?
Test that compares and determines the significance of 2 mean values.
What is the set of pre-determined values called?
Critical value table
What is the equation for DF
DF = (n1+n2)-1
N is the number of samples in each mean data set.
What does the critical values tell us in T test
The probability that the difference between means is due to chance
What does a percentage 5% or less tell us
it is a significant difference
What can we state if the number is greater than or equal to the critical value for t test?
- The probability
- That the difference between means
- Is due to chance
- Is less than or equal to X%
What is the structure of an answer for studen’ts t test when comparing means.
- On average there are more….
- The probability that the difference between means is due to chance is less than or equal to X%
- Therefore the difference is highly significant
- On average there are more….
- The probablity that the difference between means is due to chance is greater than X%
- Therefore there is no significant difference between the mean number of … vs…
What is spearmans rank correlation coefficient
Determine the probability that the correlation is due to chance and therefore its signficant.
If the stat is greater or equal than te critical value table what can we say in PRCC
- The probability that the correlation is due to chance is less than or equal to x%
What can we conclude about a table with height and mass which present a perfect linear graph
- There is a very strong positive correlation between the height and mass of daisies
- The probability that the correlation is due to chance is equal to 2%
- Therefore the correlation is highly significant
If other factors may be involved in SRCC what canw e say
correlation does not equal causation
What is Chi-squared
comparing observed frequencies of categoric daa against what would be expected.
If what is observed is significantly different to what is expected what can wwe conclude
it is dodgy
Equation for X2
DF = n-1
If the stat is more than or equal to the CVC for X2 what can we say
The probability that the difference between O and E is due to chance is less than or equal to X%
What can we conclude for X2 stat test for heads and tails
- The results show that heads was observed 49 tmes out of an expected 50
- Therefore the probability that the differencde between what was observed vs what was expected is due to chance is greater than 5%
- Therefore is no signficiatn difference between the obrsebed and expected number of head
- This is not a dodgy coin
What is the overall layout on how you would structure your answer
- This statistical test value exceeds the critical value
- Therefore they can reject/accept the null hypothesis
- Because the probability that X is due to chance is less than 5%
- Therefore the difference between x?corellation is significant
- State that hypothesis is correct
How can we describe Stat Tests
- Construct null hypothesis
- Carry out (stat test) to find correlation coefficient
- Use critical value table to show P is less than or equal to 0.05( less than 5% prob that corellation are due to chance
- Use critical value table figure o reject or accept the null hypothesis
How can we calculate the expected no of organisms in Chi2
- Total observed divided by no of categories
What is uncertainty
half the resolution of the measuring instrument
If a balance weighs to the nearest 10 g and the mass of an object is 80 what is the absolute uncertainty
80 +- 5g
What is a reading
value found from an instrument using a single judgement e.g balance thermometer
What are measurments
a value taken using two judgements e.g ruler, potractor
How to calculate percentage uncertainty
% UC = absolute UN divided by value x 100
