Term
| :A complete set of people, events, etc. that share a common characteristic. The scientific notation is (N). |
|
Definition
|
|
Term
| :A subset or subgroup that should be representative of the entire population. The scientific notation is (n). |
|
Definition
|
|
Term
| :The number that summarizes or describes a characteristic of a population. |
|
Definition
|
|
Term
| :the variable that is manipulated in an experiment to determine its effect on the dependent variable. |
|
Definition
|
|
Term
| :the variable that depends on the independent variable. This is often a measure of behavior or outcome. |
|
Definition
|
|
Term
| What are bar charts good at showing? |
|
Definition
| Counts or measures displayed in their categories. |
|
|
Term
| What are plot graphs good at showing? |
|
Definition
| Good for showing trends and relationships. |
|
|
Term
| What are scatterplots good at showing? |
|
Definition
| At showing raw data points. |
|
|
Term
| What are pie charts good at showing? |
|
Definition
| At visualizing proportions |
|
|
Term
| :the unit in which measurements are made. |
|
Definition
|
|
Term
| :the generic thing we measure |
|
Definition
|
|
Term
|
Definition
|
|
Term
| :the set of units we are interested in learning about |
|
Definition
|
|
Term
| :characteristic of an individual population unit that we are interested in learning about |
|
Definition
|
|
Term
| :subset of population observed that must be representative of the population. |
|
Definition
|
|
Term
| :generalization about a population based on sample data |
|
Definition
|
|
Term
| :statement about the uncertainty associated with a statistical inference |
|
Definition
|
|
Term
| :a statistic that compares a numerical description of two sets of data and the direction of the relationship. |
|
Definition
|
|
Term
| :a statistical method of predicting one set of values from another set of measured values |
|
Definition
|
|
Term
| :data type that has an absolute zero (zero means no value) |
|
Definition
|
|
Term
| :data type with a relative zero (zero has a value) - temperature |
|
Definition
|
|
Term
| What type of measurement classifies variables into different categories (grouping M&M colors together) and is used to ID only? |
|
Definition
|
|
Term
| What type of measurement is it when the amount of variable is placed in order of magnitude (Putting M&Ms in order of color preference). |
|
Definition
|
|
Term
| What type of measurement is a measurement where the differences between the scores are equal? |
|
Definition
|
|
Term
| What type of measurement is it when the measurement has a true zero point and an absence of that variable. |
|
Definition
|
|
Term
| What type of data is measurable or countable? |
|
Definition
|
|
Term
| What kind of data is used to grade or sort based on objective findings (grade breast cancer, sort sex, sort blood groups)? |
|
Definition
| Qualitative data or (Categorical data) |
|
|
Term
| A statistical __________ is the set of all possible values for the variable. |
|
Definition
|
|
Term
| :a subset of the population. |
|
Definition
|
|
Term
| :a sample in which each member of the population has an equal probability of entering the sample. Everyone has an equal chance to be chosen for the sample |
|
Definition
| SRS - simple random sample |
|
|
Term
| Type of error involving exclusion of a subset of the population of interest prior to sampling? |
|
Definition
|
|
Term
| Type of error introduced when responses are not obtained from all sample members? |
|
Definition
|
|
Term
| Type of error due to an inaccuracy in recorded data and can be due to survey design or interviewer impact? |
|
Definition
|
|
Term
| Type of error due to transcription error or data corruption? |
|
Definition
|
|
Term
| What are the 3 main aspects of a distribution of data? |
|
Definition
| SCS - Shape, Center and Spread |
|
|
Term
| Class intervals are ranges of score values which scores are grouped, what is the general rule of thumb for the range of how many intervals there should be? |
|
Definition
| There should be no fewer than 6 intervals and no more than 15. |
|
|
Term
| :a distribution that when folded in half, produces two identical shapes. |
|
Definition
|
|
Term
| :a distribution in which scores are clustered at one end, and rarity of scores (the tail) occur on the other end |
|
Definition
|
|
Term
| Skew direction if the tail (rare scores) occurs for the high scores to the right? |
|
Definition
|
|
Term
| Skew direction if the tail (rare scores) occurs for the low scores to the left? |
|
Definition
|
|
Term
| :tendency of data to center (mid point) about certain numerical values |
|
Definition
|
|
Term
| 3 commonly used measures of central tendency? |
|
Definition
|
|
Term
| :the sum of scores divided by the number of scores (average) |
|
Definition
|
|
Term
| :the score with an equal amount of scores above and below it (50th percentile or middle number) |
|
Definition
|
|
Term
:the score that occurs the most often
(can be unimodal, bimodal,or multimodal) |
|
Definition
|
|
Term
| How is the sample mean denoted? |
|
Definition
| a small x with a line over it |
|
|
Term
| How is the median denoted? |
|
Definition
|
|
Term
| :refers to the variety exhibited by a set of observations (If all values in a data set are the same, there is none. If the values are not all the same, there is some.) |
|
Definition
| Dispersion (AKA variation, variability, spread or scatter) |
|
|
Term
| What other terms are used synonymously with dispersion? |
|
Definition
| Variation, variability, spread or scatter. |
|
|
Term
| :the spread of the data across possible values |
|
Definition
|
|
Term
| What are 3 commonly used measures of variability? |
|
Definition
| Range, variance and standard deviation |
|
|
Term
| :Largest measurement minus the smallest measurement |
|
Definition
|
|
Term
| :Involves measuring dispersion relative to the scatter of values in a data set about their mean (better than range for describing the variety that exists among the values in a data set) |
|
Definition
|
|
Term
| :Useful as a measure of variation within a given set of data and is perhaps the most useful in determining variability when examining values in a data set by measuring dispersion in original units by taking the square root of the variance. |
|
Definition
|
|
Term
| How is variance and standard deviation noted for the sample and the population? |
|
Definition
Variance is little s (squared)
for sample and lower case sigma-σ (squared) for population. Standard deviation is lower case s for sample and lower case sigma-σ for population. |
|
|
Term
| :the square root of the sample variance. |
|
Definition
| Sample standard deviation |
|
|
Term
| :the square root of the population variance. |
|
Definition
| Population standard deviation |
|
|
Term
| What is the empirical rule for 1, 2, and 3 standard deviations of the population or sample. |
|
Definition
| 1 standard deviation should encompass 68% of the population/sample, 2 standard deviations should encompass 95% of the population/sample and 3 standard deviations should encompass 99.7% of the population/sample. |
|
|
Term
| :determines how many standard deviations an observation is above or below the mean and allows comparisons of observation from different normal distributions. |
|
Definition
|
|
Term
| 2 common measures that measure the relationship of a measurement to the rest of the data? |
|
Definition
| Percentile ranking/score and Z-score |
|
|
Term
| :the distance between a measurement x and the mean, expressed in standard units |
|
Definition
|
|
Term
| What are the 2 best detection methods for outliers? |
|
Definition
|
|
Term
| :diagram based on quartiles, values that divide the dataset into 4 groups (Lower Quartile, Middle Quartile, Upper Quartile and Interquartile Range) |
|
Definition
| Box plot (Box and whisker) |
|
|
Term
| What values are considered outliers for Z-scores? |
|
Definition
| scores of plus/minus 3 are considered outliers |
|
|
Term
| What is the best method for graphing the relationship between two quantitative variables? |
|
Definition
|
|
Term
| Every time you see a _______, someone has tested a hypothesis. |
|
Definition
|
|
Term
| :by chance the groups’ results were different |
|
Definition
|
|
Term
| :the two treatment arms really had different results |
|
Definition
|
|
Term
| :the two groups were chosen poorly and are different for reasons that have nothing to do with the treatment |
|
Definition
|
|
Term
| :the probability of obtaining by random sampling error (or chance) alone a result as extreme or more extreme than that obtained if the null hypothesis were true (could the observed differences between the groups be explained by sampling error or not). |
|
Definition
|
|
Term
| What is the null hypothesis? |
|
Definition
| An assumption that there is no difference between the two study groups. |
|
|
Term
| What is the alternate hypothesis? |
|
Definition
| What the study is trying to prove, that there is a difference between the two study groups. Can be one or two tailed (A could be preferred over B or vice versa) |
|
|
Term
| What is a two-tailed alternate hypothesis? |
|
Definition
| Alternate hypothesis that tries to disprove the null by saying that either A is better than B or that B is better than A but they are not the same(null). |
|
|
Term
| Is it more acceptable to use a one or two tailed alternative hypothesis? |
|
Definition
| Most authorities advocate a two-tailed approach unless there exists strong evidence that the one-tailed alternative hypothesis could not go in any other direction. |
|
|
Term
| If a result is unlikely due to chance it is said to be? |
|
Definition
| Statistically significant |
|
|
Term
| If a result is due to chance it is said to be? |
|
Definition
| Not statistically significant |
|
|
Term
| Where is the p-value most often set? What is this value known as? What does it mean if a p-value is higher than the set mark? |
|
Definition
| P values are most often set at 0.05 and is referred to as alpha. If a p-value is higher than 0.05 then the results of the study are not statistically significant enough to reject the null hypothesis. |
|
|
Term
| What type of error involves falsely rejecting the null hypothesis and accepting the alternative hypothesis? |
|
Definition
|
|
Term
| What type of error involves falsely failing to reject the null hypothesis or falsely failing to accept the alternative hypothesis? |
|
Definition
|
|
Term
| What 3 factors does the choice of statistical test depend on? |
|
Definition
| Type of data, distribution of data and type of study design. |
|
|
Term
| :significance tests for data from interval or ratio scales. |
|
Definition
|
|
Term
| :tests used to test hypotheses with nominal and ordinal data. |
|
Definition
|
|
Term
| Are parametric or nonparametric tests preferred? |
|
Definition
| Parametric are more powerful and are preferred. |
|
|
Term
| What are the advantages of nonparametric tests? |
|
Definition
| Easier to use than parametric, they are appropriate for non-normal population distributions, and they can be used with nominal and ordinal data. |
|
|
Term
| What are the 3 questions that you should ask when selecting a test? |
|
Definition
1. How many samples are involved?
2. Are the individual cases independent or related?
3. Is the measurement scale nominal, ordinal, interval or ratio? |
|
|
Term
| What are the indications for the parametric test (Z-score)? |
|
Definition
| large sample sizes (exceeding 30 for both independent samples) or with smaller samples when the data are normally distributed and population variances are known. |
|
|
Term
| What are the indications for the parametric test (t-score or t-test)? |
|
Definition
| t-test is appropriate when the population variances are not known but the population distribution is normal. |
|
|
Term
| What are the indications for the nonparametric test (Chi-square test)? |
|
Definition
| chi-square test is appropriate for situations in which a test for differences between samples is required. |
|
|
Term
| :measure of the differences between actual and expected frequencies between two categorical variables (nominal and ordinal measurements) |
|
Definition
|
|
Term
| :estimates the standard deviation of the difference between the measured values and the true values (how close is the sample mean to the population mean). |
|
Definition
|
|
Term
| Which test is used if you have interval or ratio data and the standard deviation of the population is known? If it is not known? |
|
Definition
| If it is known then you use a Z-test. If it is not known then you use a t-test. |
|
|
Term
| To test a sample of normal continuous data, we need? |
|
Definition
| expected value, observed mean, standard error and degrees of freedom. |
|
|
Term
| When testing a sample of normal continuous data, what does the expected value indicate? |
|
Definition
| the population or true mean |
|
|
Term
| When testing a sample of normal continuous data, what does the observed mean indicate? |
|
Definition
| the average of your sample |
|
|
Term
| When testing a sample of normal continuous data, what does the standard error indicate? |
|
Definition
| a measure of the spread, estimation of the standard deviation of the difference between the measured and the true values. |
|
|
Term
| When testing a sample of normal continuous data, how do you calculate the degrees of freedom? |
|
Definition
| the number of things in the sample minus 1. (n-1) |
|
|
Term
| Describe the Central Limit Theorem (CLT). |
|
Definition
| The theorem that the distribution of sample means taken from a large population approaches a normal (Gaussian) curve = perfect bell curve. The larger the sample the more you can arrive at the perfect curve. |
|
|
Term
| What is a sampling distribution of a mean? |
|
Definition
| When you take a sample of size “n” from a population and calculate its mean, then sample the same population again and calculate the mean, then sample it again and calculate the mean, and keep doing this many times...then graph all of the means on one curve. |
|
|
Term
| If a sampling distribution is Gaussian then it will follow what rule? |
|
Definition
| Empirical rule of standard deviation (68-95-99%) |
|
|
Term
| :a measure of the difference between your continuous data and what you expect to see, in units of standard error. Used when the standard deviation of the population is not known. |
|
Definition
|
|
Term
| :used to test the means of 3 or more groups of continuous, normally distributed data to see if they are all equal to one another |
|
Definition
| Analysis of variance of ANOVA |
|
|
Term
| How are categorical data usually tested? |
|
Definition
|
|
Term
| What does a large chi-square statistic indicate? |
|
Definition
| That the observed frequencies greatly differ from the expected frequencies. |
|
|
Term
| What is the chi-square test a part of? |
|
Definition
| Contingency table analysis |
|
|
Term
| How are the degrees of freedom for a chi-square test calculated? |
|
Definition
| (number of rows - 1) x (number of columns - 1) |
|
|
Term
| What is an important assumption of the ANOVA test? |
|
Definition
| All treatments have similar variance. |
|
|
Term
| What kind of data is used in ANOVA testing? |
|
Definition
| Categorical (Qualitative) or Continuous (Quantitative) |
|
|
Term
| What is the end result of an ANOVA test procedure? |
|
Definition
| an F-statistic that is used to calculate the p-value |
|
|
Term
| If the null hypothesis is rejected using an ANOVA study, what information is gained? What must you do to gain more information? |
|
Definition
| Only that at least two groups were different. Run an ANOVA (or t-test bc they are the same with only 2 groups) between each pair in the study to determine where the difference is. |
|
|
Term
| :when a relationship exists between two variables, the value of one variable can be predicted if the value of the other variable is known. What is this an example of? |
|
Definition
|
|
Term
| What does the magnitude of the slope in linear regression analysis indicate? |
|
Definition
| It represents the amount that the dependent variable changes for each unit change in the independent variable. |
|
|
Term
| How is the magnitude of the slope represented in a regression analysis? |
|
Definition
| the correlation coefficient (can be positive or negative). |
|
|
Term
| If a regression line correlation coefficient is positive, what will the relationship between the predicted and explanatory variable be? |
|
Definition
| If the slope is positive, the predicted variable increases as the explanatory variable increases |
|
|
Term
| If a regression line correlation coefficient is negative, what will the relationship between the predicted and explanatory variable be? |
|
Definition
| If the slope is negative, the predicted variable decreases as the explanatory variable increases |
|
|
Term
| What is the range for correlation coefficient? |
|
Definition
|
|
Term
| What correlation coefficient values indicate little or no relationship between the variables, fair degree of association, moderate degree of association and a strong degree of association? |
|
Definition
Little or no relationship = (0 to +/- 0.25).
Fair degree of association = (+/- 0.25 to +/- 0.50).
Moderate degree of association = (+/- 0.50 to +/- 0.75).
Strong degree of association = (+/- 0.75 to +/- 1.0). |
|
|
Term
| :validity that refers to generalizability of the results obtained from the study |
|
Definition
|
|
Term
| :validity that refers to methodology utilized in the study |
|
Definition
|
|
Term
| What are the three general categories of threats to internal validity? |
|
Definition
| Chance, Bias and Confounding variables |
|
|
Term
| :“Any systematic error in design, conduct or analysis of a study that results in a mistaken estimate of an exposure’s effect on the risk of disease”. |
|
Definition
| Definition of Bias according to our book, Gordis. |
|
|
Term
| :kind of bias resulting from misclassifying exposure or outcome status (predicted variable) |
|
Definition
|
|
Term
| :misclassification that occurs in the same proportion in each group being studied |
|
Definition
| Random (nondifferential) misclassification |
|
|
Term
| :misclassification that occurs in different proportions in each group |
|
Definition
| Non-random (differential) misclassification |
|
|
Term
:bias that occurs when one group is followed more closely than the other group.
Would this result in random or non-random misclassification? |
|
Definition
| Surveillance or detection bias. Would result in non-random misclassification. |
|
|
Term
:bias that may result due to a potentially relevant exposure that may be remembered by a “case” and be forgotten by a “control”.
What type of missclassification is this an example of? |
|
Definition
| Recall bias. It is an example of non-random misclassification. |
|
|
Term
| :bias that may result as subjects may not be willing to report an exposure accurately |
|
Definition
|
|
Term
:bias that result if data collection methods differ between groups.
What type of misclassification is this? |
|
Definition
| Interviewer bias. This is non-random misclassification. |
|
|
Term
| :bias occuring due to the way in which cases and controls, or exposed and non-exposed individuals, are selected is such that an apparent association is observed even when in reality, the exposure and the disease is not associated |
|
Definition
|
|
Term
| :bias occuring when there is a third factor between a variable and the exposure status that is an independent risk factor for the outcome but is not taken into account for the study. |
|
Definition
| Confounding variable/bias |
|
|
Term
| What is the major threat to external validity? Does this invalidate the study results? |
|
Definition
| Interaction or Effect Modification. It does not invalidate the study results, it just needs to be identified. |
|
|
Term
| What are the differences between Confounding variables and Effect Modification/Interaction? |
|
Definition
| Confounding variables need to be eliminated and Effect Modification just needs to be described and reported. |
|
|
Term
| How is the correlation coefficient notated? |
|
Definition
|
|
Term
| Describe the independent variable. What are some other names for it? |
|
Definition
| Independent variables are the variables that the study designer want to examine where typically one group has the independent variable and the other does not. Other names include: factor variable, explanatory variable and exposure variable. |
|
|
Term
| Describe the dependent variable. What are some other names used for the dependent variable? |
|
Definition
| Dependent variable is what the study designer wishes to observe as an outcome, possibly due to the independent variable. Other names include: Predicted variable and outcome variable. |
|
|
Term
| What is quantitative data? |
|
Definition
| They are measures that occur on a natural scale and include ratio and interval data. |
|
|
Term
| What is qualitative data? |
|
Definition
| It is categorical data that is measures by classification only and examples are ordinal and nominal data. |
|
|
Term
| Which test would you do if you have one sample and the data is continuous? |
|
Definition
|
|
Term
| Which test would you do if you have two samples and the data is continuous? |
|
Definition
|
|
Term
| Which test would you do if you have paired data and it is continuous? |
|
Definition
|
|
Term
| Which test would you do if you have three or more samples and the data is continuous? |
|
Definition
|
|
Term
| What type of error results from Random misclassification? |
|
Definition
| Type II or Beta error bc it makes you accept the null hypothesis even if it is false. |
|
|
Term
| What type of error results from Non-random missclassification? |
|
Definition
| It can be either a Type I or a Type II error. |
|
|
Term
| After deriving the null and alternative hypotheses from your research question, describe the next steps in statistical analysis. |
|
Definition
| Set alpha, Generate your statistics, compare your statistics to known distributions to find your p-value, and reject or fail to reject the null. |
|
|
Term
| Describe Chebyshev's rule of 3 standard deviations. |
|
Definition
1 = No useful info.
2 = At least 75%
3 = At least 8/9. |
|
|
Term
| How do you calculate class relative frequency? |
|
Definition
|
|
Term
| How do you calculate class percentage? |
|
Definition
| class relative frequency x 100 |
|
|
