Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
COM 304 Midterm
Com 304 Midterm
| Question | Answer |
|---|---|
| What is unique about deductive reasoning? | Do not need to “observe” or “measure” anything to judge whether conclusions are valid - 3 circle example |
| What are the 3 goals of social sciences? | (1) Social Science focuses on EMPIRICAL questions (2) Social Science seeks GENERAL EXPLANATIONS (3) Social Science focuses on FALSIFIABLE PREDICTIONS |
| What are empirical questions? | Questions that can be judged, in large part, based on observations (Wrench et al, QRM Chap. 2) Questions that have a “descriptive” orientation, not an explicitly “evaluative” orientation (line here is blurry) Procedures that can be REPLICATED: |
| Define the goal: general explanations | Explain: to relate particular events to a more general principle that helps us understand why those events occurred General: explanations that focus on what’s COMMON about people, events, or actions |
| Define the goal: falsifiable predictions | FALSIFIABILITY: Falsifiability = empirically testable, could possibly be refuted (though it may not be) predictions must be clear and specific in order to be falsifiable (otherwise there is always “wiggle room” in interpreting findings after the fact) |
| True or false:Social science defined based on its goals rather than be reliance on any single, rigid “scientific method” (true of natural and social sciences) | true |
| According to the Wrench text, a _____ is a proposed explanation for how a set of phenomenon will occur, capable of making predictions about how the phenomenon will happen in the future, and capable of being proven wrong. | theory |
| Empirical questions have a(n) ______ orientation, not a(n) ________ orientation. | descriptive and evaluative |
| __________ implies predictions that can be tested. | social science research |
| What are constructs? | Construct = abstraction generalized from particulars Construct = concept defined for scientific purposes |
| What are the building blocks for social sciences? | constructs |
| What is a theory? | proposes an explanation for how/when constructs co-occur offers predictions about how/when they will occur in future offers clear predictions potentially that can be falsified |
| What are the 3 parts of a construct? | 1. Label 2. Conceptual Definition 3. Operational Definition |
| What are labels? | Label = 1-3 word name/summary of construct Examples: “Attitude” “Verbal Aggressiveness” “Politeness” “Family” “Organizational Identification” “Parasocial Relationship” |
| What is a conceptual definition | “A germinal idea is a term for that spark that causes an individual to realize that something new can be [studied]…Conceptualization is…the development and clarification of concepts or your germinal idea” - not necessarily dictionary def. |
| What are conceptual definitions judged on? | Their Usefulness: in helping us think clearly about particular ways the concept can be defined and hence measured/studied |
| What is an operational definition? | “translates the verbal meaning provided by the (conceptual) definition into a prescription for measurement |
| Give an example of an operational definition: | Steps: Have participants respond to each of the 21 items using the 1-4 scale (but use only items 3, 6, 9, 12, 15, 18, and 21 when computing public speaking apprehension) Reverse score responses to items 3, 15, and 21 (1=4, 2=3, 3=2, 4=1) etc... |
| What is a variable? | “any entity that can take on a variety of different values…a concept or construct that varies” (Wrench et al., 2008, p. 104) any concept that can take on 2 or more categories/levels variables have different values over time or across people |
| What are the two characteristics of levels of a variable? | Mutually exclusive: each unit/observation (person) falls into only one category (R, D, or I) Exhaustive: every unit/observation (person) falls into a category |
| What are the two types of variables? | categorical and quantitative |
| Define categorical variable: | Categorical Variables: participant are placed into different categories, but categories are not arranged from low-to-high |
| Define quantitative variable: | Quantitative Variables: participants fall at different levels of the variable, and the levels indicate different amounts of the characteristic |
| What are the different level types of categorical variables? | Nominal |
| What are the different level types of quantitative variables? | ordinal, interval, ratio |
| Describe the nominal level: | Numbers assigned to variable categories have no real meaning—just convenient ways to record categories Example: Questionnaire #1, Item 6: “If you are a Communication major, what is your area of specialty within Communication?” |
| Describe the ordinal scale: | Numbers rank variable categories from high to low Numbers do not indicate how much higher or lower one category is in relation to another Example: Order of Finish in a Race (1st, 2nd, 3rd) “What is the highest level of education your mother completed |
| Describe interval scales: | Numbers indicate order of categories AND assume categories are equal distances apart ex.1=Strongly Disagree 2=Disagree 3 = Disagree some/agree some 4=Agree 5=Strongly Agree |
| Describe ratio scales: | Ratio has all an “absolute” (i.e., measurable, non-arbitrary) zero point Ratio scale: example from survey project Questionnaire #1, Item 16: How many sisters do you have? ___ |
| What do variables are identified as "scale" in SPSS? | interval and ratio |
| What do levels of measurement effect? | Type of hypothesis we make: comparison vs. relational hypotheses (next week) Type of statistics we use to describe sample (e.g., mean vs. mode), as well as to test hypotheses |
| What is a hypothesis? | Hypothesis: “Tentative statement about the relationship between independent and dependent variables” - defines the focus of the research |
| What are the two types of hypotheses? | comparison and relationship |
| What is a comparison hypothesis? | specifies how persons falling into different groups of a categorical variable will compare in terms of some 2nd variable (categorical or quantitative) Also called hypothesis of “difference” |
| What is a relationship hypothesis? | specifies nature of the association between two quantitative variables (both variables are quantitative) Also called hypothesis of “association” |
| What is a directional hypothesis? | explicitly states the direction of the difference between two groups (comparison) OR the association between two variables (relationship) |
| What is a non-directional hypothesis? | predicts that two groups will differ (comparison) or two variables will be associated (relationships) but does not specify the direction of the difference or association also called Research Question |
| Define the independent variable: | Independent variable (IV) the “causal” variable (input or stimulus variable) variable that impacts or determines the other variable In an experiment, the variable that is “manipulated” or altered |
| Define the dependent variable: | Dependent variable (DV) the “effect” variable (output or response variable) variable that is impacted/determined by the other variable In an experiment, the variable that is “measured” (not manipulated) |
| What are statistics? | set of procedures used to organize data, make inferences from data |
| What are the two types of statistics? | Descriptive and Inferential |
| What type of statistic are we using this semester and how is it defined? | DESCRIPTIVE: used to summarize responses from a sample, characterize the sample 1st half of semester Examples: Mean, Median, Mode, Range, IRQ, SD, z-scores, Cohen’s d, Correlation (r)… |
| What is a distribution? | Distribution: a sample’s scores on ONE variable arranged from low to high for quantitative variables |
| What is a frequency distribution? | Frequency Distribution: shows the frequency of occurrence (# and % of participants) at each category/level of ONE variable |
| What are the 3 key questions we can ask when describing a distributions shape at the interval and ratio levels? | What is its shape? How symmetrical is it (skewness)? How tall is it (kurtosis)? Where is the middle? (central tendency) How spread out are scores? (dispersion) |
| What is the difference between positive and negative skew? | The blue distribution is positively skewed (most scores low, tail points right) The red distribution is negatively skewed (most scores high, tail points left) |
| What is the skewness index? | Skew = 0 (symmetrical, no skew) Skew > +1 = marked positive skew Skew < -1 = marked negative skew |
| What is kurtosis? | Refers to the degree of “peakedness” of a distribution |
| What are the three types of kurtosis and what are their differences? | Leptokurtic: a tall, narrow distribution (red) Platykurtic: a wide, flat distribution (blue) Mesokurtic: falls between the two (normal distribution) |
| What is the kurtosis index? | kurtosis = 0 (normal curve) kurtosis > + 2.0 = extreme leptokurtic distribution (tall/narrow) Kurtosis < -2.0 = extreme platykurtic distribution (flat/wide) |
| What are the 3 most common things used to measure central tendency? | mean, median, mode |
| What is the mode? | most frequently occurring score(s) in the distribution |
| When is it important to report the mode? | Variable is Nominal-Level (mode doesn’t presume scores are ordered) 2. Distribution is Bimodal: 2 non-adjacent modes |
| What is the median? | Median: the middle point in the distribution |
| What is important to do when finding the median? | Ordering scores from lowest to highest |
| When is it important to report median? | interval/ratio variable, AND distribution highly skewed |
| Define mean: | ●arithmetic average of all scores in distribution ●# which if subtract all scores in distribution from it, get smallest total deviation |
| The mean is the best measure of central tendency as long as: | - variable is ordered - distribution not highly skewed and not strongly bimodal |
| What is true of the Mean, Median, and Mode if a distribution is exactly normal? | They will all equal each other |
| What is true of mean, median, and mode when a distribution is positively skewed? | the mean is greater than the median, which is greater than the mode |
| Define range: | difference between the highest and lowest scores in the distribution |
| What are the limits of range since it only depends on two most extreme scores? | Range stretched by Outliers (extreme scores) Range is unstable: new scores = big changes |
| What is the interquartile range? | (2) Interquartile Range (IQR) the range of the middle 50% of the distribution IQR= 75th percentile score – 25th percentile score |
| How is the IQR tied to the median? | **if scores on variable are highly skewed --use median (not mean) for central tendency --use IQR for dispersion |
| What are the parts of a box plot and what do they show? | Bold Line = Median (50th percentile) Box = 25th to 75th percentile (IQR) Whiskers = extend out to largest and smallest cases that are not outliers |
| What is standard deviation? | • a measure of how much all scores tend to vary from the sample mean • the square root of the average squared deviation from the mean |
| What are the desirable qualities of S? | Stable: based on all scores, not affected strongly by one extreme score Interpretable: related to normal distribution |
| What is the 2/3 rule and what does it say? | Approximate 2/3 rule (+/-1S) (when scores normally distributed, 68% of cases fall within +/-1S of mean) |
| What is the 95% rule? | Approximate 95% rule (+/-2S) (when scores normally distributed, 95% of cases fall within +/-2S of mean) |
| What percentage of subjects is encompassed by the interquartile range? | 50% |
| If everyone in a population has the same score, the value of the standard deviation is zero. | true |
| The standard deviation was designed expressly to describe what type of distribution? | normal |
| Spread and dispersion are synonymous for what term? | variability |
| What is the 99% rule? | 99% rule: about 99% of scores in a SND fall between +/-3SD of the mean |
| What can z-scores be used for? | Determine the percentile for any z-score (% of scores in SNC below that z-score) Determine the % of cases falling in between any two z-scores (any two places in SNC) Combine raw scores from two measures with different possible ranges |
| How do you determine the percent of scores between two z-scores? | Determine % of scores b/t each z-score and M (using Pyrczak, Table 1, Col. 2) Then: If z-scores are OPPOSITE in sign: add them If z-scores in SAME in sign, subtract smaller % from larger % |
| Define effect size | a family of indices that describe the size of a difference or an association in standardized units (rather than raw scores) |
| What is the most common effect size index for comparison hypotheses? | Cohen's D |
| What is Cohen's D? | difference between mean scores for two groups in standardized units used when comparing two groups (categorical IV) in terms of scores on interval/ratio level DV |
| What is the most common effect size index for relationships hypotheses? | Pearson's R |
| What does Pearson's R tell you? | association between 2 interval/ratio-level variables in standardized units |
| How should M1 and M2 be ordered in the Cohen's D formula? | d is positive if the means fall in the predicted direction d is negative if the means fall opposite of the predicted direction (see Topic 61, footnote 2) |
| What is the formula for Cohen's D? | d = (M1-M2)/Spooled |
| Does SPSS calculate Cohen's D? | No it doesn't |
| What is the size index for Cohen's D? | d around .20 (.15-.39) is a SMALL effect d around .50 (.40-.74) is a MEDIUM effect d around .80 (.75-1.09) is a LARGE effect |
| Define correlation | degree to which a group’s scores on 2 variables (X and Y) are associated: does knowing your score on X tell us anything about what your score is likely to be on Y (or vice versa) Use correlation to assess Relationship Hypothesis |
| Describe a scatter plot | Vertical (Y) axis – DV Horizontal (X) axis – IV Each dot = 1 unit (person) – place where person’s scores on 2 axes intersect |
| Define fit line | line drawn so as to minimize the squared deviations of dots from the line (roughly, the line that on average is closer to all dots than any other line) |
| What are the 4 types of correlation relationships? | no relationship, positive, negative, curvilinear |
| Define pearson correlation | provides a numerical estimate of direction and strength of the linear relationship between two variables (X and Y) |
| What is the range of a pearson correlation? | Possible range of r = -1.00 to +1.00 **r = 0 means NO relationship – knowing X tells us nothing about Y **r = -1.00 or +1.00 = perfect linear relationship: scores on X completely predictable from Y (vice versa) |
| How do you interpret pearson's r? | r = .10 is a SMALL relationship (like d = .20) r = .24 is a MEDIUM relationship (like d = .50) r = .37 is a LARGE relationship (like d = .80) |
| What is the coefficient of determination (r-squared)? | the % of variance in Variable X that is shared with variance in Variable Y (vice versa) The % of all variation in X that is explained by Y (or vice versa) |
| Define measurement | process of determining the existence, characteristics, size, and/or quantity of change in a variable through systematic recording and organizing of observations |
| Define measurement reliability | the degree to which measurements are stable or consistent over conditions in which similar results should be obtained |
| Define measurement error | random fluctuations in scores due to factors that are temporary and shifting |
| What is observed score? | True Score + Error |
| What is the problem with measurement error? | reduces chance of detecting systematic relationships between that measure and measures of other variables |
| What is temporal stability? | the degree to which people’s scores on measure are stable over time |
| How do you test temporal stability? | Test-retest r |
| How does test-retest r work? | assesses strength of relationship between the same group’s scores on the same measure at two or more points in time |
| What is the desirable level for test-retest r? | at least r = .70 (depends on length of time between 2 measurements) |
| What is internal consistency? | degree to which various questions or behaviors making up a single measure all tap the same thing |
| What are the 3 indices of internal consistency? | Average Inter-item Correlation, Split-half Correlation, cronbach's alpha |
| What is the average inter-item correlation? | the mean correlation between all pairs of items making up a measure |
| What is split-half correlation? | correlate participants’ responses to ½ of items (e.g., all odd items) with their responses to the other ½ items (e.g., all even items) |
| What is cronbach's alpha? | the average of all possible split-half correlations (odd-even items, 1st half-2nd half of items…) |
| What are the standards for measuring alpha? | Alpha > .80 = good Alpha .70-.80 = adequate Alpha .65-.70 = minimally acceptable Alpha < .65 = undesirable |
| What are some lessons learned about internal consistency? | Avoid Single Item Scales,Write Adequate Number of Similarly-worded Items,Pilot Test New Measures Before Starting the Main Research (assess their reliability in advance) |
| What is measurement validity? | “the degree to which the instrument measures what it is intended to measure” (Wrench, QRM, p. 202) the degree to which a measure performs the function it is supposed to perform |
| What is content validity? | does the measure sample relevant content adequately and appropriately? Are “the items on the measure reasonably representative of the university of possible items that could be included” |
| What's the criteria for judging content validity? | **Is a broad range of content sampled? **Is important content emphasized? **Are items written at an appropriate level and in an appropriate format? |
| What does predictive validity measure? | does a measure predict what it should predict? Does it predict relevant future outcomes (criterion)? |
| What is construct validity? | are scores on the measure related with scores on measures of different constructs as specified by theory? |
| What does judging a measure's degree of validity require? | (a) a clear conceptual definition, (b) theory about what other things about to be associated with that construct |
| Define population | an entire group of people, events, or texts that share one or more characteristics (Wrench, p. 282) |
| Define sample | a smaller # of elements from the total # making up the population |
| Define statistic | a numerical characteristic/summary of a sample (e.g., %, sample M) |
| Define parameter | numerical characteristic/summary of the entire population (value from a census) |
| Define sampling error | degree to which a sample statistic deviates from a population parameter |
| What are the two methods of sampling? | probability and non-probability |
| Define probability | sampling method that uses some form of random selection; different units of the population have an equal chance of being chosen |
| Define non-probability | sampling method that does not use random selection; leaves us limited ability to estimate how much sampling error may be present |
| Define simple random sampling | draw sample so that each member of population has an equal chance of being selected in sample |
| When can we estimate sampling error? | With random (probability) sampling, we can estimate sampling error (e.g., margin of error in political polls) |
| What are the types of probability sampling? | simple random samples,stratified random sampling, cluster or multi-stage sampling |
| Define non-probability sampling | draw sample so that: elements of population do not have an equal chance of being selected can’t determine how likely it was that any specific element would be selected |
| Define convenience sample | a type of non-probability sampling where you study readily available subset of population |
| What are some reasons you might use non-probability sampling? | for finding or recruiting volunteers for clinical trials |
| What are some downfalls of non-probability sampling? | no basis for judging the likely amount of sampling error difficult to judge amount of bias |
| Define distribution | an array of scores falling at different categories/levels of a variable; for quantitative variables, scores are ordered from low to high |
| Define frequency distribution | shows the number of individual units (people) falling at each level of a variable |
| Define sampling distribution | a distribution of sample statistics (e.g., mean scores), ordered from low to high around a population parameter |
| When will a sampling distribution resemble the normal curve? | this will ALWAYS occur for a sampling distribution of mean scores as long as the size of the samples are not tiny: n > = 30 |
| what is the mean of a standard normal distribution? | zero |
| Cohen's d is the most commonly used measure of effect size for ________ hypotheses. | comparison |
| According to the Pyrczak text, a small effect size still might represent an important research finding if it had consequences for a large number of people. | true |
| A Pearson correlation is used to test which type of hypothesis? | relationship |
| _________ is the degree to which measurements are stable or consistent over conditions in which similar results should be obtained. | reliability |
| What two factors determine the size of Cronbach's alpha? | the mean inter-item correlation and the number of items measured |
| A researcher gives a sample of 30 parents a measure of how confident they are in their parenting abilities in September, and then has these 30 parents complete the same measure again in October. Which type of reliability is this example? | temporal stability |
| According to your text, if the internal consistency for a measure is low, a researcher might try to fix this by: | clarifying the wording of ambiguous items 2. writing additional items 3. administering the measure under well controlled conditions (e.g., using standard instructions) |
| A researcher calculates Cronbach's alpha for a sample's responses to a new measure. What type of reliability is the researcher assessing in this exampe? | internal consistency |
| One major advantage of probability sampling is that such techniques... | allow the researcher to calculate the amount of sampling error likely to be present |
| Suppose that you want to use stratified random sampling to obtain a sample from a population in which there are 600 freshmen, 500 sophomores, 450 juniors, and 400 seniors. Should you draw the same percentage or the same number from each grade level? | same percentage |
| Which statement best describes the relationship between sample size and sampling error? | As sample size increases, sampling error decreases but with diminishing returns |
Created by:
mlongest