Inferential statistics Flashcards
What are inferential statistics?
make inferences about the population based on the samples tested
-The tests allow us to infer that a pattern in the data is likely to be due to chance so the hypothesis can be accepted and rejected
What are the 4 levels of measurments?
-Nominal
-Ordinal
-Interval
-Ratio
What is step one of inferential statistics
Look if the data is nominal or ordinal + (ordinal, interval and ratio)
What is step 2 of inferential statistics?
If the reaserchh is correlation or difference
What is a difference in inferential statistics?
A test for difference means that changes in one variable brings out another
A cause and effect relationship between variables
What is correlation in inferential statistics?
Relationship between variables isn’t always due to casual link
What design was used in your research?
-Independent measures- independant data
-Repeated measures- Related
-Repeated measures- Related
How do we use the correct test- Acronym
I- Independant data (independent measures)
Really- Related data (Repeated measures/ matched pairs)
Could- Correlation
Not- Nominal Data
Calculate- Chi-squared test
Sums- Sign test
On- Ordinal data
Monday- Mann Whitney U test
Without- Wilcoxon
Smiling- Spearman’s rho
Test table?
Indene Related Correl
-ndant Data ation
data MP
IM RM
Nom Chi Sign
ial squared test
Data test
Ordi Mann Wilcoxon
nal Whitney Spea
Data U test rman
Rho
What is probability expressed as?
P
What do you do after the inferential test is carried out?
decide if we reject or accept the hypothesis to do this we determine the probability level
What is the standard probability?
0.05
What’s the stringent level of probability?
In medical research
Used because results will be down to chance is 1% or less
What should a good scientific theory be?
Falsifiable, its ability to be proven wrong or right
What should we do once we have inferential test findings?
if its significant (not due to chance)
Or if its non significant (due to chance)
What should we do with hypothesis if findings are significant?
Accepting the alternative and reject the null hypothesis
What should we do with hypothesis if findings are non-significant?
Accept the null and reject the alternative
How do we find if findings are significant and non signifant?
By comparing our observed (calculated) value with our critical values
In some tests the calculated/observed value must be equal to or less then critical value. Or observed must be more or equal to critical value
-Those with R in the name are more than
Spearman’s rho rules for significance?
Observed values must be equal to or greater than critical value to be signifinces
Chi squared test rules for significance?
Observed value of X>2 must be equal to or greater than critical value shown
Sign test rule for significance?
Observed value must be equal to or less than critical value
Wilcoxon test rule for significance?
Observed value must be equal to or less than critical value
Mann-Whitney U test rule for significance?
Observed value must be equal to or less than critical value
Whats a significance level?
A numerical value that is usually expressed in value including two decimal
places. This level tells you the margin of error that could occur in your
results and shows the probability of rejecting the null hypothesis
