PSY 306 Research Methods and Statistics Test 1

What is internal validity? What is external validity? How are they related?

- Internal validity: level of accuracy in the relationship among study variables - External validity: level of accuracy for different types of people in different settings -as internal validity increases, external validity decreases

Define the term "descriptive statistics." What two categories of descriptive statistics are used to describe a sample?

-Are used to summarize and describe the behavior of participants in a study. -Measures of central tendency and measures of variability are used to describe a sample

Define the terms frequency, percentage, and cumulative percentage.

-Frequency: count of how many times a score occurred -Percentage: proportion of a score within a sample -Cumulative percentage: proportion of the sample that falls within a specified interval

What steps can be taken to reduce bias in observational research?

-Have blind observers -Carefully Train Observers -Test inter-rater reliability

What are the three measures of central tendency and how are these measures calculated?

-Mean: the most commonly used measure of central tendency, the average. Calculated by summing the scores for all cases, then dividing by the number of cases -Median: the middle score of a distribution. -Mode: the most frequent score

list the appropriate descriptive statistics (measures of central tendency and variability) for each scale of measurement.

-Nominal: frequencies and percentages, mode -Ordinal: frequencies and percentages, median, observed min/max, mode -Interval and Ratio (normal distribution): mean, standard deviation -Interval and Ratio (non-normal distribution): median, observed min/max or range

What is the difference between percentile and percentage? What is a z-score and percentile? Why are these scores useful?

-Percentiles tell you what percentage of a distribution scores below a specific score -z scores are scores that are expressed in terms of standard deviations from the mean -z scores let us compare things and describe where each individual is located.

Both reliability and validity need to occur at the level of measurement and the level of study—how are these different?

-Reliability at the study level consists of replication, Reliability at the measurement level consists of the responses or data -Validity at the study level consists of internal and external validity, Validity at the measurement level consists of the data.

What is sampling error, margin of estimation (error of estimation)?

-Sampling Error: difference between the scores of sample and entire population, can't measure sampling error because we don't know entire population, can only get estimate. -Margin of error: the degree to which we expect the sample to deviate from the population

What are the methods for nonprobability sampling? Be able to define each, describe the pros and cons, and provide an example of each.

1. Convenience sampling: use available participants. EX: stopping people on street 2. Quota sampling: convenience sample, but get a certain number of specific types of people. Drawn from whatever participants are available, but efforts are made to get certain types of people. EX: stopping people on the street that are only girls 3. Snowball sampling: find one member of the population then ask the person to help locate others FIND PROS AND CONS

Name and describe the types of observations

1. Covert (Disguised): researchers don't reveal they are observing 2. Overt (Non-disguised): researchers do reveal they are observing 3. Natural: in natural environment with no interference 4. Contrived: set up for research purposes involving researcher interference; may happen in lab or natural environment 5. Nonparticipant: researcher isn't directly involved in situation 6. Participant: researcher is directly involved in situation

What are the different types of validity?

1. Face Validity: the extent to which a measuring technique appears to measure what it is supposed to measure 2. Construct Validity: research that involves the measurement of hypothetical constructs. Assess by seeing whether a particular measure relates as it should to other measures. (convergent validity when it correlates with measures it should) (discriminant validity when it doesn't correlate with measures it shouldn't) 3. Criterion-Related Validity: the extent to which a measure allows us to distinguish among participants on the basis of a particular behavioral criterion (concurrent validity when the two measures are administered at roughly the same time) (predictive validity is when we can distinguish between a relevant behavioral criterion at some time in the future)

What are the scales of measurement? Know the various properties of each scale of measurement and be able to identify examples of various scales of measurement.

1. Nominal Scale: numbers are assigned to behaviors and characteristics as labels, not real numbers, no math. EX: physical characteristics i.e. hair color, eye color, etc. 2. Ordinal Scale: involves the rank ordering of a set of scores that reflect participants behaviors. Tell us order on a particular dimension. EX: places in a race 3. Interval Scale: equal differences between the numbers reflect differences between participants on the characteristics being measured. EX: temperature 4. Ratio Scale: highest level of measurement, involves real numbers that can do math with. Has an absolute zero. EX: height

What are the methods of probability sampling? Be able to define each, describe the pros and cons, and provide an example of each.

1. Simple random sampling: every possible sample in the population has the same chance of being selected. EX: lottery Pros: completely random, Cons: must know how many individuals are in the population 2. Systematic sampling: a sample in which individuals are chosen systematically. EX: every 4th person Pros: don't have to know size of population Cons: some participants have no chance of being selected which could effect the data 3. Stratified random sampling: a variation of simple random sampling that involves a stratum (a subset of the population that shares the same characteristic). Cases are randomly selected from each stratum. EX: having equal amount of ages in a study. Pros: ensures researchers have the the right amount of participants in the study, can increase that sample is representative of population. Cons: require that we have a sample frame before we begin 4. Cluster sampling: sample of clusters of participants, then individuals in the cluster. used when we don't have a list of all the people in the population. Pros: easier to contact participants and don't ned list of population

What are the different types of reliability?

1. Test-Retest Reliability: the consistency of participants' responses on a measure over time. Determined by measuring participants on two different occasions 2. Interitem Reliability: assesses the degree of consistency among the items on a scale. All of the items must be within the same construct 3. Interrater Reliability: involves the consistency among two or more researchers who observe and record participants behavior

A normal distribution is one type of distribution, what are the other 3 distribution types defined in your text. Be sure you can define each, a pictorial illustration is sufficient. What are the best measures of central tendency and variability for each of these distributions?

1. Uniform distribution: all scores have the same frequency, all measures of central tendency are the same, no variability 2. Bimodal distribution: two distinct peaks, must report both modes, range 3. Skewed distribution: tail of the distribution, scores at one end of the curve, the median is the best score to talk about, range

When is a descriptive study appropriate? Know the 3 times and be able to provide an example of each.

1. When trying to understand prevalence and trends 2. When trying to explore a phenomenon in depth 3. When examining a phenomenon in a different population

What are the characteristics of a normal distribution?

A specific distribution having a characteristic bell-shaped form, symmetrical, unimodal distribution. most of the scores fall near the mean of the distribution

What is the relationship between reliability and validity?

A study or measure can be reliable, but not valid. Validity depends upon reliability. Must be reliable to be valid, but doesn't have to be valid to be reliable

List the characteristics of science and the basic elements of the scientific method.

Characteristics of science: 1- based on systematic observation 2- rational 3- available for public verification 4- solvable problems Basic Elements of the scientific method: -Hypothesis: testable beliefs about the relationship between two events -Operationalize: how we define the construct we are studying -Measure: conduct the study and measure the concepts in which you are interested -Evaluate: examination of data to determine whether or not predictions are supported -Revise or Replicate: replicate the study to confirm the findings or revise hypothesis if predictions are not confirmed -Application: apply knowledge to real world studies

What is pseudoscience and what are its characteristics?

Claims of evidence that masquerade as science but in fact violate the basic criteria of scientific investigation. Not based upon observation and data is not collected in a systematic matter. Often based upon peoples beliefs

Know the definition of a construct. How does this compare to the related terms of conceptual and operational definitions?

Construct: the actual concept that you are dealing with Conceptual: broad general definition of a construct Operational: definition that specifies exactly how the construct is measured or manipulated in a study

Compare and contrast bar graphs, histograms, and frequency polygons. When would you use each one?

Frequency distributions are often portrayed graphically in the forms of histograms and bar graphs. Use a histogram for interval or ratio scales of measurement. Use bar graph for nominal or ordinal scales of measurement. Frequency polygons are similar to histograms, but rather than using bars, lines are drawn to connect the frequencies of the class intervals. only used for interval or ratio scales of measurement.

How is the importance of sample size different in probability vs. nonprobability sampling?

In probability sampling you need larger sample sizes because the sampling is random and you need a large amount of people to ensure that the sample is representative of the population. In non-probability sampling you do not have a random sample so you can use smaller sample sizes.

What is the relationship between science and the search for proof?

In science we cannot prove theories, instead we talk about theories being confirmed or supported by research. Science looks to disproof things

Bar graphs are appropriate for two different scales of measurement. What two scales of measurement can be displayed using bar graphs?

Nominal and ordinal

What are the two primary methods for obtaining a sample from the population? What feature distinguishes the two?

Non-probabilty and probability sampling. Difference between the two is that random sampling is only used in probability sampling

What type of bias is most associated with observational research?

Observer Bias

Describe the various terms used to define the peak of a distribution.

One factor is kurtosis (how peaked a distribution is) ◦Mesokurtic: moderate peak ◦Leptokurtic: high peak (most scores clustered in the middle) ◦Platykurtic: flat peak (scores are more spread out)

Define a population, population subgroups, and a sample

Population: all possible individuals making up a group of interest in a study Population Subgroups: stratums that preexist in a population Sample: a subset of individuals in the population

What are the pros and cons of using questionnaires?

Pros: less expensive, less time consuming, can be used to collect a variety of information Cons: the questionnaire may not be valid and reliable, must either make own questionnaire valid/ reliable or find one that is.

What is random sampling (or random selection—not to be confused with random assignment)?

Random sampling is a part of the sampling technique in which each sample has an equal probability of being chosen.

Define reliability and validity

Reliability: the consistency or dependability of a measuring technique. Validity: the extent to which a measurement procedure actually measures what it is intended to measure rather than measuring something else.

What are the components of science? That is, what does it mean to say that something is scientific? What are the 5 other ways of knowing?

Science wants to understand concepts with concrete data Components of science are conceptual and concrete 1. Authority- people who have perceived expertise in the area 2. Common Sense- things we believe without having to really think about it, intuition 3. Tenacity- a way of knowing and understanding the world, ones own beliefs 4. Rationalism- use logic to come up with new knowledge, original statement must be true say that premise holds true 5. Empiricism- based on observation , acquisition of knowledge by what we can observe with our senses

What is the importance of a pilot study?

So researchers can ensure than the level of the independent variable are different enough to be detected by the participants

What are the three methods for descriptive studies?

Survey research, observational research and archival research -Epidemiological and Demographic are types of descriptive research, not methods

What is power? Describe ways to increase power

The ability of a research design to detect any effects of the variables being studied that exist in the data. Increase power by increasing sample size.

How does archival research make use of secondary data?

The data that was gathered typically was not gathered for research, but the researchers use it to better understand what they are studying. Archival research lets us -study phenomenas -study social and behavioral changes over time -study events that already happened -gather large amounts of data on events that happen in the real world

What information can be used to determine how many participants we should try to recruit?

The error of estimation and to make the sample an economic sample. Must consider time, money, how common variables are.

What is the role of a confederate in a research study? What kind of observational research will most likely use a confederate?

To accomplice the researcher and pose as other participants or as uninvolved bystanders. Contrived observational research will most likely use a confederate

What is archival research?

When researchers analyze data pulled from existing records.

What procedures can be used as part of survey research?

interviews and questionnaires

What are the measures of variability? What measure of variability is most commonly used?

◦Observed minimum: the lowest score in your sample ◦Observed maximum: the highest score in your sample ◦Range: distance between the minimum and maximum score ◦Standard deviation: how much, in general, scores differ from the mean -Variance: an index of the average amount of variability in a set of data-expressed in squared units VARIANCE is the measure most commonly used