Search results

  1. J

    Probability / Statistics (Maybe Venn Diagram/Boolean)

    I think you need to try a little harder to explain your question.
  2. J

    What test do I need to use in my research?

    Assuming your dependent variable can be treated as continuous, your hypotheses suggest the following linear regression model. y_i = b0 + b1*x1_i + b2*x2_i + b3*x1_i*x2_i , where x1 and x2 are your two dependent variables. The third term, the product, captures interaction between the two...
  3. J

    Converting Likert Scale to Binary and Correlating

    Power depends on the statistical analysis technique that you plan to use, so you need to decide that first. I would probably use mixed logistic regression, with random terms for picture and rater, and a fixed term for Likert scale rating. I just googled "power for mixed logistic regression"...
  4. J

    Converting Likert Scale to Binary and Correlating

    Regarding your question 4: Using one group of raters for the Likert ratings and a different group of raters for the binary choice is statistically very inefficient, and will force you to compute the "correlation" between the average Likert rating (across raters) with the proportion of "yeses"...
  5. J

    Assumptions multiple regression violated

    Any discernable pattern in residuals vs predicted values indicates that the model does not fit. You will probably need to find a normalizing transformation for your dependent and/or independent variable, fit a more complex linear model, or abandon linear regression in favor a regression method...
  6. J

    What statistical model to be used?

    The design you present in the pdf is a full 4x4 factorial. If you eliminate the no-inoculation condition as you propose, you will not be able to ascertain the effects of inoculation versus no inoculation. If those comparisons are not of interest, it is fine to eliminate the no-inoculation...
  7. J

    What statistical model to be used?

    Your contol condition seems to be of limited usefulness, because all you can do with it is compare specific sterilization–inoculation treatment conbinations to it. It seems to me that you should either eliminate the "control," so that you have a real 4x3 factorial design, or change the design...
  8. J

    Creating variables in R- two issues

    First convert all your weirdly coded missing values to proper missing values. Provided that none of your variables are factors, you can do this for the whole data frame at once, like this: idx <- df0 == "-99" | df0 == "-98" | df0 == "NAN" df0[idx] <- NA Any comparison with NA returns NA, so...
  9. J

    Assumptions multiple regression violated

    One approach is to divide the problem into two questions: 1. What factors predict any marijuana use. 2. What factors predict frequency of marijuana use among those who use marijuana. The dependent variable in the first question is dichotomous, and so the question can be addressed by using...
  10. J

    What is the minimum sample size for factorial anova?

    @Nina_joon - Nowadays there is no reason to distinguish between different flavors of ANOVA. The modern approach is to specify them all as a linear mixed model, and to solve for the parameters of the model using the method of (restricted) maximum likelihood, which basically requires statistical...
  11. J

    Mixed ANOVA

    What R function is Field using to do the analysis? Can you type out the function call so that I can see the model? I find it bizarre that the author of the wikipedia article calls within-subjects factors "random factors." I don't recall ever having seen the term used that way. It would imply...
  12. J

    What is the minimum sample size for factorial anova?

    @GretaGarbo - since the OP stated the number of subject she had, I interpreted her question to mean "is this enough subjects," rather than literally asking about the theoretical minimum.
  13. J

    What is the minimum sample size for factorial anova?

    If any participant in the study participated in more than one "phase," then your experiment does not have a factorial design, and factorial ANOVA is not applicable. You have more of a repeated-measures design. My default method to analyze such designs, because of its flexibility, is the...
  14. J

    What is the minimum sample size for factorial anova?

    By definition, in a factorial ANOVA, you have at least 2 factors, with at least 2 levels each, and you randomize subjects to every combination of the levels of the factors. So, if factor A has levels a1 and a2, and factor B has levels b1 and b2, then in a factorial ANOVA you have subjects...
  15. J

    What is the minimum sample size for factorial anova?

    Theoretically, 10 subjects is enough to perform a 2x2 factorial ANOVA, but you won't have much statistical power. Also, you can't evenly allocate 10 subjects to four treatment groups, so you can't validly use classical sums of squares to analyze your data. You'll have to use a regression, or...
  16. J

    ERROR: lazy loading failed for package ‘RcmdrMisc’

    It looks like your system is missing whatever package provides the file libgfortran.so.4. On my computer, which runs Archlinux, the package is called gcc-libs. The package name may differ on your distro. You need to figure out the name of the package and install it.
  17. J

    Arthritis trial data: Advanced multivariate stats problem.

    @Markov_Spirello - This is certainly an interesting statistical problem. I have some ideas, but I have a couple preliminary questions: First, I'm concerned about the lack of sensitivity of your outcome(s). A reduction in the trinary score for any joint-pair would imply complete disappearance...
  18. J

    paired t test for groups with unequal sample size

    I don't know SPSS, but the situation that you eventually described cannot be analyzed by using a paired t-test. You don't have paired samples. You have multiple replicate observations for each sample before and after treatment. You don't have the statistical background to analyze this data...
  19. J

    Stress levels in work shifts

    Practically all null hypotheses are false, so testing them is usually silly and amounts to testing whether you had a large enough sample size to declare the observed effect "significant." Since the null hypothesis is almost certainty false, the only thing that makes sense to do is to estimate...
  20. J

    Stress levels in work shifts

    Well, modeling was your idea. Why else would you have brought up the issue of which effects were random and which were fixed? But modeling is always superior to mere significance testing, because modeling provides estimates of the effect sizes, as well as assessment of their statistical...