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
Stats Data 3
Statistics and Data Analysis 3
| Question | Answer | Hint |
|---|---|---|
| Name four advantages of MR? | 1. Measures magnitude of total and partial (unique) effect of IV's on DV 2. Can test statistical hypotheses 3. Can construct CI intervals 3. Major tool in methods of causal (path, structural equation) analysis | effect, statistical hypotheses, CI, causal |
| What advantage does MRC have over ANOVA/ANCOVA? | Whilst MRC, ANOVA, and ANCOVA are all general linear models, MRC can analyse all quantitative data, whilst ANOVA and ANCOVA can only analyse certain data. | general linear model, which can analyse all data? |
| Compare correlational vs experimental research methods | Correlational - analyses natural observation. Does not manipulate the environment. Eg. measuring lifestyle variables such as smoking, diabetes, etc. Experimental - manipulates parts of the environment to observe the effect of the variable of interest | natural environment, manipulation, effect on variable |
| Explain the four levels of measurment. Give examples. How are they used in MRC? | 1. Categorical 2. Ordinal (nominal): order matters but not difference between variables. eg. Ratings scale of anxiety 3. Interval: Order matters, and difference between interval matters 4. Ratio: like interval (difference matters) but 0 value = none | COIR |
| How are the four levels of measurement used in MRC? | IV: Ratio & interval - directly included; Nominal (categorical) coded 0 & 1; Ordinal treated as interval (therefore check your MRC interpretation) DV: any, but better with interval/ratio | |
| How is MRC used to test hypotheses? | To test hypothesis of causal relationships, gather data from real world, build model representing processes, use model to predict how processes operate under certain conditions | |
| How are models used for NHST? | We fit the model to the data (represents alternative hypothesis). If it fits well, we assume our initial prediction is true. As per NHST, we calculate the probability that our model would fit a non-affect population. | |
| What are limitations to NHST 1/3 | as sample size increases so does it's generalisability to the population. Therefore a significant effect is more likely to be found. However, this doesn't mean it is an important effect, it may just be due to a large sample. In reality, small/unimportant | |
| What are limitations to NHST 2/3 | Non-significant results doesn't necessarily mean null hypothesis is true, it may mean effect is not big enough = chance finding. | |
| What are limitations to NHST 3/3 | NHST is probabilistic reasoning. Therefore significant effect does not mean null hypothesis is false. | |
| When can multiple regression be used? | Where IV's, DV's, and their relationship are quantitative and unbound (not constrained). | contrained |
Created by:
phoenix79
Popular Psychology sets