# Epidemiology - Block 3 and Final

rename
davidwurbel7's
version from
2015-07-27 03:36

## Biostatistics

Question | Answer |
---|---|

The midpoints of the top of each bar of the histogram are plotted and connected with straight lines | Frequency Polygon |

Skewed curve with the tail to the right | Positively Skewed |

Skewed curve with the tail to the left | Negatively Skewed |

Average of the squared differences from the mean | Variance |

Square root of the variance; summary of dispersion around the mean | Standard Deviation |

Observations are widely spread out | Large SD |

Observations are closely centered around mean | Small SD |

68% values are within | 1 SD |

95% values are within | 2 SD |

99.7% values are within | 3 SD |

Mean + - 2SD | Normal Range |

One standard deviation from the mean in each direction | 34% |

One standard deviation from the first deviation | 13.5% |

One standard deviation from the second deviation | 2.35% |

One standard deviation from the third deviation | 0.15% |

Standard deviation percentages cannot be apply to a study that has this type of distribution | Multi-Modal Distribution |

SD / square root (n) | Standard Error of the Mean |

Specifies how close our sample based value lies to the population value and it gives the range of these values | Confidence Interval |

Mean(x) +- confidence coeff x Standard Error Mean | Confidence Interval |

Is a score for normal distribution = confidence coefficient = standard score | Z Score |

(x – mean) / SD | Z Score |

Shows variability of observations | Standard Deviation |

Shows variability of sample means about the true population mean | Standard Error of the Mean |

Is the range of values for the population mean in which you are 95% sure the true population mean falls | 95% Confidence Interval |

Whole number count | Discrete |

Includes fractional numbers | Continuous |

Characteristics of groups can be compared by comparing proportions | Chi-Square |

Characteristics of groups can be compared by comparing mean | T-Test |

States there is no difference between characteristics of groups or outcomes | Null Hypothesis (H0) |

States that there is a difference between characteristics of groups or outcomes | Alternative Hypothesis (Ha) |

When the data is interval/ratio, or if samples are different (when you are comparing “Means (averages)” between groups). If you only have 2 groups | T-Test |

When the data is interval/ratio, or if samples are different (when you are comparing “Means (averages)” between groups). If you have more than 2 groups | ANOVA |

Two groups of subjects are sampled on one occasion | Independent (non paired) T- Test |

The sample people are sampled on two occasions | Dependent (paired) T-Test |

Rejecting null hypothesis when the null hypothesis is true | Type I Error (α error) |

Accepting null hypothesis when the null hypothesis is false | Type II Error (β error) |

Calculated by 1 - β | Power of the Test |

A way to increase the power of a test is to do this | Increase Sample Size |

## Outbreak Investigation

Question | Answer |
---|---|

The occurrence of cases of an illness in excess of expectancy | Outbreak/Epidemic |

Spike in the number of cases over a period of time that eventually decrease and stop | Point Source Outbreak |

Increase in the number of cases that continue to increase over time | Person-Person Outbreak |

Number of cases continue to rise and fall over time until the source is removed | Continuous Source Outbreak |

Data collection

Generate hypothesis about pathogen, route of transmission, Vector/vehicle

Analytical epidemiology

Environmental inspection

Control Measures - Remove source and protect persons at risk

Is further investigation necessary

Preventive Measures

Communication

During the outbreak

Information for the public and the media

Information for professionals

Regular and consistent updates

After the end of the investigation

Produce a report for officials, parties involved, general public, media

Write up for scientific publication

Maintain surveillance

## Additional

Question | Answer |
---|---|

The number of patients you need to treat to prevent one additional bad outcome | Number Needed to Treat (NNT) |

1/Absolute Risk Reduction (ARR) | Number Needed to Treat (NNT) |

CER (Control Event Rate) – EER (Experimental Event Rate) | Absolute Risk Reduction (ARR) |

1/ Absolute risk increase (ARI) | Number Needed to Harm (NNH) |

Experimental event rate (EER) – control event rate (CER) | Absolute Risk Increase (ARI) |

Ratio of the number of likely outcomes to the number of possible outcomes | Clinical Probability |

Probability states that the probability of two or more independent events occurring at same time | Multiplication Rule |

Probability of any one of several particular events occurring is equal to the sum of their individual probabilities, provided the events are mutually exclusive | Addition Rule |

## Recent badges

## Pages linking here (main versions and versions by same user)

No other pages link to this page. See Linking Quickstart for more info.