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
psy400ch6p131-138
Obtain Your Sample
| Term | Definition |
|---|---|
| although MTurk may not be effective for sampling specific targeted populations, | it does a pretty good job of population random sampling |
| young, working, single people are more readily accessed online | than elderly or non-Western populations |
| collect multiple samples from different populations with the hope of | providing converging evidence for your findings |
| Although paying participants may help with recruitment and retention, it may also have detrimental effects on effort and | behavior, particularly when payment is based on participants' performance |
| paying participants to do inherently interesting tasks or perform prosocial acts, | or paying participants too much or too little, may be counterproductive |
| check the methods section for whether | the researchers paid their participants and, if so, how much |
| call your local institutional review board representatives and ask them for advice about payment | because they have likely encountered similar research |
| CHOOSE YOUR MEASURES | determining your scale of measurement and considering the reliability and validity of your chosen instruments |
| Measurement error: The difference between the actual or true value of what you are measuring | and the result obtained using the measurement instrument. |
| four scales of measurement | nominal, ordinal, interval, and ratio |
| Nominal scale (categorical) | The most basic measurement, when scale points are defined by categories. |
| Ordinal (rank order) | Responses are ordered ("greater than" or "less than" relationships make sense); has identity and magnitude |
| Interval Scale | Responses are numerical and the differences between points on the scale are numerically meaningful |
| Ratio Scale | Responses are interval AND there is a meaningful 0 value. |
| Parametric tests: require that the measurement scale be | interval or ratio and make strong assumptions about the distribution of measurements in your population |
| Nonparametric tests: make few assumptions about the population distribution | and may be applied to nominal (names or categories) and ordinal (order) measurements |
| researchers try to select measures that enable parametric analyses | (interval and ratio data) whenever possible |
| Likert-type ratings: Items that ask participants to rate their attitudes | or behavior using a predetermined set of responses that are quantified (that are often treated as an interval scale) |
| any measures you use | should capture what they are intended to measure (validity), and they should yield consistent results (reliability) |
| Prospective versus Retrospective Power Analysis | |
| Statistical power | The probability that your study will be able to detect an effect in your research, if such an effect exists. |
| If yourstudy does not elicit the hypothesized effect, | no amount of statistical power can help you |
| Prospective power analysis: A series of computations that help you to determine the | number of participants that you will need to successfully detect an effect in your research |
| psychology researchers should strive for a | power of .8 (80% chance of detecting a real effect of a given size) |
| Effect size: The magnitude of the primary measure you use to test | your hypothesis (such as a difference of means or a relationship between two variables). |
| doing a prospective power analysis requires that you | know the effect size of the phenomenon that is being studied before you conduct the research |
| a small or moderate-size effect will require | a larger sample size to get adequate statistical power |
Created by:
james22222222