Descriptive and Inferential Statistics: Understanding Data Analysis, Exams of Advanced Education

Download Descriptive and Inferential Statistics: Understanding Data Analysis and more Exams Advanced Education in PDF only on Docsity!

PH 490 test 3 complete questions and answers

Descriptive statistics - -used to describe basic features of data -provide simple summaries -allow you to present quantitative data in a manageable form -run the risk of distorting the original data or losing important detail inferential statistics - -used to try to reach conclusions beyond the immediate data alone --> to make assumptions about the population --> or to make predictions about what might happen in the future -used to test hypotheses -underlying assumption that sampling is random hypothesis testing - -when we are using inferential statistics, we are testing hypothesis -hypotheses are typically written in null form: there is NO difference between group A and group B -if the result of the test IS significant(usually a p value of less than .05), we reject the null hypothesis and conclude that there is a significant difference -if the result of a test is NOT significant, we accept (or fail to reject) the null hypothesis and conclude there is no significant difference what is a variable? - -a measurable factor, characteristic, or attribute of an individual or a system -a numeric value or a characteristic that can vary over time or between individuals -a characteristic that may assume more than one set of values what is a group? - -the possible responses for a categorical variable -the categories created when the values of a continuous variable are collapsed into specific groups

what are values? - -the code that identifies the legitimate options for a given variable -numerical quantity or test representing the characteristic being measured categorical variables - -a discrete variable -there is a finite number of potential values -qualitative -typically a grouping variable -can be nominal, ordinal, or interval data -can run descriptive statistics such as frequencies and percentages but not measures of central tendency continuous variables - -a variable that can theoretically assume an infinite number of values between any two points on the scale(BP, weight, temp) -quantitative -ordinal(sometimes), interval, or ratio data measures of central tendency - -the mean (average value ) -->population mean represented by mu -->sample mean represented by x-bar -median(the midpoint of a distribution, the same # of scores are above the median as below it) -mode(the most frequently occurring value) what is the standard deviation? - -the most common measure of dispersion from the mean -a measure of how spread out a distribution is -->a large standard deviation=data points are far from the mean -->a small standard deviation = data closely clustered around the mean

what is probability? - -chance behavior is unpredictable in the short run, but has a predictable pattern in the long run -the probability of any outcome of a random phenoma is the proportion of times the outcome would occur in a very long series of repetitions probability distribution - -a table or equation that links each outcome of an experiment with its probability of occurring -suppose you flip a coin twice --> possible outcomes: HH, HT, TH, TT probability and p value - -p value represents the probability of error that is involved in accepting the observed result as valid(or representative) -typically a p value of .05 is the threshold for accepting that the relationship between variables is not a result of chance -a p value of .05 indicates that there is a 5% probability that the relationship is a fluke -the lower the p value, the stronger the evidence and the more certain we can be about the relationship statistical significance - -the probability that the observed relationship between variables or a difference between means did not occur by chance -tells us something about the degree to which the result is true -statistical significance does NOT mean the result: --> is of practical significance -->demonstrates a large effect in the population -->is important Confidence interval - -the range of values that you can be certain contains the true mean in the population

-a 95% confidence interval means that if you take repeated samples and the 95% CI was computed for each sample, 95% of the intervals would contain the population mean correlation coefficients - -tests for a linear relationship between two continuous variables -relationship can be positive or negative -ranges from +1 to -1. 0 indicates no relationship -the larger the correlation coefficient, the more closely the two measures vary together or oppositely -does not indicate causality -variables must contain interval or ratio data -data must be normally distributed -there is no relationship between the strength(size) of the correlation and its statistical significance -a correlation report also reports the significance level -->or the likelihood that the correlation reported may be due to chance -a challenge in interpreting correlation coefficients is interpreting strength relationship -->multiple scales can exist, describing the different levels differently -scatterplots are helpful in interpreting the strength of correlation coefficients Null=there is no relationship between __ and __ T-tests - -dependent variable must be continuous and evaluates the differences between a categorical variable with 2 groups -compares the means of 2 groups -data must be normally distributed -must check for equality of variance -independent 2 sample=used whent the groups are independent of each other(ex: one group given medication and another group given a placebo)

-paired=used when the two groups of observations are based on the same sample of subjects(ex:BP before and after an intervention) null= there is no difference between __ and __ ANOVA - -dependent variable must be continuous and evaluates the difference among a categorical variable with more than two groups -data must be normally distributed -compares the means of the different groups -result only determines id there is a significant difference somewhere, but it does not tell you where --> to find out where the differences are, must run additional tests(called post hoc tests) null= there is not difference between __ and __ chi- square test - -both variables are categorical -measured variables must be independent -evaluates for a relationship between two variables (by testing the difference between theoretically expected and observed frequencies) What is SPSS - -statistical package for social sciences -a powerful tool used to manage and analyze data -user friendly because it is menu driven What can you do with SPSS - -create a data file -edit data -manage data --> compute new variables

-->recode variables -->select specific cases -->sort cases -->merge files -create graphs and charts -frequencies -descriptive statistics(mean, median, mode, standard deviation) -cross tab and chi-square -correlations -t tests -one way analysis of variance(ANOVA) -linear regression -logistic regression sound decision making requires an understanding of... - -how the data was analyzed -why the analysis was performed in a specific manner data= output= syntax= - data=sav file output=spo file syntax=sps file data file's 2 views - data view -variables in columns

-cases in rows Variable view -allows you to change how the data appears(EX:the # of decimal points that will show) -enables you to include information that will simplify your life(EX: labels that will make it easier to read results) Variable view - -Name can appear at the head of each column in the data view -->no spaces --> cannot begin with a number -Type: numeric, dollar, string -Width: the maximum number of characters allowed in the field -Label: can appear in the data view header -->invaluable when reading results -Values: include a value label so you don't have to remember if 1 is male or female -Columns: important if importing data from flat files -Missing: codes are used for missing data -->listing these codes tells SPSS not to use these data points in analysis Output file - -shows the results of your work -can be set to show the log in the output --> log shows syntax, or instructions to SPSS, that describes what you have done in the file -can copy results and paste into a Word file -can copy results into an excel file -can manipulate output tables easily if paste to "match destination formatting" --> sort the results differently -->adjust # of decimal places

-->copy and paste into tables that contain results from multiple tests syntax file - -since SPSS writes syntax(instructions) for you, you don't have to do anything with this file -but if you are going to be running the same tests again, it may be to your advantage to use this -syntax is NOT written automatically into the file. you must tell spss to do that SPSS steps - Step 1: Read Data In -enter data directly into SPSS -open and SPSS data file -import data from another proprietary program(Excel, acess, SAS) -Raw text data(csv, fixed, tab separated) Step 2: Organize your data file -assign variable labels -assign value labels -these help you easily identify the different variables and the values used in each Step 3: Check data for accuracy -run frequencies and descriptive statistics to check whether data are reasonable --> look for outliers(> 3 standard deviations) --> bad data entry -verify that variables are what you think they are Step 4: Begin working with your data -create new variables --> compute new variables from existing ones -recode -->collapse categories

-transform string variables into numeric -always check your data after making changes to your variables Next steps: -merge one file with another -select a sub sample -perform statistical analyses -present results