Probability And Statistical Significance (Epi)

Front 1

What are the two types of random error?

Back 1

Random error: Due to Change
-the result of fluctuations around a true value beacuse of sampling or measureing variability
does not bias a study

Systemic Error: due to bias
error is one that is inherent to the study method being used and results in a predictable and repeatable error for each observation - caused not by chance

Front 2

What are tests of statistical inference?

Back 2

estimate the likelihood that a study results was caused by chance
-significant if it is unlikely to have occurred by chance

Statically significant does not mean important or meaningful

Front 3

Whatis chance occurance?

Back 3

something that happens unpredictably without discernible human intention or without any observable cause: caused by chance or random variation

-random variation - error in every measurement
-statistical inference - how sure are we that our measurement is close to the true value and not an extreme if only measured once

Front 4

What are two methods for estimating how close out measurement is to the true value?

Back 4

Confidence interval

P-values
--used to estimate whether the measure was likely to have been caused by chance or not

Front 5

What is a confidence interval?

Back 5

- tells us the range the true value of a measurement is likely to be found
-for some measure it can estimate whether the measure was likely to have been caused by chance
-can tell us something about the size of the sample

95% confident that the true value of our measurement can be found

Front 6

What are P-values?

Back 6

-used to estimate whether the measure was likely to have been caused by chance or not

measure association is considered to be statistically significant if it is greater that 95% of the values from many samples from the hypothetical distribution

Front 7

What is a null hypothesis? (H0)

Back 7

the hypothesis of no association

there is no association between exposure and disease

we use p values to accept or reject the Null Hypothesis

Front 8

What is an alternative hypothesis (Ha)

Back 8

The research question

there is an association between exposure and disease

Front 9

If p-value is less than .05?

Back 9

reject the null hypothesis and accept the alternative hypothesis

Front 10

if the p-value is greater than .05?

Back 10

accept the null hypothesis and reject the alternative hypothesis

Front 11

What is a type I error?

Back 11

Rejecting the null when it is not false (no association exits)

conventionally set at .05 (p = .o5, 95%Cl)

Saying there is an association when there isn't

Front 12

What is a type II error?

Back 12

not rejecting the null when it is false (an association truthfully exists)

conventionally set at .20

saying there is no association where there is

Front 13

What are measures of central tendency?

Back 13

mean - some of all values/ number of data points, very sensitive to extreme values

Median - the values which is in the center, with half of the data points "below" and half of the data points "above"
-less affected by extreme values

Mode - most frequently occurring value

Front 14

What is dispersion?

Back 14

describes how closely the values are gathered around the center of the distribution

Measure of dispersion
-range - the difference between the min and max
--standard deviation - a measure of the distance between each measurement and the mean

Front 15

What are the commonly used statistical test?

Back 15

chi-squared test: difference in proportions - used for category data

student's t-test - difference in means
-compare the average of two populations, used for continuous data

Correlation - strength of linear relationship
-dose response curves