Lecture 5 Chapter 5 Selecting and Interpreting Inferential Statistics Flashcards
If the P value is less than or equal to the alpha value then you ______ the null hypothesis?
Reject
If the P value is less than the alpha value then you ______ the null hypothesis?
Fail to reject the null or accept the null
What does the p value indicate?
The percent of how much of your results are due to coincidence/randomness
What do we use to decide whether to accept or reject the null hypothesis? Two things?
P-value
Alpha Level
What is a type 1 error ?
rejecting a true null hypothesis (when p value is greater than Alpha)
What is a type 2 error?
-Accepting a false when it is statistically significant
-Accepting null hypothesis when we shouldn’t
Why are type 1 and 2 errors related?
As the probability of making a Type I error increases, the probability of making a Type II error decreases, and vice-versa
What value determines the probability of making a Type I error?
Alpha
If the alpha is set at 0.01, the researcher how likely to commit Type I errors?
1% of the time
If the alpha is set at 0.05, the researcher how likely to commit Type I errors?
5% of the time
If the alpha is set at 0.10, the researcher how likely to commit Type I errors
10% of the time
Researchers don’t like making _____ errors, so they tend to have very low alpha values
Type 1 errors
The alpha level describes the_________researchers place in their research results
level of confidence
What are the three steps to seeing if you have a statistically significant results?
ASSOCIATION QUESTION
1) First, determine if you have a statistically significant association (by comparing the computed p-value to the selected alpha-level)
2) Second, determine the effect size of the association (see Table 5.5).
3) Third, determine the direction of the association using the sign in front of the correlation coefficients.
What are the three steps to seeing if you have a statistically significant results?
DIFFERENCE QUESTION
1) First, determine if you have a statistically significant difference (by comparing the computed p-value to the selected alpha-level)
2) Second, determine the direction of the difference or the direction of effect (by identifying the group with the highest mean or mean rank or frequency)
3) Examine the clinical or practical significance of the difference
What are the upper and lower limits when we reject the null hypothesis?
both positive
both negative
What are the upper and lower limits when we fail to reject the null hypothesis?
One negative and one positive
When Levene’s test is significant do we assume equal variance or do not assume equal variance?
When Levene’s test is significant we do not assume equality of variance
When Levene’s test is NOT significant do we assume equal variance or do not assume equal variance?
A non-significant p value of levene’s test show that the variances are indeed equal and there is no difference in variances of both groups
TRUE/FALSE
The larger the sample, the more likely the results will be statistically
significant
True
Any association or difference can be statistically significant if sample sizes are ______
Large enough
The bigger the _______ it is less likely our research results would be due to chance
sample
What does statistical power give us? Three things
-Ability to reject the null hypothesis when we really should
* Ability to find a true difference or association that actually exists
* Ability to claim we have statistically significant results
How do we increase power?
two options
Have a low alpha value
Have a large sample size
Statistical Significance does mean real-life importance?
true/false
False
Real-life importance of statistical results is referred to as______
Practical or
Clinical Significance
If a result is practically important, it means that?
There is real life significants
Determining whether a statistically significant research result has practical or clinical importance in real-life is?
Subjective
Statistical significance ______ or imply clinical or practical significance!
does or does not
does not
How to determine the practical or clinical significance of a statistical test result?
Because statistical significance doesn’t imply clinical or practical significance, some researchers use effect sizes to determine practical significance of their results
How does effect size direction work for differences questions ?
Compare group means (for a scale DV) or the mean ranks (for an ordinal DV) or the frequencies (for a nominal DV)Which group did “better”?
When you are calculating effect size direction for difference questions what do you compare in scale data?
Means
When you are calculating effect size direction for difference questions what do you compare in ordinal data?
Mean Ranks
When you are calculating effect size direction for difference questions what do you compare in nominal data?
Which group did better
Effect size is defined?
as the strength of the relationship between the independent variable and the dependent variable,
What is effect direction?
the directions of the results
EXAMPLE:
as eating candy goes up so does cavities
What is cross-tabulation?
A two- (or more) dimensional table that records the number (frequency) of respondents that have the specific characteristics described in the cells of the table.